Text Generation
Transformers
Safetensors
English
French
Estonian
llama4_text
legal
law
multilingual
english
french
estonian
legal-reasoning
lora
instruction-tuning
llama-3
adaption-labs
conversational
4-bit precision
bitsandbytes
Instructions to use RayNene/Trilex with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RayNene/Trilex with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RayNene/Trilex") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("RayNene/Trilex") model = AutoModelForCausalLM.from_pretrained("RayNene/Trilex") 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 RayNene/Trilex with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RayNene/Trilex" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RayNene/Trilex", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/RayNene/Trilex
- SGLang
How to use RayNene/Trilex 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 "RayNene/Trilex" \ --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": "RayNene/Trilex", "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 "RayNene/Trilex" \ --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": "RayNene/Trilex", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use RayNene/Trilex with Docker Model Runner:
docker model run hf.co/RayNene/Trilex
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 47, | |
| "global_step": 235, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02127659574468085, | |
| "grad_norm": 0.23393794894218445, | |
| "learning_rate": 0.0, | |
| "loss": 1.498046875, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0425531914893617, | |
| "grad_norm": 0.35629600286483765, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.4755859375, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06382978723404255, | |
| "grad_norm": 0.23825904726982117, | |
| "learning_rate": 5e-05, | |
| "loss": 1.46875, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": 0.2110234946012497, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.4609375, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10638297872340426, | |
| "grad_norm": 0.11191354691982269, | |
| "learning_rate": 0.0001, | |
| "loss": 1.283203125, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1276595744680851, | |
| "grad_norm": 0.10534299165010452, | |
| "learning_rate": 0.000125, | |
| "loss": 1.40625, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14893617021276595, | |
| "grad_norm": 0.2014382779598236, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.341796875, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1702127659574468, | |
| "grad_norm": 0.18545843660831451, | |
| "learning_rate": 0.000175, | |
| "loss": 1.21185302734375, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.19148936170212766, | |
| "grad_norm": 0.10173580050468445, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2802734375, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2127659574468085, | |
| "grad_norm": 0.07516055554151535, | |
| "learning_rate": 0.00019999185989458338, | |
| "loss": 1.357421875, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.23404255319148937, | |
| "grad_norm": 0.06378420442342758, | |
| "learning_rate": 0.00019996744113742325, | |
| "loss": 1.0709228515625, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2553191489361702, | |
| "grad_norm": 0.07495936006307602, | |
| "learning_rate": 0.00019992674840549045, | |
| "loss": 1.283203125, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2765957446808511, | |
| "grad_norm": 0.07314153015613556, | |
| "learning_rate": 0.00019986978949274083, | |
| "loss": 1.2734375, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2978723404255319, | |
| "grad_norm": 0.05656423047184944, | |
| "learning_rate": 0.00019979657530862276, | |
| "loss": 1.1826171875, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3191489361702128, | |
| "grad_norm": 0.0377945713698864, | |
| "learning_rate": 0.00019970711987598753, | |
| "loss": 1.2021484375, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 0.03924940899014473, | |
| "learning_rate": 0.00019960144032840334, | |
| "loss": 1.2109375, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3617021276595745, | |
| "grad_norm": 0.051506128162145615, | |
| "learning_rate": 0.00019947955690687388, | |
| "loss": 1.15380859375, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3829787234042553, | |
| "grad_norm": 0.05868421867489815, | |
| "learning_rate": 0.00019934149295596157, | |
| "loss": 1.16259765625, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.40425531914893614, | |
| "grad_norm": 0.06149609386920929, | |
| "learning_rate": 0.0001991872749193161, | |
| "loss": 1.1240234375, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.425531914893617, | |
| "grad_norm": 0.039777159690856934, | |
| "learning_rate": 0.00019901693233460987, | |
| "loss": 1.224609375, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.44680851063829785, | |
| "grad_norm": 0.04213375225663185, | |
| "learning_rate": 0.00019883049782788045, | |
| "loss": 1.15869140625, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.46808510638297873, | |
| "grad_norm": 0.04403379186987877, | |
| "learning_rate": 0.00019862800710728168, | |
| "loss": 1.1796875, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.48936170212765956, | |
| "grad_norm": 0.03600035607814789, | |
| "learning_rate": 0.00019840949895624438, | |
| "loss": 1.2626953125, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5106382978723404, | |
| "grad_norm": 0.03431978449225426, | |
| "learning_rate": 0.0001981750152260482, | |
| "loss": 1.2353515625, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5319148936170213, | |
| "grad_norm": 0.0372556671500206, | |
| "learning_rate": 0.00019792460082780568, | |
| "loss": 1.1591796875, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5531914893617021, | |
| "grad_norm": 0.028302719816565514, | |
| "learning_rate": 0.0001976583037238603, | |
| "loss": 1.197265625, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.574468085106383, | |
| "grad_norm": 0.026456288993358612, | |
| "learning_rate": 0.00019737617491860028, | |
| "loss": 1.1591796875, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5957446808510638, | |
| "grad_norm": 0.03277663141489029, | |
| "learning_rate": 0.00019707826844868952, | |
| "loss": 1.166015625, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6170212765957447, | |
| "grad_norm": 0.03094353713095188, | |
| "learning_rate": 0.00019676464137271786, | |
| "loss": 1.2197265625, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6382978723404256, | |
| "grad_norm": 0.026416977867484093, | |
| "learning_rate": 0.00019643535376027263, | |
| "loss": 1.1787109375, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6595744680851063, | |
| "grad_norm": 0.02268395945429802, | |
| "learning_rate": 0.00019609046868043328, | |
| "loss": 0.9776611328125, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 0.027079889550805092, | |
| "learning_rate": 0.00019573005218969175, | |
| "loss": 1.19140625, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7021276595744681, | |
| "grad_norm": 0.03761419281363487, | |
| "learning_rate": 0.00019535417331930047, | |
| "loss": 1.1455078125, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.723404255319149, | |
| "grad_norm": 0.029582127928733826, | |
| "learning_rate": 0.0001949629040620507, | |
| "loss": 1.03955078125, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7446808510638298, | |
| "grad_norm": 0.027478355914354324, | |
| "learning_rate": 0.0001945563193584836, | |
| "loss": 1.15234375, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7659574468085106, | |
| "grad_norm": 0.043285392224788666, | |
| "learning_rate": 0.0001941344970825368, | |
| "loss": 1.1416015625, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7872340425531915, | |
| "grad_norm": 0.02737746201455593, | |
| "learning_rate": 0.000193697518026629, | |
| "loss": 1.0283203125, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8085106382978723, | |
| "grad_norm": 0.027979858219623566, | |
| "learning_rate": 0.00019324546588618552, | |
| "loss": 1.169921875, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8297872340425532, | |
| "grad_norm": 0.02747548371553421, | |
| "learning_rate": 0.00019277842724360825, | |
| "loss": 1.1865234375, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 0.0261751189827919, | |
| "learning_rate": 0.00019229649155169207, | |
| "loss": 1.1396484375, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8723404255319149, | |
| "grad_norm": 0.026329027488827705, | |
| "learning_rate": 0.00019179975111649196, | |
| "loss": 1.177734375, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8936170212765957, | |
| "grad_norm": 0.026858177036046982, | |
| "learning_rate": 0.00019128830107964338, | |
| "loss": 1.1123046875, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9148936170212766, | |
| "grad_norm": 0.02628260664641857, | |
| "learning_rate": 0.00019076223940013966, | |
| "loss": 1.1318359375, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9361702127659575, | |
| "grad_norm": 0.027040669694542885, | |
| "learning_rate": 0.00019022166683556964, | |
| "loss": 1.1669921875, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9574468085106383, | |
| "grad_norm": 0.030067605897784233, | |
| "learning_rate": 0.00018966668692281947, | |
| "loss": 1.09228515625, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9787234042553191, | |
| "grad_norm": 0.024822646751999855, | |
| "learning_rate": 0.00018909740595824193, | |
| "loss": 1.068359375, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.04047278314828873, | |
| "learning_rate": 0.00018851393297729732, | |
| "loss": 1.095703125, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.130859375, | |
| "eval_runtime": 5.5329, | |
| "eval_samples_per_second": 0.542, | |
| "eval_steps_per_second": 0.181, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0212765957446808, | |
| "grad_norm": 0.02252831682562828, | |
| "learning_rate": 0.0001879163797336698, | |
| "loss": 1.0732421875, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0425531914893618, | |
| "grad_norm": 0.03408103808760643, | |
| "learning_rate": 0.00018730486067786265, | |
| "loss": 1.04296875, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "grad_norm": 0.04057957977056503, | |
| "learning_rate": 0.00018667949293527783, | |
| "loss": 1.033203125, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0851063829787233, | |
| "grad_norm": 0.03971686214208603, | |
| "learning_rate": 0.0001860403962837823, | |
| "loss": 1.068359375, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.1063829787234043, | |
| "grad_norm": 0.0383610762655735, | |
| "learning_rate": 0.000185387693130767, | |
| "loss": 1.01318359375, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.127659574468085, | |
| "grad_norm": 0.031908098608255386, | |
| "learning_rate": 0.0001847215084897019, | |
| "loss": 1.1396484375, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.148936170212766, | |
| "grad_norm": 0.0396200455725193, | |
| "learning_rate": 0.00018404196995619175, | |
| "loss": 1.1015625, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.1702127659574468, | |
| "grad_norm": 0.0316191166639328, | |
| "learning_rate": 0.0001833492076835377, | |
| "loss": 1.0084228515625, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.1914893617021276, | |
| "grad_norm": 0.023904742673039436, | |
| "learning_rate": 0.0001826433543578087, | |
| "loss": 1.0810546875, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.2127659574468086, | |
| "grad_norm": 0.03784968703985214, | |
| "learning_rate": 0.00018192454517242768, | |
| "loss": 1.1533203125, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.2340425531914894, | |
| "grad_norm": 0.03177719935774803, | |
| "learning_rate": 0.00018119291780227816, | |
| "loss": 0.9163818359375, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.2553191489361701, | |
| "grad_norm": 0.029503269121050835, | |
| "learning_rate": 0.00018044861237733462, | |
| "loss": 1.115234375, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.2765957446808511, | |
| "grad_norm": 0.03916515037417412, | |
| "learning_rate": 0.00017969177145582346, | |
| "loss": 1.10498046875, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.297872340425532, | |
| "grad_norm": 0.0334615521132946, | |
| "learning_rate": 0.00017892253999691842, | |
| "loss": 1.03173828125, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.3191489361702127, | |
| "grad_norm": 0.02631629817187786, | |
| "learning_rate": 0.00017814106533297632, | |
| "loss": 1.056640625, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.3404255319148937, | |
| "grad_norm": 0.03638143837451935, | |
| "learning_rate": 0.00017734749714131827, | |
| "loss": 1.0673828125, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.3617021276595744, | |
| "grad_norm": 0.03113693557679653, | |
| "learning_rate": 0.0001765419874155616, | |
| "loss": 1.00830078125, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.3829787234042552, | |
| "grad_norm": 0.03078601136803627, | |
| "learning_rate": 0.00017572469043650808, | |
| "loss": 1.03125, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.4042553191489362, | |
| "grad_norm": 0.02543475851416588, | |
| "learning_rate": 0.00017489576274259472, | |
| "loss": 1.0009765625, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.425531914893617, | |
| "grad_norm": 0.031025195494294167, | |
| "learning_rate": 0.0001740553630999111, | |
| "loss": 1.0927734375, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.4468085106382977, | |
| "grad_norm": 0.02687178924679756, | |
| "learning_rate": 0.000173203652471791, | |
| "loss": 1.03076171875, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.4680851063829787, | |
| "grad_norm": 0.02888372913002968, | |
| "learning_rate": 0.0001723407939879826, | |
| "loss": 1.05419921875, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.4893617021276595, | |
| "grad_norm": 0.0319877564907074, | |
| "learning_rate": 0.00017146695291340392, | |
| "loss": 1.140625, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.5106382978723403, | |
| "grad_norm": 0.0288713201880455, | |
| "learning_rate": 0.00017058229661648947, | |
| "loss": 1.1103515625, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.5319148936170213, | |
| "grad_norm": 0.033843640238046646, | |
| "learning_rate": 0.00016968699453713367, | |
| "loss": 1.0419921875, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.5531914893617023, | |
| "grad_norm": 0.02779719978570938, | |
| "learning_rate": 0.00016878121815423782, | |
| "loss": 1.08154296875, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.574468085106383, | |
| "grad_norm": 0.029009222984313965, | |
| "learning_rate": 0.00016786514095286646, | |
| "loss": 1.04931640625, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.5957446808510638, | |
| "grad_norm": 0.03975093364715576, | |
| "learning_rate": 0.0001669389383910193, | |
| "loss": 1.05126953125, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.6170212765957448, | |
| "grad_norm": 0.030499164015054703, | |
| "learning_rate": 0.00016600278786602549, | |
| "loss": 1.1044921875, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.6382978723404256, | |
| "grad_norm": 0.03535850718617439, | |
| "learning_rate": 0.00016505686868056646, | |
| "loss": 1.072265625, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.6595744680851063, | |
| "grad_norm": 0.028383029624819756, | |
| "learning_rate": 0.00016410136200833365, | |
| "loss": 0.89642333984375, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.6808510638297873, | |
| "grad_norm": 0.02772560343146324, | |
| "learning_rate": 0.0001631364508593279, | |
| "loss": 1.08740234375, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.702127659574468, | |
| "grad_norm": 0.0280919149518013, | |
| "learning_rate": 0.00016216232004480745, | |
| "loss": 1.0400390625, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.7234042553191489, | |
| "grad_norm": 0.03165218606591225, | |
| "learning_rate": 0.0001611791561418903, | |
| "loss": 0.950927734375, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.7446808510638299, | |
| "grad_norm": 0.031245512887835503, | |
| "learning_rate": 0.00016018714745781912, | |
| "loss": 1.0517578125, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.7659574468085106, | |
| "grad_norm": 0.02875831164419651, | |
| "learning_rate": 0.00015918648399389424, | |
| "loss": 1.03857421875, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.7872340425531914, | |
| "grad_norm": 0.02935316413640976, | |
| "learning_rate": 0.00015817735740908227, | |
| "loss": 0.9404296875, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.8085106382978724, | |
| "grad_norm": 0.028770264238119125, | |
| "learning_rate": 0.00015715996098330742, | |
| "loss": 1.07666015625, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.8297872340425532, | |
| "grad_norm": 0.03135351464152336, | |
| "learning_rate": 0.00015613448958043223, | |
| "loss": 1.09716796875, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.851063829787234, | |
| "grad_norm": 0.030160393565893173, | |
| "learning_rate": 0.0001551011396109348, | |
| "loss": 1.04296875, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.872340425531915, | |
| "grad_norm": 0.028330618515610695, | |
| "learning_rate": 0.00015406010899429007, | |
| "loss": 1.08642578125, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.8936170212765957, | |
| "grad_norm": 0.029394598677754402, | |
| "learning_rate": 0.00015301159712106187, | |
| "loss": 1.021484375, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.9148936170212765, | |
| "grad_norm": 0.029200712218880653, | |
| "learning_rate": 0.0001519558048147132, | |
| "loss": 1.037109375, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.9361702127659575, | |
| "grad_norm": 0.02774479240179062, | |
| "learning_rate": 0.00015089293429314216, | |
| "loss": 1.0791015625, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.9574468085106385, | |
| "grad_norm": 0.028711751103401184, | |
| "learning_rate": 0.00014982318912995095, | |
| "loss": 1.0048828125, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.978723404255319, | |
| "grad_norm": 0.02777498960494995, | |
| "learning_rate": 0.00014874677421545477, | |
| "loss": 0.98388671875, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.029884032905101776, | |
| "learning_rate": 0.00014766389571743894, | |
| "loss": 0.990234375, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.08203125, | |
| "eval_runtime": 5.516, | |
| "eval_samples_per_second": 0.544, | |
| "eval_steps_per_second": 0.181, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 2.021276595744681, | |
| "grad_norm": 0.029040010645985603, | |
| "learning_rate": 0.00014657476104167115, | |
| "loss": 0.97216796875, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 2.0425531914893615, | |
| "grad_norm": 0.0317298099398613, | |
| "learning_rate": 0.00014547957879217668, | |
| "loss": 0.966796875, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.0638297872340425, | |
| "grad_norm": 0.03343191742897034, | |
| "learning_rate": 0.000144378558731284, | |
| "loss": 0.94873046875, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 2.0851063829787235, | |
| "grad_norm": 0.030764257535338402, | |
| "learning_rate": 0.00014327191173944874, | |
| "loss": 0.984375, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 2.106382978723404, | |
| "grad_norm": 0.031886182725429535, | |
| "learning_rate": 0.00014215984977486315, | |
| "loss": 0.93408203125, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 2.127659574468085, | |
| "grad_norm": 0.029551995918154716, | |
| "learning_rate": 0.00014104258583285946, | |
| "loss": 1.05908203125, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.148936170212766, | |
| "grad_norm": 0.038718681782484055, | |
| "learning_rate": 0.00013992033390511458, | |
| "loss": 1.02294921875, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 2.1702127659574466, | |
| "grad_norm": 0.029679151251912117, | |
| "learning_rate": 0.0001387933089386637, | |
| "loss": 0.937591552734375, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.1914893617021276, | |
| "grad_norm": 0.041849151253700256, | |
| "learning_rate": 0.00013766172679473114, | |
| "loss": 1.00146484375, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 2.2127659574468086, | |
| "grad_norm": 0.030312562361359596, | |
| "learning_rate": 0.00013652580420738607, | |
| "loss": 1.07080078125, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.2340425531914896, | |
| "grad_norm": 0.030917160212993622, | |
| "learning_rate": 0.00013538575874203095, | |
| "loss": 0.8511962890625, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.25531914893617, | |
| "grad_norm": 0.03268856555223465, | |
| "learning_rate": 0.00013424180875373093, | |
| "loss": 1.03759765625, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 2.276595744680851, | |
| "grad_norm": 0.030307801440358162, | |
| "learning_rate": 0.00013309417334539183, | |
| "loss": 1.02734375, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 2.297872340425532, | |
| "grad_norm": 0.029849864542484283, | |
| "learning_rate": 0.00013194307232579488, | |
| "loss": 0.95849609375, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.3191489361702127, | |
| "grad_norm": 0.030392149463295937, | |
| "learning_rate": 0.00013078872616749642, | |
| "loss": 0.98291015625, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 2.3404255319148937, | |
| "grad_norm": 0.03271440789103508, | |
| "learning_rate": 0.00012963135596460036, | |
| "loss": 0.99072265625, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.3617021276595747, | |
| "grad_norm": 0.029442068189382553, | |
| "learning_rate": 0.0001284711833904116, | |
| "loss": 0.93798828125, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 2.382978723404255, | |
| "grad_norm": 0.03272737190127373, | |
| "learning_rate": 0.00012730843065497847, | |
| "loss": 0.96240234375, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.404255319148936, | |
| "grad_norm": 0.03141280636191368, | |
| "learning_rate": 0.00012614332046253254, | |
| "loss": 0.93408203125, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 2.425531914893617, | |
| "grad_norm": 0.033171191811561584, | |
| "learning_rate": 0.00012497607596883352, | |
| "loss": 1.01904296875, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.4468085106382977, | |
| "grad_norm": 0.03286304324865341, | |
| "learning_rate": 0.0001238069207384279, | |
| "loss": 0.95947265625, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.4680851063829787, | |
| "grad_norm": 0.12366930395364761, | |
| "learning_rate": 0.00012263607870182918, | |
| "loss": 0.982421875, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.4893617021276597, | |
| "grad_norm": 0.0373450331389904, | |
| "learning_rate": 0.00012146377411262806, | |
| "loss": 1.06884765625, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 2.5106382978723403, | |
| "grad_norm": 0.03353523090481758, | |
| "learning_rate": 0.00012029023150454064, | |
| "loss": 1.0361328125, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.5319148936170213, | |
| "grad_norm": 0.03350302577018738, | |
| "learning_rate": 0.00011911567564840325, | |
| "loss": 0.974609375, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 2.5531914893617023, | |
| "grad_norm": 0.03674326464533806, | |
| "learning_rate": 0.00011794033150912135, | |
| "loss": 1.01123046875, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.574468085106383, | |
| "grad_norm": 0.03349175676703453, | |
| "learning_rate": 0.00011676442420258202, | |
| "loss": 0.984375, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 2.595744680851064, | |
| "grad_norm": 0.03776804730296135, | |
| "learning_rate": 0.00011558817895253658, | |
| "loss": 0.9833984375, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.617021276595745, | |
| "grad_norm": 0.037562087178230286, | |
| "learning_rate": 0.00011441182104746344, | |
| "loss": 1.03369140625, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.6382978723404253, | |
| "grad_norm": 0.03163403272628784, | |
| "learning_rate": 0.00011323557579741797, | |
| "loss": 1.00439453125, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.6595744680851063, | |
| "grad_norm": 0.03091254085302353, | |
| "learning_rate": 0.00011205966849087864, | |
| "loss": 0.84625244140625, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.6808510638297873, | |
| "grad_norm": 0.043524835258722305, | |
| "learning_rate": 0.00011088432435159679, | |
| "loss": 1.0205078125, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.702127659574468, | |
| "grad_norm": 0.0412999652326107, | |
| "learning_rate": 0.00010970976849545936, | |
| "loss": 0.97412109375, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 2.723404255319149, | |
| "grad_norm": 0.03663191571831703, | |
| "learning_rate": 0.00010853622588737198, | |
| "loss": 0.89208984375, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.74468085106383, | |
| "grad_norm": 0.049419160932302475, | |
| "learning_rate": 0.00010736392129817083, | |
| "loss": 0.9853515625, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.7659574468085104, | |
| "grad_norm": 0.11463593691587448, | |
| "learning_rate": 0.0001061930792615721, | |
| "loss": 0.974609375, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.7872340425531914, | |
| "grad_norm": 0.032455358654260635, | |
| "learning_rate": 0.0001050239240311665, | |
| "loss": 0.88623046875, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 2.8085106382978724, | |
| "grad_norm": 0.03574486821889877, | |
| "learning_rate": 0.00010385667953746748, | |
| "loss": 1.01123046875, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.829787234042553, | |
| "grad_norm": 0.03459080681204796, | |
| "learning_rate": 0.00010269156934502154, | |
| "loss": 1.03564453125, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 2.851063829787234, | |
| "grad_norm": 0.031877003610134125, | |
| "learning_rate": 0.00010152881660958842, | |
| "loss": 0.98046875, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.872340425531915, | |
| "grad_norm": 0.03113487735390663, | |
| "learning_rate": 0.00010036864403539965, | |
| "loss": 1.0205078125, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.8936170212765955, | |
| "grad_norm": 0.03436438366770744, | |
| "learning_rate": 9.921127383250361e-05, | |
| "loss": 0.9609375, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.9148936170212765, | |
| "grad_norm": 0.032232243567705154, | |
| "learning_rate": 9.805692767420514e-05, | |
| "loss": 0.97265625, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 2.9361702127659575, | |
| "grad_norm": 0.033736906945705414, | |
| "learning_rate": 9.690582665460819e-05, | |
| "loss": 1.01611328125, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.9574468085106385, | |
| "grad_norm": 0.030821099877357483, | |
| "learning_rate": 9.575819124626905e-05, | |
| "loss": 0.94287109375, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 2.978723404255319, | |
| "grad_norm": 0.03239232301712036, | |
| "learning_rate": 9.461424125796907e-05, | |
| "loss": 0.9228515625, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.035801757127046585, | |
| "learning_rate": 9.347419579261398e-05, | |
| "loss": 0.91064453125, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.068359375, | |
| "eval_runtime": 5.5027, | |
| "eval_samples_per_second": 0.545, | |
| "eval_steps_per_second": 0.182, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 3.021276595744681, | |
| "grad_norm": 0.031308405101299286, | |
| "learning_rate": 9.233827320526887e-05, | |
| "loss": 0.89306640625, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 3.0425531914893615, | |
| "grad_norm": 0.042995061725378036, | |
| "learning_rate": 9.12066910613363e-05, | |
| "loss": 0.912109375, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 3.0638297872340425, | |
| "grad_norm": 0.04316018521785736, | |
| "learning_rate": 9.007966609488546e-05, | |
| "loss": 0.89013671875, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 3.0851063829787235, | |
| "grad_norm": 0.03554543852806091, | |
| "learning_rate": 8.895741416714056e-05, | |
| "loss": 0.92919921875, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 3.106382978723404, | |
| "grad_norm": 0.04152313992381096, | |
| "learning_rate": 8.78401502251369e-05, | |
| "loss": 0.87744140625, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 3.127659574468085, | |
| "grad_norm": 0.039277493953704834, | |
| "learning_rate": 8.672808826055129e-05, | |
| "loss": 1.001953125, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 3.148936170212766, | |
| "grad_norm": 0.0363825261592865, | |
| "learning_rate": 8.562144126871601e-05, | |
| "loss": 0.96533203125, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 3.1702127659574466, | |
| "grad_norm": 0.040966104716062546, | |
| "learning_rate": 8.452042120782332e-05, | |
| "loss": 0.886871337890625, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 3.1914893617021276, | |
| "grad_norm": 0.041720908135175705, | |
| "learning_rate": 8.342523895832885e-05, | |
| "loss": 0.943359375, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.2127659574468086, | |
| "grad_norm": 0.03947775438427925, | |
| "learning_rate": 8.23361042825611e-05, | |
| "loss": 1.01416015625, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 3.2340425531914896, | |
| "grad_norm": 0.03244869410991669, | |
| "learning_rate": 8.125322578454524e-05, | |
| "loss": 0.8028564453125, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 3.25531914893617, | |
| "grad_norm": 0.04258759692311287, | |
| "learning_rate": 8.017681087004904e-05, | |
| "loss": 0.98095703125, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 3.276595744680851, | |
| "grad_norm": 0.03907298296689987, | |
| "learning_rate": 7.910706570685784e-05, | |
| "loss": 0.97314453125, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 3.297872340425532, | |
| "grad_norm": 0.03476712107658386, | |
| "learning_rate": 7.804419518528682e-05, | |
| "loss": 0.904296875, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 3.3191489361702127, | |
| "grad_norm": 0.042200688272714615, | |
| "learning_rate": 7.698840287893813e-05, | |
| "loss": 0.92822265625, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 3.3404255319148937, | |
| "grad_norm": 0.03728483244776726, | |
| "learning_rate": 7.593989100570993e-05, | |
| "loss": 0.9365234375, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 3.3617021276595747, | |
| "grad_norm": 0.0334622859954834, | |
| "learning_rate": 7.48988603890652e-05, | |
| "loss": 0.88623046875, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 3.382978723404255, | |
| "grad_norm": 0.03617995232343674, | |
| "learning_rate": 7.386551041956778e-05, | |
| "loss": 0.911865234375, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 3.404255319148936, | |
| "grad_norm": 0.03311219438910484, | |
| "learning_rate": 7.284003901669259e-05, | |
| "loss": 0.88427734375, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.425531914893617, | |
| "grad_norm": 0.037256091833114624, | |
| "learning_rate": 7.182264259091774e-05, | |
| "loss": 0.96630859375, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 3.4468085106382977, | |
| "grad_norm": 0.0344235897064209, | |
| "learning_rate": 7.081351600610575e-05, | |
| "loss": 0.908203125, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 3.4680851063829787, | |
| "grad_norm": 0.04023665934801102, | |
| "learning_rate": 6.981285254218084e-05, | |
| "loss": 0.9306640625, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 3.4893617021276597, | |
| "grad_norm": 0.038979027420282364, | |
| "learning_rate": 6.882084385810971e-05, | |
| "loss": 1.01513671875, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 3.5106382978723403, | |
| "grad_norm": 0.036239344626665115, | |
| "learning_rate": 6.783767995519255e-05, | |
| "loss": 0.982421875, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 3.5319148936170213, | |
| "grad_norm": 0.041207022964954376, | |
| "learning_rate": 6.686354914067206e-05, | |
| "loss": 0.9228515625, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 3.5531914893617023, | |
| "grad_norm": 0.03745558485388756, | |
| "learning_rate": 6.589863799166639e-05, | |
| "loss": 0.95849609375, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 3.574468085106383, | |
| "grad_norm": 0.03531312942504883, | |
| "learning_rate": 6.494313131943356e-05, | |
| "loss": 0.93505859375, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 3.595744680851064, | |
| "grad_norm": 0.03886643052101135, | |
| "learning_rate": 6.399721213397453e-05, | |
| "loss": 0.93212890625, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 3.617021276595745, | |
| "grad_norm": 0.038001321256160736, | |
| "learning_rate": 6.306106160898076e-05, | |
| "loss": 0.97900390625, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.6382978723404253, | |
| "grad_norm": 0.03643008694052696, | |
| "learning_rate": 6.213485904713357e-05, | |
| "loss": 0.95556640625, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 3.6595744680851063, | |
| "grad_norm": 0.036596424877643585, | |
| "learning_rate": 6.121878184576219e-05, | |
| "loss": 0.81085205078125, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 3.6808510638297873, | |
| "grad_norm": 0.042928438633680344, | |
| "learning_rate": 6.031300546286637e-05, | |
| "loss": 0.96875, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 3.702127659574468, | |
| "grad_norm": 0.041720643639564514, | |
| "learning_rate": 5.941770338351056e-05, | |
| "loss": 0.92431640625, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 3.723404255319149, | |
| "grad_norm": 0.041083648800849915, | |
| "learning_rate": 5.853304708659608e-05, | |
| "loss": 0.849609375, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 3.74468085106383, | |
| "grad_norm": 0.04229078069329262, | |
| "learning_rate": 5.76592060120174e-05, | |
| "loss": 0.93701171875, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 3.7659574468085104, | |
| "grad_norm": 0.052078451961278915, | |
| "learning_rate": 5.6796347528209006e-05, | |
| "loss": 0.92578125, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 3.7872340425531914, | |
| "grad_norm": 0.033227503299713135, | |
| "learning_rate": 5.594463690008891e-05, | |
| "loss": 0.84375, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 3.8085106382978724, | |
| "grad_norm": 0.042091649025678635, | |
| "learning_rate": 5.51042372574053e-05, | |
| "loss": 0.962890625, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 3.829787234042553, | |
| "grad_norm": 0.039128612726926804, | |
| "learning_rate": 5.427530956349194e-05, | |
| "loss": 0.9873046875, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.851063829787234, | |
| "grad_norm": 0.04030850902199745, | |
| "learning_rate": 5.3458012584438444e-05, | |
| "loss": 0.93359375, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 3.872340425531915, | |
| "grad_norm": 0.03772120922803879, | |
| "learning_rate": 5.265250285868172e-05, | |
| "loss": 0.97412109375, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 3.8936170212765955, | |
| "grad_norm": 0.03561572730541229, | |
| "learning_rate": 5.1858934667023686e-05, | |
| "loss": 0.9150390625, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 3.9148936170212765, | |
| "grad_norm": 0.040115874260663986, | |
| "learning_rate": 5.10774600030816e-05, | |
| "loss": 0.92724609375, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 3.9361702127659575, | |
| "grad_norm": 0.039529941976070404, | |
| "learning_rate": 5.030822854417656e-05, | |
| "loss": 0.9697265625, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 3.9574468085106385, | |
| "grad_norm": 0.0371088832616806, | |
| "learning_rate": 4.955138762266541e-05, | |
| "loss": 0.89892578125, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 3.978723404255319, | |
| "grad_norm": 0.04574158415198326, | |
| "learning_rate": 4.880708219772186e-05, | |
| "loss": 0.880859375, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.04366738349199295, | |
| "learning_rate": 4.8075454827572316e-05, | |
| "loss": 0.85009765625, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.060546875, | |
| "eval_runtime": 5.504, | |
| "eval_samples_per_second": 0.545, | |
| "eval_steps_per_second": 0.182, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 4.0212765957446805, | |
| "grad_norm": 0.03930988535284996, | |
| "learning_rate": 4.7356645642191354e-05, | |
| "loss": 0.8349609375, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 4.042553191489362, | |
| "grad_norm": 0.04266972094774246, | |
| "learning_rate": 4.665079231646232e-05, | |
| "loss": 0.87353515625, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.0638297872340425, | |
| "grad_norm": 0.05122610181570053, | |
| "learning_rate": 4.5958030043808264e-05, | |
| "loss": 0.84716796875, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 4.085106382978723, | |
| "grad_norm": 0.04046507924795151, | |
| "learning_rate": 4.527849151029813e-05, | |
| "loss": 0.88720703125, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 4.1063829787234045, | |
| "grad_norm": 0.04002128913998604, | |
| "learning_rate": 4.461230686923302e-05, | |
| "loss": 0.83642578125, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 4.127659574468085, | |
| "grad_norm": 0.04339519888162613, | |
| "learning_rate": 4.395960371621773e-05, | |
| "loss": 0.9609375, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 4.148936170212766, | |
| "grad_norm": 0.044231873005628586, | |
| "learning_rate": 4.3320507064722186e-05, | |
| "loss": 0.9248046875, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 4.170212765957447, | |
| "grad_norm": 0.03891272470355034, | |
| "learning_rate": 4.269513932213737e-05, | |
| "loss": 0.84954833984375, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 4.191489361702128, | |
| "grad_norm": 0.03978855907917023, | |
| "learning_rate": 4.208362026633024e-05, | |
| "loss": 0.89892578125, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 4.212765957446808, | |
| "grad_norm": 0.04313793033361435, | |
| "learning_rate": 4.148606702270267e-05, | |
| "loss": 0.97216796875, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 4.23404255319149, | |
| "grad_norm": 0.037154123187065125, | |
| "learning_rate": 4.09025940417581e-05, | |
| "loss": 0.77178955078125, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 4.25531914893617, | |
| "grad_norm": 0.04250561445951462, | |
| "learning_rate": 4.033331307718056e-05, | |
| "loss": 0.94140625, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.276595744680851, | |
| "grad_norm": 0.038513898849487305, | |
| "learning_rate": 3.9778333164430374e-05, | |
| "loss": 0.935546875, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 4.297872340425532, | |
| "grad_norm": 0.03767329454421997, | |
| "learning_rate": 3.923776059986035e-05, | |
| "loss": 0.8671875, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 4.319148936170213, | |
| "grad_norm": 0.03793912008404732, | |
| "learning_rate": 3.871169892035663e-05, | |
| "loss": 0.88818359375, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 4.340425531914893, | |
| "grad_norm": 0.03997759893536568, | |
| "learning_rate": 3.820024888350806e-05, | |
| "loss": 0.8994140625, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 4.361702127659575, | |
| "grad_norm": 0.036675214767456055, | |
| "learning_rate": 3.7703508448307947e-05, | |
| "loss": 0.84814453125, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 4.382978723404255, | |
| "grad_norm": 0.03600461781024933, | |
| "learning_rate": 3.722157275639177e-05, | |
| "loss": 0.879150390625, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 4.404255319148936, | |
| "grad_norm": 0.036929093301296234, | |
| "learning_rate": 3.675453411381449e-05, | |
| "loss": 0.85205078125, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 4.425531914893617, | |
| "grad_norm": 0.044605664908885956, | |
| "learning_rate": 3.630248197337103e-05, | |
| "loss": 0.92919921875, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 4.446808510638298, | |
| "grad_norm": 0.03827337920665741, | |
| "learning_rate": 3.586550291746319e-05, | |
| "loss": 0.8720703125, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 4.468085106382979, | |
| "grad_norm": 0.03790247067809105, | |
| "learning_rate": 3.5443680641516394e-05, | |
| "loss": 0.89404296875, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 4.48936170212766, | |
| "grad_norm": 0.03629126027226448, | |
| "learning_rate": 3.503709593794933e-05, | |
| "loss": 0.978515625, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 4.51063829787234, | |
| "grad_norm": 0.040744345635175705, | |
| "learning_rate": 3.464582668069955e-05, | |
| "loss": 0.9482421875, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 4.531914893617021, | |
| "grad_norm": 0.03703819215297699, | |
| "learning_rate": 3.426994781030826e-05, | |
| "loss": 0.89111328125, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 4.553191489361702, | |
| "grad_norm": 0.037714630365371704, | |
| "learning_rate": 3.3909531319566716e-05, | |
| "loss": 0.92578125, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 4.574468085106383, | |
| "grad_norm": 0.03681576997041702, | |
| "learning_rate": 3.3564646239727386e-05, | |
| "loss": 0.9033203125, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 4.595744680851064, | |
| "grad_norm": 0.039367783814668655, | |
| "learning_rate": 3.323535862728216e-05, | |
| "loss": 0.900390625, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 4.617021276595745, | |
| "grad_norm": 0.03795965760946274, | |
| "learning_rate": 3.292173155131051e-05, | |
| "loss": 0.9453125, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 4.638297872340425, | |
| "grad_norm": 0.03927023336291313, | |
| "learning_rate": 3.262382508139974e-05, | |
| "loss": 0.92431640625, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 4.659574468085106, | |
| "grad_norm": 0.03417414799332619, | |
| "learning_rate": 3.234169627613971e-05, | |
| "loss": 0.785308837890625, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 4.680851063829787, | |
| "grad_norm": 0.039658013731241226, | |
| "learning_rate": 3.2075399172194336e-05, | |
| "loss": 0.935546875, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.702127659574468, | |
| "grad_norm": 0.041840773075819016, | |
| "learning_rate": 3.18249847739518e-05, | |
| "loss": 0.89453125, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 4.723404255319149, | |
| "grad_norm": 0.036156002432107925, | |
| "learning_rate": 3.1590501043755626e-05, | |
| "loss": 0.82373046875, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 4.74468085106383, | |
| "grad_norm": 0.039113543927669525, | |
| "learning_rate": 3.1371992892718335e-05, | |
| "loss": 0.9052734375, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 4.76595744680851, | |
| "grad_norm": 0.037734437733888626, | |
| "learning_rate": 3.116950217211955e-05, | |
| "loss": 0.89794921875, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 4.787234042553192, | |
| "grad_norm": 0.03511641174554825, | |
| "learning_rate": 3.098306766539013e-05, | |
| "loss": 0.8203125, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 4.808510638297872, | |
| "grad_norm": 0.041939668357372284, | |
| "learning_rate": 3.081272508068391e-05, | |
| "loss": 0.93359375, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 4.829787234042553, | |
| "grad_norm": 0.04047448933124542, | |
| "learning_rate": 3.065850704403845e-05, | |
| "loss": 0.9580078125, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 4.851063829787234, | |
| "grad_norm": 0.03897187486290932, | |
| "learning_rate": 3.0520443093126134e-05, | |
| "loss": 0.9052734375, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 4.872340425531915, | |
| "grad_norm": 0.03869474306702614, | |
| "learning_rate": 3.0398559671596688e-05, | |
| "loss": 0.94677734375, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 4.8936170212765955, | |
| "grad_norm": 0.03831680491566658, | |
| "learning_rate": 3.0292880124012486e-05, | |
| "loss": 0.88671875, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.914893617021277, | |
| "grad_norm": 0.03840392827987671, | |
| "learning_rate": 3.0203424691377225e-05, | |
| "loss": 0.90087890625, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 4.9361702127659575, | |
| "grad_norm": 0.03766055777668953, | |
| "learning_rate": 3.013021050725918e-05, | |
| "loss": 0.9443359375, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 4.957446808510638, | |
| "grad_norm": 0.039559632539749146, | |
| "learning_rate": 3.0073251594509578e-05, | |
| "loss": 0.8740234375, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 4.9787234042553195, | |
| "grad_norm": 0.05103755742311478, | |
| "learning_rate": 3.0032558862576754e-05, | |
| "loss": 0.85498046875, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.046121180057525635, | |
| "learning_rate": 3.000814010541664e-05, | |
| "loss": 0.814453125, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.0634765625, | |
| "eval_runtime": 5.5227, | |
| "eval_samples_per_second": 0.543, | |
| "eval_steps_per_second": 0.181, | |
| "step": 235 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 235, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.046024116602929e+19, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |