Text Generation
Transformers
TensorBoard
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use lldois/v04_balanced_core_lr2e5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lldois/v04_balanced_core_lr2e5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lldois/v04_balanced_core_lr2e5") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lldois/v04_balanced_core_lr2e5") model = AutoModelForCausalLM.from_pretrained("lldois/v04_balanced_core_lr2e5", 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 lldois/v04_balanced_core_lr2e5 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lldois/v04_balanced_core_lr2e5" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lldois/v04_balanced_core_lr2e5", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/lldois/v04_balanced_core_lr2e5
- SGLang
How to use lldois/v04_balanced_core_lr2e5 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 "lldois/v04_balanced_core_lr2e5" \ --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": "lldois/v04_balanced_core_lr2e5", "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 "lldois/v04_balanced_core_lr2e5" \ --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": "lldois/v04_balanced_core_lr2e5", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use lldois/v04_balanced_core_lr2e5 with Docker Model Runner:
docker model run hf.co/lldois/v04_balanced_core_lr2e5
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 613, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008159934720522236, | |
| "grad_norm": 42.25, | |
| "learning_rate": 4.210526315789474e-06, | |
| "loss": 2.764590835571289, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016319869441044473, | |
| "grad_norm": 9.75, | |
| "learning_rate": 9.473684210526315e-06, | |
| "loss": 2.489868927001953, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02447980416156671, | |
| "grad_norm": 8.1875, | |
| "learning_rate": 1.4736842105263159e-05, | |
| "loss": 2.2080495834350584, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.032639738882088945, | |
| "grad_norm": 4.4375, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0085981369018553, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04079967360261118, | |
| "grad_norm": 3.515625, | |
| "learning_rate": 1.9996503676899863e-05, | |
| "loss": 1.855879020690918, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04895960832313342, | |
| "grad_norm": 3.359375, | |
| "learning_rate": 1.9986017152454497e-05, | |
| "loss": 1.8655593872070313, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05711954304365565, | |
| "grad_norm": 3.140625, | |
| "learning_rate": 1.9968547759519426e-05, | |
| "loss": 1.764651107788086, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06527947776417789, | |
| "grad_norm": 3.453125, | |
| "learning_rate": 1.9944107713823068e-05, | |
| "loss": 1.8568502426147462, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07343941248470012, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 1.9912714105424694e-05, | |
| "loss": 1.7390193939208984, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08159934720522236, | |
| "grad_norm": 4.03125, | |
| "learning_rate": 1.9874388886763944e-05, | |
| "loss": 1.5365073204040527, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08975928192574459, | |
| "grad_norm": 2.296875, | |
| "learning_rate": 1.9829158857310288e-05, | |
| "loss": 1.7221796035766601, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.09791921664626684, | |
| "grad_norm": 3.25, | |
| "learning_rate": 1.9777055644823087e-05, | |
| "loss": 1.6801658630371095, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.10607915136678907, | |
| "grad_norm": 3.75, | |
| "learning_rate": 1.9718115683235418e-05, | |
| "loss": 1.6599308013916017, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1142390860873113, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 1.9652380187177128e-05, | |
| "loss": 1.5088156700134276, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.12239902080783353, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 1.957989512315489e-05, | |
| "loss": 1.541905117034912, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.13055895552835578, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.9500711177409456e-05, | |
| "loss": 1.635506820678711, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.138718890248878, | |
| "grad_norm": 3.421875, | |
| "learning_rate": 1.9414883720472557e-05, | |
| "loss": 1.4972270011901856, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.14687882496940025, | |
| "grad_norm": 2.921875, | |
| "learning_rate": 1.932247276844826e-05, | |
| "loss": 1.5120899200439453, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.15503875968992248, | |
| "grad_norm": 2.421875, | |
| "learning_rate": 1.9223542941045817e-05, | |
| "loss": 1.516195011138916, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.1631986944104447, | |
| "grad_norm": 3.578125, | |
| "learning_rate": 1.9118163416393392e-05, | |
| "loss": 1.5576241493225098, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17135862913096694, | |
| "grad_norm": 3.875, | |
| "learning_rate": 1.9006407882664256e-05, | |
| "loss": 1.4911109924316406, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.17951856385148918, | |
| "grad_norm": 2.875, | |
| "learning_rate": 1.8888354486549238e-05, | |
| "loss": 1.4046802520751953, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.18767849857201144, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 1.8764085778611507e-05, | |
| "loss": 1.4821024894714356, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.19583843329253367, | |
| "grad_norm": 2.625, | |
| "learning_rate": 1.863368865556191e-05, | |
| "loss": 1.4233411788940429, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2039983680130559, | |
| "grad_norm": 4.0, | |
| "learning_rate": 1.8497254299495147e-05, | |
| "loss": 1.4180265426635743, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.21215830273357814, | |
| "grad_norm": 3.796875, | |
| "learning_rate": 1.8354878114129368e-05, | |
| "loss": 1.4138151168823243, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.22031823745410037, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 1.820665965809373e-05, | |
| "loss": 1.5245219230651856, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.2284781721746226, | |
| "grad_norm": 3.75, | |
| "learning_rate": 1.8052702575310588e-05, | |
| "loss": 1.4437243461608886, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.23663810689514483, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 1.789311452252092e-05, | |
| "loss": 1.3076929092407226, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.24479804161566707, | |
| "grad_norm": 3.890625, | |
| "learning_rate": 1.772800709400383e-05, | |
| "loss": 1.4008633613586425, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2529579763361893, | |
| "grad_norm": 2.375, | |
| "learning_rate": 1.7557495743542586e-05, | |
| "loss": 1.5305479049682618, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.26111791105671156, | |
| "grad_norm": 3.34375, | |
| "learning_rate": 1.7381699703691866e-05, | |
| "loss": 1.3546552658081055, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2692778457772338, | |
| "grad_norm": 3.953125, | |
| "learning_rate": 1.720074190240269e-05, | |
| "loss": 1.374640655517578, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.277437780497756, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 1.7014748877063212e-05, | |
| "loss": 1.4571109771728517, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.28559771521827826, | |
| "grad_norm": 3.9375, | |
| "learning_rate": 1.682385068601563e-05, | |
| "loss": 1.3947142601013183, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2937576499388005, | |
| "grad_norm": 2.421875, | |
| "learning_rate": 1.6628180817610963e-05, | |
| "loss": 1.425752830505371, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3019175846593227, | |
| "grad_norm": 3.4375, | |
| "learning_rate": 1.6427876096865394e-05, | |
| "loss": 1.4002631187438965, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.31007751937984496, | |
| "grad_norm": 3.8125, | |
| "learning_rate": 1.6223076589783368e-05, | |
| "loss": 1.3912601470947266, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3182374541003672, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 1.6013925505414386e-05, | |
| "loss": 1.2885801315307617, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.3263973888208894, | |
| "grad_norm": 3.96875, | |
| "learning_rate": 1.5800569095711983e-05, | |
| "loss": 1.3117466926574708, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33455732354141166, | |
| "grad_norm": 3.6875, | |
| "learning_rate": 1.5583156553264923e-05, | |
| "loss": 1.4435410499572754, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.3427172582619339, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 1.5361839906972095e-05, | |
| "loss": 1.3575885772705079, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "grad_norm": 4.125, | |
| "learning_rate": 1.5136773915734067e-05, | |
| "loss": 1.3277423858642579, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.35903712770297835, | |
| "grad_norm": 3.25, | |
| "learning_rate": 1.4908115960235683e-05, | |
| "loss": 1.4906869888305665, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.3671970624235006, | |
| "grad_norm": 2.875, | |
| "learning_rate": 1.4676025932895315e-05, | |
| "loss": 1.472239875793457, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.3753569971440229, | |
| "grad_norm": 3.0625, | |
| "learning_rate": 1.4440666126057743e-05, | |
| "loss": 1.3827289581298827, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.3835169318645451, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 1.4202201118508863e-05, | |
| "loss": 1.4698705673217773, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.39167686658506734, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 1.396079766039157e-05, | |
| "loss": 1.390995407104492, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.3998368013055896, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 1.3716624556603275e-05, | |
| "loss": 1.4784428596496582, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.4079967360261118, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 1.3469852548756626e-05, | |
| "loss": 1.4209571838378907, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.41615667074663404, | |
| "grad_norm": 3.6875, | |
| "learning_rate": 1.3220654195785917e-05, | |
| "loss": 1.3656881332397461, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.42431660546715627, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 1.296920375328275e-05, | |
| "loss": 1.5011524200439452, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.4324765401876785, | |
| "grad_norm": 3.421875, | |
| "learning_rate": 1.2715677051645259e-05, | |
| "loss": 1.4276366233825684, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.44063647490820074, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 1.2460251373126136e-05, | |
| "loss": 1.390436553955078, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.44879640962872297, | |
| "grad_norm": 3.265625, | |
| "learning_rate": 1.2203105327865407e-05, | |
| "loss": 1.3565399169921875, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.4569563443492452, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 1.194441872899471e-05, | |
| "loss": 1.472177791595459, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.46511627906976744, | |
| "grad_norm": 2.296875, | |
| "learning_rate": 1.1684372466900306e-05, | |
| "loss": 1.4198420524597168, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.47327621379028967, | |
| "grad_norm": 4.03125, | |
| "learning_rate": 1.1423148382732854e-05, | |
| "loss": 1.322580337524414, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.4814361485108119, | |
| "grad_norm": 2.296875, | |
| "learning_rate": 1.1160929141252303e-05, | |
| "loss": 1.4380602836608887, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.48959608323133413, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 1.0897898103096917e-05, | |
| "loss": 1.285576343536377, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.49775601795185637, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 1.0634239196565646e-05, | |
| "loss": 1.4786340713500976, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.5059159526723787, | |
| "grad_norm": 2.953125, | |
| "learning_rate": 1.0370136789003582e-05, | |
| "loss": 1.374602699279785, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.5140758873929009, | |
| "grad_norm": 3.84375, | |
| "learning_rate": 1.0105775557880398e-05, | |
| "loss": 1.4532788276672364, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.5222358221134231, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 9.841340361651921e-06, | |
| "loss": 1.3536710739135742, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5303957568339454, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 9.57701611049517e-06, | |
| "loss": 1.3883792877197265, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.5385556915544676, | |
| "grad_norm": 3.78125, | |
| "learning_rate": 9.312987637007191e-06, | |
| "loss": 1.3699709892272949, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.5467156262749898, | |
| "grad_norm": 3.140625, | |
| "learning_rate": 9.049439566958176e-06, | |
| "loss": 1.4548574447631837, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.554875560995512, | |
| "grad_norm": 3.0, | |
| "learning_rate": 8.786556190189183e-06, | |
| "loss": 1.3517833709716798, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.5630354957160343, | |
| "grad_norm": 3.25, | |
| "learning_rate": 8.52452133174478e-06, | |
| "loss": 1.426644992828369, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.5711954304365565, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 1.383060359954834, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5793553651570787, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 8.00372937518636e-06, | |
| "loss": 1.331951904296875, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.587515299877601, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 7.745336448461958e-06, | |
| "loss": 1.445413303375244, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.5956752345981232, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 7.488520128189209e-06, | |
| "loss": 1.4074223518371582, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.6038351693186454, | |
| "grad_norm": 3.609375, | |
| "learning_rate": 7.233459996934731e-06, | |
| "loss": 1.3592453956604005, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.6119951040391677, | |
| "grad_norm": 4.28125, | |
| "learning_rate": 6.9803344092242855e-06, | |
| "loss": 1.3151020050048827, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.6201550387596899, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 6.729320366825785e-06, | |
| "loss": 1.3170394897460938, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.6283149734802121, | |
| "grad_norm": 2.46875, | |
| "learning_rate": 6.480593394978208e-06, | |
| "loss": 1.4254400253295898, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.6364749082007344, | |
| "grad_norm": 4.34375, | |
| "learning_rate": 6.234327419653013e-06, | |
| "loss": 1.3528937339782714, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.6446348429212566, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 5.990694645933866e-06, | |
| "loss": 1.3909344673156738, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.6527947776417788, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 5.749865437599703e-06, | |
| "loss": 1.4332430839538575, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6609547123623011, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 5.512008197995379e-06, | |
| "loss": 1.4415637016296388, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.6691146470828233, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 5.277289252273175e-06, | |
| "loss": 1.3970324516296386, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.6772745818033455, | |
| "grad_norm": 3.9375, | |
| "learning_rate": 5.045872731087479e-06, | |
| "loss": 1.3478738784790039, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.6854345165238678, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 4.817920455824045e-06, | |
| "loss": 1.3553836822509766, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.69359445124439, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 4.593591825444028e-06, | |
| "loss": 1.4708582878112793, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 2.328125, | |
| "learning_rate": 4.373043705021899e-06, | |
| "loss": 1.4501720428466798, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.7099143206854345, | |
| "grad_norm": 4.3125, | |
| "learning_rate": 4.1564303160552935e-06, | |
| "loss": 1.3744462966918944, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.7180742554059567, | |
| "grad_norm": 1.859375, | |
| "learning_rate": 3.943903128623336e-06, | |
| "loss": 1.3946028709411622, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.7262341901264789, | |
| "grad_norm": 3.4375, | |
| "learning_rate": 3.735610755468988e-06, | |
| "loss": 1.2606407165527345, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.7343941248470012, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 3.5316988480794255e-06, | |
| "loss": 1.3681606292724608, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.7425540595675234, | |
| "grad_norm": 2.46875, | |
| "learning_rate": 3.3323099948370853e-06, | |
| "loss": 1.3252838134765625, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.7507139942880457, | |
| "grad_norm": 3.90625, | |
| "learning_rate": 3.1375836213126653e-06, | |
| "loss": 1.414201831817627, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.758873929008568, | |
| "grad_norm": 4.4375, | |
| "learning_rate": 2.9476558927697605e-06, | |
| "loss": 1.318328857421875, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.7670338637290902, | |
| "grad_norm": 3.78125, | |
| "learning_rate": 2.7626596189492983e-06, | |
| "loss": 1.3034313201904297, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.7751937984496124, | |
| "grad_norm": 2.25, | |
| "learning_rate": 2.582724161200405e-06, | |
| "loss": 1.3811626434326172, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.7833537331701347, | |
| "grad_norm": 3.125, | |
| "learning_rate": 2.4079753420225694e-06, | |
| "loss": 1.3948455810546876, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.7915136678906569, | |
| "grad_norm": 2.125, | |
| "learning_rate": 2.2385353570824308e-06, | |
| "loss": 1.3906720161437989, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.7996736026111791, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 2.0745226897666858e-06, | |
| "loss": 1.4307458877563477, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.8078335373317014, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 1.9160520283308115e-06, | |
| "loss": 1.3465310096740724, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.8159934720522236, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 1.7632341857016733e-06, | |
| "loss": 1.4635851860046387, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8241534067727458, | |
| "grad_norm": 3.578125, | |
| "learning_rate": 1.616176021989926e-06, | |
| "loss": 1.4342742919921876, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.8323133414932681, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.4749803697665366e-06, | |
| "loss": 1.4339244842529297, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.8404732762137903, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 1.339745962155613e-06, | |
| "loss": 1.3769190788269043, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.8486332109343125, | |
| "grad_norm": 3.4375, | |
| "learning_rate": 1.2105673637938054e-06, | |
| "loss": 1.3848706245422364, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.8567931456548348, | |
| "grad_norm": 2.75, | |
| "learning_rate": 1.0875349047046113e-06, | |
| "loss": 1.460084819793701, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.864953080375357, | |
| "grad_norm": 4.3125, | |
| "learning_rate": 9.707346171337895e-07, | |
| "loss": 1.4155464172363281, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.8731130150958792, | |
| "grad_norm": 3.78125, | |
| "learning_rate": 8.602481753900427e-07, | |
| "loss": 1.370467472076416, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.8812729498164015, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 7.561528387330797e-07, | |
| "loss": 1.4545866012573243, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.8894328845369237, | |
| "grad_norm": 3.203125, | |
| "learning_rate": 6.585213973489335e-07, | |
| "loss": 1.3990278244018555, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.8975928192574459, | |
| "grad_norm": 2.375, | |
| "learning_rate": 5.674221214503639e-07, | |
| "loss": 1.3850707054138183, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.9057527539779682, | |
| "grad_norm": 3.125, | |
| "learning_rate": 4.829187135379221e-07, | |
| "loss": 1.4300135612487792, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.9139126886984904, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 4.0507026385502747e-07, | |
| "loss": 1.3187259674072265, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.9220726234190126, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 3.339312090682689e-07, | |
| "loss": 1.4685959815979004, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.9302325581395349, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 2.6955129420176193e-07, | |
| "loss": 1.4852921485900878, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.9383924928600571, | |
| "grad_norm": 3.4375, | |
| "learning_rate": 2.119755378522137e-07, | |
| "loss": 1.3241841316223144, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.9465524275805793, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 1.612442007090076e-07, | |
| "loss": 1.3388869285583496, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.9547123623011016, | |
| "grad_norm": 4.625, | |
| "learning_rate": 1.1739275740134004e-07, | |
| "loss": 1.2855671882629394, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.9628722970216238, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 8.04518716920466e-08, | |
| "loss": 1.3641891479492188, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.971032231742146, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 5.044737503554165e-08, | |
| "loss": 1.5328051567077636, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.9791921664626683, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 2.7400248514776184e-08, | |
| "loss": 1.3465785026550292, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.9873521011831905, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 1.1326608169920373e-08, | |
| "loss": 1.39981107711792, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.9955120359037127, | |
| "grad_norm": 3.125, | |
| "learning_rate": 2.237693728981416e-09, | |
| "loss": 1.4022762298583984, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 613, | |
| "total_flos": 2.961647362958254e+17, | |
| "train_loss": 1.4641528666311143, | |
| "train_runtime": 5382.2079, | |
| "train_samples_per_second": 0.455, | |
| "train_steps_per_second": 0.114 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 613, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 2.961647362958254e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |