Instructions to use rmdhirr/kenanga-lora-b-1-1200 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use rmdhirr/kenanga-lora-b-1-1200 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-3-12b-it-unsloth-bnb-4bit") model = PeftModel.from_pretrained(base_model, "rmdhirr/kenanga-lora-b-1-1200") - Transformers
How to use rmdhirr/kenanga-lora-b-1-1200 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="rmdhirr/kenanga-lora-b-1-1200") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("rmdhirr/kenanga-lora-b-1-1200", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use rmdhirr/kenanga-lora-b-1-1200 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "rmdhirr/kenanga-lora-b-1-1200" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rmdhirr/kenanga-lora-b-1-1200", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/rmdhirr/kenanga-lora-b-1-1200
- SGLang
How to use rmdhirr/kenanga-lora-b-1-1200 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 "rmdhirr/kenanga-lora-b-1-1200" \ --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": "rmdhirr/kenanga-lora-b-1-1200", "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 "rmdhirr/kenanga-lora-b-1-1200" \ --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": "rmdhirr/kenanga-lora-b-1-1200", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Desktop
- Docker Model Runner
How to use rmdhirr/kenanga-lora-b-1-1200 with Docker Model Runner:
docker model run hf.co/rmdhirr/kenanga-lora-b-1-1200
| { | |
| "best_global_step": 1200, | |
| "best_metric": 1.2411783933639526, | |
| "best_model_checkpoint": "outputs/checkpoint-1200", | |
| "epoch": 0.23074704355350448, | |
| "eval_steps": 300, | |
| "global_step": 1200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009614460148062686, | |
| "grad_norm": 5.263479232788086, | |
| "learning_rate": 2.3032629558541267e-07, | |
| "loss": 2.2998, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0019228920296125373, | |
| "grad_norm": 4.919901371002197, | |
| "learning_rate": 5.182341650671785e-07, | |
| "loss": 2.2468, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002884338044418806, | |
| "grad_norm": 3.7949042320251465, | |
| "learning_rate": 8.061420345489444e-07, | |
| "loss": 2.2097, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0038457840592250746, | |
| "grad_norm": 3.5610361099243164, | |
| "learning_rate": 1.0940499040307102e-06, | |
| "loss": 2.083, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0048072300740313436, | |
| "grad_norm": 3.32427978515625, | |
| "learning_rate": 1.381957773512476e-06, | |
| "loss": 2.0052, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005768676088837612, | |
| "grad_norm": 3.5147716999053955, | |
| "learning_rate": 1.6698656429942417e-06, | |
| "loss": 2.043, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006730122103643881, | |
| "grad_norm": 2.091193437576294, | |
| "learning_rate": 1.9577735124760077e-06, | |
| "loss": 2.0161, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007691568118450149, | |
| "grad_norm": 2.3086185455322266, | |
| "learning_rate": 2.2456813819577732e-06, | |
| "loss": 1.9567, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008653014133256417, | |
| "grad_norm": 1.6346129179000854, | |
| "learning_rate": 2.5335892514395392e-06, | |
| "loss": 1.8985, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009614460148062687, | |
| "grad_norm": 1.260735034942627, | |
| "learning_rate": 2.821497120921305e-06, | |
| "loss": 1.8132, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010575906162868956, | |
| "grad_norm": 1.5411990880966187, | |
| "learning_rate": 3.109404990403071e-06, | |
| "loss": 1.6944, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.011537352177675224, | |
| "grad_norm": 1.319563388824463, | |
| "learning_rate": 3.397312859884837e-06, | |
| "loss": 1.7036, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.012498798192481493, | |
| "grad_norm": 1.0878187417984009, | |
| "learning_rate": 3.6852207293666026e-06, | |
| "loss": 1.7662, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.013460244207287761, | |
| "grad_norm": 1.1386423110961914, | |
| "learning_rate": 3.973128598848369e-06, | |
| "loss": 1.6783, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01442169022209403, | |
| "grad_norm": 1.2391140460968018, | |
| "learning_rate": 4.2610364683301346e-06, | |
| "loss": 1.5672, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.015383136236900298, | |
| "grad_norm": 1.0566521883010864, | |
| "learning_rate": 4.5489443378119e-06, | |
| "loss": 1.6949, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.016344582251706565, | |
| "grad_norm": 1.0937573909759521, | |
| "learning_rate": 4.8368522072936665e-06, | |
| "loss": 1.5464, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.017306028266512834, | |
| "grad_norm": 1.0400891304016113, | |
| "learning_rate": 5.124760076775432e-06, | |
| "loss": 1.5824, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.018267474281319102, | |
| "grad_norm": 1.1960211992263794, | |
| "learning_rate": 5.4126679462571984e-06, | |
| "loss": 1.6269, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.019228920296125374, | |
| "grad_norm": 1.197791576385498, | |
| "learning_rate": 5.7005758157389635e-06, | |
| "loss": 1.5177, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.020190366310931643, | |
| "grad_norm": 0.9536961913108826, | |
| "learning_rate": 5.9884836852207295e-06, | |
| "loss": 1.6222, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.02115181232573791, | |
| "grad_norm": 0.9854758977890015, | |
| "learning_rate": 6.2763915547024955e-06, | |
| "loss": 1.5503, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02211325834054418, | |
| "grad_norm": 0.8579792976379395, | |
| "learning_rate": 6.5642994241842614e-06, | |
| "loss": 1.5246, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.02307470435535045, | |
| "grad_norm": 0.8161287307739258, | |
| "learning_rate": 6.852207293666027e-06, | |
| "loss": 1.5207, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.024036150370156717, | |
| "grad_norm": 1.0825903415679932, | |
| "learning_rate": 7.1401151631477925e-06, | |
| "loss": 1.4963, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.024997596384962985, | |
| "grad_norm": 0.9904459118843079, | |
| "learning_rate": 7.4280230326295585e-06, | |
| "loss": 1.5351, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.025959042399769254, | |
| "grad_norm": 1.0706708431243896, | |
| "learning_rate": 7.715930902111324e-06, | |
| "loss": 1.477, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.026920488414575523, | |
| "grad_norm": 0.910792887210846, | |
| "learning_rate": 8.003838771593091e-06, | |
| "loss": 1.563, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.02788193442938179, | |
| "grad_norm": 0.8813047409057617, | |
| "learning_rate": 8.291746641074856e-06, | |
| "loss": 1.5286, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.02884338044418806, | |
| "grad_norm": 1.135494589805603, | |
| "learning_rate": 8.579654510556621e-06, | |
| "loss": 1.4987, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.029804826458994328, | |
| "grad_norm": 1.4200812578201294, | |
| "learning_rate": 8.867562380038388e-06, | |
| "loss": 1.5176, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.030766272473800597, | |
| "grad_norm": 0.9361958503723145, | |
| "learning_rate": 9.155470249520153e-06, | |
| "loss": 1.5375, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.031727718488606865, | |
| "grad_norm": 0.7996511459350586, | |
| "learning_rate": 9.44337811900192e-06, | |
| "loss": 1.504, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.03268916450341313, | |
| "grad_norm": 0.8341512680053711, | |
| "learning_rate": 9.731285988483685e-06, | |
| "loss": 1.5099, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0336506105182194, | |
| "grad_norm": 0.8165861368179321, | |
| "learning_rate": 1.001919385796545e-05, | |
| "loss": 1.4714, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.03461205653302567, | |
| "grad_norm": 1.0153369903564453, | |
| "learning_rate": 1.0307101727447217e-05, | |
| "loss": 1.4675, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03557350254783194, | |
| "grad_norm": 0.8753921985626221, | |
| "learning_rate": 1.0595009596928982e-05, | |
| "loss": 1.478, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.036534948562638205, | |
| "grad_norm": 0.8925352096557617, | |
| "learning_rate": 1.088291746641075e-05, | |
| "loss": 1.4238, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.037496394577444477, | |
| "grad_norm": 0.8326230049133301, | |
| "learning_rate": 1.1170825335892514e-05, | |
| "loss": 1.4648, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.03845784059225075, | |
| "grad_norm": 1.0663974285125732, | |
| "learning_rate": 1.1458733205374281e-05, | |
| "loss": 1.5123, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.039419286607057014, | |
| "grad_norm": 1.0833837985992432, | |
| "learning_rate": 1.1746641074856046e-05, | |
| "loss": 1.5031, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.040380732621863286, | |
| "grad_norm": 0.8054072260856628, | |
| "learning_rate": 1.2034548944337811e-05, | |
| "loss": 1.4416, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.04134217863666955, | |
| "grad_norm": 0.8595219850540161, | |
| "learning_rate": 1.2322456813819578e-05, | |
| "loss": 1.4417, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.04230362465147582, | |
| "grad_norm": 0.8635595440864563, | |
| "learning_rate": 1.2610364683301345e-05, | |
| "loss": 1.4175, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.04326507066628209, | |
| "grad_norm": 0.8640530705451965, | |
| "learning_rate": 1.289827255278311e-05, | |
| "loss": 1.4442, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.04422651668108836, | |
| "grad_norm": 0.8653771281242371, | |
| "learning_rate": 1.3186180422264875e-05, | |
| "loss": 1.4193, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.045187962695894625, | |
| "grad_norm": 0.7947669625282288, | |
| "learning_rate": 1.347408829174664e-05, | |
| "loss": 1.4092, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.0461494087107009, | |
| "grad_norm": 0.8416963815689087, | |
| "learning_rate": 1.3761996161228407e-05, | |
| "loss": 1.5512, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.04711085472550716, | |
| "grad_norm": 0.9726578593254089, | |
| "learning_rate": 1.4049904030710174e-05, | |
| "loss": 1.4525, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.048072300740313434, | |
| "grad_norm": 1.0061571598052979, | |
| "learning_rate": 1.4337811900191939e-05, | |
| "loss": 1.4552, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.0490337467551197, | |
| "grad_norm": 0.8465285897254944, | |
| "learning_rate": 1.4625719769673704e-05, | |
| "loss": 1.3991, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.04999519276992597, | |
| "grad_norm": 0.9697036147117615, | |
| "learning_rate": 1.491362763915547e-05, | |
| "loss": 1.4067, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.050956638784732236, | |
| "grad_norm": 0.9910932183265686, | |
| "learning_rate": 1.5201535508637236e-05, | |
| "loss": 1.4834, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.05191808479953851, | |
| "grad_norm": 0.937353789806366, | |
| "learning_rate": 1.5489443378119003e-05, | |
| "loss": 1.4806, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.05287953081434477, | |
| "grad_norm": 0.873612105846405, | |
| "learning_rate": 1.577735124760077e-05, | |
| "loss": 1.4694, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.053840976829151045, | |
| "grad_norm": 0.7373448610305786, | |
| "learning_rate": 1.6065259117082533e-05, | |
| "loss": 1.4042, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.05480242284395731, | |
| "grad_norm": 0.771385908126831, | |
| "learning_rate": 1.63531669865643e-05, | |
| "loss": 1.418, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.05576386885876358, | |
| "grad_norm": 0.8392884731292725, | |
| "learning_rate": 1.6641074856046063e-05, | |
| "loss": 1.3782, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.05672531487356985, | |
| "grad_norm": 0.8971521258354187, | |
| "learning_rate": 1.692898272552783e-05, | |
| "loss": 1.503, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.05768676088837612, | |
| "grad_norm": 0.938372790813446, | |
| "learning_rate": 1.72168905950096e-05, | |
| "loss": 1.4005, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05768676088837612, | |
| "eval_loss": 1.4069678783416748, | |
| "eval_runtime": 1829.2346, | |
| "eval_samples_per_second": 11.372, | |
| "eval_steps_per_second": 2.843, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.058648206903182384, | |
| "grad_norm": 0.8293926119804382, | |
| "learning_rate": 1.7504798464491364e-05, | |
| "loss": 1.3648, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.059609652917988656, | |
| "grad_norm": 0.9733208417892456, | |
| "learning_rate": 1.779270633397313e-05, | |
| "loss": 1.4087, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.06057109893279492, | |
| "grad_norm": 0.9246333241462708, | |
| "learning_rate": 1.8080614203454894e-05, | |
| "loss": 1.4551, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.061532544947601193, | |
| "grad_norm": 0.7493950724601746, | |
| "learning_rate": 1.836852207293666e-05, | |
| "loss": 1.4551, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.06249399096240746, | |
| "grad_norm": 1.0027576684951782, | |
| "learning_rate": 1.8656429942418428e-05, | |
| "loss": 1.3908, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.06345543697721373, | |
| "grad_norm": 0.8040695190429688, | |
| "learning_rate": 1.894433781190019e-05, | |
| "loss": 1.424, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.06441688299202, | |
| "grad_norm": 0.8406041264533997, | |
| "learning_rate": 1.9232245681381958e-05, | |
| "loss": 1.353, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.06537832900682626, | |
| "grad_norm": 0.9334944486618042, | |
| "learning_rate": 1.952015355086372e-05, | |
| "loss": 1.431, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.06633977502163253, | |
| "grad_norm": 0.7912152409553528, | |
| "learning_rate": 1.980806142034549e-05, | |
| "loss": 1.4298, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.0673012210364388, | |
| "grad_norm": 0.9743331670761108, | |
| "learning_rate": 2.009596928982726e-05, | |
| "loss": 1.357, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.06826266705124508, | |
| "grad_norm": 0.9452155232429504, | |
| "learning_rate": 2.0383877159309022e-05, | |
| "loss": 1.4023, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.06922411306605133, | |
| "grad_norm": 0.8321967124938965, | |
| "learning_rate": 2.067178502879079e-05, | |
| "loss": 1.4188, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.0701855590808576, | |
| "grad_norm": 0.8946035504341125, | |
| "learning_rate": 2.0959692898272552e-05, | |
| "loss": 1.3417, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.07114700509566388, | |
| "grad_norm": 0.8722978234291077, | |
| "learning_rate": 2.124760076775432e-05, | |
| "loss": 1.4045, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.07210845111047015, | |
| "grad_norm": 1.0040546655654907, | |
| "learning_rate": 2.1535508637236086e-05, | |
| "loss": 1.4069, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.07306989712527641, | |
| "grad_norm": 0.8072942495346069, | |
| "learning_rate": 2.182341650671785e-05, | |
| "loss": 1.3406, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.07403134314008268, | |
| "grad_norm": 0.9878551363945007, | |
| "learning_rate": 2.2111324376199616e-05, | |
| "loss": 1.4355, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.07499278915488895, | |
| "grad_norm": 1.0963833332061768, | |
| "learning_rate": 2.2399232245681383e-05, | |
| "loss": 1.4208, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.07595423516969523, | |
| "grad_norm": 0.9907721281051636, | |
| "learning_rate": 2.268714011516315e-05, | |
| "loss": 1.3403, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.0769156811845015, | |
| "grad_norm": 0.9433814287185669, | |
| "learning_rate": 2.2975047984644916e-05, | |
| "loss": 1.3567, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07787712719930776, | |
| "grad_norm": 0.9044313430786133, | |
| "learning_rate": 2.326295585412668e-05, | |
| "loss": 1.4668, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.07883857321411403, | |
| "grad_norm": 0.9079594612121582, | |
| "learning_rate": 2.3550863723608447e-05, | |
| "loss": 1.3796, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.0798000192289203, | |
| "grad_norm": 0.9176523685455322, | |
| "learning_rate": 2.383877159309021e-05, | |
| "loss": 1.41, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.08076146524372657, | |
| "grad_norm": 0.9850307106971741, | |
| "learning_rate": 2.4126679462571977e-05, | |
| "loss": 1.4052, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.08172291125853283, | |
| "grad_norm": 1.0259281396865845, | |
| "learning_rate": 2.4414587332053744e-05, | |
| "loss": 1.4044, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.0826843572733391, | |
| "grad_norm": 0.9912247061729431, | |
| "learning_rate": 2.470249520153551e-05, | |
| "loss": 1.3343, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.08364580328814537, | |
| "grad_norm": 0.9430367946624756, | |
| "learning_rate": 2.4990403071017277e-05, | |
| "loss": 1.4015, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.08460724930295165, | |
| "grad_norm": 0.9094961285591125, | |
| "learning_rate": 2.527831094049904e-05, | |
| "loss": 1.469, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.0855686953177579, | |
| "grad_norm": 0.8672477006912231, | |
| "learning_rate": 2.5566218809980807e-05, | |
| "loss": 1.3456, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.08653014133256418, | |
| "grad_norm": 0.9972670078277588, | |
| "learning_rate": 2.5854126679462574e-05, | |
| "loss": 1.2994, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.08749158734737045, | |
| "grad_norm": 0.9733589887619019, | |
| "learning_rate": 2.6142034548944338e-05, | |
| "loss": 1.3375, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.08845303336217672, | |
| "grad_norm": 0.9801984429359436, | |
| "learning_rate": 2.6429942418426104e-05, | |
| "loss": 1.3271, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.08941447937698298, | |
| "grad_norm": 0.8056566715240479, | |
| "learning_rate": 2.6717850287907868e-05, | |
| "loss": 1.3696, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.09037592539178925, | |
| "grad_norm": 0.9498573541641235, | |
| "learning_rate": 2.7005758157389635e-05, | |
| "loss": 1.3724, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.09133737140659552, | |
| "grad_norm": 0.9388139247894287, | |
| "learning_rate": 2.7293666026871405e-05, | |
| "loss": 1.3394, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.0922988174214018, | |
| "grad_norm": 0.9051626324653625, | |
| "learning_rate": 2.758157389635317e-05, | |
| "loss": 1.3465, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.09326026343620805, | |
| "grad_norm": 1.0678194761276245, | |
| "learning_rate": 2.7869481765834935e-05, | |
| "loss": 1.3369, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.09422170945101432, | |
| "grad_norm": 1.0179715156555176, | |
| "learning_rate": 2.81573896353167e-05, | |
| "loss": 1.2868, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.0951831554658206, | |
| "grad_norm": 1.025252103805542, | |
| "learning_rate": 2.8445297504798465e-05, | |
| "loss": 1.4128, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.09614460148062687, | |
| "grad_norm": 0.9994450211524963, | |
| "learning_rate": 2.8733205374280232e-05, | |
| "loss": 1.3105, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09710604749543313, | |
| "grad_norm": 1.0843088626861572, | |
| "learning_rate": 2.9021113243761996e-05, | |
| "loss": 1.4405, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.0980674935102394, | |
| "grad_norm": 0.8648557662963867, | |
| "learning_rate": 2.9309021113243762e-05, | |
| "loss": 1.3738, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.09902893952504567, | |
| "grad_norm": 1.0407732725143433, | |
| "learning_rate": 2.9596928982725526e-05, | |
| "loss": 1.4331, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.09999038553985194, | |
| "grad_norm": 1.8220276832580566, | |
| "learning_rate": 2.9884836852207296e-05, | |
| "loss": 1.3347, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.1009518315546582, | |
| "grad_norm": 0.8917143940925598, | |
| "learning_rate": 2.9990891610160915e-05, | |
| "loss": 1.3576, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.10191327756946447, | |
| "grad_norm": 0.9336162209510803, | |
| "learning_rate": 2.9975710960429106e-05, | |
| "loss": 1.3353, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.10287472358427074, | |
| "grad_norm": 0.9028390049934387, | |
| "learning_rate": 2.9960530310697297e-05, | |
| "loss": 1.4185, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.10383616959907702, | |
| "grad_norm": 0.9123654365539551, | |
| "learning_rate": 2.9945349660965488e-05, | |
| "loss": 1.3747, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.10479761561388327, | |
| "grad_norm": 0.9282749891281128, | |
| "learning_rate": 2.993016901123368e-05, | |
| "loss": 1.3323, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.10575906162868955, | |
| "grad_norm": 1.06288743019104, | |
| "learning_rate": 2.9914988361501872e-05, | |
| "loss": 1.3638, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.10672050764349582, | |
| "grad_norm": 0.9988644123077393, | |
| "learning_rate": 2.9899807711770063e-05, | |
| "loss": 1.3527, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.10768195365830209, | |
| "grad_norm": 0.963537871837616, | |
| "learning_rate": 2.9884627062038254e-05, | |
| "loss": 1.3287, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.10864339967310835, | |
| "grad_norm": 1.1065447330474854, | |
| "learning_rate": 2.9869446412306445e-05, | |
| "loss": 1.3152, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.10960484568791462, | |
| "grad_norm": 0.9934567213058472, | |
| "learning_rate": 2.985426576257464e-05, | |
| "loss": 1.285, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.11056629170272089, | |
| "grad_norm": 0.9684432148933411, | |
| "learning_rate": 2.983908511284283e-05, | |
| "loss": 1.4081, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.11152773771752716, | |
| "grad_norm": 1.044866919517517, | |
| "learning_rate": 2.982390446311102e-05, | |
| "loss": 1.3684, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.11248918373233342, | |
| "grad_norm": 0.9235266447067261, | |
| "learning_rate": 2.9808723813379215e-05, | |
| "loss": 1.2453, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.1134506297471397, | |
| "grad_norm": 1.0257271528244019, | |
| "learning_rate": 2.9793543163647405e-05, | |
| "loss": 1.3664, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.11441207576194597, | |
| "grad_norm": 1.1091939210891724, | |
| "learning_rate": 2.97783625139156e-05, | |
| "loss": 1.2905, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.11537352177675224, | |
| "grad_norm": 0.9549099802970886, | |
| "learning_rate": 2.976318186418379e-05, | |
| "loss": 1.4162, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.11537352177675224, | |
| "eval_loss": 1.3265293836593628, | |
| "eval_runtime": 1813.3194, | |
| "eval_samples_per_second": 11.472, | |
| "eval_steps_per_second": 2.868, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.11633496779155851, | |
| "grad_norm": 1.1611406803131104, | |
| "learning_rate": 2.974800121445198e-05, | |
| "loss": 1.2258, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.11729641380636477, | |
| "grad_norm": 1.0069003105163574, | |
| "learning_rate": 2.9732820564720172e-05, | |
| "loss": 1.2956, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.11825785982117104, | |
| "grad_norm": 0.8448907732963562, | |
| "learning_rate": 2.9717639914988363e-05, | |
| "loss": 1.35, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.11921930583597731, | |
| "grad_norm": 0.8714330792427063, | |
| "learning_rate": 2.9702459265256557e-05, | |
| "loss": 1.2409, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.12018075185078358, | |
| "grad_norm": 0.8822401762008667, | |
| "learning_rate": 2.9687278615524747e-05, | |
| "loss": 1.3148, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.12114219786558984, | |
| "grad_norm": 1.030093789100647, | |
| "learning_rate": 2.9672097965792938e-05, | |
| "loss": 1.3713, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.12210364388039611, | |
| "grad_norm": 1.0077892541885376, | |
| "learning_rate": 2.965691731606113e-05, | |
| "loss": 1.354, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.12306508989520239, | |
| "grad_norm": 1.0031296014785767, | |
| "learning_rate": 2.964173666632932e-05, | |
| "loss": 1.3483, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.12402653591000866, | |
| "grad_norm": 0.9184396266937256, | |
| "learning_rate": 2.9626556016597514e-05, | |
| "loss": 1.2783, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.12498798192481492, | |
| "grad_norm": 0.9425734281539917, | |
| "learning_rate": 2.9611375366865705e-05, | |
| "loss": 1.2896, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.1259494279396212, | |
| "grad_norm": 0.8437754511833191, | |
| "learning_rate": 2.9596194717133895e-05, | |
| "loss": 1.3343, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.12691087395442746, | |
| "grad_norm": 0.9617599844932556, | |
| "learning_rate": 2.9581014067402086e-05, | |
| "loss": 1.2472, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.12787231996923373, | |
| "grad_norm": 0.9239601492881775, | |
| "learning_rate": 2.9565833417670277e-05, | |
| "loss": 1.3209, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.12883376598404, | |
| "grad_norm": 0.9953628182411194, | |
| "learning_rate": 2.955065276793847e-05, | |
| "loss": 1.3152, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.12979521199884628, | |
| "grad_norm": 0.8559119701385498, | |
| "learning_rate": 2.9535472118206662e-05, | |
| "loss": 1.3301, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.13075665801365252, | |
| "grad_norm": 0.984180212020874, | |
| "learning_rate": 2.9520291468474853e-05, | |
| "loss": 1.3678, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.1317181040284588, | |
| "grad_norm": 0.9163925647735596, | |
| "learning_rate": 2.9505110818743043e-05, | |
| "loss": 1.3398, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.13267955004326507, | |
| "grad_norm": 1.1147078275680542, | |
| "learning_rate": 2.9489930169011234e-05, | |
| "loss": 1.2758, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.13364099605807134, | |
| "grad_norm": 0.980420708656311, | |
| "learning_rate": 2.947474951927943e-05, | |
| "loss": 1.3137, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.1346024420728776, | |
| "grad_norm": 1.0157663822174072, | |
| "learning_rate": 2.945956886954762e-05, | |
| "loss": 1.2144, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.13556388808768388, | |
| "grad_norm": 0.8547846078872681, | |
| "learning_rate": 2.944438821981581e-05, | |
| "loss": 1.2879, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.13652533410249015, | |
| "grad_norm": 1.018324851989746, | |
| "learning_rate": 2.9429207570084e-05, | |
| "loss": 1.267, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.13748678011729643, | |
| "grad_norm": 0.832151472568512, | |
| "learning_rate": 2.941402692035219e-05, | |
| "loss": 1.3185, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.13844822613210267, | |
| "grad_norm": 1.0583784580230713, | |
| "learning_rate": 2.9398846270620386e-05, | |
| "loss": 1.2489, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.13940967214690894, | |
| "grad_norm": 1.0460695028305054, | |
| "learning_rate": 2.9383665620888576e-05, | |
| "loss": 1.3299, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.1403711181617152, | |
| "grad_norm": 0.8800564408302307, | |
| "learning_rate": 2.9368484971156767e-05, | |
| "loss": 1.3494, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.14133256417652149, | |
| "grad_norm": 0.9371108412742615, | |
| "learning_rate": 2.9353304321424958e-05, | |
| "loss": 1.3129, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.14229401019132776, | |
| "grad_norm": 0.9252986907958984, | |
| "learning_rate": 2.933812367169315e-05, | |
| "loss": 1.3028, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.14325545620613403, | |
| "grad_norm": 0.9625592827796936, | |
| "learning_rate": 2.9322943021961343e-05, | |
| "loss": 1.366, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.1442169022209403, | |
| "grad_norm": 0.9188767671585083, | |
| "learning_rate": 2.9307762372229534e-05, | |
| "loss": 1.3584, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.14517834823574657, | |
| "grad_norm": 0.8308439254760742, | |
| "learning_rate": 2.9292581722497724e-05, | |
| "loss": 1.2567, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.14613979425055282, | |
| "grad_norm": 0.9764241576194763, | |
| "learning_rate": 2.9277401072765915e-05, | |
| "loss": 1.299, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.1471012402653591, | |
| "grad_norm": 0.854916512966156, | |
| "learning_rate": 2.9262220423034106e-05, | |
| "loss": 1.2568, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.14806268628016536, | |
| "grad_norm": 0.9988142251968384, | |
| "learning_rate": 2.92470397733023e-05, | |
| "loss": 1.2633, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.14902413229497163, | |
| "grad_norm": 1.032973051071167, | |
| "learning_rate": 2.923185912357049e-05, | |
| "loss": 1.3592, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.1499855783097779, | |
| "grad_norm": 1.057490587234497, | |
| "learning_rate": 2.921667847383868e-05, | |
| "loss": 1.3316, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.15094702432458418, | |
| "grad_norm": 0.9987697005271912, | |
| "learning_rate": 2.9201497824106872e-05, | |
| "loss": 1.2957, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.15190847033939045, | |
| "grad_norm": 1.0518527030944824, | |
| "learning_rate": 2.9186317174375063e-05, | |
| "loss": 1.3373, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.15286991635419672, | |
| "grad_norm": 0.9941504001617432, | |
| "learning_rate": 2.9171136524643257e-05, | |
| "loss": 1.3207, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.153831362369003, | |
| "grad_norm": 0.9565390348434448, | |
| "learning_rate": 2.9155955874911448e-05, | |
| "loss": 1.3035, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.15479280838380924, | |
| "grad_norm": 0.9072451591491699, | |
| "learning_rate": 2.914077522517964e-05, | |
| "loss": 1.3077, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.1557542543986155, | |
| "grad_norm": 0.8639485239982605, | |
| "learning_rate": 2.912559457544783e-05, | |
| "loss": 1.2388, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.15671570041342178, | |
| "grad_norm": 0.8549638390541077, | |
| "learning_rate": 2.911041392571602e-05, | |
| "loss": 1.2112, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.15767714642822805, | |
| "grad_norm": 0.9586772322654724, | |
| "learning_rate": 2.9095233275984214e-05, | |
| "loss": 1.3981, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.15863859244303433, | |
| "grad_norm": 1.0374456644058228, | |
| "learning_rate": 2.9080052626252405e-05, | |
| "loss": 1.2159, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.1596000384578406, | |
| "grad_norm": 0.9278589487075806, | |
| "learning_rate": 2.9064871976520596e-05, | |
| "loss": 1.2849, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.16056148447264687, | |
| "grad_norm": 0.8326074481010437, | |
| "learning_rate": 2.9049691326788787e-05, | |
| "loss": 1.3178, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.16152293048745314, | |
| "grad_norm": 1.0694983005523682, | |
| "learning_rate": 2.9034510677056977e-05, | |
| "loss": 1.2796, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.1624843765022594, | |
| "grad_norm": 1.1848194599151611, | |
| "learning_rate": 2.901933002732517e-05, | |
| "loss": 1.3145, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.16344582251706566, | |
| "grad_norm": 1.1083351373672485, | |
| "learning_rate": 2.9004149377593362e-05, | |
| "loss": 1.3274, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.16440726853187193, | |
| "grad_norm": 0.8984082937240601, | |
| "learning_rate": 2.8988968727861553e-05, | |
| "loss": 1.3023, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.1653687145466782, | |
| "grad_norm": 1.0397671461105347, | |
| "learning_rate": 2.8973788078129744e-05, | |
| "loss": 1.2713, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.16633016056148447, | |
| "grad_norm": 0.9931337237358093, | |
| "learning_rate": 2.8958607428397935e-05, | |
| "loss": 1.26, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.16729160657629075, | |
| "grad_norm": 1.0527026653289795, | |
| "learning_rate": 2.894342677866613e-05, | |
| "loss": 1.2944, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.16825305259109702, | |
| "grad_norm": 1.153441309928894, | |
| "learning_rate": 2.892824612893432e-05, | |
| "loss": 1.2475, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.1692144986059033, | |
| "grad_norm": 0.8572908639907837, | |
| "learning_rate": 2.891306547920251e-05, | |
| "loss": 1.242, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.17017594462070953, | |
| "grad_norm": 1.0271085500717163, | |
| "learning_rate": 2.88978848294707e-05, | |
| "loss": 1.3052, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.1711373906355158, | |
| "grad_norm": 1.0767736434936523, | |
| "learning_rate": 2.8882704179738892e-05, | |
| "loss": 1.2851, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.17209883665032208, | |
| "grad_norm": 0.9310041069984436, | |
| "learning_rate": 2.8867523530007086e-05, | |
| "loss": 1.367, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.17306028266512835, | |
| "grad_norm": 0.8906955122947693, | |
| "learning_rate": 2.8852342880275277e-05, | |
| "loss": 1.2853, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.17306028266512835, | |
| "eval_loss": 1.2756867408752441, | |
| "eval_runtime": 1880.9614, | |
| "eval_samples_per_second": 11.059, | |
| "eval_steps_per_second": 2.765, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.17402172867993462, | |
| "grad_norm": 0.8874945640563965, | |
| "learning_rate": 2.8837162230543468e-05, | |
| "loss": 1.252, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.1749831746947409, | |
| "grad_norm": 0.992651641368866, | |
| "learning_rate": 2.882198158081166e-05, | |
| "loss": 1.3451, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.17594462070954717, | |
| "grad_norm": 1.1066889762878418, | |
| "learning_rate": 2.8806800931079852e-05, | |
| "loss": 1.2555, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.17690606672435344, | |
| "grad_norm": 1.0017170906066895, | |
| "learning_rate": 2.8791620281348043e-05, | |
| "loss": 1.3645, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.17786751273915968, | |
| "grad_norm": 1.146898627281189, | |
| "learning_rate": 2.8776439631616234e-05, | |
| "loss": 1.3557, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.17882895875396596, | |
| "grad_norm": 0.9736440777778625, | |
| "learning_rate": 2.8761258981884425e-05, | |
| "loss": 1.2755, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.17979040476877223, | |
| "grad_norm": 0.9591579437255859, | |
| "learning_rate": 2.8746078332152616e-05, | |
| "loss": 1.2618, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.1807518507835785, | |
| "grad_norm": 1.3127062320709229, | |
| "learning_rate": 2.873089768242081e-05, | |
| "loss": 1.2494, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.18171329679838477, | |
| "grad_norm": 1.2093756198883057, | |
| "learning_rate": 2.8715717032689e-05, | |
| "loss": 1.3055, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.18267474281319104, | |
| "grad_norm": 1.2279831171035767, | |
| "learning_rate": 2.870053638295719e-05, | |
| "loss": 1.2797, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.18363618882799732, | |
| "grad_norm": 0.9829315543174744, | |
| "learning_rate": 2.8685355733225382e-05, | |
| "loss": 1.252, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.1845976348428036, | |
| "grad_norm": 1.0075795650482178, | |
| "learning_rate": 2.8670175083493573e-05, | |
| "loss": 1.2432, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.18555908085760983, | |
| "grad_norm": 0.9815109968185425, | |
| "learning_rate": 2.8654994433761767e-05, | |
| "loss": 1.3011, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.1865205268724161, | |
| "grad_norm": 0.9473528265953064, | |
| "learning_rate": 2.8639813784029958e-05, | |
| "loss": 1.328, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.18748197288722238, | |
| "grad_norm": 1.0563870668411255, | |
| "learning_rate": 2.862463313429815e-05, | |
| "loss": 1.4197, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.18844341890202865, | |
| "grad_norm": 0.999548614025116, | |
| "learning_rate": 2.860945248456634e-05, | |
| "loss": 1.2636, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.18940486491683492, | |
| "grad_norm": 1.0543882846832275, | |
| "learning_rate": 2.859427183483453e-05, | |
| "loss": 1.2293, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.1903663109316412, | |
| "grad_norm": 1.0018796920776367, | |
| "learning_rate": 2.8579091185102724e-05, | |
| "loss": 1.262, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.19132775694644746, | |
| "grad_norm": 1.0547089576721191, | |
| "learning_rate": 2.8563910535370915e-05, | |
| "loss": 1.2329, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.19228920296125374, | |
| "grad_norm": 0.9648796916007996, | |
| "learning_rate": 2.8548729885639106e-05, | |
| "loss": 1.327, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.19325064897606, | |
| "grad_norm": 0.964148998260498, | |
| "learning_rate": 2.8533549235907296e-05, | |
| "loss": 1.2733, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.19421209499086625, | |
| "grad_norm": 1.0552051067352295, | |
| "learning_rate": 2.8518368586175487e-05, | |
| "loss": 1.2462, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.19517354100567252, | |
| "grad_norm": 1.1029739379882812, | |
| "learning_rate": 2.850318793644368e-05, | |
| "loss": 1.2478, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.1961349870204788, | |
| "grad_norm": 1.1883385181427002, | |
| "learning_rate": 2.8488007286711872e-05, | |
| "loss": 1.1937, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.19709643303528507, | |
| "grad_norm": 0.9168397784233093, | |
| "learning_rate": 2.8472826636980063e-05, | |
| "loss": 1.3682, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.19805787905009134, | |
| "grad_norm": 0.9574885964393616, | |
| "learning_rate": 2.8457645987248254e-05, | |
| "loss": 1.2358, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.1990193250648976, | |
| "grad_norm": 1.0165746212005615, | |
| "learning_rate": 2.8442465337516444e-05, | |
| "loss": 1.2765, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.19998077107970388, | |
| "grad_norm": 0.8473765254020691, | |
| "learning_rate": 2.842728468778464e-05, | |
| "loss": 1.1938, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.20094221709451016, | |
| "grad_norm": 1.000200629234314, | |
| "learning_rate": 2.841210403805283e-05, | |
| "loss": 1.2242, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.2019036631093164, | |
| "grad_norm": 1.1640363931655884, | |
| "learning_rate": 2.839692338832102e-05, | |
| "loss": 1.3152, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.20286510912412267, | |
| "grad_norm": 1.0977058410644531, | |
| "learning_rate": 2.838174273858921e-05, | |
| "loss": 1.2639, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.20382655513892894, | |
| "grad_norm": 1.0105798244476318, | |
| "learning_rate": 2.83665620888574e-05, | |
| "loss": 1.2381, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.20478800115373522, | |
| "grad_norm": 0.9707632064819336, | |
| "learning_rate": 2.8351381439125596e-05, | |
| "loss": 1.2691, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.2057494471685415, | |
| "grad_norm": 0.8312526345252991, | |
| "learning_rate": 2.8336200789393787e-05, | |
| "loss": 1.2571, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.20671089318334776, | |
| "grad_norm": 0.8867915868759155, | |
| "learning_rate": 2.8321020139661977e-05, | |
| "loss": 1.3126, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.20767233919815403, | |
| "grad_norm": 0.9358422160148621, | |
| "learning_rate": 2.8305839489930168e-05, | |
| "loss": 1.3131, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.2086337852129603, | |
| "grad_norm": 1.0027930736541748, | |
| "learning_rate": 2.829065884019836e-05, | |
| "loss": 1.3345, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.20959523122776655, | |
| "grad_norm": 0.9601215720176697, | |
| "learning_rate": 2.8275478190466553e-05, | |
| "loss": 1.2801, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.21055667724257282, | |
| "grad_norm": 0.8792690634727478, | |
| "learning_rate": 2.8260297540734744e-05, | |
| "loss": 1.2366, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.2115181232573791, | |
| "grad_norm": 1.0058884620666504, | |
| "learning_rate": 2.8245116891002935e-05, | |
| "loss": 1.192, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.21247956927218536, | |
| "grad_norm": 1.0079177618026733, | |
| "learning_rate": 2.8229936241271125e-05, | |
| "loss": 1.2698, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.21344101528699164, | |
| "grad_norm": 1.0556343793869019, | |
| "learning_rate": 2.8214755591539316e-05, | |
| "loss": 1.2477, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.2144024613017979, | |
| "grad_norm": 0.9617932438850403, | |
| "learning_rate": 2.819957494180751e-05, | |
| "loss": 1.2387, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.21536390731660418, | |
| "grad_norm": 0.9451227188110352, | |
| "learning_rate": 2.81843942920757e-05, | |
| "loss": 1.276, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.21632535333141045, | |
| "grad_norm": 0.9511146545410156, | |
| "learning_rate": 2.8169213642343892e-05, | |
| "loss": 1.2211, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.2172867993462167, | |
| "grad_norm": 0.9459360241889954, | |
| "learning_rate": 2.8154032992612082e-05, | |
| "loss": 1.1895, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.21824824536102297, | |
| "grad_norm": 0.9601720571517944, | |
| "learning_rate": 2.8138852342880273e-05, | |
| "loss": 1.2573, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 0.21920969137582924, | |
| "grad_norm": 0.9400343894958496, | |
| "learning_rate": 2.8123671693148467e-05, | |
| "loss": 1.2944, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.2201711373906355, | |
| "grad_norm": 1.0376919507980347, | |
| "learning_rate": 2.8108491043416658e-05, | |
| "loss": 1.2634, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 0.22113258340544178, | |
| "grad_norm": 0.9042131304740906, | |
| "learning_rate": 2.809331039368485e-05, | |
| "loss": 1.2978, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.22209402942024806, | |
| "grad_norm": 0.8955277800559998, | |
| "learning_rate": 2.807812974395304e-05, | |
| "loss": 1.314, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.22305547543505433, | |
| "grad_norm": 0.9650217890739441, | |
| "learning_rate": 2.806294909422123e-05, | |
| "loss": 1.3183, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.2240169214498606, | |
| "grad_norm": 0.9972891211509705, | |
| "learning_rate": 2.8047768444489425e-05, | |
| "loss": 1.2108, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 0.22497836746466685, | |
| "grad_norm": 0.841851532459259, | |
| "learning_rate": 2.8032587794757615e-05, | |
| "loss": 1.2214, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.22593981347947312, | |
| "grad_norm": 1.0023276805877686, | |
| "learning_rate": 2.8017407145025806e-05, | |
| "loss": 1.3031, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.2269012594942794, | |
| "grad_norm": 0.9950117468833923, | |
| "learning_rate": 2.8002226495293997e-05, | |
| "loss": 1.2046, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.22786270550908566, | |
| "grad_norm": 0.9552078247070312, | |
| "learning_rate": 2.7987045845562188e-05, | |
| "loss": 1.2556, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 0.22882415152389193, | |
| "grad_norm": 0.9237502813339233, | |
| "learning_rate": 2.7971865195830382e-05, | |
| "loss": 1.3269, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.2297855975386982, | |
| "grad_norm": 0.8797445893287659, | |
| "learning_rate": 2.7956684546098576e-05, | |
| "loss": 1.2626, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 0.23074704355350448, | |
| "grad_norm": 1.0588504076004028, | |
| "learning_rate": 2.7941503896366767e-05, | |
| "loss": 1.2855, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.23074704355350448, | |
| "eval_loss": 1.2411783933639526, | |
| "eval_runtime": 1809.2447, | |
| "eval_samples_per_second": 11.498, | |
| "eval_steps_per_second": 2.875, | |
| "step": 1200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 10402, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 300, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": [ | |
| { | |
| "args": { | |
| "early_stopping_patience": 8, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| { | |
| "args": { | |
| "early_stopping_patience": 8, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| { | |
| "args": { | |
| "early_stopping_patience": 8, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| { | |
| "args": { | |
| "early_stopping_patience": 8, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| { | |
| "args": { | |
| "early_stopping_patience": 8, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| { | |
| "args": { | |
| "early_stopping_patience": 8, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| { | |
| "args": { | |
| "early_stopping_patience": 8, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| { | |
| "args": { | |
| "early_stopping_patience": 8, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| { | |
| "args": { | |
| "early_stopping_patience": 8, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| { | |
| "args": { | |
| "early_stopping_patience": 8, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| { | |
| "args": { | |
| "early_stopping_patience": 8, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| { | |
| "args": { | |
| "early_stopping_patience": 8, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| { | |
| "args": { | |
| "early_stopping_patience": 8, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| } | |
| ], | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.135052072490493e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |