Instructions to use mjf-su/New-Edge-Critic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use mjf-su/New-Edge-Critic with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-VL-4B-Instruct") model = PeftModel.from_pretrained(base_model, "mjf-su/New-Edge-Critic") - Transformers
How to use mjf-su/New-Edge-Critic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="mjf-su/New-Edge-Critic") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mjf-su/New-Edge-Critic", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use mjf-su/New-Edge-Critic with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mjf-su/New-Edge-Critic" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mjf-su/New-Edge-Critic", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/mjf-su/New-Edge-Critic
- SGLang
How to use mjf-su/New-Edge-Critic 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 "mjf-su/New-Edge-Critic" \ --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": "mjf-su/New-Edge-Critic", "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 "mjf-su/New-Edge-Critic" \ --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": "mjf-su/New-Edge-Critic", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use mjf-su/New-Edge-Critic with Docker Model Runner:
docker model run hf.co/mjf-su/New-Edge-Critic
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9998117824204781, | |
| "eval_steps": 531, | |
| "global_step": 5312, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0, | |
| "eval_E1/acc_on_CONSISTENT": 0.7284768211920529, | |
| "eval_E1/acc_on_INCONSISTENT": 0.6122448979591837, | |
| "eval_E1/accuracy": 0.7, | |
| "eval_E1/balanced_accuracy": 0.6703608595756183, | |
| "eval_E1/f1_INC": 0.4999999999999999, | |
| "eval_E1/n": 200.0, | |
| "eval_E1/precision_INC": 0.4225352112676056, | |
| "eval_E1/recall_INC": 0.6122448979591837, | |
| "eval_E2/acc_on_CONSISTENT": 0.9507042253521126, | |
| "eval_E2/acc_on_INCONSISTENT": 0.6724137931034483, | |
| "eval_E2/accuracy": 0.87, | |
| "eval_E2/balanced_accuracy": 0.8115590092277805, | |
| "eval_E2/f1_INC": 0.75, | |
| "eval_E2/n": 200.0, | |
| "eval_E2/precision_INC": 0.8478260869565217, | |
| "eval_E2/recall_INC": 0.6724137931034483, | |
| "eval_E3/acc_on_CONSISTENT": 1.0, | |
| "eval_E3/acc_on_INCONSISTENT": 0.11428571428571428, | |
| "eval_E3/accuracy": 0.69, | |
| "eval_E3/balanced_accuracy": 0.5571428571428572, | |
| "eval_E3/f1_INC": 0.20512820512820512, | |
| "eval_E3/n": 200.0, | |
| "eval_E3/precision_INC": 1.0, | |
| "eval_E3/recall_INC": 0.11428571428571428, | |
| "eval_E4/acc_on_CONSISTENT": 1.0, | |
| "eval_E4/acc_on_INCONSISTENT": 0.09411764705882353, | |
| "eval_E4/accuracy": 0.615, | |
| "eval_E4/balanced_accuracy": 0.5470588235294118, | |
| "eval_E4/f1_INC": 0.17204301075268816, | |
| "eval_E4/n": 200.0, | |
| "eval_E4/precision_INC": 1.0, | |
| "eval_E4/recall_INC": 0.09411764705882353, | |
| "eval_edge_macro_accuracy": 0.721, | |
| "eval_edge_macro_balanced_accuracy": 0.6421245947954184, | |
| "eval_edge_macro_f1_INC": 0.41293424317617866, | |
| "eval_malformed_rate": 0.0, | |
| "eval_n_eval": 1000.0, | |
| "eval_overall/acc_on_CONSISTENT": 0.8372093023255814, | |
| "eval_overall/acc_on_INCONSISTENT": 0.6624203821656051, | |
| "eval_overall/accuracy": 0.7, | |
| "eval_overall/balanced_accuracy": 0.7498148422455932, | |
| "eval_overall/f1_INC": 0.7761194029850745, | |
| "eval_overall/n": 200.0, | |
| "eval_overall/n_complete_groups": 200.0, | |
| "eval_overall/precision_INC": 0.9369369369369369, | |
| "eval_overall/recall_INC": 0.6624203821656051, | |
| "eval_overall_exact_match": 0.275, | |
| "eval_scene/acc_on_CONSISTENT": 0.9259259259259259, | |
| "eval_scene/acc_on_INCONSISTENT": 0.3230769230769231, | |
| "eval_scene/accuracy": 0.73, | |
| "eval_scene/balanced_accuracy": 0.6245014245014245, | |
| "eval_scene/f1_INC": 0.4375, | |
| "eval_scene/n": 200.0, | |
| "eval_scene/precision_INC": 0.6774193548387096, | |
| "eval_scene/recall_INC": 0.3230769230769231, | |
| "step": 0 | |
| }, | |
| { | |
| "epoch": 0.0018821757952192735, | |
| "grad_norm": 2.9527316093444824, | |
| "learning_rate": 2.821316614420063e-06, | |
| "loss": 0.2619, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003764351590438547, | |
| "grad_norm": 2.514927625656128, | |
| "learning_rate": 5.956112852664577e-06, | |
| "loss": 0.1351, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00564652738565782, | |
| "grad_norm": 0.3812353312969208, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 0.0615, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007528703180877094, | |
| "grad_norm": 0.41659271717071533, | |
| "learning_rate": 1.2225705329153606e-05, | |
| "loss": 0.0457, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009410878976096368, | |
| "grad_norm": 0.35191452503204346, | |
| "learning_rate": 1.536050156739812e-05, | |
| "loss": 0.047, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01129305477131564, | |
| "grad_norm": 0.37843215465545654, | |
| "learning_rate": 1.8495297805642632e-05, | |
| "loss": 0.0463, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.013175230566534914, | |
| "grad_norm": 0.4428830146789551, | |
| "learning_rate": 2.1630094043887147e-05, | |
| "loss": 0.0455, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.015057406361754188, | |
| "grad_norm": 0.3365268111228943, | |
| "learning_rate": 2.4764890282131662e-05, | |
| "loss": 0.0476, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01693958215697346, | |
| "grad_norm": 0.231501042842865, | |
| "learning_rate": 2.7899686520376177e-05, | |
| "loss": 0.0432, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.018821757952192736, | |
| "grad_norm": 0.1805897206068039, | |
| "learning_rate": 3.103448275862069e-05, | |
| "loss": 0.0435, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.020703933747412008, | |
| "grad_norm": 0.18661439418792725, | |
| "learning_rate": 3.4169278996865206e-05, | |
| "loss": 0.0444, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02258610954263128, | |
| "grad_norm": 0.3476637005805969, | |
| "learning_rate": 3.730407523510972e-05, | |
| "loss": 0.0453, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.024468285337850556, | |
| "grad_norm": 0.1493861973285675, | |
| "learning_rate": 4.0438871473354236e-05, | |
| "loss": 0.0453, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.026350461133069828, | |
| "grad_norm": 0.22454732656478882, | |
| "learning_rate": 4.357366771159875e-05, | |
| "loss": 0.0399, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.028232636928289104, | |
| "grad_norm": 0.13001784682273865, | |
| "learning_rate": 4.670846394984326e-05, | |
| "loss": 0.04, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.030114812723508376, | |
| "grad_norm": 0.18267126381397247, | |
| "learning_rate": 4.9843260188087774e-05, | |
| "loss": 0.04, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03199698851872765, | |
| "grad_norm": 0.18140390515327454, | |
| "learning_rate": 5.297805642633229e-05, | |
| "loss": 0.0434, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03387916431394692, | |
| "grad_norm": 0.21444028615951538, | |
| "learning_rate": 5.611285266457681e-05, | |
| "loss": 0.0365, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0357613401091662, | |
| "grad_norm": 0.16569875180721283, | |
| "learning_rate": 5.924764890282132e-05, | |
| "loss": 0.0447, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.03764351590438547, | |
| "grad_norm": 0.3612789511680603, | |
| "learning_rate": 6.238244514106584e-05, | |
| "loss": 0.0403, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.039525691699604744, | |
| "grad_norm": 0.170634463429451, | |
| "learning_rate": 6.551724137931034e-05, | |
| "loss": 0.0402, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.041407867494824016, | |
| "grad_norm": 0.155662402510643, | |
| "learning_rate": 6.865203761755487e-05, | |
| "loss": 0.0422, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.04329004329004329, | |
| "grad_norm": 0.1258857697248459, | |
| "learning_rate": 7.178683385579937e-05, | |
| "loss": 0.0426, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.04517221908526256, | |
| "grad_norm": 0.16679541766643524, | |
| "learning_rate": 7.49216300940439e-05, | |
| "loss": 0.0396, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.04705439488048184, | |
| "grad_norm": 0.13958600163459778, | |
| "learning_rate": 7.80564263322884e-05, | |
| "loss": 0.0381, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.04893657067570111, | |
| "grad_norm": 0.2316679060459137, | |
| "learning_rate": 8.119122257053292e-05, | |
| "loss": 0.042, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.050818746470920384, | |
| "grad_norm": 0.16344308853149414, | |
| "learning_rate": 8.432601880877743e-05, | |
| "loss": 0.0392, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.052700922266139656, | |
| "grad_norm": 0.18365642428398132, | |
| "learning_rate": 8.746081504702195e-05, | |
| "loss": 0.0391, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.05458309806135893, | |
| "grad_norm": 0.24187475442886353, | |
| "learning_rate": 9.059561128526646e-05, | |
| "loss": 0.0384, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.05646527385657821, | |
| "grad_norm": 0.10886389017105103, | |
| "learning_rate": 9.373040752351098e-05, | |
| "loss": 0.0448, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05834744965179748, | |
| "grad_norm": 0.24063026905059814, | |
| "learning_rate": 9.686520376175549e-05, | |
| "loss": 0.0403, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.06022962544701675, | |
| "grad_norm": 0.11817719042301178, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0439, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.062111801242236024, | |
| "grad_norm": 0.10869932174682617, | |
| "learning_rate": 9.990297855826138e-05, | |
| "loss": 0.0405, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.0639939770374553, | |
| "grad_norm": 0.12196257710456848, | |
| "learning_rate": 9.980595711652275e-05, | |
| "loss": 0.0418, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.06587615283267458, | |
| "grad_norm": 0.14207176864147186, | |
| "learning_rate": 9.970893567478413e-05, | |
| "loss": 0.0421, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.06775832862789384, | |
| "grad_norm": 0.1136246919631958, | |
| "learning_rate": 9.961191423304552e-05, | |
| "loss": 0.037, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.06964050442311312, | |
| "grad_norm": 0.17720963060855865, | |
| "learning_rate": 9.951489279130688e-05, | |
| "loss": 0.0354, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.0715226802183324, | |
| "grad_norm": 0.11347354203462601, | |
| "learning_rate": 9.941787134956826e-05, | |
| "loss": 0.0397, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.07340485601355166, | |
| "grad_norm": 0.13800372183322906, | |
| "learning_rate": 9.932084990782964e-05, | |
| "loss": 0.0356, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.07528703180877094, | |
| "grad_norm": 0.11324790865182877, | |
| "learning_rate": 9.922382846609101e-05, | |
| "loss": 0.0351, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07716920760399021, | |
| "grad_norm": 0.09300073236227036, | |
| "learning_rate": 9.912680702435239e-05, | |
| "loss": 0.0369, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.07905138339920949, | |
| "grad_norm": 0.17908748984336853, | |
| "learning_rate": 9.902978558261376e-05, | |
| "loss": 0.0434, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.08093355919442875, | |
| "grad_norm": 0.152435764670372, | |
| "learning_rate": 9.893276414087514e-05, | |
| "loss": 0.0342, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.08281573498964803, | |
| "grad_norm": 0.12728841602802277, | |
| "learning_rate": 9.883574269913651e-05, | |
| "loss": 0.0396, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.08469791078486731, | |
| "grad_norm": 0.12795382738113403, | |
| "learning_rate": 9.87387212573979e-05, | |
| "loss": 0.0388, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.08658008658008658, | |
| "grad_norm": 0.2675169110298157, | |
| "learning_rate": 9.864169981565926e-05, | |
| "loss": 0.037, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.08846226237530586, | |
| "grad_norm": 0.07247938960790634, | |
| "learning_rate": 9.854467837392065e-05, | |
| "loss": 0.0442, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.09034443817052512, | |
| "grad_norm": 0.2071535289287567, | |
| "learning_rate": 9.844765693218202e-05, | |
| "loss": 0.0364, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.0922266139657444, | |
| "grad_norm": 0.12736307084560394, | |
| "learning_rate": 9.835063549044338e-05, | |
| "loss": 0.0356, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.09410878976096368, | |
| "grad_norm": 0.15026968717575073, | |
| "learning_rate": 9.825361404870477e-05, | |
| "loss": 0.0368, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09599096555618294, | |
| "grad_norm": 0.11605150252580643, | |
| "learning_rate": 9.815659260696614e-05, | |
| "loss": 0.0341, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.09787314135140222, | |
| "grad_norm": 0.09585551172494888, | |
| "learning_rate": 9.805957116522752e-05, | |
| "loss": 0.0386, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.09975531714662149, | |
| "grad_norm": 0.07335048168897629, | |
| "learning_rate": 9.796254972348889e-05, | |
| "loss": 0.038, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.09994353472614342, | |
| "eval_E1/acc_on_CONSISTENT": 0.7152317880794702, | |
| "eval_E1/acc_on_INCONSISTENT": 0.673469387755102, | |
| "eval_E1/accuracy": 0.705, | |
| "eval_E1/balanced_accuracy": 0.6943505879172861, | |
| "eval_E1/f1_INC": 0.528, | |
| "eval_E1/n": 200.0, | |
| "eval_E1/precision_INC": 0.4342105263157895, | |
| "eval_E1/recall_INC": 0.673469387755102, | |
| "eval_E2/acc_on_CONSISTENT": 0.9577464788732394, | |
| "eval_E2/acc_on_INCONSISTENT": 0.9482758620689655, | |
| "eval_E2/accuracy": 0.955, | |
| "eval_E2/balanced_accuracy": 0.9530111704711024, | |
| "eval_E2/f1_INC": 0.9243697478991596, | |
| "eval_E2/n": 200.0, | |
| "eval_E2/precision_INC": 0.9016393442622951, | |
| "eval_E2/recall_INC": 0.9482758620689655, | |
| "eval_E3/acc_on_CONSISTENT": 0.9538461538461539, | |
| "eval_E3/acc_on_INCONSISTENT": 0.5857142857142857, | |
| "eval_E3/accuracy": 0.825, | |
| "eval_E3/balanced_accuracy": 0.7697802197802198, | |
| "eval_E3/f1_INC": 0.7008547008547009, | |
| "eval_E3/n": 200.0, | |
| "eval_E3/precision_INC": 0.8723404255319149, | |
| "eval_E3/recall_INC": 0.5857142857142857, | |
| "eval_E4/acc_on_CONSISTENT": 0.9652173913043478, | |
| "eval_E4/acc_on_INCONSISTENT": 0.7411764705882353, | |
| "eval_E4/accuracy": 0.87, | |
| "eval_E4/balanced_accuracy": 0.8531969309462916, | |
| "eval_E4/f1_INC": 0.8289473684210527, | |
| "eval_E4/n": 200.0, | |
| "eval_E4/precision_INC": 0.9402985074626866, | |
| "eval_E4/recall_INC": 0.7411764705882353, | |
| "eval_edge_macro_accuracy": 0.796, | |
| "eval_edge_macro_balanced_accuracy": 0.7945236222788205, | |
| "eval_edge_macro_f1_INC": 0.7195112865119058, | |
| "eval_malformed_rate": 0.0, | |
| "eval_n_eval": 1000.0, | |
| "eval_overall/acc_on_CONSISTENT": 0.32558139534883723, | |
| "eval_overall/acc_on_INCONSISTENT": 0.9681528662420382, | |
| "eval_overall/accuracy": 0.83, | |
| "eval_overall/balanced_accuracy": 0.6468671307954377, | |
| "eval_overall/f1_INC": 0.8994082840236687, | |
| "eval_overall/n": 200.0, | |
| "eval_overall/n_complete_groups": 200.0, | |
| "eval_overall/precision_INC": 0.8397790055248618, | |
| "eval_overall/recall_INC": 0.9681528662420382, | |
| "eval_overall_exact_match": 0.325, | |
| "eval_scene/acc_on_CONSISTENT": 0.48148148148148145, | |
| "eval_scene/acc_on_INCONSISTENT": 0.9230769230769231, | |
| "eval_scene/accuracy": 0.625, | |
| "eval_scene/balanced_accuracy": 0.7022792022792023, | |
| "eval_scene/f1_INC": 0.6153846153846155, | |
| "eval_scene/n": 200.0, | |
| "eval_scene/precision_INC": 0.46153846153846156, | |
| "eval_scene/recall_INC": 0.9230769230769231, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 0.10163749294184077, | |
| "grad_norm": 0.08944286406040192, | |
| "learning_rate": 9.786552828175028e-05, | |
| "loss": 0.0385, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.10351966873706005, | |
| "grad_norm": 0.17637431621551514, | |
| "learning_rate": 9.776850684001164e-05, | |
| "loss": 0.0373, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.10540184453227931, | |
| "grad_norm": 0.16188663244247437, | |
| "learning_rate": 9.767148539827302e-05, | |
| "loss": 0.037, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.10728402032749859, | |
| "grad_norm": 0.107484832406044, | |
| "learning_rate": 9.75744639565344e-05, | |
| "loss": 0.0392, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.10916619612271786, | |
| "grad_norm": 0.10150787979364395, | |
| "learning_rate": 9.747744251479576e-05, | |
| "loss": 0.0326, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.11104837191793714, | |
| "grad_norm": 0.12644043564796448, | |
| "learning_rate": 9.738042107305715e-05, | |
| "loss": 0.0364, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.11293054771315642, | |
| "grad_norm": 0.17111940681934357, | |
| "learning_rate": 9.728339963131853e-05, | |
| "loss": 0.0338, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.11481272350837568, | |
| "grad_norm": 0.10448424518108368, | |
| "learning_rate": 9.71863781895799e-05, | |
| "loss": 0.0355, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.11669489930359496, | |
| "grad_norm": 0.11952169984579086, | |
| "learning_rate": 9.708935674784127e-05, | |
| "loss": 0.0296, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.11857707509881422, | |
| "grad_norm": 0.13310925662517548, | |
| "learning_rate": 9.699233530610265e-05, | |
| "loss": 0.0359, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.1204592508940335, | |
| "grad_norm": 0.10829820483922958, | |
| "learning_rate": 9.689531386436404e-05, | |
| "loss": 0.0355, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.12234142668925278, | |
| "grad_norm": 0.2412945181131363, | |
| "learning_rate": 9.67982924226254e-05, | |
| "loss": 0.0321, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.12422360248447205, | |
| "grad_norm": 0.22749365866184235, | |
| "learning_rate": 9.670127098088679e-05, | |
| "loss": 0.0311, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.12610577827969133, | |
| "grad_norm": 0.11110606044530869, | |
| "learning_rate": 9.660424953914816e-05, | |
| "loss": 0.039, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.1279879540749106, | |
| "grad_norm": 0.1248956024646759, | |
| "learning_rate": 9.650722809740953e-05, | |
| "loss": 0.0342, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.12987012987012986, | |
| "grad_norm": 0.09956880658864975, | |
| "learning_rate": 9.641020665567091e-05, | |
| "loss": 0.0406, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.13175230566534915, | |
| "grad_norm": 0.1490594893693924, | |
| "learning_rate": 9.631318521393228e-05, | |
| "loss": 0.0323, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.13363448146056842, | |
| "grad_norm": 0.13403694331645966, | |
| "learning_rate": 9.621616377219366e-05, | |
| "loss": 0.0339, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.13551665725578768, | |
| "grad_norm": 0.16613461077213287, | |
| "learning_rate": 9.611914233045503e-05, | |
| "loss": 0.0333, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.13739883305100697, | |
| "grad_norm": 0.15149520337581635, | |
| "learning_rate": 9.602212088871642e-05, | |
| "loss": 0.0331, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.13928100884622624, | |
| "grad_norm": 0.1589352935552597, | |
| "learning_rate": 9.592509944697778e-05, | |
| "loss": 0.0342, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.1411631846414455, | |
| "grad_norm": 0.10555554926395416, | |
| "learning_rate": 9.582807800523917e-05, | |
| "loss": 0.0357, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.1430453604366648, | |
| "grad_norm": 0.09868290275335312, | |
| "learning_rate": 9.573105656350054e-05, | |
| "loss": 0.0303, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.14492753623188406, | |
| "grad_norm": 0.2058541476726532, | |
| "learning_rate": 9.563403512176192e-05, | |
| "loss": 0.0326, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.14680971202710333, | |
| "grad_norm": 0.08362213522195816, | |
| "learning_rate": 9.553701368002329e-05, | |
| "loss": 0.0321, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.1486918878223226, | |
| "grad_norm": 0.08654452115297318, | |
| "learning_rate": 9.543999223828467e-05, | |
| "loss": 0.0388, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.1505740636175419, | |
| "grad_norm": 0.14298202097415924, | |
| "learning_rate": 9.534297079654604e-05, | |
| "loss": 0.036, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.15245623941276115, | |
| "grad_norm": 0.09087004512548447, | |
| "learning_rate": 9.524594935480741e-05, | |
| "loss": 0.0335, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.15433841520798042, | |
| "grad_norm": 0.17010165750980377, | |
| "learning_rate": 9.51489279130688e-05, | |
| "loss": 0.0332, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.1562205910031997, | |
| "grad_norm": 0.3323134183883667, | |
| "learning_rate": 9.505190647133016e-05, | |
| "loss": 0.0332, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.15810276679841898, | |
| "grad_norm": 0.1222422793507576, | |
| "learning_rate": 9.495488502959155e-05, | |
| "loss": 0.0275, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.15998494259363824, | |
| "grad_norm": 0.0881538912653923, | |
| "learning_rate": 9.485786358785292e-05, | |
| "loss": 0.0399, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.1618671183888575, | |
| "grad_norm": 0.14195188879966736, | |
| "learning_rate": 9.47608421461143e-05, | |
| "loss": 0.0383, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.1637492941840768, | |
| "grad_norm": 0.10698339343070984, | |
| "learning_rate": 9.466382070437567e-05, | |
| "loss": 0.0319, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.16563146997929606, | |
| "grad_norm": 0.12031501531600952, | |
| "learning_rate": 9.456679926263705e-05, | |
| "loss": 0.034, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.16751364577451533, | |
| "grad_norm": 0.08794030547142029, | |
| "learning_rate": 9.446977782089842e-05, | |
| "loss": 0.0326, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.16939582156973462, | |
| "grad_norm": 0.09387672692537308, | |
| "learning_rate": 9.43727563791598e-05, | |
| "loss": 0.033, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.1712779973649539, | |
| "grad_norm": 0.10707499086856842, | |
| "learning_rate": 9.427573493742118e-05, | |
| "loss": 0.0364, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.17316017316017315, | |
| "grad_norm": 0.09533264487981796, | |
| "learning_rate": 9.417871349568254e-05, | |
| "loss": 0.0331, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.17504234895539245, | |
| "grad_norm": 0.09901942312717438, | |
| "learning_rate": 9.408169205394393e-05, | |
| "loss": 0.0384, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.1769245247506117, | |
| "grad_norm": 0.09254682064056396, | |
| "learning_rate": 9.398467061220531e-05, | |
| "loss": 0.0317, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.17880670054583098, | |
| "grad_norm": 0.16224852204322815, | |
| "learning_rate": 9.388764917046667e-05, | |
| "loss": 0.0321, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.18068887634105024, | |
| "grad_norm": 0.11423856765031815, | |
| "learning_rate": 9.379062772872806e-05, | |
| "loss": 0.0367, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.18257105213626953, | |
| "grad_norm": 0.08567370474338531, | |
| "learning_rate": 9.369360628698943e-05, | |
| "loss": 0.0375, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.1844532279314888, | |
| "grad_norm": 0.15707381069660187, | |
| "learning_rate": 9.35965848452508e-05, | |
| "loss": 0.0275, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.18633540372670807, | |
| "grad_norm": 0.121824711561203, | |
| "learning_rate": 9.349956340351218e-05, | |
| "loss": 0.0346, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.18821757952192736, | |
| "grad_norm": 0.09984467923641205, | |
| "learning_rate": 9.340254196177357e-05, | |
| "loss": 0.0296, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.19009975531714662, | |
| "grad_norm": 0.1463792771100998, | |
| "learning_rate": 9.330552052003493e-05, | |
| "loss": 0.0315, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.1919819311123659, | |
| "grad_norm": 0.0836787298321724, | |
| "learning_rate": 9.32084990782963e-05, | |
| "loss": 0.0342, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.19386410690758518, | |
| "grad_norm": 0.08766288310289383, | |
| "learning_rate": 9.311147763655769e-05, | |
| "loss": 0.0371, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.19574628270280445, | |
| "grad_norm": 0.12990380823612213, | |
| "learning_rate": 9.301445619481905e-05, | |
| "loss": 0.032, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.1976284584980237, | |
| "grad_norm": 0.07059783488512039, | |
| "learning_rate": 9.291743475308044e-05, | |
| "loss": 0.0291, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.19951063429324298, | |
| "grad_norm": 0.10190416872501373, | |
| "learning_rate": 9.282041331134181e-05, | |
| "loss": 0.0307, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.19988706945228685, | |
| "eval_E1/acc_on_CONSISTENT": 0.7549668874172185, | |
| "eval_E1/acc_on_INCONSISTENT": 0.7551020408163265, | |
| "eval_E1/accuracy": 0.755, | |
| "eval_E1/balanced_accuracy": 0.7550344641167726, | |
| "eval_E1/f1_INC": 0.6016260162601625, | |
| "eval_E1/n": 200.0, | |
| "eval_E1/precision_INC": 0.5, | |
| "eval_E1/recall_INC": 0.7551020408163265, | |
| "eval_E2/acc_on_CONSISTENT": 0.9507042253521126, | |
| "eval_E2/acc_on_INCONSISTENT": 0.9310344827586207, | |
| "eval_E2/accuracy": 0.945, | |
| "eval_E2/balanced_accuracy": 0.9408693540553666, | |
| "eval_E2/f1_INC": 0.9075630252100839, | |
| "eval_E2/n": 200.0, | |
| "eval_E2/precision_INC": 0.8852459016393442, | |
| "eval_E2/recall_INC": 0.9310344827586207, | |
| "eval_E3/acc_on_CONSISTENT": 0.9076923076923077, | |
| "eval_E3/acc_on_INCONSISTENT": 0.8, | |
| "eval_E3/accuracy": 0.87, | |
| "eval_E3/balanced_accuracy": 0.8538461538461539, | |
| "eval_E3/f1_INC": 0.8115942028985507, | |
| "eval_E3/n": 200.0, | |
| "eval_E3/precision_INC": 0.8235294117647058, | |
| "eval_E3/recall_INC": 0.8, | |
| "eval_E4/acc_on_CONSISTENT": 0.8434782608695652, | |
| "eval_E4/acc_on_INCONSISTENT": 0.8588235294117647, | |
| "eval_E4/accuracy": 0.85, | |
| "eval_E4/balanced_accuracy": 0.851150895140665, | |
| "eval_E4/f1_INC": 0.8295454545454546, | |
| "eval_E4/n": 200.0, | |
| "eval_E4/precision_INC": 0.8021978021978022, | |
| "eval_E4/recall_INC": 0.8588235294117647, | |
| "eval_edge_macro_accuracy": 0.836, | |
| "eval_edge_macro_balanced_accuracy": 0.8326588059104241, | |
| "eval_edge_macro_f1_INC": 0.7652008749179855, | |
| "eval_malformed_rate": 0.0, | |
| "eval_n_eval": 1000.0, | |
| "eval_overall/acc_on_CONSISTENT": 0.5581395348837209, | |
| "eval_overall/acc_on_INCONSISTENT": 0.9426751592356688, | |
| "eval_overall/accuracy": 0.86, | |
| "eval_overall/balanced_accuracy": 0.7504073470596948, | |
| "eval_overall/f1_INC": 0.9135802469135802, | |
| "eval_overall/n": 200.0, | |
| "eval_overall/n_complete_groups": 200.0, | |
| "eval_overall/precision_INC": 0.8862275449101796, | |
| "eval_overall/recall_INC": 0.9426751592356688, | |
| "eval_overall_exact_match": 0.44, | |
| "eval_scene/acc_on_CONSISTENT": 0.7555555555555555, | |
| "eval_scene/acc_on_INCONSISTENT": 0.7692307692307693, | |
| "eval_scene/accuracy": 0.76, | |
| "eval_scene/balanced_accuracy": 0.7623931623931623, | |
| "eval_scene/f1_INC": 0.6756756756756758, | |
| "eval_scene/n": 200.0, | |
| "eval_scene/precision_INC": 0.6024096385542169, | |
| "eval_scene/recall_INC": 0.7692307692307693, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 0.20139281008846227, | |
| "grad_norm": 0.12929263710975647, | |
| "learning_rate": 9.272339186960319e-05, | |
| "loss": 0.0265, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.20327498588368154, | |
| "grad_norm": 0.11602164059877396, | |
| "learning_rate": 9.262637042786456e-05, | |
| "loss": 0.0313, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.2051571616789008, | |
| "grad_norm": 0.07657571136951447, | |
| "learning_rate": 9.252934898612594e-05, | |
| "loss": 0.0343, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.2070393374741201, | |
| "grad_norm": 0.10203532129526138, | |
| "learning_rate": 9.243232754438731e-05, | |
| "loss": 0.0307, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.20892151326933936, | |
| "grad_norm": 0.10417009890079498, | |
| "learning_rate": 9.233530610264868e-05, | |
| "loss": 0.0261, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.21080368906455862, | |
| "grad_norm": 0.2223087102174759, | |
| "learning_rate": 9.223828466091007e-05, | |
| "loss": 0.0339, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.2126858648597779, | |
| "grad_norm": 0.07738861441612244, | |
| "learning_rate": 9.214126321917143e-05, | |
| "loss": 0.0357, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.21456804065499718, | |
| "grad_norm": 0.0794491246342659, | |
| "learning_rate": 9.204424177743282e-05, | |
| "loss": 0.0298, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.21645021645021645, | |
| "grad_norm": 0.1376914381980896, | |
| "learning_rate": 9.19472203356942e-05, | |
| "loss": 0.0364, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.2183323922454357, | |
| "grad_norm": 0.14536234736442566, | |
| "learning_rate": 9.185019889395557e-05, | |
| "loss": 0.0334, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.220214568040655, | |
| "grad_norm": 0.07669340819120407, | |
| "learning_rate": 9.175317745221694e-05, | |
| "loss": 0.0318, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.22209674383587427, | |
| "grad_norm": 0.06761075556278229, | |
| "learning_rate": 9.165615601047832e-05, | |
| "loss": 0.0278, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.22397891963109354, | |
| "grad_norm": 0.1162271574139595, | |
| "learning_rate": 9.155913456873969e-05, | |
| "loss": 0.0261, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.22586109542631283, | |
| "grad_norm": 0.08550535887479782, | |
| "learning_rate": 9.146211312700107e-05, | |
| "loss": 0.0276, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.2277432712215321, | |
| "grad_norm": 0.13457736372947693, | |
| "learning_rate": 9.136509168526245e-05, | |
| "loss": 0.0319, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.22962544701675136, | |
| "grad_norm": 0.119078628718853, | |
| "learning_rate": 9.126807024352381e-05, | |
| "loss": 0.0325, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.23150762281197063, | |
| "grad_norm": 0.16809587180614471, | |
| "learning_rate": 9.11710488017852e-05, | |
| "loss": 0.0293, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.23338979860718992, | |
| "grad_norm": 0.09518276900053024, | |
| "learning_rate": 9.107402736004658e-05, | |
| "loss": 0.0338, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.23527197440240918, | |
| "grad_norm": 0.08279918879270554, | |
| "learning_rate": 9.097700591830795e-05, | |
| "loss": 0.0344, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.23715415019762845, | |
| "grad_norm": 0.1353113055229187, | |
| "learning_rate": 9.087998447656933e-05, | |
| "loss": 0.0319, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.23903632599284774, | |
| "grad_norm": 0.09605402499437332, | |
| "learning_rate": 9.07829630348307e-05, | |
| "loss": 0.029, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.240918501788067, | |
| "grad_norm": 0.09455064684152603, | |
| "learning_rate": 9.068594159309209e-05, | |
| "loss": 0.033, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.24280067758328627, | |
| "grad_norm": 0.10571754723787308, | |
| "learning_rate": 9.058892015135345e-05, | |
| "loss": 0.033, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.24468285337850557, | |
| "grad_norm": 0.2133651077747345, | |
| "learning_rate": 9.049189870961484e-05, | |
| "loss": 0.0332, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.24656502917372483, | |
| "grad_norm": 0.087664894759655, | |
| "learning_rate": 9.039487726787621e-05, | |
| "loss": 0.0356, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.2484472049689441, | |
| "grad_norm": 0.16927213966846466, | |
| "learning_rate": 9.029785582613758e-05, | |
| "loss": 0.036, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.2503293807641634, | |
| "grad_norm": 0.15412355959415436, | |
| "learning_rate": 9.020083438439896e-05, | |
| "loss": 0.0311, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.25221155655938265, | |
| "grad_norm": 0.14744532108306885, | |
| "learning_rate": 9.010381294266033e-05, | |
| "loss": 0.0302, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.2540937323546019, | |
| "grad_norm": 0.05497835949063301, | |
| "learning_rate": 9.000679150092171e-05, | |
| "loss": 0.0317, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.2559759081498212, | |
| "grad_norm": 0.09722839295864105, | |
| "learning_rate": 8.990977005918308e-05, | |
| "loss": 0.0287, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.25785808394504045, | |
| "grad_norm": 0.09889890998601913, | |
| "learning_rate": 8.981274861744447e-05, | |
| "loss": 0.0269, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.2597402597402597, | |
| "grad_norm": 0.09397543966770172, | |
| "learning_rate": 8.971572717570583e-05, | |
| "loss": 0.0275, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.26162243553547904, | |
| "grad_norm": 0.08513490110635757, | |
| "learning_rate": 8.961870573396722e-05, | |
| "loss": 0.0323, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.2635046113306983, | |
| "grad_norm": 0.08179810643196106, | |
| "learning_rate": 8.952168429222859e-05, | |
| "loss": 0.0295, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.26538678712591757, | |
| "grad_norm": 0.11643363535404205, | |
| "learning_rate": 8.942466285048995e-05, | |
| "loss": 0.0308, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.26726896292113683, | |
| "grad_norm": 0.08557505905628204, | |
| "learning_rate": 8.932764140875134e-05, | |
| "loss": 0.0285, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.2691511387163561, | |
| "grad_norm": 0.14439290761947632, | |
| "learning_rate": 8.923061996701272e-05, | |
| "loss": 0.0357, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.27103331451157536, | |
| "grad_norm": 0.06755843758583069, | |
| "learning_rate": 8.913359852527409e-05, | |
| "loss": 0.0327, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.27291549030679463, | |
| "grad_norm": 0.05954171344637871, | |
| "learning_rate": 8.903657708353546e-05, | |
| "loss": 0.03, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.27479766610201395, | |
| "grad_norm": 0.13399435579776764, | |
| "learning_rate": 8.893955564179685e-05, | |
| "loss": 0.029, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.2766798418972332, | |
| "grad_norm": 0.09965696185827255, | |
| "learning_rate": 8.884253420005821e-05, | |
| "loss": 0.0301, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.2785620176924525, | |
| "grad_norm": 0.11371038854122162, | |
| "learning_rate": 8.874551275831959e-05, | |
| "loss": 0.0319, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.28044419348767174, | |
| "grad_norm": 0.1467040777206421, | |
| "learning_rate": 8.864849131658098e-05, | |
| "loss": 0.0343, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.282326369282891, | |
| "grad_norm": 0.08408571034669876, | |
| "learning_rate": 8.855146987484234e-05, | |
| "loss": 0.0339, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.2842085450781103, | |
| "grad_norm": 0.07174082100391388, | |
| "learning_rate": 8.845444843310372e-05, | |
| "loss": 0.0336, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.2860907208733296, | |
| "grad_norm": 0.1409539431333542, | |
| "learning_rate": 8.83574269913651e-05, | |
| "loss": 0.0265, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.28797289666854886, | |
| "grad_norm": 0.06694231927394867, | |
| "learning_rate": 8.826040554962647e-05, | |
| "loss": 0.0321, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.2898550724637681, | |
| "grad_norm": 0.12007555365562439, | |
| "learning_rate": 8.816338410788785e-05, | |
| "loss": 0.0269, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.2917372482589874, | |
| "grad_norm": 0.10798055678606033, | |
| "learning_rate": 8.806636266614922e-05, | |
| "loss": 0.0258, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.29361942405420666, | |
| "grad_norm": 0.20466643571853638, | |
| "learning_rate": 8.79693412244106e-05, | |
| "loss": 0.026, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.2955015998494259, | |
| "grad_norm": 0.11347216367721558, | |
| "learning_rate": 8.787231978267197e-05, | |
| "loss": 0.0336, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.2973837756446452, | |
| "grad_norm": 0.1293070763349533, | |
| "learning_rate": 8.777529834093336e-05, | |
| "loss": 0.0323, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.2992659514398645, | |
| "grad_norm": 0.16921190917491913, | |
| "learning_rate": 8.767827689919472e-05, | |
| "loss": 0.0315, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.29983060417843027, | |
| "eval_E1/acc_on_CONSISTENT": 0.6821192052980133, | |
| "eval_E1/acc_on_INCONSISTENT": 0.8367346938775511, | |
| "eval_E1/accuracy": 0.72, | |
| "eval_E1/balanced_accuracy": 0.7594269495877821, | |
| "eval_E1/f1_INC": 0.5942028985507247, | |
| "eval_E1/n": 200.0, | |
| "eval_E1/precision_INC": 0.4606741573033708, | |
| "eval_E1/recall_INC": 0.8367346938775511, | |
| "eval_E2/acc_on_CONSISTENT": 0.9859154929577465, | |
| "eval_E2/acc_on_INCONSISTENT": 0.8793103448275862, | |
| "eval_E2/accuracy": 0.955, | |
| "eval_E2/balanced_accuracy": 0.9326129188926664, | |
| "eval_E2/f1_INC": 0.9189189189189189, | |
| "eval_E2/n": 200.0, | |
| "eval_E2/precision_INC": 0.9622641509433962, | |
| "eval_E2/recall_INC": 0.8793103448275862, | |
| "eval_E3/acc_on_CONSISTENT": 0.9307692307692308, | |
| "eval_E3/acc_on_INCONSISTENT": 0.8, | |
| "eval_E3/accuracy": 0.885, | |
| "eval_E3/balanced_accuracy": 0.8653846153846154, | |
| "eval_E3/f1_INC": 0.8296296296296297, | |
| "eval_E3/n": 200.0, | |
| "eval_E3/precision_INC": 0.8615384615384616, | |
| "eval_E3/recall_INC": 0.8, | |
| "eval_E4/acc_on_CONSISTENT": 0.8608695652173913, | |
| "eval_E4/acc_on_INCONSISTENT": 0.8705882352941177, | |
| "eval_E4/accuracy": 0.865, | |
| "eval_E4/balanced_accuracy": 0.8657289002557544, | |
| "eval_E4/f1_INC": 0.8457142857142856, | |
| "eval_E4/n": 200.0, | |
| "eval_E4/precision_INC": 0.8222222222222222, | |
| "eval_E4/recall_INC": 0.8705882352941177, | |
| "eval_edge_macro_accuracy": 0.845, | |
| "eval_edge_macro_balanced_accuracy": 0.8438329560264428, | |
| "eval_edge_macro_f1_INC": 0.7813551183936978, | |
| "eval_malformed_rate": 0.0, | |
| "eval_n_eval": 1000.0, | |
| "eval_overall/acc_on_CONSISTENT": 0.5116279069767442, | |
| "eval_overall/acc_on_INCONSISTENT": 0.9617834394904459, | |
| "eval_overall/accuracy": 0.865, | |
| "eval_overall/balanced_accuracy": 0.736705673233595, | |
| "eval_overall/f1_INC": 0.9179331306990881, | |
| "eval_overall/n": 200.0, | |
| "eval_overall/n_complete_groups": 200.0, | |
| "eval_overall/precision_INC": 0.877906976744186, | |
| "eval_overall/recall_INC": 0.9617834394904459, | |
| "eval_overall_exact_match": 0.44, | |
| "eval_scene/acc_on_CONSISTENT": 0.8074074074074075, | |
| "eval_scene/acc_on_INCONSISTENT": 0.7846153846153846, | |
| "eval_scene/accuracy": 0.8, | |
| "eval_scene/balanced_accuracy": 0.796011396011396, | |
| "eval_scene/f1_INC": 0.7183098591549296, | |
| "eval_scene/n": 200.0, | |
| "eval_scene/precision_INC": 0.6623376623376623, | |
| "eval_scene/recall_INC": 0.7846153846153846, | |
| "step": 1593 | |
| }, | |
| { | |
| "epoch": 0.3011481272350838, | |
| "grad_norm": 0.13088257610797882, | |
| "learning_rate": 8.75812554574561e-05, | |
| "loss": 0.0357, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.30303030303030304, | |
| "grad_norm": 0.12424547970294952, | |
| "learning_rate": 8.748423401571748e-05, | |
| "loss": 0.0351, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.3049124788255223, | |
| "grad_norm": 0.13020102679729462, | |
| "learning_rate": 8.738721257397885e-05, | |
| "loss": 0.0285, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.30679465462074157, | |
| "grad_norm": 0.0963355079293251, | |
| "learning_rate": 8.729019113224023e-05, | |
| "loss": 0.0321, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.30867683041596083, | |
| "grad_norm": 0.10007308423519135, | |
| "learning_rate": 8.71931696905016e-05, | |
| "loss": 0.035, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.3105590062111801, | |
| "grad_norm": 0.09309057146310806, | |
| "learning_rate": 8.709614824876298e-05, | |
| "loss": 0.0332, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.3124411820063994, | |
| "grad_norm": 0.13886569440364838, | |
| "learning_rate": 8.699912680702435e-05, | |
| "loss": 0.0312, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.3143233578016187, | |
| "grad_norm": 0.10759452730417252, | |
| "learning_rate": 8.690210536528574e-05, | |
| "loss": 0.0334, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.31620553359683795, | |
| "grad_norm": 0.11499182879924774, | |
| "learning_rate": 8.68050839235471e-05, | |
| "loss": 0.0301, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.3180877093920572, | |
| "grad_norm": 0.1072067990899086, | |
| "learning_rate": 8.670806248180849e-05, | |
| "loss": 0.0336, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.3199698851872765, | |
| "grad_norm": 0.10061544179916382, | |
| "learning_rate": 8.661104104006986e-05, | |
| "loss": 0.0331, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.32185206098249575, | |
| "grad_norm": 0.12949976325035095, | |
| "learning_rate": 8.651401959833124e-05, | |
| "loss": 0.0291, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.323734236777715, | |
| "grad_norm": 0.14409397542476654, | |
| "learning_rate": 8.641699815659261e-05, | |
| "loss": 0.0266, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.32561641257293433, | |
| "grad_norm": 0.10314024984836578, | |
| "learning_rate": 8.631997671485399e-05, | |
| "loss": 0.0313, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.3274985883681536, | |
| "grad_norm": 0.15678931772708893, | |
| "learning_rate": 8.622295527311536e-05, | |
| "loss": 0.0351, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.32938076416337286, | |
| "grad_norm": 0.09819275140762329, | |
| "learning_rate": 8.612593383137673e-05, | |
| "loss": 0.0337, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.33126293995859213, | |
| "grad_norm": 0.13852599263191223, | |
| "learning_rate": 8.602891238963812e-05, | |
| "loss": 0.0312, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.3331451157538114, | |
| "grad_norm": 0.11017139256000519, | |
| "learning_rate": 8.593189094789948e-05, | |
| "loss": 0.0305, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.33502729154903066, | |
| "grad_norm": 0.07422087341547012, | |
| "learning_rate": 8.583486950616087e-05, | |
| "loss": 0.0263, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.33690946734425, | |
| "grad_norm": 0.1125585064291954, | |
| "learning_rate": 8.573784806442225e-05, | |
| "loss": 0.0315, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.33879164313946925, | |
| "grad_norm": 0.08203578740358353, | |
| "learning_rate": 8.56408266226836e-05, | |
| "loss": 0.0307, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.3406738189346885, | |
| "grad_norm": 0.10316994786262512, | |
| "learning_rate": 8.5543805180945e-05, | |
| "loss": 0.0249, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.3425559947299078, | |
| "grad_norm": 0.18619760870933533, | |
| "learning_rate": 8.544678373920637e-05, | |
| "loss": 0.0264, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.34443817052512704, | |
| "grad_norm": 0.08711568266153336, | |
| "learning_rate": 8.534976229746774e-05, | |
| "loss": 0.0342, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.3463203463203463, | |
| "grad_norm": 0.11246860027313232, | |
| "learning_rate": 8.525274085572912e-05, | |
| "loss": 0.03, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.34820252211556557, | |
| "grad_norm": 0.05884129926562309, | |
| "learning_rate": 8.51557194139905e-05, | |
| "loss": 0.0299, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.3500846979107849, | |
| "grad_norm": 0.12434038519859314, | |
| "learning_rate": 8.505869797225187e-05, | |
| "loss": 0.0263, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.35196687370600416, | |
| "grad_norm": 0.0966510996222496, | |
| "learning_rate": 8.496167653051324e-05, | |
| "loss": 0.029, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.3538490495012234, | |
| "grad_norm": 0.12718771398067474, | |
| "learning_rate": 8.486465508877463e-05, | |
| "loss": 0.0346, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.3557312252964427, | |
| "grad_norm": 0.04632233828306198, | |
| "learning_rate": 8.4767633647036e-05, | |
| "loss": 0.029, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.35761340109166195, | |
| "grad_norm": 0.1020045280456543, | |
| "learning_rate": 8.467061220529738e-05, | |
| "loss": 0.0283, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.3594955768868812, | |
| "grad_norm": 0.14108321070671082, | |
| "learning_rate": 8.457359076355875e-05, | |
| "loss": 0.0298, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.3613777526821005, | |
| "grad_norm": 0.12967492640018463, | |
| "learning_rate": 8.447656932182014e-05, | |
| "loss": 0.0298, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.3632599284773198, | |
| "grad_norm": 0.07042180001735687, | |
| "learning_rate": 8.43795478800815e-05, | |
| "loss": 0.0284, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.36514210427253907, | |
| "grad_norm": 0.14567403495311737, | |
| "learning_rate": 8.428252643834287e-05, | |
| "loss": 0.028, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.36702428006775834, | |
| "grad_norm": 0.10920072346925735, | |
| "learning_rate": 8.418550499660426e-05, | |
| "loss": 0.0319, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.3689064558629776, | |
| "grad_norm": 0.0970524400472641, | |
| "learning_rate": 8.408848355486562e-05, | |
| "loss": 0.0263, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.37078863165819687, | |
| "grad_norm": 0.13133934140205383, | |
| "learning_rate": 8.399146211312701e-05, | |
| "loss": 0.0333, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.37267080745341613, | |
| "grad_norm": 0.12621761858463287, | |
| "learning_rate": 8.389444067138838e-05, | |
| "loss": 0.0302, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.3745529832486354, | |
| "grad_norm": 0.08393672108650208, | |
| "learning_rate": 8.379741922964976e-05, | |
| "loss": 0.0296, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.3764351590438547, | |
| "grad_norm": 0.11379829049110413, | |
| "learning_rate": 8.370039778791113e-05, | |
| "loss": 0.0255, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.378317334839074, | |
| "grad_norm": 0.07760214060544968, | |
| "learning_rate": 8.360337634617251e-05, | |
| "loss": 0.0244, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.38019951063429325, | |
| "grad_norm": 0.07392806559801102, | |
| "learning_rate": 8.350635490443388e-05, | |
| "loss": 0.0315, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.3820816864295125, | |
| "grad_norm": 0.12959477305412292, | |
| "learning_rate": 8.340933346269526e-05, | |
| "loss": 0.0302, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.3839638622247318, | |
| "grad_norm": 0.09377480298280716, | |
| "learning_rate": 8.331231202095664e-05, | |
| "loss": 0.0302, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.38584603801995104, | |
| "grad_norm": 0.06865111738443375, | |
| "learning_rate": 8.3215290579218e-05, | |
| "loss": 0.0314, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.38772821381517036, | |
| "grad_norm": 0.11195676028728485, | |
| "learning_rate": 8.311826913747939e-05, | |
| "loss": 0.0273, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.38961038961038963, | |
| "grad_norm": 0.1206878051161766, | |
| "learning_rate": 8.302124769574077e-05, | |
| "loss": 0.034, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.3914925654056089, | |
| "grad_norm": 0.09009220451116562, | |
| "learning_rate": 8.292422625400214e-05, | |
| "loss": 0.0296, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.39337474120082816, | |
| "grad_norm": 0.1171526163816452, | |
| "learning_rate": 8.282720481226351e-05, | |
| "loss": 0.031, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.3952569169960474, | |
| "grad_norm": 0.0794205442070961, | |
| "learning_rate": 8.273018337052489e-05, | |
| "loss": 0.0255, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.3971390927912667, | |
| "grad_norm": 0.07322624325752258, | |
| "learning_rate": 8.263316192878626e-05, | |
| "loss": 0.0287, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.39902126858648596, | |
| "grad_norm": 0.09714718908071518, | |
| "learning_rate": 8.253614048704764e-05, | |
| "loss": 0.0261, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.3997741389045737, | |
| "eval_E1/acc_on_CONSISTENT": 0.8807947019867549, | |
| "eval_E1/acc_on_INCONSISTENT": 0.6530612244897959, | |
| "eval_E1/accuracy": 0.825, | |
| "eval_E1/balanced_accuracy": 0.7669279632382754, | |
| "eval_E1/f1_INC": 0.6464646464646464, | |
| "eval_E1/n": 200.0, | |
| "eval_E1/precision_INC": 0.64, | |
| "eval_E1/recall_INC": 0.6530612244897959, | |
| "eval_E2/acc_on_CONSISTENT": 0.9929577464788732, | |
| "eval_E2/acc_on_INCONSISTENT": 0.9137931034482759, | |
| "eval_E2/accuracy": 0.97, | |
| "eval_E2/balanced_accuracy": 0.9533754249635746, | |
| "eval_E2/f1_INC": 0.9464285714285714, | |
| "eval_E2/n": 200.0, | |
| "eval_E2/precision_INC": 0.9814814814814815, | |
| "eval_E2/recall_INC": 0.9137931034482759, | |
| "eval_E3/acc_on_CONSISTENT": 0.9615384615384616, | |
| "eval_E3/acc_on_INCONSISTENT": 0.7857142857142857, | |
| "eval_E3/accuracy": 0.9, | |
| "eval_E3/balanced_accuracy": 0.8736263736263736, | |
| "eval_E3/f1_INC": 0.8461538461538461, | |
| "eval_E3/n": 200.0, | |
| "eval_E3/precision_INC": 0.9166666666666666, | |
| "eval_E3/recall_INC": 0.7857142857142857, | |
| "eval_E4/acc_on_CONSISTENT": 0.9478260869565217, | |
| "eval_E4/acc_on_INCONSISTENT": 0.8117647058823529, | |
| "eval_E4/accuracy": 0.89, | |
| "eval_E4/balanced_accuracy": 0.8797953964194374, | |
| "eval_E4/f1_INC": 0.8625, | |
| "eval_E4/n": 200.0, | |
| "eval_E4/precision_INC": 0.92, | |
| "eval_E4/recall_INC": 0.8117647058823529, | |
| "eval_edge_macro_accuracy": 0.877, | |
| "eval_edge_macro_balanced_accuracy": 0.8403860572905579, | |
| "eval_edge_macro_f1_INC": 0.7862353387353387, | |
| "eval_malformed_rate": 0.0, | |
| "eval_n_eval": 1000.0, | |
| "eval_overall/acc_on_CONSISTENT": 0.8604651162790697, | |
| "eval_overall/acc_on_INCONSISTENT": 0.8789808917197452, | |
| "eval_overall/accuracy": 0.875, | |
| "eval_overall/balanced_accuracy": 0.8697230039994075, | |
| "eval_overall/f1_INC": 0.9169435215946845, | |
| "eval_overall/n": 200.0, | |
| "eval_overall/n_complete_groups": 200.0, | |
| "eval_overall/precision_INC": 0.9583333333333334, | |
| "eval_overall/recall_INC": 0.8789808917197452, | |
| "eval_overall_exact_match": 0.56, | |
| "eval_scene/acc_on_CONSISTENT": 0.9333333333333333, | |
| "eval_scene/acc_on_INCONSISTENT": 0.5230769230769231, | |
| "eval_scene/accuracy": 0.8, | |
| "eval_scene/balanced_accuracy": 0.7282051282051283, | |
| "eval_scene/f1_INC": 0.6296296296296297, | |
| "eval_scene/n": 200.0, | |
| "eval_scene/precision_INC": 0.7906976744186046, | |
| "eval_scene/recall_INC": 0.5230769230769231, | |
| "step": 2124 | |
| }, | |
| { | |
| "epoch": 0.4009034443817053, | |
| "grad_norm": 0.15719006955623627, | |
| "learning_rate": 8.243911904530903e-05, | |
| "loss": 0.0269, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.40278562017692454, | |
| "grad_norm": 0.06503473967313766, | |
| "learning_rate": 8.234209760357039e-05, | |
| "loss": 0.0283, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.4046677959721438, | |
| "grad_norm": 0.09964703023433685, | |
| "learning_rate": 8.224507616183177e-05, | |
| "loss": 0.0232, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.40654997176736307, | |
| "grad_norm": 0.13143323361873627, | |
| "learning_rate": 8.214805472009315e-05, | |
| "loss": 0.0267, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.40843214756258234, | |
| "grad_norm": 0.12974168360233307, | |
| "learning_rate": 8.205103327835452e-05, | |
| "loss": 0.0256, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.4103143233578016, | |
| "grad_norm": 0.09947684407234192, | |
| "learning_rate": 8.19540118366159e-05, | |
| "loss": 0.0307, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.41219649915302087, | |
| "grad_norm": 0.10723303258419037, | |
| "learning_rate": 8.185699039487727e-05, | |
| "loss": 0.0283, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.4140786749482402, | |
| "grad_norm": 0.07822173833847046, | |
| "learning_rate": 8.175996895313865e-05, | |
| "loss": 0.0269, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.41596085074345945, | |
| "grad_norm": 0.10570277273654938, | |
| "learning_rate": 8.166294751140002e-05, | |
| "loss": 0.0295, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.4178430265386787, | |
| "grad_norm": 0.09187448024749756, | |
| "learning_rate": 8.156592606966141e-05, | |
| "loss": 0.0308, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.419725202333898, | |
| "grad_norm": 0.10860244184732437, | |
| "learning_rate": 8.146890462792277e-05, | |
| "loss": 0.0312, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.42160737812911725, | |
| "grad_norm": 0.07823146134614944, | |
| "learning_rate": 8.137188318618416e-05, | |
| "loss": 0.0302, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.4234895539243365, | |
| "grad_norm": 0.05982290208339691, | |
| "learning_rate": 8.127486174444553e-05, | |
| "loss": 0.0261, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.4253717297195558, | |
| "grad_norm": 0.13135980069637299, | |
| "learning_rate": 8.117784030270689e-05, | |
| "loss": 0.0357, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.4272539055147751, | |
| "grad_norm": 0.08659800887107849, | |
| "learning_rate": 8.108081886096828e-05, | |
| "loss": 0.0331, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.42913608130999437, | |
| "grad_norm": 0.07572152465581894, | |
| "learning_rate": 8.098379741922965e-05, | |
| "loss": 0.0284, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.43101825710521363, | |
| "grad_norm": 0.11546391248703003, | |
| "learning_rate": 8.088677597749103e-05, | |
| "loss": 0.034, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.4329004329004329, | |
| "grad_norm": 0.09705963730812073, | |
| "learning_rate": 8.07897545357524e-05, | |
| "loss": 0.0277, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.43478260869565216, | |
| "grad_norm": 0.1337226778268814, | |
| "learning_rate": 8.069273309401379e-05, | |
| "loss": 0.0275, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.4366647844908714, | |
| "grad_norm": 0.10398007929325104, | |
| "learning_rate": 8.059571165227515e-05, | |
| "loss": 0.0269, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.43854696028609075, | |
| "grad_norm": 0.059763580560684204, | |
| "learning_rate": 8.049869021053653e-05, | |
| "loss": 0.03, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.44042913608131, | |
| "grad_norm": 0.1391168087720871, | |
| "learning_rate": 8.040166876879791e-05, | |
| "loss": 0.0259, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.4423113118765293, | |
| "grad_norm": 0.12780527770519257, | |
| "learning_rate": 8.030464732705927e-05, | |
| "loss": 0.0306, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.44419348767174854, | |
| "grad_norm": 0.09013444930315018, | |
| "learning_rate": 8.020762588532066e-05, | |
| "loss": 0.0238, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.4460756634669678, | |
| "grad_norm": 0.08515927940607071, | |
| "learning_rate": 8.011060444358204e-05, | |
| "loss": 0.0315, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.4479578392621871, | |
| "grad_norm": 0.07814784348011017, | |
| "learning_rate": 8.001358300184341e-05, | |
| "loss": 0.0284, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.44984001505740634, | |
| "grad_norm": 0.10175956785678864, | |
| "learning_rate": 7.991656156010478e-05, | |
| "loss": 0.03, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.45172219085262566, | |
| "grad_norm": 0.0597836934030056, | |
| "learning_rate": 7.981954011836616e-05, | |
| "loss": 0.0266, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.4536043666478449, | |
| "grad_norm": 0.07506367564201355, | |
| "learning_rate": 7.972251867662753e-05, | |
| "loss": 0.0319, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.4554865424430642, | |
| "grad_norm": 0.08653825521469116, | |
| "learning_rate": 7.962549723488891e-05, | |
| "loss": 0.0264, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.45736871823828346, | |
| "grad_norm": 0.14505213499069214, | |
| "learning_rate": 7.95284757931503e-05, | |
| "loss": 0.0252, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.4592508940335027, | |
| "grad_norm": 0.13145671784877777, | |
| "learning_rate": 7.943145435141166e-05, | |
| "loss": 0.0295, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.461133069828722, | |
| "grad_norm": 0.07361818104982376, | |
| "learning_rate": 7.933443290967304e-05, | |
| "loss": 0.0269, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.46301524562394125, | |
| "grad_norm": 0.1015157401561737, | |
| "learning_rate": 7.923741146793442e-05, | |
| "loss": 0.0279, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.4648974214191606, | |
| "grad_norm": 0.09409838169813156, | |
| "learning_rate": 7.914039002619579e-05, | |
| "loss": 0.0294, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.46677959721437984, | |
| "grad_norm": 0.0932067483663559, | |
| "learning_rate": 7.904336858445717e-05, | |
| "loss": 0.0265, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.4686617730095991, | |
| "grad_norm": 0.15952104330062866, | |
| "learning_rate": 7.894634714271854e-05, | |
| "loss": 0.0255, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.47054394880481837, | |
| "grad_norm": 0.09479888528585434, | |
| "learning_rate": 7.884932570097993e-05, | |
| "loss": 0.0279, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.47242612460003763, | |
| "grad_norm": 0.1220136433839798, | |
| "learning_rate": 7.875230425924129e-05, | |
| "loss": 0.0294, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.4743083003952569, | |
| "grad_norm": 0.08821658045053482, | |
| "learning_rate": 7.865528281750268e-05, | |
| "loss": 0.0305, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 0.23937903344631195, | |
| "learning_rate": 7.855826137576405e-05, | |
| "loss": 0.0269, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.4780726519856955, | |
| "grad_norm": 0.09873885661363602, | |
| "learning_rate": 7.846123993402543e-05, | |
| "loss": 0.0324, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.47995482778091475, | |
| "grad_norm": 0.08553300052881241, | |
| "learning_rate": 7.83642184922868e-05, | |
| "loss": 0.0328, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.481837003576134, | |
| "grad_norm": 0.1176324337720871, | |
| "learning_rate": 7.826719705054818e-05, | |
| "loss": 0.0353, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.4837191793713533, | |
| "grad_norm": 0.09982674568891525, | |
| "learning_rate": 7.817017560880955e-05, | |
| "loss": 0.0301, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.48560135516657255, | |
| "grad_norm": 0.08941078931093216, | |
| "learning_rate": 7.807315416707092e-05, | |
| "loss": 0.0286, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.4874835309617918, | |
| "grad_norm": 0.15026530623435974, | |
| "learning_rate": 7.797613272533231e-05, | |
| "loss": 0.0266, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.48936570675701113, | |
| "grad_norm": 0.10724597424268723, | |
| "learning_rate": 7.787911128359367e-05, | |
| "loss": 0.0284, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.4912478825522304, | |
| "grad_norm": 0.08620548248291016, | |
| "learning_rate": 7.778208984185506e-05, | |
| "loss": 0.0296, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.49313005834744966, | |
| "grad_norm": 0.08863481879234314, | |
| "learning_rate": 7.768506840011643e-05, | |
| "loss": 0.0241, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.4950122341426689, | |
| "grad_norm": 0.08469167351722717, | |
| "learning_rate": 7.758804695837781e-05, | |
| "loss": 0.0273, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.4968944099378882, | |
| "grad_norm": 0.133014976978302, | |
| "learning_rate": 7.749102551663918e-05, | |
| "loss": 0.0295, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.49877658573310746, | |
| "grad_norm": 0.09178700298070908, | |
| "learning_rate": 7.739400407490056e-05, | |
| "loss": 0.0293, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.4997176736307171, | |
| "eval_E1/acc_on_CONSISTENT": 0.8211920529801324, | |
| "eval_E1/acc_on_INCONSISTENT": 0.7346938775510204, | |
| "eval_E1/accuracy": 0.8, | |
| "eval_E1/balanced_accuracy": 0.7779429652655765, | |
| "eval_E1/f1_INC": 0.6428571428571428, | |
| "eval_E1/n": 200.0, | |
| "eval_E1/precision_INC": 0.5714285714285714, | |
| "eval_E1/recall_INC": 0.7346938775510204, | |
| "eval_E2/acc_on_CONSISTENT": 0.9929577464788732, | |
| "eval_E2/acc_on_INCONSISTENT": 0.8793103448275862, | |
| "eval_E2/accuracy": 0.96, | |
| "eval_E2/balanced_accuracy": 0.9361340456532297, | |
| "eval_E2/f1_INC": 0.9272727272727272, | |
| "eval_E2/n": 200.0, | |
| "eval_E2/precision_INC": 0.9807692307692307, | |
| "eval_E2/recall_INC": 0.8793103448275862, | |
| "eval_E3/acc_on_CONSISTENT": 0.9692307692307692, | |
| "eval_E3/acc_on_INCONSISTENT": 0.7857142857142857, | |
| "eval_E3/accuracy": 0.905, | |
| "eval_E3/balanced_accuracy": 0.8774725274725275, | |
| "eval_E3/f1_INC": 0.8527131782945736, | |
| "eval_E3/n": 200.0, | |
| "eval_E3/precision_INC": 0.9322033898305084, | |
| "eval_E3/recall_INC": 0.7857142857142857, | |
| "eval_E4/acc_on_CONSISTENT": 0.9565217391304348, | |
| "eval_E4/acc_on_INCONSISTENT": 0.8352941176470589, | |
| "eval_E4/accuracy": 0.905, | |
| "eval_E4/balanced_accuracy": 0.8959079283887468, | |
| "eval_E4/f1_INC": 0.8819875776397516, | |
| "eval_E4/n": 200.0, | |
| "eval_E4/precision_INC": 0.9342105263157895, | |
| "eval_E4/recall_INC": 0.8352941176470589, | |
| "eval_edge_macro_accuracy": 0.881, | |
| "eval_edge_macro_balanced_accuracy": 0.8602835161480389, | |
| "eval_edge_macro_f1_INC": 0.8105844458235261, | |
| "eval_malformed_rate": 0.0, | |
| "eval_n_eval": 1000.0, | |
| "eval_overall/acc_on_CONSISTENT": 0.813953488372093, | |
| "eval_overall/acc_on_INCONSISTENT": 0.9235668789808917, | |
| "eval_overall/accuracy": 0.9, | |
| "eval_overall/balanced_accuracy": 0.8687601836764924, | |
| "eval_overall/f1_INC": 0.935483870967742, | |
| "eval_overall/n": 200.0, | |
| "eval_overall/n_complete_groups": 200.0, | |
| "eval_overall/precision_INC": 0.9477124183006536, | |
| "eval_overall/recall_INC": 0.9235668789808917, | |
| "eval_overall_exact_match": 0.575, | |
| "eval_scene/acc_on_CONSISTENT": 0.8740740740740741, | |
| "eval_scene/acc_on_INCONSISTENT": 0.7538461538461538, | |
| "eval_scene/accuracy": 0.835, | |
| "eval_scene/balanced_accuracy": 0.813960113960114, | |
| "eval_scene/f1_INC": 0.7480916030534351, | |
| "eval_scene/n": 200.0, | |
| "eval_scene/precision_INC": 0.7424242424242424, | |
| "eval_scene/recall_INC": 0.7538461538461538, | |
| "step": 2655 | |
| }, | |
| { | |
| "epoch": 0.5006587615283268, | |
| "grad_norm": 0.11279813200235367, | |
| "learning_rate": 7.729698263316193e-05, | |
| "loss": 0.0309, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.502540937323546, | |
| "grad_norm": 0.08533964306116104, | |
| "learning_rate": 7.71999611914233e-05, | |
| "loss": 0.0256, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.5044231131187653, | |
| "grad_norm": 0.14148874580860138, | |
| "learning_rate": 7.71029397496847e-05, | |
| "loss": 0.0236, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.5063052889139845, | |
| "grad_norm": 0.11055805534124374, | |
| "learning_rate": 7.700591830794605e-05, | |
| "loss": 0.0305, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.5081874647092038, | |
| "grad_norm": 0.0990087240934372, | |
| "learning_rate": 7.690889686620744e-05, | |
| "loss": 0.0294, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.5100696405044232, | |
| "grad_norm": 0.12202861160039902, | |
| "learning_rate": 7.681187542446882e-05, | |
| "loss": 0.025, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.5119518162996424, | |
| "grad_norm": 0.10385531932115555, | |
| "learning_rate": 7.671485398273018e-05, | |
| "loss": 0.0314, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.5138339920948617, | |
| "grad_norm": 0.07932283729314804, | |
| "learning_rate": 7.661783254099157e-05, | |
| "loss": 0.0248, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.5157161678900809, | |
| "grad_norm": 0.10993891954421997, | |
| "learning_rate": 7.652081109925294e-05, | |
| "loss": 0.0242, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.5175983436853002, | |
| "grad_norm": 0.16471970081329346, | |
| "learning_rate": 7.642378965751431e-05, | |
| "loss": 0.0303, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.5194805194805194, | |
| "grad_norm": 0.10347539931535721, | |
| "learning_rate": 7.632676821577569e-05, | |
| "loss": 0.0274, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.5213626952757388, | |
| "grad_norm": 0.11677437275648117, | |
| "learning_rate": 7.622974677403706e-05, | |
| "loss": 0.0288, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.5232448710709581, | |
| "grad_norm": 0.09840503334999084, | |
| "learning_rate": 7.613272533229844e-05, | |
| "loss": 0.0269, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.5251270468661773, | |
| "grad_norm": 0.06443244963884354, | |
| "learning_rate": 7.603570389055981e-05, | |
| "loss": 0.0337, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.5270092226613966, | |
| "grad_norm": 0.11365149915218353, | |
| "learning_rate": 7.59386824488212e-05, | |
| "loss": 0.0269, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.5288913984566158, | |
| "grad_norm": 0.09044452011585236, | |
| "learning_rate": 7.584166100708256e-05, | |
| "loss": 0.0299, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.5307735742518351, | |
| "grad_norm": 0.10111326724290848, | |
| "learning_rate": 7.574463956534395e-05, | |
| "loss": 0.0262, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.5326557500470543, | |
| "grad_norm": 0.1057933047413826, | |
| "learning_rate": 7.564761812360532e-05, | |
| "loss": 0.0232, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.5345379258422737, | |
| "grad_norm": 0.11712583154439926, | |
| "learning_rate": 7.55505966818667e-05, | |
| "loss": 0.0282, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.536420101637493, | |
| "grad_norm": 0.09643035382032394, | |
| "learning_rate": 7.545357524012807e-05, | |
| "loss": 0.0269, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.5383022774327122, | |
| "grad_norm": 0.10376808047294617, | |
| "learning_rate": 7.535655379838945e-05, | |
| "loss": 0.024, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.5401844532279315, | |
| "grad_norm": 0.24281369149684906, | |
| "learning_rate": 7.525953235665082e-05, | |
| "loss": 0.0283, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.5420666290231507, | |
| "grad_norm": 0.10237613320350647, | |
| "learning_rate": 7.51625109149122e-05, | |
| "loss": 0.0316, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.54394880481837, | |
| "grad_norm": 0.12895576655864716, | |
| "learning_rate": 7.506548947317358e-05, | |
| "loss": 0.0294, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.5458309806135893, | |
| "grad_norm": 0.11355803906917572, | |
| "learning_rate": 7.496846803143494e-05, | |
| "loss": 0.0277, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.5477131564088086, | |
| "grad_norm": 0.16196122765541077, | |
| "learning_rate": 7.487144658969633e-05, | |
| "loss": 0.0305, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.5495953322040279, | |
| "grad_norm": 0.08025684952735901, | |
| "learning_rate": 7.47744251479577e-05, | |
| "loss": 0.0291, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.5514775079992471, | |
| "grad_norm": 0.10405171662569046, | |
| "learning_rate": 7.467740370621908e-05, | |
| "loss": 0.0266, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.5533596837944664, | |
| "grad_norm": 0.17075183987617493, | |
| "learning_rate": 7.458038226448045e-05, | |
| "loss": 0.0261, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.5552418595896856, | |
| "grad_norm": 0.13905194401741028, | |
| "learning_rate": 7.448336082274183e-05, | |
| "loss": 0.0234, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.557124035384905, | |
| "grad_norm": 0.08814238011837006, | |
| "learning_rate": 7.43863393810032e-05, | |
| "loss": 0.0342, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.5590062111801242, | |
| "grad_norm": 0.08515793830156326, | |
| "learning_rate": 7.428931793926458e-05, | |
| "loss": 0.0293, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.5608883869753435, | |
| "grad_norm": 0.0772959515452385, | |
| "learning_rate": 7.419229649752596e-05, | |
| "loss": 0.026, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.5627705627705628, | |
| "grad_norm": 0.12232999503612518, | |
| "learning_rate": 7.409527505578732e-05, | |
| "loss": 0.0315, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.564652738565782, | |
| "grad_norm": 0.062099162489175797, | |
| "learning_rate": 7.399825361404871e-05, | |
| "loss": 0.0261, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.5665349143610013, | |
| "grad_norm": 0.08616367727518082, | |
| "learning_rate": 7.390123217231009e-05, | |
| "loss": 0.0221, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.5684170901562206, | |
| "grad_norm": 0.1390579491853714, | |
| "learning_rate": 7.380421073057146e-05, | |
| "loss": 0.0289, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.5702992659514399, | |
| "grad_norm": 0.0917593464255333, | |
| "learning_rate": 7.370718928883284e-05, | |
| "loss": 0.0249, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.5721814417466592, | |
| "grad_norm": 0.12263333052396774, | |
| "learning_rate": 7.361016784709421e-05, | |
| "loss": 0.0284, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.5740636175418784, | |
| "grad_norm": 0.08040110766887665, | |
| "learning_rate": 7.351314640535558e-05, | |
| "loss": 0.0231, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.5759457933370977, | |
| "grad_norm": 0.11405957490205765, | |
| "learning_rate": 7.341612496361696e-05, | |
| "loss": 0.0238, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.5778279691323169, | |
| "grad_norm": 0.05968109518289566, | |
| "learning_rate": 7.331910352187835e-05, | |
| "loss": 0.0282, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.5797101449275363, | |
| "grad_norm": 0.10681314766407013, | |
| "learning_rate": 7.322208208013971e-05, | |
| "loss": 0.027, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.5815923207227555, | |
| "grad_norm": 0.0905841812491417, | |
| "learning_rate": 7.31250606384011e-05, | |
| "loss": 0.0258, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.5834744965179748, | |
| "grad_norm": 0.07992485910654068, | |
| "learning_rate": 7.302803919666247e-05, | |
| "loss": 0.021, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.5853566723131941, | |
| "grad_norm": 0.09587814658880234, | |
| "learning_rate": 7.293101775492384e-05, | |
| "loss": 0.0338, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.5872388481084133, | |
| "grad_norm": 0.07799631357192993, | |
| "learning_rate": 7.283399631318522e-05, | |
| "loss": 0.0284, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.5891210239036326, | |
| "grad_norm": 0.1305895447731018, | |
| "learning_rate": 7.273697487144659e-05, | |
| "loss": 0.0271, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.5910031996988518, | |
| "grad_norm": 0.13612420856952667, | |
| "learning_rate": 7.263995342970798e-05, | |
| "loss": 0.0241, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.5928853754940712, | |
| "grad_norm": 0.10845185816287994, | |
| "learning_rate": 7.254293198796934e-05, | |
| "loss": 0.0281, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.5947675512892904, | |
| "grad_norm": 0.10513018816709518, | |
| "learning_rate": 7.244591054623073e-05, | |
| "loss": 0.0264, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.5966497270845097, | |
| "grad_norm": 0.17080609500408173, | |
| "learning_rate": 7.23488891044921e-05, | |
| "loss": 0.0273, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.598531902879729, | |
| "grad_norm": 0.08871451020240784, | |
| "learning_rate": 7.225186766275346e-05, | |
| "loss": 0.0309, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.5996612083568605, | |
| "eval_E1/acc_on_CONSISTENT": 0.8211920529801324, | |
| "eval_E1/acc_on_INCONSISTENT": 0.7346938775510204, | |
| "eval_E1/accuracy": 0.8, | |
| "eval_E1/balanced_accuracy": 0.7779429652655765, | |
| "eval_E1/f1_INC": 0.6428571428571428, | |
| "eval_E1/n": 200.0, | |
| "eval_E1/precision_INC": 0.5714285714285714, | |
| "eval_E1/recall_INC": 0.7346938775510204, | |
| "eval_E2/acc_on_CONSISTENT": 0.9929577464788732, | |
| "eval_E2/acc_on_INCONSISTENT": 0.9655172413793104, | |
| "eval_E2/accuracy": 0.985, | |
| "eval_E2/balanced_accuracy": 0.9792374939290918, | |
| "eval_E2/f1_INC": 0.9739130434782608, | |
| "eval_E2/n": 200.0, | |
| "eval_E2/precision_INC": 0.9824561403508771, | |
| "eval_E2/recall_INC": 0.9655172413793104, | |
| "eval_E3/acc_on_CONSISTENT": 0.9384615384615385, | |
| "eval_E3/acc_on_INCONSISTENT": 0.7714285714285715, | |
| "eval_E3/accuracy": 0.88, | |
| "eval_E3/balanced_accuracy": 0.854945054945055, | |
| "eval_E3/f1_INC": 0.8181818181818182, | |
| "eval_E3/n": 200.0, | |
| "eval_E3/precision_INC": 0.8709677419354839, | |
| "eval_E3/recall_INC": 0.7714285714285715, | |
| "eval_E4/acc_on_CONSISTENT": 0.9478260869565217, | |
| "eval_E4/acc_on_INCONSISTENT": 0.7764705882352941, | |
| "eval_E4/accuracy": 0.875, | |
| "eval_E4/balanced_accuracy": 0.8621483375959079, | |
| "eval_E4/f1_INC": 0.8407643312101911, | |
| "eval_E4/n": 200.0, | |
| "eval_E4/precision_INC": 0.9166666666666666, | |
| "eval_E4/recall_INC": 0.7764705882352941, | |
| "eval_edge_macro_accuracy": 0.853, | |
| "eval_edge_macro_balanced_accuracy": 0.8437436592360152, | |
| "eval_edge_macro_f1_INC": 0.7859608772083757, | |
| "eval_malformed_rate": 0.0, | |
| "eval_n_eval": 1000.0, | |
| "eval_overall/acc_on_CONSISTENT": 0.5348837209302325, | |
| "eval_overall/acc_on_INCONSISTENT": 0.9171974522292994, | |
| "eval_overall/accuracy": 0.835, | |
| "eval_overall/balanced_accuracy": 0.7260405865797659, | |
| "eval_overall/f1_INC": 0.897196261682243, | |
| "eval_overall/n": 200.0, | |
| "eval_overall/n_complete_groups": 200.0, | |
| "eval_overall/precision_INC": 0.8780487804878049, | |
| "eval_overall/recall_INC": 0.9171974522292994, | |
| "eval_overall_exact_match": 0.47, | |
| "eval_scene/acc_on_CONSISTENT": 0.6888888888888889, | |
| "eval_scene/acc_on_INCONSISTENT": 0.8, | |
| "eval_scene/accuracy": 0.725, | |
| "eval_scene/balanced_accuracy": 0.7444444444444445, | |
| "eval_scene/f1_INC": 0.6540880503144655, | |
| "eval_scene/n": 200.0, | |
| "eval_scene/precision_INC": 0.5531914893617021, | |
| "eval_scene/recall_INC": 0.8, | |
| "step": 3186 | |
| }, | |
| { | |
| "epoch": 0.6004140786749482, | |
| "grad_norm": 0.12375885248184204, | |
| "learning_rate": 7.215484622101485e-05, | |
| "loss": 0.0275, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.6022962544701675, | |
| "grad_norm": 0.10502137243747711, | |
| "learning_rate": 7.205782477927623e-05, | |
| "loss": 0.0279, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.6041784302653868, | |
| "grad_norm": 0.1351398080587387, | |
| "learning_rate": 7.19608033375376e-05, | |
| "loss": 0.0234, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 0.14613057672977448, | |
| "learning_rate": 7.186378189579897e-05, | |
| "loss": 0.0235, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.6079427818558253, | |
| "grad_norm": 0.09466767311096191, | |
| "learning_rate": 7.176676045406035e-05, | |
| "loss": 0.0322, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 0.6098249576510446, | |
| "grad_norm": 0.11353032290935516, | |
| "learning_rate": 7.166973901232172e-05, | |
| "loss": 0.0277, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.6117071334462639, | |
| "grad_norm": 0.0853382870554924, | |
| "learning_rate": 7.15727175705831e-05, | |
| "loss": 0.0311, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.6135893092414831, | |
| "grad_norm": 0.055036455392837524, | |
| "learning_rate": 7.147569612884449e-05, | |
| "loss": 0.0278, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.6154714850367025, | |
| "grad_norm": 0.06104744225740433, | |
| "learning_rate": 7.137867468710585e-05, | |
| "loss": 0.0286, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 0.6173536608319217, | |
| "grad_norm": 0.08071596175432205, | |
| "learning_rate": 7.128165324536723e-05, | |
| "loss": 0.0257, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.619235836627141, | |
| "grad_norm": 0.14282366633415222, | |
| "learning_rate": 7.118463180362861e-05, | |
| "loss": 0.0276, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 0.6211180124223602, | |
| "grad_norm": 0.15172088146209717, | |
| "learning_rate": 7.108761036188998e-05, | |
| "loss": 0.0245, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.6230001882175795, | |
| "grad_norm": 0.0917058140039444, | |
| "learning_rate": 7.099058892015136e-05, | |
| "loss": 0.0293, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 0.6248823640127988, | |
| "grad_norm": 0.11406487971544266, | |
| "learning_rate": 7.089356747841273e-05, | |
| "loss": 0.0276, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.626764539808018, | |
| "grad_norm": 0.11802924424409866, | |
| "learning_rate": 7.07965460366741e-05, | |
| "loss": 0.0263, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 0.6286467156032374, | |
| "grad_norm": 0.11947114020586014, | |
| "learning_rate": 7.069952459493548e-05, | |
| "loss": 0.0285, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.6305288913984566, | |
| "grad_norm": 0.10451506078243256, | |
| "learning_rate": 7.060250315319687e-05, | |
| "loss": 0.0275, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.6324110671936759, | |
| "grad_norm": 0.10557418316602707, | |
| "learning_rate": 7.050548171145823e-05, | |
| "loss": 0.0265, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.6342932429888951, | |
| "grad_norm": 0.12705279886722565, | |
| "learning_rate": 7.040846026971962e-05, | |
| "loss": 0.0246, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 0.6361754187841144, | |
| "grad_norm": 0.18986289203166962, | |
| "learning_rate": 7.031143882798099e-05, | |
| "loss": 0.0285, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.6380575945793338, | |
| "grad_norm": 0.09949778020381927, | |
| "learning_rate": 7.021441738624236e-05, | |
| "loss": 0.0265, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 0.639939770374553, | |
| "grad_norm": 0.07037244737148285, | |
| "learning_rate": 7.011739594450374e-05, | |
| "loss": 0.0249, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.6418219461697723, | |
| "grad_norm": 0.10179682075977325, | |
| "learning_rate": 7.002037450276511e-05, | |
| "loss": 0.0303, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 0.6437041219649915, | |
| "grad_norm": 0.08202063292264938, | |
| "learning_rate": 6.992335306102649e-05, | |
| "loss": 0.0262, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.6455862977602108, | |
| "grad_norm": 0.1346074640750885, | |
| "learning_rate": 6.982633161928786e-05, | |
| "loss": 0.0218, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 0.64746847355543, | |
| "grad_norm": 0.11997853219509125, | |
| "learning_rate": 6.972931017754925e-05, | |
| "loss": 0.0291, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.6493506493506493, | |
| "grad_norm": 0.05166507139801979, | |
| "learning_rate": 6.963228873581061e-05, | |
| "loss": 0.0267, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.6512328251458687, | |
| "grad_norm": 0.08481217920780182, | |
| "learning_rate": 6.9535267294072e-05, | |
| "loss": 0.0275, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.6531150009410879, | |
| "grad_norm": 0.19386963546276093, | |
| "learning_rate": 6.943824585233337e-05, | |
| "loss": 0.0255, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 0.6549971767363072, | |
| "grad_norm": 0.19028638303279877, | |
| "learning_rate": 6.934122441059475e-05, | |
| "loss": 0.0275, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.6568793525315264, | |
| "grad_norm": 0.07005799561738968, | |
| "learning_rate": 6.924420296885612e-05, | |
| "loss": 0.0265, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 0.6587615283267457, | |
| "grad_norm": 0.08579978346824646, | |
| "learning_rate": 6.91471815271175e-05, | |
| "loss": 0.023, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.6606437041219649, | |
| "grad_norm": 0.12526081502437592, | |
| "learning_rate": 6.905016008537887e-05, | |
| "loss": 0.0306, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 0.6625258799171843, | |
| "grad_norm": 0.10663193464279175, | |
| "learning_rate": 6.895313864364024e-05, | |
| "loss": 0.0305, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.6644080557124036, | |
| "grad_norm": 0.0989537239074707, | |
| "learning_rate": 6.885611720190163e-05, | |
| "loss": 0.0263, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 0.6662902315076228, | |
| "grad_norm": 0.13903282582759857, | |
| "learning_rate": 6.875909576016299e-05, | |
| "loss": 0.0283, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.6681724073028421, | |
| "grad_norm": 0.07183618098497391, | |
| "learning_rate": 6.866207431842438e-05, | |
| "loss": 0.0282, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.6700545830980613, | |
| "grad_norm": 0.06900515407323837, | |
| "learning_rate": 6.856505287668576e-05, | |
| "loss": 0.0198, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.6719367588932806, | |
| "grad_norm": 0.16435284912586212, | |
| "learning_rate": 6.846803143494712e-05, | |
| "loss": 0.0291, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 0.6738189346885, | |
| "grad_norm": 0.12341795861721039, | |
| "learning_rate": 6.83710099932085e-05, | |
| "loss": 0.0279, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.6757011104837192, | |
| "grad_norm": 0.15621671080589294, | |
| "learning_rate": 6.827398855146988e-05, | |
| "loss": 0.0258, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 0.6775832862789385, | |
| "grad_norm": 0.11459346860647202, | |
| "learning_rate": 6.817696710973125e-05, | |
| "loss": 0.0324, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.6794654620741577, | |
| "grad_norm": 0.10974545776844025, | |
| "learning_rate": 6.807994566799263e-05, | |
| "loss": 0.0284, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 0.681347637869377, | |
| "grad_norm": 0.07209113240242004, | |
| "learning_rate": 6.7982924226254e-05, | |
| "loss": 0.0263, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.6832298136645962, | |
| "grad_norm": 0.12532223761081696, | |
| "learning_rate": 6.788590278451538e-05, | |
| "loss": 0.0298, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 0.6851119894598156, | |
| "grad_norm": 0.14268836379051208, | |
| "learning_rate": 6.778888134277675e-05, | |
| "loss": 0.027, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.6869941652550349, | |
| "grad_norm": 0.20249424874782562, | |
| "learning_rate": 6.769185990103814e-05, | |
| "loss": 0.0275, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.6888763410502541, | |
| "grad_norm": 0.1736336499452591, | |
| "learning_rate": 6.75948384592995e-05, | |
| "loss": 0.0258, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.6907585168454734, | |
| "grad_norm": 0.042560216039419174, | |
| "learning_rate": 6.749781701756089e-05, | |
| "loss": 0.0239, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 0.6926406926406926, | |
| "grad_norm": 0.042638007551431656, | |
| "learning_rate": 6.740079557582226e-05, | |
| "loss": 0.029, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.6945228684359119, | |
| "grad_norm": 0.1276584416627884, | |
| "learning_rate": 6.730377413408363e-05, | |
| "loss": 0.0288, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 0.6964050442311311, | |
| "grad_norm": 0.07026208192110062, | |
| "learning_rate": 6.720675269234501e-05, | |
| "loss": 0.0225, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.6982872200263505, | |
| "grad_norm": 0.14463388919830322, | |
| "learning_rate": 6.710973125060638e-05, | |
| "loss": 0.025, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 0.6996047430830039, | |
| "eval_E1/acc_on_CONSISTENT": 0.9337748344370861, | |
| "eval_E1/acc_on_INCONSISTENT": 0.6122448979591837, | |
| "eval_E1/accuracy": 0.855, | |
| "eval_E1/balanced_accuracy": 0.7730098661981348, | |
| "eval_E1/f1_INC": 0.6741573033707865, | |
| "eval_E1/n": 200.0, | |
| "eval_E1/precision_INC": 0.75, | |
| "eval_E1/recall_INC": 0.6122448979591837, | |
| "eval_E2/acc_on_CONSISTENT": 0.9788732394366197, | |
| "eval_E2/acc_on_INCONSISTENT": 0.9310344827586207, | |
| "eval_E2/accuracy": 0.965, | |
| "eval_E2/balanced_accuracy": 0.9549538610976203, | |
| "eval_E2/f1_INC": 0.9391304347826087, | |
| "eval_E2/n": 200.0, | |
| "eval_E2/precision_INC": 0.9473684210526315, | |
| "eval_E2/recall_INC": 0.9310344827586207, | |
| "eval_E3/acc_on_CONSISTENT": 0.9769230769230769, | |
| "eval_E3/acc_on_INCONSISTENT": 0.7857142857142857, | |
| "eval_E3/accuracy": 0.91, | |
| "eval_E3/balanced_accuracy": 0.8813186813186813, | |
| "eval_E3/f1_INC": 0.859375, | |
| "eval_E3/n": 200.0, | |
| "eval_E3/precision_INC": 0.9482758620689655, | |
| "eval_E3/recall_INC": 0.7857142857142857, | |
| "eval_E4/acc_on_CONSISTENT": 0.9826086956521739, | |
| "eval_E4/acc_on_INCONSISTENT": 0.7294117647058823, | |
| "eval_E4/accuracy": 0.875, | |
| "eval_E4/balanced_accuracy": 0.8560102301790281, | |
| "eval_E4/f1_INC": 0.832214765100671, | |
| "eval_E4/n": 200.0, | |
| "eval_E4/precision_INC": 0.96875, | |
| "eval_E4/recall_INC": 0.7294117647058823, | |
| "eval_edge_macro_accuracy": 0.889, | |
| "eval_edge_macro_balanced_accuracy": 0.8526026873028524, | |
| "eval_edge_macro_f1_INC": 0.80764216731748, | |
| "eval_malformed_rate": 0.0, | |
| "eval_n_eval": 1000.0, | |
| "eval_overall/acc_on_CONSISTENT": 0.8837209302325582, | |
| "eval_overall/acc_on_INCONSISTENT": 0.8598726114649682, | |
| "eval_overall/accuracy": 0.865, | |
| "eval_overall/balanced_accuracy": 0.8717967708487632, | |
| "eval_overall/f1_INC": 0.9090909090909091, | |
| "eval_overall/n": 200.0, | |
| "eval_overall/n_complete_groups": 200.0, | |
| "eval_overall/precision_INC": 0.9642857142857143, | |
| "eval_overall/recall_INC": 0.8598726114649682, | |
| "eval_overall_exact_match": 0.61, | |
| "eval_scene/acc_on_CONSISTENT": 0.9185185185185185, | |
| "eval_scene/acc_on_INCONSISTENT": 0.676923076923077, | |
| "eval_scene/accuracy": 0.84, | |
| "eval_scene/balanced_accuracy": 0.7977207977207977, | |
| "eval_scene/f1_INC": 0.7333333333333334, | |
| "eval_scene/n": 200.0, | |
| "eval_scene/precision_INC": 0.8, | |
| "eval_scene/recall_INC": 0.676923076923077, | |
| "step": 3717 | |
| }, | |
| { | |
| "epoch": 0.7001693958215698, | |
| "grad_norm": 0.06821384280920029, | |
| "learning_rate": 6.701270980886777e-05, | |
| "loss": 0.0281, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.702051571616789, | |
| "grad_norm": 0.0533619187772274, | |
| "learning_rate": 6.691568836712913e-05, | |
| "loss": 0.0296, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 0.7039337474120083, | |
| "grad_norm": 0.09107464551925659, | |
| "learning_rate": 6.681866692539052e-05, | |
| "loss": 0.0268, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.7058159232072275, | |
| "grad_norm": 0.08339343965053558, | |
| "learning_rate": 6.67216454836519e-05, | |
| "loss": 0.0295, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.7076980990024468, | |
| "grad_norm": 0.09445764124393463, | |
| "learning_rate": 6.662462404191327e-05, | |
| "loss": 0.026, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.709580274797666, | |
| "grad_norm": 0.1917838305234909, | |
| "learning_rate": 6.652760260017464e-05, | |
| "loss": 0.0288, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 0.7114624505928854, | |
| "grad_norm": 0.13823284208774567, | |
| "learning_rate": 6.643058115843602e-05, | |
| "loss": 0.0243, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.7133446263881047, | |
| "grad_norm": 0.09427863359451294, | |
| "learning_rate": 6.633355971669739e-05, | |
| "loss": 0.0224, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 0.7152268021833239, | |
| "grad_norm": 0.15948054194450378, | |
| "learning_rate": 6.623653827495877e-05, | |
| "loss": 0.0196, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.7171089779785432, | |
| "grad_norm": 0.20518970489501953, | |
| "learning_rate": 6.613951683322015e-05, | |
| "loss": 0.026, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 0.7189911537737624, | |
| "grad_norm": 0.15291956067085266, | |
| "learning_rate": 6.604249539148151e-05, | |
| "loss": 0.028, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.7208733295689818, | |
| "grad_norm": 0.12342661619186401, | |
| "learning_rate": 6.59454739497429e-05, | |
| "loss": 0.0283, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 0.722755505364201, | |
| "grad_norm": 0.07337340712547302, | |
| "learning_rate": 6.584845250800428e-05, | |
| "loss": 0.023, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.7246376811594203, | |
| "grad_norm": 0.12145810574293137, | |
| "learning_rate": 6.575143106626565e-05, | |
| "loss": 0.0302, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.7265198569546396, | |
| "grad_norm": 0.10396488010883331, | |
| "learning_rate": 6.565440962452703e-05, | |
| "loss": 0.026, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.7284020327498588, | |
| "grad_norm": 0.08993718773126602, | |
| "learning_rate": 6.55573881827884e-05, | |
| "loss": 0.0281, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 0.7302842085450781, | |
| "grad_norm": 0.09292326867580414, | |
| "learning_rate": 6.546036674104977e-05, | |
| "loss": 0.0281, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.7321663843402973, | |
| "grad_norm": 0.1312495619058609, | |
| "learning_rate": 6.536334529931115e-05, | |
| "loss": 0.0248, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 0.7340485601355167, | |
| "grad_norm": 0.09885958582162857, | |
| "learning_rate": 6.526632385757254e-05, | |
| "loss": 0.0227, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.7359307359307359, | |
| "grad_norm": 0.05759183689951897, | |
| "learning_rate": 6.51693024158339e-05, | |
| "loss": 0.0316, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 0.7378129117259552, | |
| "grad_norm": 0.1465388834476471, | |
| "learning_rate": 6.507228097409528e-05, | |
| "loss": 0.0239, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.7396950875211745, | |
| "grad_norm": 0.13463398814201355, | |
| "learning_rate": 6.497525953235666e-05, | |
| "loss": 0.0243, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 0.7415772633163937, | |
| "grad_norm": 0.10613127052783966, | |
| "learning_rate": 6.487823809061803e-05, | |
| "loss": 0.0225, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.743459439111613, | |
| "grad_norm": 0.07204587757587433, | |
| "learning_rate": 6.478121664887941e-05, | |
| "loss": 0.0284, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.7453416149068323, | |
| "grad_norm": 0.09663920104503632, | |
| "learning_rate": 6.468419520714078e-05, | |
| "loss": 0.0241, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.7472237907020516, | |
| "grad_norm": 0.13608111441135406, | |
| "learning_rate": 6.458717376540216e-05, | |
| "loss": 0.0237, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 0.7491059664972708, | |
| "grad_norm": 0.07337552309036255, | |
| "learning_rate": 6.449015232366353e-05, | |
| "loss": 0.0222, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.7509881422924901, | |
| "grad_norm": 0.14900878071784973, | |
| "learning_rate": 6.439313088192492e-05, | |
| "loss": 0.0286, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 0.7528703180877094, | |
| "grad_norm": 0.07007355242967606, | |
| "learning_rate": 6.429610944018628e-05, | |
| "loss": 0.028, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.7547524938829286, | |
| "grad_norm": 0.15586300194263458, | |
| "learning_rate": 6.419908799844765e-05, | |
| "loss": 0.0267, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 0.756634669678148, | |
| "grad_norm": 0.1284913569688797, | |
| "learning_rate": 6.410206655670904e-05, | |
| "loss": 0.0228, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.7585168454733672, | |
| "grad_norm": 0.1646757572889328, | |
| "learning_rate": 6.40050451149704e-05, | |
| "loss": 0.0262, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 0.7603990212685865, | |
| "grad_norm": 0.09742174297571182, | |
| "learning_rate": 6.390802367323179e-05, | |
| "loss": 0.029, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.7622811970638057, | |
| "grad_norm": 0.07278095930814743, | |
| "learning_rate": 6.381100223149316e-05, | |
| "loss": 0.0263, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.764163372859025, | |
| "grad_norm": 0.10488718748092651, | |
| "learning_rate": 6.371398078975454e-05, | |
| "loss": 0.0217, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.7660455486542443, | |
| "grad_norm": 0.21971240639686584, | |
| "learning_rate": 6.361695934801591e-05, | |
| "loss": 0.0286, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 0.7679277244494636, | |
| "grad_norm": 0.08719635754823685, | |
| "learning_rate": 6.351993790627729e-05, | |
| "loss": 0.0265, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.7698099002446829, | |
| "grad_norm": 0.09772541373968124, | |
| "learning_rate": 6.342291646453866e-05, | |
| "loss": 0.0197, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 0.7716920760399021, | |
| "grad_norm": 0.07383599132299423, | |
| "learning_rate": 6.332589502280004e-05, | |
| "loss": 0.0287, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.7735742518351214, | |
| "grad_norm": 0.09341705590486526, | |
| "learning_rate": 6.322887358106142e-05, | |
| "loss": 0.0203, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 0.7754564276303407, | |
| "grad_norm": 0.19727744162082672, | |
| "learning_rate": 6.313185213932278e-05, | |
| "loss": 0.0233, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.7773386034255599, | |
| "grad_norm": 0.11619048565626144, | |
| "learning_rate": 6.303483069758417e-05, | |
| "loss": 0.0218, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 0.7792207792207793, | |
| "grad_norm": 0.25396350026130676, | |
| "learning_rate": 6.293780925584555e-05, | |
| "loss": 0.022, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.7811029550159985, | |
| "grad_norm": 0.14137905836105347, | |
| "learning_rate": 6.284078781410692e-05, | |
| "loss": 0.0215, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.7829851308112178, | |
| "grad_norm": 0.053330399096012115, | |
| "learning_rate": 6.27437663723683e-05, | |
| "loss": 0.0236, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.784867306606437, | |
| "grad_norm": 0.08605629950761795, | |
| "learning_rate": 6.264674493062967e-05, | |
| "loss": 0.0235, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 0.7867494824016563, | |
| "grad_norm": 0.16659440100193024, | |
| "learning_rate": 6.254972348889104e-05, | |
| "loss": 0.0253, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.7886316581968756, | |
| "grad_norm": 0.09707406908273697, | |
| "learning_rate": 6.245270204715242e-05, | |
| "loss": 0.0259, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 0.7905138339920948, | |
| "grad_norm": 0.07335163652896881, | |
| "learning_rate": 6.23556806054138e-05, | |
| "loss": 0.0254, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.7923960097873142, | |
| "grad_norm": 0.07250624150037766, | |
| "learning_rate": 6.225865916367517e-05, | |
| "loss": 0.0297, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 0.7942781855825334, | |
| "grad_norm": 0.13132064044475555, | |
| "learning_rate": 6.216163772193655e-05, | |
| "loss": 0.0284, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.7961603613777527, | |
| "grad_norm": 0.16921114921569824, | |
| "learning_rate": 6.206461628019793e-05, | |
| "loss": 0.0303, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 0.7980425371729719, | |
| "grad_norm": 0.09276404231786728, | |
| "learning_rate": 6.19675948384593e-05, | |
| "loss": 0.0234, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.7995482778091474, | |
| "eval_E1/acc_on_CONSISTENT": 0.7880794701986755, | |
| "eval_E1/acc_on_INCONSISTENT": 0.6938775510204082, | |
| "eval_E1/accuracy": 0.765, | |
| "eval_E1/balanced_accuracy": 0.7409785106095419, | |
| "eval_E1/f1_INC": 0.5913043478260871, | |
| "eval_E1/n": 200.0, | |
| "eval_E1/precision_INC": 0.5151515151515151, | |
| "eval_E1/recall_INC": 0.6938775510204082, | |
| "eval_E2/acc_on_CONSISTENT": 0.9859154929577465, | |
| "eval_E2/acc_on_INCONSISTENT": 0.9655172413793104, | |
| "eval_E2/accuracy": 0.98, | |
| "eval_E2/balanced_accuracy": 0.9757163671685285, | |
| "eval_E2/f1_INC": 0.9655172413793104, | |
| "eval_E2/n": 200.0, | |
| "eval_E2/precision_INC": 0.9655172413793104, | |
| "eval_E2/recall_INC": 0.9655172413793104, | |
| "eval_E3/acc_on_CONSISTENT": 0.9461538461538461, | |
| "eval_E3/acc_on_INCONSISTENT": 0.8, | |
| "eval_E3/accuracy": 0.895, | |
| "eval_E3/balanced_accuracy": 0.8730769230769231, | |
| "eval_E3/f1_INC": 0.8421052631578948, | |
| "eval_E3/n": 200.0, | |
| "eval_E3/precision_INC": 0.8888888888888888, | |
| "eval_E3/recall_INC": 0.8, | |
| "eval_E4/acc_on_CONSISTENT": 0.9304347826086956, | |
| "eval_E4/acc_on_INCONSISTENT": 0.8117647058823529, | |
| "eval_E4/accuracy": 0.88, | |
| "eval_E4/balanced_accuracy": 0.8710997442455243, | |
| "eval_E4/f1_INC": 0.8518518518518517, | |
| "eval_E4/n": 200.0, | |
| "eval_E4/precision_INC": 0.8961038961038961, | |
| "eval_E4/recall_INC": 0.8117647058823529, | |
| "eval_edge_macro_accuracy": 0.866, | |
| "eval_edge_macro_balanced_accuracy": 0.8560489528947475, | |
| "eval_edge_macro_f1_INC": 0.7988043894916774, | |
| "eval_malformed_rate": 0.0, | |
| "eval_n_eval": 1000.0, | |
| "eval_overall/acc_on_CONSISTENT": 0.6511627906976745, | |
| "eval_overall/acc_on_INCONSISTENT": 0.9426751592356688, | |
| "eval_overall/accuracy": 0.88, | |
| "eval_overall/balanced_accuracy": 0.7969189749666716, | |
| "eval_overall/f1_INC": 0.925, | |
| "eval_overall/n": 200.0, | |
| "eval_overall/n_complete_groups": 200.0, | |
| "eval_overall/precision_INC": 0.9079754601226994, | |
| "eval_overall/recall_INC": 0.9426751592356688, | |
| "eval_overall_exact_match": 0.515, | |
| "eval_scene/acc_on_CONSISTENT": 0.7925925925925926, | |
| "eval_scene/acc_on_INCONSISTENT": 0.8461538461538461, | |
| "eval_scene/accuracy": 0.81, | |
| "eval_scene/balanced_accuracy": 0.8193732193732194, | |
| "eval_scene/f1_INC": 0.7432432432432433, | |
| "eval_scene/n": 200.0, | |
| "eval_scene/precision_INC": 0.6626506024096386, | |
| "eval_scene/recall_INC": 0.8461538461538461, | |
| "step": 4248 | |
| }, | |
| { | |
| "epoch": 0.7999247129681912, | |
| "grad_norm": 0.07519380003213882, | |
| "learning_rate": 6.187057339672068e-05, | |
| "loss": 0.0227, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.8018068887634106, | |
| "grad_norm": 0.15206333994865417, | |
| "learning_rate": 6.177355195498205e-05, | |
| "loss": 0.0263, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.8036890645586298, | |
| "grad_norm": 0.09467748552560806, | |
| "learning_rate": 6.167653051324343e-05, | |
| "loss": 0.0215, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 0.8055712403538491, | |
| "grad_norm": 0.09524611383676529, | |
| "learning_rate": 6.15795090715048e-05, | |
| "loss": 0.0253, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.8074534161490683, | |
| "grad_norm": 0.09639701247215271, | |
| "learning_rate": 6.148248762976619e-05, | |
| "loss": 0.0273, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 0.8093355919442876, | |
| "grad_norm": 0.14750158786773682, | |
| "learning_rate": 6.138546618802755e-05, | |
| "loss": 0.0247, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.8112177677395068, | |
| "grad_norm": 0.15283837914466858, | |
| "learning_rate": 6.128844474628894e-05, | |
| "loss": 0.0255, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 0.8130999435347261, | |
| "grad_norm": 0.1801212579011917, | |
| "learning_rate": 6.119142330455031e-05, | |
| "loss": 0.0236, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.8149821193299455, | |
| "grad_norm": 0.18473784625530243, | |
| "learning_rate": 6.109440186281169e-05, | |
| "loss": 0.0321, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 0.8168642951251647, | |
| "grad_norm": 0.13694533705711365, | |
| "learning_rate": 6.099738042107306e-05, | |
| "loss": 0.0231, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.818746470920384, | |
| "grad_norm": 0.08112656325101852, | |
| "learning_rate": 6.090035897933444e-05, | |
| "loss": 0.0259, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.8206286467156032, | |
| "grad_norm": 0.07673269510269165, | |
| "learning_rate": 6.0803337537595815e-05, | |
| "loss": 0.027, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.8225108225108225, | |
| "grad_norm": 0.13535504043102264, | |
| "learning_rate": 6.070631609585718e-05, | |
| "loss": 0.0285, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 0.8243929983060417, | |
| "grad_norm": 0.08035381883382797, | |
| "learning_rate": 6.0609294654118564e-05, | |
| "loss": 0.0263, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.8262751741012611, | |
| "grad_norm": 0.142923042178154, | |
| "learning_rate": 6.0512273212379945e-05, | |
| "loss": 0.0228, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 0.8281573498964804, | |
| "grad_norm": 0.19256168603897095, | |
| "learning_rate": 6.041525177064131e-05, | |
| "loss": 0.0215, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.8300395256916996, | |
| "grad_norm": 0.08662780374288559, | |
| "learning_rate": 6.0318230328902694e-05, | |
| "loss": 0.0281, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 0.8319217014869189, | |
| "grad_norm": 0.11855155229568481, | |
| "learning_rate": 6.022120888716407e-05, | |
| "loss": 0.0238, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.8338038772821381, | |
| "grad_norm": 0.0649333968758583, | |
| "learning_rate": 6.012418744542544e-05, | |
| "loss": 0.0308, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 0.8356860530773574, | |
| "grad_norm": 0.13388758897781372, | |
| "learning_rate": 6.0027166003686816e-05, | |
| "loss": 0.0285, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.8375682288725766, | |
| "grad_norm": 0.1069571003317833, | |
| "learning_rate": 5.99301445619482e-05, | |
| "loss": 0.0215, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.839450404667796, | |
| "grad_norm": 0.07490979135036469, | |
| "learning_rate": 5.9833123120209565e-05, | |
| "loss": 0.0266, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.8413325804630153, | |
| "grad_norm": 0.11468319594860077, | |
| "learning_rate": 5.9736101678470946e-05, | |
| "loss": 0.0284, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 0.8432147562582345, | |
| "grad_norm": 0.1102227121591568, | |
| "learning_rate": 5.963908023673233e-05, | |
| "loss": 0.0273, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.8450969320534538, | |
| "grad_norm": 0.08790767937898636, | |
| "learning_rate": 5.9542058794993695e-05, | |
| "loss": 0.0226, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 0.846979107848673, | |
| "grad_norm": 0.07965442538261414, | |
| "learning_rate": 5.9445037353255076e-05, | |
| "loss": 0.0164, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.8488612836438924, | |
| "grad_norm": 0.12062489241361618, | |
| "learning_rate": 5.934801591151645e-05, | |
| "loss": 0.0271, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 0.8507434594391116, | |
| "grad_norm": 0.12974771857261658, | |
| "learning_rate": 5.925099446977782e-05, | |
| "loss": 0.0253, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.8526256352343309, | |
| "grad_norm": 0.15159684419631958, | |
| "learning_rate": 5.91539730280392e-05, | |
| "loss": 0.0277, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 0.8545078110295502, | |
| "grad_norm": 0.10359372198581696, | |
| "learning_rate": 5.905695158630058e-05, | |
| "loss": 0.0278, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.8563899868247694, | |
| "grad_norm": 0.11358320713043213, | |
| "learning_rate": 5.895993014456195e-05, | |
| "loss": 0.0232, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.8582721626199887, | |
| "grad_norm": 0.0856373980641365, | |
| "learning_rate": 5.886290870282333e-05, | |
| "loss": 0.0305, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.8601543384152079, | |
| "grad_norm": 0.08378347009420395, | |
| "learning_rate": 5.876588726108471e-05, | |
| "loss": 0.0199, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 0.8620365142104273, | |
| "grad_norm": 0.13333091139793396, | |
| "learning_rate": 5.866886581934608e-05, | |
| "loss": 0.0247, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.8639186900056465, | |
| "grad_norm": 0.15513169765472412, | |
| "learning_rate": 5.857184437760745e-05, | |
| "loss": 0.0206, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 0.8658008658008658, | |
| "grad_norm": 0.12354400008916855, | |
| "learning_rate": 5.847482293586883e-05, | |
| "loss": 0.0222, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.8676830415960851, | |
| "grad_norm": 0.1295776218175888, | |
| "learning_rate": 5.83778014941302e-05, | |
| "loss": 0.0239, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 0.8695652173913043, | |
| "grad_norm": 0.15621507167816162, | |
| "learning_rate": 5.828078005239158e-05, | |
| "loss": 0.0277, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.8714473931865236, | |
| "grad_norm": 0.17905867099761963, | |
| "learning_rate": 5.818375861065296e-05, | |
| "loss": 0.0225, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 0.8733295689817429, | |
| "grad_norm": 0.1387549340724945, | |
| "learning_rate": 5.808673716891433e-05, | |
| "loss": 0.0258, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.8752117447769622, | |
| "grad_norm": 0.12285871803760529, | |
| "learning_rate": 5.798971572717571e-05, | |
| "loss": 0.0249, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.8770939205721815, | |
| "grad_norm": 0.119094617664814, | |
| "learning_rate": 5.7892694285437085e-05, | |
| "loss": 0.0302, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.8789760963674007, | |
| "grad_norm": 0.08970344066619873, | |
| "learning_rate": 5.779567284369846e-05, | |
| "loss": 0.0205, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 0.88085827216262, | |
| "grad_norm": 0.1598692238330841, | |
| "learning_rate": 5.7698651401959834e-05, | |
| "loss": 0.0218, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.8827404479578392, | |
| "grad_norm": 0.24901559948921204, | |
| "learning_rate": 5.7601629960221215e-05, | |
| "loss": 0.0214, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 0.8846226237530586, | |
| "grad_norm": 0.22025392949581146, | |
| "learning_rate": 5.750460851848258e-05, | |
| "loss": 0.0207, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.8865047995482778, | |
| "grad_norm": 0.11392150819301605, | |
| "learning_rate": 5.7407587076743963e-05, | |
| "loss": 0.0235, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 0.8883869753434971, | |
| "grad_norm": 0.07520972937345505, | |
| "learning_rate": 5.7310565635005345e-05, | |
| "loss": 0.0212, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.8902691511387164, | |
| "grad_norm": 0.13182830810546875, | |
| "learning_rate": 5.721354419326671e-05, | |
| "loss": 0.02, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 0.8921513269339356, | |
| "grad_norm": 0.1381557583808899, | |
| "learning_rate": 5.711652275152809e-05, | |
| "loss": 0.0277, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.8940335027291549, | |
| "grad_norm": 0.12975607812404633, | |
| "learning_rate": 5.701950130978947e-05, | |
| "loss": 0.0256, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.8959156785243741, | |
| "grad_norm": 0.17318369448184967, | |
| "learning_rate": 5.6922479868050835e-05, | |
| "loss": 0.0247, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.8977978543195935, | |
| "grad_norm": 0.126237154006958, | |
| "learning_rate": 5.6825458426312216e-05, | |
| "loss": 0.0234, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 0.8994918125352908, | |
| "eval_E1/acc_on_CONSISTENT": 0.8675496688741722, | |
| "eval_E1/acc_on_INCONSISTENT": 0.5714285714285714, | |
| "eval_E1/accuracy": 0.795, | |
| "eval_E1/balanced_accuracy": 0.7194891201513718, | |
| "eval_E1/f1_INC": 0.577319587628866, | |
| "eval_E1/n": 200.0, | |
| "eval_E1/precision_INC": 0.5833333333333334, | |
| "eval_E1/recall_INC": 0.5714285714285714, | |
| "eval_E2/acc_on_CONSISTENT": 0.9929577464788732, | |
| "eval_E2/acc_on_INCONSISTENT": 0.9482758620689655, | |
| "eval_E2/accuracy": 0.98, | |
| "eval_E2/balanced_accuracy": 0.9706168042739194, | |
| "eval_E2/f1_INC": 0.9649122807017544, | |
| "eval_E2/n": 200.0, | |
| "eval_E2/precision_INC": 0.9821428571428571, | |
| "eval_E2/recall_INC": 0.9482758620689655, | |
| "eval_E3/acc_on_CONSISTENT": 0.9846153846153847, | |
| "eval_E3/acc_on_INCONSISTENT": 0.7857142857142857, | |
| "eval_E3/accuracy": 0.915, | |
| "eval_E3/balanced_accuracy": 0.8851648351648351, | |
| "eval_E3/f1_INC": 0.8661417322834646, | |
| "eval_E3/n": 200.0, | |
| "eval_E3/precision_INC": 0.9649122807017544, | |
| "eval_E3/recall_INC": 0.7857142857142857, | |
| "eval_E4/acc_on_CONSISTENT": 0.9652173913043478, | |
| "eval_E4/acc_on_INCONSISTENT": 0.7647058823529411, | |
| "eval_E4/accuracy": 0.88, | |
| "eval_E4/balanced_accuracy": 0.8649616368286445, | |
| "eval_E4/f1_INC": 0.8441558441558441, | |
| "eval_E4/n": 200.0, | |
| "eval_E4/precision_INC": 0.9420289855072463, | |
| "eval_E4/recall_INC": 0.7647058823529411, | |
| "eval_edge_macro_accuracy": 0.881, | |
| "eval_edge_macro_balanced_accuracy": 0.8508385020757769, | |
| "eval_edge_macro_f1_INC": 0.8001242095646729, | |
| "eval_malformed_rate": 0.0, | |
| "eval_n_eval": 1000.0, | |
| "eval_overall/acc_on_CONSISTENT": 0.813953488372093, | |
| "eval_overall/acc_on_INCONSISTENT": 0.9044585987261147, | |
| "eval_overall/accuracy": 0.885, | |
| "eval_overall/balanced_accuracy": 0.8592060435491038, | |
| "eval_overall/f1_INC": 0.9250814332247558, | |
| "eval_overall/n": 200.0, | |
| "eval_overall/n_complete_groups": 200.0, | |
| "eval_overall/precision_INC": 0.9466666666666667, | |
| "eval_overall/recall_INC": 0.9044585987261147, | |
| "eval_overall_exact_match": 0.58, | |
| "eval_scene/acc_on_CONSISTENT": 0.8740740740740741, | |
| "eval_scene/acc_on_INCONSISTENT": 0.7538461538461538, | |
| "eval_scene/accuracy": 0.835, | |
| "eval_scene/balanced_accuracy": 0.813960113960114, | |
| "eval_scene/f1_INC": 0.7480916030534351, | |
| "eval_scene/n": 200.0, | |
| "eval_scene/precision_INC": 0.7424242424242424, | |
| "eval_scene/recall_INC": 0.7538461538461538, | |
| "step": 4779 | |
| }, | |
| { | |
| "epoch": 0.8996800301148127, | |
| "grad_norm": 0.1269172877073288, | |
| "learning_rate": 5.67284369845736e-05, | |
| "loss": 0.0252, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.901562205910032, | |
| "grad_norm": 0.10349240154027939, | |
| "learning_rate": 5.6631415542834965e-05, | |
| "loss": 0.022, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 0.9034443817052513, | |
| "grad_norm": 0.24686415493488312, | |
| "learning_rate": 5.6534394101096346e-05, | |
| "loss": 0.0265, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.9053265575004705, | |
| "grad_norm": 0.11216803640127182, | |
| "learning_rate": 5.643737265935772e-05, | |
| "loss": 0.0216, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 0.9072087332956899, | |
| "grad_norm": 0.14201720058918, | |
| "learning_rate": 5.6340351217619094e-05, | |
| "loss": 0.0283, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 0.07003463804721832, | |
| "learning_rate": 5.624332977588047e-05, | |
| "loss": 0.0254, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 0.9109730848861284, | |
| "grad_norm": 0.10892708599567413, | |
| "learning_rate": 5.614630833414185e-05, | |
| "loss": 0.0273, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.9128552606813476, | |
| "grad_norm": 0.06218297407031059, | |
| "learning_rate": 5.604928689240322e-05, | |
| "loss": 0.0258, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.9147374364765669, | |
| "grad_norm": 0.10862410068511963, | |
| "learning_rate": 5.59522654506646e-05, | |
| "loss": 0.0206, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.9166196122717862, | |
| "grad_norm": 0.07507742196321487, | |
| "learning_rate": 5.585524400892598e-05, | |
| "loss": 0.0262, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 0.9185017880670054, | |
| "grad_norm": 0.10350686311721802, | |
| "learning_rate": 5.575822256718735e-05, | |
| "loss": 0.025, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.9203839638622248, | |
| "grad_norm": 0.16628728806972504, | |
| "learning_rate": 5.566120112544873e-05, | |
| "loss": 0.0284, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 0.922266139657444, | |
| "grad_norm": 0.045880332589149475, | |
| "learning_rate": 5.55641796837101e-05, | |
| "loss": 0.0235, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.9241483154526633, | |
| "grad_norm": 0.17356722056865692, | |
| "learning_rate": 5.546715824197147e-05, | |
| "loss": 0.026, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 0.9260304912478825, | |
| "grad_norm": 0.11924988031387329, | |
| "learning_rate": 5.537013680023285e-05, | |
| "loss": 0.0217, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.9279126670431018, | |
| "grad_norm": 0.08413538336753845, | |
| "learning_rate": 5.527311535849423e-05, | |
| "loss": 0.0249, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 0.9297948428383211, | |
| "grad_norm": 0.09474111348390579, | |
| "learning_rate": 5.51760939167556e-05, | |
| "loss": 0.0229, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.9316770186335404, | |
| "grad_norm": 0.07419522106647491, | |
| "learning_rate": 5.507907247501698e-05, | |
| "loss": 0.022, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.9335591944287597, | |
| "grad_norm": 0.09347780793905258, | |
| "learning_rate": 5.498205103327836e-05, | |
| "loss": 0.0252, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.9354413702239789, | |
| "grad_norm": 0.053250234574079514, | |
| "learning_rate": 5.4885029591539736e-05, | |
| "loss": 0.0249, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 0.9373235460191982, | |
| "grad_norm": 0.09263543039560318, | |
| "learning_rate": 5.4788008149801104e-05, | |
| "loss": 0.0189, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.9392057218144174, | |
| "grad_norm": 0.12147948890924454, | |
| "learning_rate": 5.4690986708062485e-05, | |
| "loss": 0.0218, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 0.9410878976096367, | |
| "grad_norm": 0.12498101592063904, | |
| "learning_rate": 5.4593965266323866e-05, | |
| "loss": 0.0206, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.9429700734048561, | |
| "grad_norm": 0.1211477741599083, | |
| "learning_rate": 5.449694382458523e-05, | |
| "loss": 0.0262, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 0.9448522492000753, | |
| "grad_norm": 0.10046116262674332, | |
| "learning_rate": 5.4399922382846614e-05, | |
| "loss": 0.0167, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.9467344249952946, | |
| "grad_norm": 0.10313168913125992, | |
| "learning_rate": 5.4302900941107996e-05, | |
| "loss": 0.0263, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 0.9486166007905138, | |
| "grad_norm": 0.07489953190088272, | |
| "learning_rate": 5.420587949936936e-05, | |
| "loss": 0.0233, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.9504987765857331, | |
| "grad_norm": 0.09977987408638, | |
| "learning_rate": 5.410885805763074e-05, | |
| "loss": 0.0229, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 0.09566326439380646, | |
| "learning_rate": 5.401183661589212e-05, | |
| "loss": 0.0249, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.9542631281761716, | |
| "grad_norm": 0.11907912790775299, | |
| "learning_rate": 5.3914815174153486e-05, | |
| "loss": 0.0256, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 0.956145303971391, | |
| "grad_norm": 0.10536547005176544, | |
| "learning_rate": 5.381779373241487e-05, | |
| "loss": 0.0236, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.9580274797666102, | |
| "grad_norm": 0.07869280129671097, | |
| "learning_rate": 5.372077229067625e-05, | |
| "loss": 0.0194, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 0.9599096555618295, | |
| "grad_norm": 0.12649060785770416, | |
| "learning_rate": 5.3623750848937616e-05, | |
| "loss": 0.0248, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.9617918313570487, | |
| "grad_norm": 0.07347354292869568, | |
| "learning_rate": 5.3526729407199e-05, | |
| "loss": 0.0276, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 0.963674007152268, | |
| "grad_norm": 0.1066274419426918, | |
| "learning_rate": 5.342970796546037e-05, | |
| "loss": 0.0224, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.9655561829474872, | |
| "grad_norm": 0.10295616090297699, | |
| "learning_rate": 5.3332686523721745e-05, | |
| "loss": 0.0293, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 0.9674383587427066, | |
| "grad_norm": 0.07118721306324005, | |
| "learning_rate": 5.323566508198312e-05, | |
| "loss": 0.0278, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.9693205345379259, | |
| "grad_norm": 0.11095461249351501, | |
| "learning_rate": 5.31386436402445e-05, | |
| "loss": 0.0259, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.9712027103331451, | |
| "grad_norm": 0.11480211466550827, | |
| "learning_rate": 5.304162219850587e-05, | |
| "loss": 0.0213, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.9730848861283644, | |
| "grad_norm": 0.13368651270866394, | |
| "learning_rate": 5.294460075676725e-05, | |
| "loss": 0.0219, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 0.9749670619235836, | |
| "grad_norm": 0.10452937334775925, | |
| "learning_rate": 5.284757931502863e-05, | |
| "loss": 0.024, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.9768492377188029, | |
| "grad_norm": 0.0894588828086853, | |
| "learning_rate": 5.275055787329e-05, | |
| "loss": 0.026, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 0.9787314135140223, | |
| "grad_norm": 0.0918290838599205, | |
| "learning_rate": 5.265353643155137e-05, | |
| "loss": 0.0205, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.9806135893092415, | |
| "grad_norm": 0.15705926716327667, | |
| "learning_rate": 5.2556514989812753e-05, | |
| "loss": 0.0279, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 0.9824957651044608, | |
| "grad_norm": 0.07733868807554245, | |
| "learning_rate": 5.245949354807412e-05, | |
| "loss": 0.0258, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.98437794089968, | |
| "grad_norm": 0.11112848669290543, | |
| "learning_rate": 5.23624721063355e-05, | |
| "loss": 0.0228, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 0.9862601166948993, | |
| "grad_norm": 0.12285085022449493, | |
| "learning_rate": 5.226545066459688e-05, | |
| "loss": 0.025, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.9881422924901185, | |
| "grad_norm": 0.13352616131305695, | |
| "learning_rate": 5.216842922285825e-05, | |
| "loss": 0.0248, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.9900244682853379, | |
| "grad_norm": 0.09676120430231094, | |
| "learning_rate": 5.207140778111963e-05, | |
| "loss": 0.0227, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 0.9919066440805572, | |
| "grad_norm": 0.08933494240045547, | |
| "learning_rate": 5.1974386339381006e-05, | |
| "loss": 0.0216, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 0.9937888198757764, | |
| "grad_norm": 0.15473978221416473, | |
| "learning_rate": 5.187736489764238e-05, | |
| "loss": 0.0187, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.9956709956709957, | |
| "grad_norm": 0.13211970031261444, | |
| "learning_rate": 5.1780343455903755e-05, | |
| "loss": 0.0203, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 0.9975531714662149, | |
| "grad_norm": 0.14397864043712616, | |
| "learning_rate": 5.1683322014165136e-05, | |
| "loss": 0.0209, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.9994353472614342, | |
| "grad_norm": 0.08155430108308792, | |
| "learning_rate": 5.15863005724265e-05, | |
| "loss": 0.0247, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 0.9994353472614342, | |
| "eval_E1/acc_on_CONSISTENT": 0.7682119205298014, | |
| "eval_E1/acc_on_INCONSISTENT": 0.7551020408163265, | |
| "eval_E1/accuracy": 0.765, | |
| "eval_E1/balanced_accuracy": 0.761656980673064, | |
| "eval_E1/f1_INC": 0.6115702479338843, | |
| "eval_E1/n": 200.0, | |
| "eval_E1/precision_INC": 0.5138888888888888, | |
| "eval_E1/recall_INC": 0.7551020408163265, | |
| "eval_E2/acc_on_CONSISTENT": 0.9859154929577465, | |
| "eval_E2/acc_on_INCONSISTENT": 0.9482758620689655, | |
| "eval_E2/accuracy": 0.975, | |
| "eval_E2/balanced_accuracy": 0.967095677513356, | |
| "eval_E2/f1_INC": 0.9565217391304347, | |
| "eval_E2/n": 200.0, | |
| "eval_E2/precision_INC": 0.9649122807017544, | |
| "eval_E2/recall_INC": 0.9482758620689655, | |
| "eval_E3/acc_on_CONSISTENT": 0.9769230769230769, | |
| "eval_E3/acc_on_INCONSISTENT": 0.7857142857142857, | |
| "eval_E3/accuracy": 0.91, | |
| "eval_E3/balanced_accuracy": 0.8813186813186813, | |
| "eval_E3/f1_INC": 0.859375, | |
| "eval_E3/n": 200.0, | |
| "eval_E3/precision_INC": 0.9482758620689655, | |
| "eval_E3/recall_INC": 0.7857142857142857, | |
| "eval_E4/acc_on_CONSISTENT": 0.9478260869565217, | |
| "eval_E4/acc_on_INCONSISTENT": 0.8117647058823529, | |
| "eval_E4/accuracy": 0.89, | |
| "eval_E4/balanced_accuracy": 0.8797953964194374, | |
| "eval_E4/f1_INC": 0.8625, | |
| "eval_E4/n": 200.0, | |
| "eval_E4/precision_INC": 0.92, | |
| "eval_E4/recall_INC": 0.8117647058823529, | |
| "eval_edge_macro_accuracy": 0.865, | |
| "eval_edge_macro_balanced_accuracy": 0.8541556833672439, | |
| "eval_edge_macro_f1_INC": 0.7978535372730037, | |
| "eval_malformed_rate": 0.0, | |
| "eval_n_eval": 1000.0, | |
| "eval_overall/acc_on_CONSISTENT": 0.6744186046511628, | |
| "eval_overall/acc_on_INCONSISTENT": 0.9426751592356688, | |
| "eval_overall/accuracy": 0.885, | |
| "eval_overall/balanced_accuracy": 0.8085468819434158, | |
| "eval_overall/f1_INC": 0.9278996865203761, | |
| "eval_overall/n": 200.0, | |
| "eval_overall/n_complete_groups": 200.0, | |
| "eval_overall/precision_INC": 0.9135802469135802, | |
| "eval_overall/recall_INC": 0.9426751592356688, | |
| "eval_overall_exact_match": 0.53, | |
| "eval_scene/acc_on_CONSISTENT": 0.7925925925925926, | |
| "eval_scene/acc_on_INCONSISTENT": 0.7692307692307693, | |
| "eval_scene/accuracy": 0.785, | |
| "eval_scene/balanced_accuracy": 0.780911680911681, | |
| "eval_scene/f1_INC": 0.6993006993006994, | |
| "eval_scene/n": 200.0, | |
| "eval_scene/precision_INC": 0.6410256410256411, | |
| "eval_scene/recall_INC": 0.7692307692307693, | |
| "step": 5310 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 10626, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 2656, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.316422271085052e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |