Instructions to use abdelkader-dev/Quark-pre-30M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use abdelkader-dev/Quark-pre-30M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="abdelkader-dev/Quark-pre-30M")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("abdelkader-dev/Quark-pre-30M") model = AutoModelForCausalLM.from_pretrained("abdelkader-dev/Quark-pre-30M", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use abdelkader-dev/Quark-pre-30M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "abdelkader-dev/Quark-pre-30M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "abdelkader-dev/Quark-pre-30M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/abdelkader-dev/Quark-pre-30M
- SGLang
How to use abdelkader-dev/Quark-pre-30M 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 "abdelkader-dev/Quark-pre-30M" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "abdelkader-dev/Quark-pre-30M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "abdelkader-dev/Quark-pre-30M" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "abdelkader-dev/Quark-pre-30M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use abdelkader-dev/Quark-pre-30M with Docker Model Runner:
docker model run hf.co/abdelkader-dev/Quark-pre-30M
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 11480, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08710801393728224, | |
| "grad_norm": 0.9188959002494812, | |
| "learning_rate": 3.960000000000001e-05, | |
| "loss": 6.191905517578125, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17421602787456447, | |
| "grad_norm": 1.3060380220413208, | |
| "learning_rate": 7.960000000000001e-05, | |
| "loss": 6.121124877929687, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2613240418118467, | |
| "grad_norm": 1.1203659772872925, | |
| "learning_rate": 0.00011960000000000001, | |
| "loss": 6.003787231445313, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.34843205574912894, | |
| "grad_norm": 1.421034812927246, | |
| "learning_rate": 0.0001596, | |
| "loss": 5.94820556640625, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4355400696864111, | |
| "grad_norm": 1.2131978273391724, | |
| "learning_rate": 0.0001996, | |
| "loss": 5.933410034179688, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5226480836236934, | |
| "grad_norm": 1.2755587100982666, | |
| "learning_rate": 0.0001999598850347455, | |
| "loss": 5.781154174804687, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6097560975609756, | |
| "grad_norm": 1.4233345985412598, | |
| "learning_rate": 0.0001998379481883983, | |
| "loss": 5.668782958984375, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6968641114982579, | |
| "grad_norm": 1.2652695178985596, | |
| "learning_rate": 0.0001996342851837924, | |
| "loss": 5.601710205078125, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.7839721254355401, | |
| "grad_norm": 1.1004737615585327, | |
| "learning_rate": 0.0001993490627370437, | |
| "loss": 5.515267944335937, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.8710801393728222, | |
| "grad_norm": 1.0849263668060303, | |
| "learning_rate": 0.00019898251432785851, | |
| "loss": 5.444522705078125, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9581881533101045, | |
| "grad_norm": 1.1359233856201172, | |
| "learning_rate": 0.00019853494000840986, | |
| "loss": 5.3566357421875, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.0452961672473868, | |
| "grad_norm": 1.2210420370101929, | |
| "learning_rate": 0.00019800670615771816, | |
| "loss": 5.266632690429687, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.132404181184669, | |
| "grad_norm": 1.4381468296051025, | |
| "learning_rate": 0.00019739824518173792, | |
| "loss": 5.174177856445312, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.2195121951219512, | |
| "grad_norm": 1.0924814939498901, | |
| "learning_rate": 0.00019671005515939518, | |
| "loss": 5.1578131103515625, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.3066202090592334, | |
| "grad_norm": 1.2317713499069214, | |
| "learning_rate": 0.00019594269943486623, | |
| "loss": 5.09080078125, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.3937282229965158, | |
| "grad_norm": 1.1351029872894287, | |
| "learning_rate": 0.00019509680615643058, | |
| "loss": 5.07963623046875, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.480836236933798, | |
| "grad_norm": 1.190399169921875, | |
| "learning_rate": 0.00019417306776227622, | |
| "loss": 5.024771118164063, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.5679442508710801, | |
| "grad_norm": 1.2222275733947754, | |
| "learning_rate": 0.00019317224041367817, | |
| "loss": 5.00032470703125, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.6550522648083623, | |
| "grad_norm": 1.535797119140625, | |
| "learning_rate": 0.0001920951433760136, | |
| "loss": 4.976044616699219, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.7421602787456445, | |
| "grad_norm": 1.2563319206237793, | |
| "learning_rate": 0.00019094265834812104, | |
| "loss": 4.9138116455078125, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.8292682926829267, | |
| "grad_norm": 1.526935338973999, | |
| "learning_rate": 0.00018971572874055216, | |
| "loss": 4.905592041015625, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.916376306620209, | |
| "grad_norm": 1.355762004852295, | |
| "learning_rate": 0.0001884153589033072, | |
| "loss": 4.857882080078125, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.0034843205574915, | |
| "grad_norm": 1.423733115196228, | |
| "learning_rate": 0.00018704261330368583, | |
| "loss": 4.808562316894531, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.0905923344947737, | |
| "grad_norm": 1.6864680051803589, | |
| "learning_rate": 0.00018559861565492692, | |
| "loss": 4.654463806152344, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.177700348432056, | |
| "grad_norm": 1.3302619457244873, | |
| "learning_rate": 0.00018408454799635028, | |
| "loss": 4.666855163574219, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.264808362369338, | |
| "grad_norm": 1.3893911838531494, | |
| "learning_rate": 0.00018250164972575327, | |
| "loss": 4.609520568847656, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.35191637630662, | |
| "grad_norm": 1.344896912574768, | |
| "learning_rate": 0.0001808512165848545, | |
| "loss": 4.636769409179688, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.4390243902439024, | |
| "grad_norm": 1.274559497833252, | |
| "learning_rate": 0.0001791345995986152, | |
| "loss": 4.598162536621094, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.5261324041811846, | |
| "grad_norm": 1.3674043416976929, | |
| "learning_rate": 0.00017735320396930585, | |
| "loss": 4.5604150390625, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.6132404181184667, | |
| "grad_norm": 1.3470535278320312, | |
| "learning_rate": 0.00017550848792622473, | |
| "loss": 4.572581481933594, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.7003484320557494, | |
| "grad_norm": 1.6086684465408325, | |
| "learning_rate": 0.0001736019615320085, | |
| "loss": 4.542828063964844, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.7874564459930316, | |
| "grad_norm": 1.623887300491333, | |
| "learning_rate": 0.00017163518544651283, | |
| "loss": 4.519979858398438, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.8745644599303137, | |
| "grad_norm": 1.4141863584518433, | |
| "learning_rate": 0.00016960976964927507, | |
| "loss": 4.497909240722656, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.961672473867596, | |
| "grad_norm": 1.2833305597305298, | |
| "learning_rate": 0.00016752737212160374, | |
| "loss": 4.4761376953125, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 3.048780487804878, | |
| "grad_norm": 1.5807830095291138, | |
| "learning_rate": 0.000165389697489375, | |
| "loss": 4.386007385253906, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.1358885017421603, | |
| "grad_norm": 1.5675005912780762, | |
| "learning_rate": 0.00016319849562764608, | |
| "loss": 4.305965576171875, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 3.2229965156794425, | |
| "grad_norm": 1.4463677406311035, | |
| "learning_rate": 0.00016095556022822837, | |
| "loss": 4.2965829467773435, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 3.3101045296167246, | |
| "grad_norm": 1.495564341545105, | |
| "learning_rate": 0.00015866272733139252, | |
| "loss": 4.296761474609375, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 3.397212543554007, | |
| "grad_norm": 1.6361560821533203, | |
| "learning_rate": 0.0001563218738229078, | |
| "loss": 4.255560607910156, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 3.484320557491289, | |
| "grad_norm": 1.61375892162323, | |
| "learning_rate": 0.00015393491589764567, | |
| "loss": 4.2361297607421875, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.571428571428571, | |
| "grad_norm": 1.710850715637207, | |
| "learning_rate": 0.00015150380749100545, | |
| "loss": 4.241318054199219, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 3.658536585365854, | |
| "grad_norm": 1.888376235961914, | |
| "learning_rate": 0.00014903053867944589, | |
| "loss": 4.263135375976563, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.745644599303136, | |
| "grad_norm": 1.5190894603729248, | |
| "learning_rate": 0.00014651713405143234, | |
| "loss": 4.203194580078125, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 3.832752613240418, | |
| "grad_norm": 1.4314178228378296, | |
| "learning_rate": 0.00014396565105013283, | |
| "loss": 4.2452734375, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.9198606271777003, | |
| "grad_norm": 1.4185148477554321, | |
| "learning_rate": 0.0001413781782892191, | |
| "loss": 4.218402099609375, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.006968641114983, | |
| "grad_norm": 1.42833411693573, | |
| "learning_rate": 0.00013875683384315278, | |
| "loss": 4.195860290527344, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 4.094076655052265, | |
| "grad_norm": 1.8272066116333008, | |
| "learning_rate": 0.00013610376351335437, | |
| "loss": 4.000545654296875, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 4.181184668989547, | |
| "grad_norm": 1.6578880548477173, | |
| "learning_rate": 0.00013342113907167596, | |
| "loss": 4.044533386230468, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 4.2682926829268295, | |
| "grad_norm": 1.719120740890503, | |
| "learning_rate": 0.00013071115648261453, | |
| "loss": 4.006611633300781, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 4.355400696864112, | |
| "grad_norm": 1.8038350343704224, | |
| "learning_rate": 0.00012797603410572144, | |
| "loss": 4.005461120605469, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.442508710801394, | |
| "grad_norm": 1.4871196746826172, | |
| "learning_rate": 0.00012521801087967964, | |
| "loss": 4.042769470214844, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 4.529616724738676, | |
| "grad_norm": 1.4674580097198486, | |
| "learning_rate": 0.00012243934448953522, | |
| "loss": 4.014598999023438, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 4.616724738675958, | |
| "grad_norm": 1.650697112083435, | |
| "learning_rate": 0.00011964230951858309, | |
| "loss": 4.0176239013671875, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 4.70383275261324, | |
| "grad_norm": 2.049278497695923, | |
| "learning_rate": 0.00011682919558642024, | |
| "loss": 4.01257568359375, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 4.790940766550523, | |
| "grad_norm": 1.789766550064087, | |
| "learning_rate": 0.00011400230547469015, | |
| "loss": 3.983531494140625, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 4.878048780487805, | |
| "grad_norm": 1.9967801570892334, | |
| "learning_rate": 0.0001111639532420534, | |
| "loss": 3.9888790893554686, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 4.965156794425087, | |
| "grad_norm": 1.5817842483520508, | |
| "learning_rate": 0.00010831646232992643, | |
| "loss": 3.9807525634765626, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 5.052264808362369, | |
| "grad_norm": 1.8074733018875122, | |
| "learning_rate": 0.00010546216366054025, | |
| "loss": 3.868643798828125, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 5.139372822299651, | |
| "grad_norm": 1.5427536964416504, | |
| "learning_rate": 0.00010260339372887494, | |
| "loss": 3.806876220703125, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 5.2264808362369335, | |
| "grad_norm": 1.7108198404312134, | |
| "learning_rate": 9.974249269003289e-05, | |
| "loss": 3.824035949707031, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 5.313588850174216, | |
| "grad_norm": 1.7547175884246826, | |
| "learning_rate": 9.688180244361546e-05, | |
| "loss": 3.8009918212890623, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 5.400696864111498, | |
| "grad_norm": 2.0099358558654785, | |
| "learning_rate": 9.40236647166718e-05, | |
| "loss": 3.8154830932617188, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 5.487804878048781, | |
| "grad_norm": 1.7973719835281372, | |
| "learning_rate": 9.117041914678904e-05, | |
| "loss": 3.8090631103515626, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 5.574912891986063, | |
| "grad_norm": 1.7361223697662354, | |
| "learning_rate": 8.832440136689258e-05, | |
| "loss": 3.8208245849609375, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 5.662020905923345, | |
| "grad_norm": 2.053532361984253, | |
| "learning_rate": 8.548794109332481e-05, | |
| "loss": 3.82370361328125, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 5.7491289198606275, | |
| "grad_norm": 1.8259886503219604, | |
| "learning_rate": 8.266336021876698e-05, | |
| "loss": 3.826884460449219, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 5.83623693379791, | |
| "grad_norm": 1.9447393417358398, | |
| "learning_rate": 7.985297091156554e-05, | |
| "loss": 3.8073544311523437, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 5.923344947735192, | |
| "grad_norm": 1.7228244543075562, | |
| "learning_rate": 7.70590737230184e-05, | |
| "loss": 3.8064419555664064, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 6.010452961672474, | |
| "grad_norm": 2.16105055809021, | |
| "learning_rate": 7.428395570417108e-05, | |
| "loss": 3.7939053344726563, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 6.097560975609756, | |
| "grad_norm": 1.5277420282363892, | |
| "learning_rate": 7.152988853366395e-05, | |
| "loss": 3.6774615478515624, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 6.184668989547038, | |
| "grad_norm": 1.8056442737579346, | |
| "learning_rate": 6.879912665816299e-05, | |
| "loss": 3.6514688110351563, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 6.2717770034843205, | |
| "grad_norm": 1.9114874601364136, | |
| "learning_rate": 6.60939054468966e-05, | |
| "loss": 3.6658111572265626, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 6.358885017421603, | |
| "grad_norm": 1.9075324535369873, | |
| "learning_rate": 6.341643936180881e-05, | |
| "loss": 3.6535992431640625, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 6.445993031358885, | |
| "grad_norm": 1.952846646308899, | |
| "learning_rate": 6.076892014482714e-05, | |
| "loss": 3.6586459350585936, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 6.533101045296167, | |
| "grad_norm": 1.8436208963394165, | |
| "learning_rate": 5.8153515023728645e-05, | |
| "loss": 3.6709304809570313, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 6.620209059233449, | |
| "grad_norm": 1.5615363121032715, | |
| "learning_rate": 5.5572364938073104e-05, | |
| "loss": 3.6649066162109376, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 6.7073170731707314, | |
| "grad_norm": 1.9237865209579468, | |
| "learning_rate": 5.30275827866552e-05, | |
| "loss": 3.6293704223632814, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 6.794425087108014, | |
| "grad_norm": 1.8327174186706543, | |
| "learning_rate": 5.052125169791064e-05, | |
| "loss": 3.652876892089844, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 6.881533101045296, | |
| "grad_norm": 1.786590576171875, | |
| "learning_rate": 4.805542332469209e-05, | |
| "loss": 3.655260009765625, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 6.968641114982578, | |
| "grad_norm": 2.09110164642334, | |
| "learning_rate": 4.563211616481061e-05, | |
| "loss": 3.6624679565429688, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 7.055749128919861, | |
| "grad_norm": 1.8738207817077637, | |
| "learning_rate": 4.325331390871703e-05, | |
| "loss": 3.606045837402344, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 7.142857142857143, | |
| "grad_norm": 1.9863561391830444, | |
| "learning_rate": 4.092096381567675e-05, | |
| "loss": 3.5570523071289064, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 7.229965156794425, | |
| "grad_norm": 2.195230722427368, | |
| "learning_rate": 3.863697511976634e-05, | |
| "loss": 3.5478726196289063, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 7.317073170731708, | |
| "grad_norm": 1.8687387704849243, | |
| "learning_rate": 3.640321746699732e-05, | |
| "loss": 3.5580734252929687, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 7.40418118466899, | |
| "grad_norm": 1.9148145914077759, | |
| "learning_rate": 3.4221519384846014e-05, | |
| "loss": 3.5321905517578127, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 7.491289198606272, | |
| "grad_norm": 1.9626288414001465, | |
| "learning_rate": 3.209366678544267e-05, | |
| "loss": 3.539649658203125, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 7.578397212543554, | |
| "grad_norm": 2.042051315307617, | |
| "learning_rate": 3.002140150364511e-05, | |
| "loss": 3.5744259643554686, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 7.665505226480836, | |
| "grad_norm": 2.2132978439331055, | |
| "learning_rate": 2.800641987119348e-05, | |
| "loss": 3.5455661010742188, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 7.7526132404181185, | |
| "grad_norm": 2.3339362144470215, | |
| "learning_rate": 2.6050371328113e-05, | |
| "loss": 3.5393295288085938, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 7.839721254355401, | |
| "grad_norm": 2.091668128967285, | |
| "learning_rate": 2.4154857072502135e-05, | |
| "loss": 3.5512890625, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 7.926829268292683, | |
| "grad_norm": 1.863627552986145, | |
| "learning_rate": 2.232142874981077e-05, | |
| "loss": 3.554620361328125, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 8.013937282229966, | |
| "grad_norm": 2.4418959617614746, | |
| "learning_rate": 2.055158718268182e-05, | |
| "loss": 3.52468994140625, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 8.101045296167248, | |
| "grad_norm": 2.270392417907715, | |
| "learning_rate": 1.884678114239542e-05, | |
| "loss": 3.488939208984375, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 8.18815331010453, | |
| "grad_norm": 1.8760238885879517, | |
| "learning_rate": 1.7208406162922185e-05, | |
| "loss": 3.480302734375, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 8.275261324041812, | |
| "grad_norm": 1.9609935283660889, | |
| "learning_rate": 1.5637803398555462e-05, | |
| "loss": 3.4763052368164065, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 8.362369337979095, | |
| "grad_norm": 1.92599356174469, | |
| "learning_rate": 1.4136258526058632e-05, | |
| "loss": 3.4983941650390626, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 8.449477351916377, | |
| "grad_norm": 1.9898569583892822, | |
| "learning_rate": 1.2705000692225133e-05, | |
| "loss": 3.48035888671875, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 8.536585365853659, | |
| "grad_norm": 1.9657682180404663, | |
| "learning_rate": 1.1345201507713633e-05, | |
| "loss": 3.4602105712890623, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 8.623693379790941, | |
| "grad_norm": 2.095853567123413, | |
| "learning_rate": 1.0057974087981414e-05, | |
| "loss": 3.4798574829101563, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 8.710801393728223, | |
| "grad_norm": 1.7846027612686157, | |
| "learning_rate": 8.844372142101364e-06, | |
| "loss": 3.4902532958984374, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 8.797909407665506, | |
| "grad_norm": 2.2382795810699463, | |
| "learning_rate": 7.705389110208106e-06, | |
| "loss": 3.4924716186523437, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 8.885017421602788, | |
| "grad_norm": 1.776693344116211, | |
| "learning_rate": 6.6419573502798374e-06, | |
| "loss": 3.5006637573242188, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 8.97212543554007, | |
| "grad_norm": 1.9248723983764648, | |
| "learning_rate": 5.65494737492106e-06, | |
| "loss": 3.4578341674804687, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 9.059233449477352, | |
| "grad_norm": 2.082202911376953, | |
| "learning_rate": 4.7451671387714335e-06, | |
| "loss": 3.461600341796875, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 9.146341463414634, | |
| "grad_norm": 1.8617357015609741, | |
| "learning_rate": 3.913361377123581e-06, | |
| "loss": 3.477802429199219, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 9.233449477351916, | |
| "grad_norm": 1.711703896522522, | |
| "learning_rate": 3.1602109962916905e-06, | |
| "loss": 3.442166748046875, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 9.320557491289199, | |
| "grad_norm": 2.361995220184326, | |
| "learning_rate": 2.4863325162296726e-06, | |
| "loss": 3.454795227050781, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 9.40766550522648, | |
| "grad_norm": 1.8906856775283813, | |
| "learning_rate": 1.8922775658552715e-06, | |
| "loss": 3.4653359985351564, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 9.494773519163763, | |
| "grad_norm": 2.1279709339141846, | |
| "learning_rate": 1.3785324314931847e-06, | |
| "loss": 3.4191864013671873, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 9.581881533101045, | |
| "grad_norm": 2.1340105533599854, | |
| "learning_rate": 9.455176588068382e-07, | |
| "loss": 3.4499856567382814, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 9.668989547038327, | |
| "grad_norm": 2.4744954109191895, | |
| "learning_rate": 5.935877085446851e-07, | |
| "loss": 3.446976318359375, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 9.75609756097561, | |
| "grad_norm": 1.9351354837417603, | |
| "learning_rate": 3.230306663828841e-07, | |
| "loss": 3.423928527832031, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 9.843205574912892, | |
| "grad_norm": 2.3089027404785156, | |
| "learning_rate": 1.3406800710182853e-07, | |
| "loss": 3.4793524169921874, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 9.930313588850174, | |
| "grad_norm": 2.702860116958618, | |
| "learning_rate": 2.685441328938998e-08, | |
| "loss": 3.4213021850585936, | |
| "step": 11400 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 11480, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3002513580490752.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |