Instructions to use BananaMind/normal-model-ablation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BananaMind/normal-model-ablation with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BananaMind/normal-model-ablation", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("BananaMind/normal-model-ablation", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use BananaMind/normal-model-ablation with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BananaMind/normal-model-ablation" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BananaMind/normal-model-ablation", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BananaMind/normal-model-ablation
- SGLang
How to use BananaMind/normal-model-ablation 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 "BananaMind/normal-model-ablation" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BananaMind/normal-model-ablation", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "BananaMind/normal-model-ablation" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BananaMind/normal-model-ablation", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BananaMind/normal-model-ablation with Docker Model Runner:
docker model run hf.co/BananaMind/normal-model-ablation
Download train_log.json from BananaMind/normal-model-ablation: direct link, hf CLI and curl.
- Browser
- Download file 121 kB
-
https://huggingface.co/BananaMind/normal-model-ablation/resolve/main/train_log.json
- Command line
-
hf download hf://BananaMind/normal-model-ablation/train_log.json
-
curl -L -o train_log.json https://huggingface.co/BananaMind/normal-model-ablation/resolve/main/train_log.json
121 kB
| { | |
| "name": "normal-model-ablation", | |
| "attention_type": "standard", | |
| "params": 1498496, | |
| "params_excluding_indexers": 1498496, | |
| "val_loss": 3.4248253107070923, | |
| "val_ppl": 30.71727840314173, | |
| "steps": 40690, | |
| "train_tokens": 1999994880, | |
| "seed": 1337, | |
| "log": [ | |
| { | |
| "step": 50, | |
| "loss": 7.648939208984375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001, | |
| "tokens_per_s": 2363149.0623330018 | |
| }, | |
| { | |
| "step": 100, | |
| "loss": 6.532793579101562, | |
| "indexer_kl": 0.0, | |
| "lr": 0.002, | |
| "tokens_per_s": 2363988.825870876 | |
| }, | |
| { | |
| "step": 150, | |
| "loss": 5.866292114257813, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001999993527593341, | |
| "tokens_per_s": 2364134.4022017717 | |
| }, | |
| { | |
| "step": 200, | |
| "loss": 5.428878173828125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001999973579415524, | |
| "tokens_per_s": 2364310.093602896 | |
| }, | |
| { | |
| "step": 250, | |
| "loss": 5.125506591796875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019999401530695817, | |
| "tokens_per_s": 2364501.540194997 | |
| }, | |
| { | |
| "step": 300, | |
| "loss": 4.932823791503906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019998932490561125, | |
| "tokens_per_s": 2364898.813939611 | |
| }, | |
| { | |
| "step": 350, | |
| "loss": 4.802083129882813, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00199983286807756, | |
| "tokens_per_s": 2364946.2249820535 | |
| }, | |
| { | |
| "step": 400, | |
| "loss": 4.702893676757813, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019997590110381997, | |
| "tokens_per_s": 2364936.7490808354 | |
| }, | |
| { | |
| "step": 450, | |
| "loss": 4.638193359375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019996716790441284, | |
| "tokens_per_s": 2365077.030751819 | |
| }, | |
| { | |
| "step": 500, | |
| "loss": 4.567515869140625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019995708734032464, | |
| "tokens_per_s": 2365186.9887292064 | |
| }, | |
| { | |
| "step": 550, | |
| "loss": 4.511327209472657, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001999456595625237, | |
| "tokens_per_s": 2365294.823211181 | |
| }, | |
| { | |
| "step": 600, | |
| "loss": 4.4699462890625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001999328847421545, | |
| "tokens_per_s": 2365321.278435137 | |
| }, | |
| { | |
| "step": 650, | |
| "loss": 4.422857666015625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001999187630705351, | |
| "tokens_per_s": 2365351.2629185687 | |
| }, | |
| { | |
| "step": 700, | |
| "loss": 4.3891299438476565, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019990329475915417, | |
| "tokens_per_s": 2365414.378649714 | |
| }, | |
| { | |
| "step": 750, | |
| "loss": 4.359731140136719, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019988648003966803, | |
| "tokens_per_s": 2365481.4582522465 | |
| }, | |
| { | |
| "step": 800, | |
| "loss": 4.3241729736328125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019986831916389692, | |
| "tokens_per_s": 2365593.0862674806 | |
| }, | |
| { | |
| "step": 850, | |
| "loss": 4.301809387207031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019984881240382147, | |
| "tokens_per_s": 2365628.0370933237 | |
| }, | |
| { | |
| "step": 900, | |
| "loss": 4.25659423828125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001998279600515784, | |
| "tokens_per_s": 2365700.2772627347 | |
| }, | |
| { | |
| "step": 950, | |
| "loss": 4.203756713867188, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019980576241945642, | |
| "tokens_per_s": 2365757.744108179 | |
| }, | |
| { | |
| "step": 1000, | |
| "loss": 4.183764953613281, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001997822198398912, | |
| "tokens_per_s": 2365765.8114079665 | |
| }, | |
| { | |
| "step": 1050, | |
| "loss": 4.1194775390625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001997573326654608, | |
| "tokens_per_s": 2365811.713585091 | |
| }, | |
| { | |
| "step": 1100, | |
| "loss": 4.085085144042969, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001997311012688801, | |
| "tokens_per_s": 2365878.1760932603 | |
| }, | |
| { | |
| "step": 1150, | |
| "loss": 4.049246215820313, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001997035260429951, | |
| "tokens_per_s": 2365908.7120877816 | |
| }, | |
| { | |
| "step": 1200, | |
| "loss": 4.034196472167968, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019967460740077754, | |
| "tokens_per_s": 2365901.542522324 | |
| }, | |
| { | |
| "step": 1250, | |
| "loss": 4.01317138671875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019964434577531827, | |
| "tokens_per_s": 2365885.193871997 | |
| }, | |
| { | |
| "step": 1300, | |
| "loss": 3.997111511230469, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001996127416198208, | |
| "tokens_per_s": 2365852.580510005 | |
| }, | |
| { | |
| "step": 1350, | |
| "loss": 3.969423828125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001995797954075948, | |
| "tokens_per_s": 2365862.9077159036 | |
| }, | |
| { | |
| "step": 1400, | |
| "loss": 3.96874755859375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019954550763204874, | |
| "tokens_per_s": 2365863.653996134 | |
| }, | |
| { | |
| "step": 1450, | |
| "loss": 3.9396133422851562, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019950987880668256, | |
| "tokens_per_s": 2365855.1738323844 | |
| }, | |
| { | |
| "step": 1500, | |
| "loss": 3.942455139160156, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019947290946508004, | |
| "tokens_per_s": 2365844.200154269 | |
| }, | |
| { | |
| "step": 1550, | |
| "loss": 3.9267047119140623, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019943460016090078, | |
| "tokens_per_s": 2365845.9681223766 | |
| }, | |
| { | |
| "step": 1600, | |
| "loss": 3.907215270996094, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001993949514678718, | |
| "tokens_per_s": 2365859.300222584 | |
| }, | |
| { | |
| "step": 1650, | |
| "loss": 3.886343994140625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001993539639797793, | |
| "tokens_per_s": 2365850.367353153 | |
| }, | |
| { | |
| "step": 1700, | |
| "loss": 3.8931393432617187, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001993116383104593, | |
| "tokens_per_s": 2365874.716178031 | |
| }, | |
| { | |
| "step": 1750, | |
| "loss": 3.8917095947265623, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019926797509378868, | |
| "tokens_per_s": 2365898.4963976922 | |
| }, | |
| { | |
| "step": 1800, | |
| "loss": 3.8888079833984377, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019922297498367577, | |
| "tokens_per_s": 2365907.9231186537 | |
| }, | |
| { | |
| "step": 1850, | |
| "loss": 3.8674688720703125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019917663865405034, | |
| "tokens_per_s": 2365910.3386303657 | |
| }, | |
| { | |
| "step": 1900, | |
| "loss": 3.868305358886719, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001991289667988538, | |
| "tokens_per_s": 2365725.8240885152 | |
| }, | |
| { | |
| "step": 1950, | |
| "loss": 3.861421813964844, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001990799601320285, | |
| "tokens_per_s": 2365721.28488152 | |
| }, | |
| { | |
| "step": 2000, | |
| "loss": 3.8439151000976564, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019902961938750713, | |
| "tokens_per_s": 2365723.270809914 | |
| }, | |
| { | |
| "step": 2050, | |
| "loss": 3.844996032714844, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001989779453192019, | |
| "tokens_per_s": 2365724.312340054 | |
| }, | |
| { | |
| "step": 2100, | |
| "loss": 3.8411569213867187, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001989249387009931, | |
| "tokens_per_s": 2365728.807581166 | |
| }, | |
| { | |
| "step": 2150, | |
| "loss": 3.8154672241210936, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001988706003267174, | |
| "tokens_per_s": 2365619.9002684793 | |
| }, | |
| { | |
| "step": 2200, | |
| "loss": 3.8307904052734374, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019881493101015623, | |
| "tokens_per_s": 2365656.226260755 | |
| }, | |
| { | |
| "step": 2250, | |
| "loss": 3.8134255981445313, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001987579315850234, | |
| "tokens_per_s": 2365603.2284849808 | |
| }, | |
| { | |
| "step": 2300, | |
| "loss": 3.809312744140625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001986996029049527, | |
| "tokens_per_s": 2365610.2005907726 | |
| }, | |
| { | |
| "step": 2350, | |
| "loss": 3.7917156982421876, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00198639945843485, | |
| "tokens_per_s": 2365646.816639603 | |
| }, | |
| { | |
| "step": 2400, | |
| "loss": 3.8041644287109375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001985789612940554, | |
| "tokens_per_s": 2365661.831258642 | |
| }, | |
| { | |
| "step": 2450, | |
| "loss": 3.8070977783203124, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001985166501699796, | |
| "tokens_per_s": 2365668.4771750565 | |
| }, | |
| { | |
| "step": 2500, | |
| "loss": 3.783924255371094, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019845301340444023, | |
| "tokens_per_s": 2365674.412092384 | |
| }, | |
| { | |
| "step": 2550, | |
| "loss": 3.7888543701171873, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019838805195047313, | |
| "tokens_per_s": 2365688.8650238784 | |
| }, | |
| { | |
| "step": 2600, | |
| "loss": 3.7852914428710935, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001983217667809529, | |
| "tokens_per_s": 2365706.9595662183 | |
| }, | |
| { | |
| "step": 2650, | |
| "loss": 3.7806036376953127, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019825415888857826, | |
| "tokens_per_s": 2365719.034300667 | |
| }, | |
| { | |
| "step": 2700, | |
| "loss": 3.777296447753906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001981852292858573, | |
| "tokens_per_s": 2365740.6562754093 | |
| }, | |
| { | |
| "step": 2750, | |
| "loss": 3.7734365844726563, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019811497900509237, | |
| "tokens_per_s": 2365730.4155096156 | |
| }, | |
| { | |
| "step": 2800, | |
| "loss": 3.7739547729492187, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001980434090983644, | |
| "tokens_per_s": 2365728.3648194945 | |
| }, | |
| { | |
| "step": 2850, | |
| "loss": 3.7633148193359376, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001979705206375173, | |
| "tokens_per_s": 2365741.207696818 | |
| }, | |
| { | |
| "step": 2900, | |
| "loss": 3.762046203613281, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019789631471414204, | |
| "tokens_per_s": 2365743.478877632 | |
| }, | |
| { | |
| "step": 2950, | |
| "loss": 3.7482318115234374, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001978207924395599, | |
| "tokens_per_s": 2365739.6453517764 | |
| }, | |
| { | |
| "step": 3000, | |
| "loss": 3.7447048950195314, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001977439549448063, | |
| "tokens_per_s": 2365759.096751134 | |
| }, | |
| { | |
| "step": 3050, | |
| "loss": 3.7526791381835936, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001976658033806136, | |
| "tokens_per_s": 2365765.689463216 | |
| }, | |
| { | |
| "step": 3100, | |
| "loss": 3.7484735107421874, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001975863389173937, | |
| "tokens_per_s": 2365785.6701074634 | |
| }, | |
| { | |
| "step": 3150, | |
| "loss": 3.745319519042969, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019750556274522094, | |
| "tokens_per_s": 2365795.941217237 | |
| }, | |
| { | |
| "step": 3200, | |
| "loss": 3.7427322387695314, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019742347607381396, | |
| "tokens_per_s": 2365804.00796527 | |
| }, | |
| { | |
| "step": 3250, | |
| "loss": 3.734724426269531, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019734008013251774, | |
| "tokens_per_s": 2365806.8728579464 | |
| }, | |
| { | |
| "step": 3300, | |
| "loss": 3.7363052368164062, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019725537617028503, | |
| "tokens_per_s": 2365813.8549764343 | |
| }, | |
| { | |
| "step": 3350, | |
| "loss": 3.7382769775390625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001971693654556578, | |
| "tokens_per_s": 2365824.1946284124 | |
| }, | |
| { | |
| "step": 3400, | |
| "loss": 3.73150634765625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019708204927674816, | |
| "tokens_per_s": 2365820.519661802 | |
| }, | |
| { | |
| "step": 3450, | |
| "loss": 3.725441589355469, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001969934289412191, | |
| "tokens_per_s": 2365696.240661284 | |
| }, | |
| { | |
| "step": 3500, | |
| "loss": 3.7239511108398435, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001969035057762649, | |
| "tokens_per_s": 2365702.945406527 | |
| }, | |
| { | |
| "step": 3550, | |
| "loss": 3.7278607177734373, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019681228112859122, | |
| "tokens_per_s": 2365709.1630875976 | |
| }, | |
| { | |
| "step": 3600, | |
| "loss": 3.730074462890625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00196719756364395, | |
| "tokens_per_s": 2365595.5631893845 | |
| }, | |
| { | |
| "step": 3650, | |
| "loss": 3.7295181274414064, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00196625932869344, | |
| "tokens_per_s": 2365604.73188933 | |
| }, | |
| { | |
| "step": 3700, | |
| "loss": 3.714951477050781, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001965308120485559, | |
| "tokens_per_s": 2365615.406263004 | |
| }, | |
| { | |
| "step": 3750, | |
| "loss": 3.718502197265625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001964343953265774, | |
| "tokens_per_s": 2365628.7349893274 | |
| }, | |
| { | |
| "step": 3800, | |
| "loss": 3.7099569702148436, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019633668414736293, | |
| "tokens_per_s": 2365626.2974535734 | |
| }, | |
| { | |
| "step": 3850, | |
| "loss": 3.7241705322265624, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001962376799742529, | |
| "tokens_per_s": 2365627.6741906614 | |
| }, | |
| { | |
| "step": 3900, | |
| "loss": 3.715791015625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001961373842899518, | |
| "tokens_per_s": 2365634.7370036696 | |
| }, | |
| { | |
| "step": 3950, | |
| "loss": 3.70549560546875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019603579859650603, | |
| "tokens_per_s": 2365642.6381470906 | |
| }, | |
| { | |
| "step": 4000, | |
| "loss": 3.7019998168945314, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001959329244152815, | |
| "tokens_per_s": 2365655.5402133064 | |
| }, | |
| { | |
| "step": 4050, | |
| "loss": 3.7154296875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019582876328694057, | |
| "tokens_per_s": 2365663.478865041 | |
| }, | |
| { | |
| "step": 4100, | |
| "loss": 3.716644592285156, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019572331677141933, | |
| "tokens_per_s": 2365667.19837918 | |
| }, | |
| { | |
| "step": 4150, | |
| "loss": 3.704065856933594, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019561658644790397, | |
| "tokens_per_s": 2365674.739939881 | |
| }, | |
| { | |
| "step": 4200, | |
| "loss": 3.699429626464844, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019550857391480727, | |
| "tokens_per_s": 2365672.6395769287 | |
| }, | |
| { | |
| "step": 4250, | |
| "loss": 3.6998077392578126, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001953992807897445, | |
| "tokens_per_s": 2365685.362595788 | |
| }, | |
| { | |
| "step": 4300, | |
| "loss": 3.7020452880859374, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019528870870950947, | |
| "tokens_per_s": 2365690.176177968 | |
| }, | |
| { | |
| "step": 4350, | |
| "loss": 3.682428894042969, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019517685933004977, | |
| "tokens_per_s": 2365706.1185155995 | |
| }, | |
| { | |
| "step": 4400, | |
| "loss": 3.70173095703125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00195063734326442, | |
| "tokens_per_s": 2365722.210831372 | |
| }, | |
| { | |
| "step": 4450, | |
| "loss": 3.6870770263671875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019494933539286688, | |
| "tokens_per_s": 2365720.9639009563 | |
| }, | |
| { | |
| "step": 4500, | |
| "loss": 3.6904336547851564, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019483366424258364, | |
| "tokens_per_s": 2365724.6010287995 | |
| }, | |
| { | |
| "step": 4550, | |
| "loss": 3.687826843261719, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019471672260790447, | |
| "tokens_per_s": 2365729.1904296842 | |
| }, | |
| { | |
| "step": 4600, | |
| "loss": 3.679774169921875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019459851224016855, | |
| "tokens_per_s": 2365731.8859807616 | |
| }, | |
| { | |
| "step": 4650, | |
| "loss": 3.6956427001953127, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019447903490971592, | |
| "tokens_per_s": 2365737.8571781293 | |
| }, | |
| { | |
| "step": 4700, | |
| "loss": 3.687264099121094, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019435829240586077, | |
| "tokens_per_s": 2365748.6746102404 | |
| }, | |
| { | |
| "step": 4750, | |
| "loss": 3.6860531616210936, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019423628653686487, | |
| "tokens_per_s": 2365755.966623381 | |
| }, | |
| { | |
| "step": 4800, | |
| "loss": 3.680949401855469, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019411301912991025, | |
| "tokens_per_s": 2365753.7519748863 | |
| }, | |
| { | |
| "step": 4850, | |
| "loss": 3.682414855957031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001939884920310721, | |
| "tokens_per_s": 2365742.3919056314 | |
| }, | |
| { | |
| "step": 4900, | |
| "loss": 3.677304992675781, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019386270710529088, | |
| "tokens_per_s": 2365662.377639233 | |
| }, | |
| { | |
| "step": 4950, | |
| "loss": 3.682525939941406, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019373566623634452, | |
| "tokens_per_s": 2365661.082347401 | |
| }, | |
| { | |
| "step": 5000, | |
| "loss": 3.6768450927734375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019360737132682027, | |
| "tokens_per_s": 2365656.620614829 | |
| }, | |
| { | |
| "step": 5050, | |
| "loss": 3.6778695678710935, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019347782429808595, | |
| "tokens_per_s": 2365653.548092881 | |
| }, | |
| { | |
| "step": 5100, | |
| "loss": 3.6749481201171874, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019334702709026146, | |
| "tokens_per_s": 2365647.0814135415 | |
| }, | |
| { | |
| "step": 5150, | |
| "loss": 3.66169677734375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019321498166218964, | |
| "tokens_per_s": 2365654.3500175234 | |
| }, | |
| { | |
| "step": 5200, | |
| "loss": 3.6875457763671875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001930816899914068, | |
| "tokens_per_s": 2365642.0958327623 | |
| }, | |
| { | |
| "step": 5250, | |
| "loss": 3.677765197753906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019294715407411332, | |
| "tokens_per_s": 2365642.9808442355 | |
| }, | |
| { | |
| "step": 5300, | |
| "loss": 3.6712857055664063, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019281137592514353, | |
| "tokens_per_s": 2365567.239906478 | |
| }, | |
| { | |
| "step": 5350, | |
| "loss": 3.6632171630859376, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019267435757793572, | |
| "tokens_per_s": 2365570.30967417 | |
| }, | |
| { | |
| "step": 5400, | |
| "loss": 3.6715707397460937, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019253610108450163, | |
| "tokens_per_s": 2365549.6925933226 | |
| }, | |
| { | |
| "step": 5450, | |
| "loss": 3.665740966796875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001923966085153956, | |
| "tokens_per_s": 2365555.277509411 | |
| }, | |
| { | |
| "step": 5500, | |
| "loss": 3.6599325561523437, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001922558819596838, | |
| "tokens_per_s": 2365564.3191890744 | |
| }, | |
| { | |
| "step": 5550, | |
| "loss": 3.6636090087890625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001921139235249127, | |
| "tokens_per_s": 2365559.606605402 | |
| }, | |
| { | |
| "step": 5600, | |
| "loss": 3.6606784057617188, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019197073533707765, | |
| "tokens_per_s": 2365556.9994123806 | |
| }, | |
| { | |
| "step": 5650, | |
| "loss": 3.6625640869140623, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019182631954059103, | |
| "tokens_per_s": 2365551.440585623 | |
| }, | |
| { | |
| "step": 5700, | |
| "loss": 3.6650271606445313, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019168067829825012, | |
| "tokens_per_s": 2365543.0935560986 | |
| }, | |
| { | |
| "step": 5750, | |
| "loss": 3.653719787597656, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019153381379120463, | |
| "tokens_per_s": 2365467.3336076057 | |
| }, | |
| { | |
| "step": 5800, | |
| "loss": 3.6499945068359376, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019138572821892417, | |
| "tokens_per_s": 2365446.7113829986 | |
| }, | |
| { | |
| "step": 5850, | |
| "loss": 3.653059997558594, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001912364237991652, | |
| "tokens_per_s": 2365361.5710576777 | |
| }, | |
| { | |
| "step": 5900, | |
| "loss": 3.6531854248046876, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019108590276793792, | |
| "tokens_per_s": 2365362.7345012086 | |
| }, | |
| { | |
| "step": 5950, | |
| "loss": 3.659659729003906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019093416737947266, | |
| "tokens_per_s": 2365311.4852002426 | |
| }, | |
| { | |
| "step": 6000, | |
| "loss": 3.673414611816406, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019078121990618623, | |
| "tokens_per_s": 2365303.5257385755 | |
| }, | |
| { | |
| "step": 6050, | |
| "loss": 3.6563531494140626, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001906270626386478, | |
| "tokens_per_s": 2365307.9210410696 | |
| }, | |
| { | |
| "step": 6100, | |
| "loss": 3.6574200439453124, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019047169788554473, | |
| "tokens_per_s": 2365299.849923774 | |
| }, | |
| { | |
| "step": 6150, | |
| "loss": 3.648107604980469, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019031512797364773, | |
| "tokens_per_s": 2365233.3785801805 | |
| }, | |
| { | |
| "step": 6200, | |
| "loss": 3.641368408203125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0019015735524777642, | |
| "tokens_per_s": 2365233.050855107 | |
| }, | |
| { | |
| "step": 6250, | |
| "loss": 3.648925476074219, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018999838207076382, | |
| "tokens_per_s": 2365233.653170734 | |
| }, | |
| { | |
| "step": 6300, | |
| "loss": 3.6356442260742186, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018983821082342112, | |
| "tokens_per_s": 2365228.9264036003 | |
| }, | |
| { | |
| "step": 6350, | |
| "loss": 3.639400634765625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018967684390450209, | |
| "tokens_per_s": 2365225.4791812995 | |
| }, | |
| { | |
| "step": 6400, | |
| "loss": 3.6440493774414064, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001895142837306671, | |
| "tokens_per_s": 2365225.8466909877 | |
| }, | |
| { | |
| "step": 6450, | |
| "loss": 3.642680358886719, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018935053273644688, | |
| "tokens_per_s": 2365229.6835864075 | |
| }, | |
| { | |
| "step": 6500, | |
| "loss": 3.64785400390625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018918559337420615, | |
| "tokens_per_s": 2365221.375539062 | |
| }, | |
| { | |
| "step": 6550, | |
| "loss": 3.6406289672851564, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018901946811410678, | |
| "tokens_per_s": 2365180.590685803 | |
| }, | |
| { | |
| "step": 6600, | |
| "loss": 3.6532958984375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001888521594440709, | |
| "tokens_per_s": 2365167.662187262 | |
| }, | |
| { | |
| "step": 6650, | |
| "loss": 3.6528497314453126, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018868366986974363, | |
| "tokens_per_s": 2365107.584993063 | |
| }, | |
| { | |
| "step": 6700, | |
| "loss": 3.6515374755859376, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018851400191445553, | |
| "tokens_per_s": 2365099.307042194 | |
| }, | |
| { | |
| "step": 6750, | |
| "loss": 3.641993103027344, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018834315811918471, | |
| "tokens_per_s": 2365103.930398825 | |
| }, | |
| { | |
| "step": 6800, | |
| "loss": 3.6519775390625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00188171141042519, | |
| "tokens_per_s": 2365095.026993393 | |
| }, | |
| { | |
| "step": 6850, | |
| "loss": 3.63876708984375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018799795326061742, | |
| "tokens_per_s": 2365067.2608990665 | |
| }, | |
| { | |
| "step": 6900, | |
| "loss": 3.6280551147460938, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001878235973671717, | |
| "tokens_per_s": 2365050.475299618 | |
| }, | |
| { | |
| "step": 6950, | |
| "loss": 3.6306121826171873, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018764807597336747, | |
| "tokens_per_s": 2365041.981139623 | |
| }, | |
| { | |
| "step": 7000, | |
| "loss": 3.623145751953125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018747139170784504, | |
| "tokens_per_s": 2365038.914539301 | |
| }, | |
| { | |
| "step": 7050, | |
| "loss": 3.645218505859375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018729354721666014, | |
| "tokens_per_s": 2365040.8790395563 | |
| }, | |
| { | |
| "step": 7100, | |
| "loss": 3.6277902221679685, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018711454516324422, | |
| "tokens_per_s": 2365033.8662700774 | |
| }, | |
| { | |
| "step": 7150, | |
| "loss": 3.62594482421875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018693438822836468, | |
| "tokens_per_s": 2364975.782660542 | |
| }, | |
| { | |
| "step": 7200, | |
| "loss": 3.622897033691406, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018675307911008448, | |
| "tokens_per_s": 2364976.5920859785 | |
| }, | |
| { | |
| "step": 7250, | |
| "loss": 3.616207275390625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00186570620523722, | |
| "tokens_per_s": 2364982.0492656985 | |
| }, | |
| { | |
| "step": 7300, | |
| "loss": 3.634427490234375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018638701520181024, | |
| "tokens_per_s": 2364977.42694824 | |
| }, | |
| { | |
| "step": 7350, | |
| "loss": 3.621290588378906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018620226589405597, | |
| "tokens_per_s": 2364975.108078643 | |
| }, | |
| { | |
| "step": 7400, | |
| "loss": 3.619018249511719, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018601637536729838, | |
| "tokens_per_s": 2364976.5344445417 | |
| }, | |
| { | |
| "step": 7450, | |
| "loss": 3.6386614990234376, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018582934640546786, | |
| "tokens_per_s": 2364940.6118204915 | |
| }, | |
| { | |
| "step": 7500, | |
| "loss": 3.6343368530273437, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018564118180954417, | |
| "tokens_per_s": 2364943.9383568126 | |
| }, | |
| { | |
| "step": 7550, | |
| "loss": 3.626528015136719, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018545188439751455, | |
| "tokens_per_s": 2364939.455721778 | |
| }, | |
| { | |
| "step": 7600, | |
| "loss": 3.630843200683594, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018526145700433153, | |
| "tokens_per_s": 2364876.487960935 | |
| }, | |
| { | |
| "step": 7650, | |
| "loss": 3.6246981811523438, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018506990248187037, | |
| "tokens_per_s": 2364883.501569451 | |
| }, | |
| { | |
| "step": 7700, | |
| "loss": 3.6175244140625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018487722369888646, | |
| "tokens_per_s": 2364885.0302139176 | |
| }, | |
| { | |
| "step": 7750, | |
| "loss": 3.6196307373046874, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018468342354097237, | |
| "tokens_per_s": 2364887.312724784 | |
| }, | |
| { | |
| "step": 7800, | |
| "loss": 3.6219744873046875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018448850491051445, | |
| "tokens_per_s": 2364881.691875571 | |
| }, | |
| { | |
| "step": 7850, | |
| "loss": 3.62067626953125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018429247072664966, | |
| "tokens_per_s": 2364881.9518356295 | |
| }, | |
| { | |
| "step": 7900, | |
| "loss": 3.6147811889648436, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018409532392522161, | |
| "tokens_per_s": 2364880.9585569776 | |
| }, | |
| { | |
| "step": 7950, | |
| "loss": 3.627166442871094, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018389706745873665, | |
| "tokens_per_s": 2364885.314656563 | |
| }, | |
| { | |
| "step": 8000, | |
| "loss": 3.626260070800781, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001836977042963197, | |
| "tokens_per_s": 2364885.031667207 | |
| }, | |
| { | |
| "step": 8050, | |
| "loss": 3.6284640502929686, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001834972374236698, | |
| "tokens_per_s": 2364876.2666989216 | |
| }, | |
| { | |
| "step": 8100, | |
| "loss": 3.641448974609375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018329566984301537, | |
| "tokens_per_s": 2364874.8641672824 | |
| }, | |
| { | |
| "step": 8150, | |
| "loss": 3.6088037109375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018309300457306909, | |
| "tokens_per_s": 2364877.8659037896 | |
| }, | |
| { | |
| "step": 8200, | |
| "loss": 3.619315185546875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018288924464898294, | |
| "tokens_per_s": 2364879.3059205334 | |
| }, | |
| { | |
| "step": 8250, | |
| "loss": 3.608692932128906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018268439312230265, | |
| "tokens_per_s": 2364875.967123093 | |
| }, | |
| { | |
| "step": 8300, | |
| "loss": 3.6183990478515624, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018247845306092196, | |
| "tokens_per_s": 2364843.0375410705 | |
| }, | |
| { | |
| "step": 8350, | |
| "loss": 3.6180816650390626, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018227142754903673, | |
| "tokens_per_s": 2364840.8656519637 | |
| }, | |
| { | |
| "step": 8400, | |
| "loss": 3.603656005859375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001820633196870987, | |
| "tokens_per_s": 2364842.549704516 | |
| }, | |
| { | |
| "step": 8450, | |
| "loss": 3.6040631103515626, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018185413259176907, | |
| "tokens_per_s": 2364788.448812087 | |
| }, | |
| { | |
| "step": 8500, | |
| "loss": 3.618874816894531, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001816438693958719, | |
| "tokens_per_s": 2364785.5354625946 | |
| }, | |
| { | |
| "step": 8550, | |
| "loss": 3.6168673706054686, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018143253324834703, | |
| "tokens_per_s": 2364788.1987387124 | |
| }, | |
| { | |
| "step": 8600, | |
| "loss": 3.609369201660156, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001812201273142031, | |
| "tokens_per_s": 2364787.954447432 | |
| }, | |
| { | |
| "step": 8650, | |
| "loss": 3.6126895141601563, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018100665477447, | |
| "tokens_per_s": 2364796.1173172467 | |
| }, | |
| { | |
| "step": 8700, | |
| "loss": 3.6114541625976564, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018079211882615137, | |
| "tokens_per_s": 2364799.497019427 | |
| }, | |
| { | |
| "step": 8750, | |
| "loss": 3.615689392089844, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018057652268217662, | |
| "tokens_per_s": 2364801.4833473475 | |
| }, | |
| { | |
| "step": 8800, | |
| "loss": 3.6078955078125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018035986957135285, | |
| "tokens_per_s": 2364801.5451914654 | |
| }, | |
| { | |
| "step": 8850, | |
| "loss": 3.615896911621094, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0018014216273831642, | |
| "tokens_per_s": 2364801.330477557 | |
| }, | |
| { | |
| "step": 8900, | |
| "loss": 3.616408386230469, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017992340544348456, | |
| "tokens_per_s": 2364747.51629173 | |
| }, | |
| { | |
| "step": 8950, | |
| "loss": 3.5964016723632812, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001797036009630063, | |
| "tokens_per_s": 2364738.544006515 | |
| }, | |
| { | |
| "step": 9000, | |
| "loss": 3.620291442871094, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017948275258871352, | |
| "tokens_per_s": 2364700.1151752463 | |
| }, | |
| { | |
| "step": 9050, | |
| "loss": 3.613389587402344, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017926086362807171, | |
| "tokens_per_s": 2364703.3907696293 | |
| }, | |
| { | |
| "step": 9100, | |
| "loss": 3.607340087890625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017903793740413037, | |
| "tokens_per_s": 2364704.4127704375 | |
| }, | |
| { | |
| "step": 9150, | |
| "loss": 3.60697998046875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001788139772554731, | |
| "tokens_per_s": 2364709.2713567335 | |
| }, | |
| { | |
| "step": 9200, | |
| "loss": 3.604131164550781, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001785889865361679, | |
| "tokens_per_s": 2364712.5234107664 | |
| }, | |
| { | |
| "step": 9250, | |
| "loss": 3.5959896850585937, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017836296861571672, | |
| "tokens_per_s": 2364712.9252684885 | |
| }, | |
| { | |
| "step": 9300, | |
| "loss": 3.5956317138671876, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017813592687900511, | |
| "tokens_per_s": 2364718.972221969 | |
| }, | |
| { | |
| "step": 9350, | |
| "loss": 3.6035455322265624, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017790786472625141, | |
| "tokens_per_s": 2364722.7990874248 | |
| }, | |
| { | |
| "step": 9400, | |
| "loss": 3.610584411621094, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017767878557295594, | |
| "tokens_per_s": 2364732.001497261 | |
| }, | |
| { | |
| "step": 9450, | |
| "loss": 3.604847717285156, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017744869284984975, | |
| "tokens_per_s": 2364738.4658819544 | |
| }, | |
| { | |
| "step": 9500, | |
| "loss": 3.593907775878906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017721759000284341, | |
| "tokens_per_s": 2364731.933761791 | |
| }, | |
| { | |
| "step": 9550, | |
| "loss": 3.595683898925781, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001769854804929752, | |
| "tokens_per_s": 2364726.5948169352 | |
| }, | |
| { | |
| "step": 9600, | |
| "loss": 3.5920730590820313, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017675236779635935, | |
| "tokens_per_s": 2364732.404277861 | |
| }, | |
| { | |
| "step": 9650, | |
| "loss": 3.6064910888671875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017651825540413405, | |
| "tokens_per_s": 2364695.9690775853 | |
| }, | |
| { | |
| "step": 9700, | |
| "loss": 3.59421875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017628314682240909, | |
| "tokens_per_s": 2364701.7728992705 | |
| }, | |
| { | |
| "step": 9750, | |
| "loss": 3.5996664428710936, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017604704557221342, | |
| "tokens_per_s": 2364706.977524667 | |
| }, | |
| { | |
| "step": 9800, | |
| "loss": 3.602231750488281, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001758099551894423, | |
| "tokens_per_s": 2364712.214864954 | |
| }, | |
| { | |
| "step": 9850, | |
| "loss": 3.6064202880859373, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017557187922480444, | |
| "tokens_per_s": 2364670.4103628304 | |
| }, | |
| { | |
| "step": 9900, | |
| "loss": 3.590587158203125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017533282124376885, | |
| "tokens_per_s": 2364673.447817483 | |
| }, | |
| { | |
| "step": 9950, | |
| "loss": 3.593367004394531, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017509278482651137, | |
| "tokens_per_s": 2364673.7560565863 | |
| }, | |
| { | |
| "step": 10000, | |
| "loss": 3.5957794189453125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00174851773567861, | |
| "tokens_per_s": 2364678.08902054 | |
| }, | |
| { | |
| "step": 10050, | |
| "loss": 3.5963470458984377, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017460979107724634, | |
| "tokens_per_s": 2364676.638449722 | |
| }, | |
| { | |
| "step": 10100, | |
| "loss": 3.5905441284179687, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017436684097864106, | |
| "tokens_per_s": 2364635.8338883487 | |
| }, | |
| { | |
| "step": 10150, | |
| "loss": 3.5904031372070313, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017412292691051019, | |
| "tokens_per_s": 2364634.835614576 | |
| }, | |
| { | |
| "step": 10200, | |
| "loss": 3.5910330200195313, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017387805252575515, | |
| "tokens_per_s": 2364634.9346806556 | |
| }, | |
| { | |
| "step": 10250, | |
| "loss": 3.5820733642578126, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017363222149165928, | |
| "tokens_per_s": 2364635.7392843124 | |
| }, | |
| { | |
| "step": 10300, | |
| "loss": 3.5871868896484376, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017338543748983291, | |
| "tokens_per_s": 2364637.2128197337 | |
| }, | |
| { | |
| "step": 10350, | |
| "loss": 3.5957821655273436, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017313770421615818, | |
| "tokens_per_s": 2364636.6176309437 | |
| }, | |
| { | |
| "step": 10400, | |
| "loss": 3.5816354370117187, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017288902538073365, | |
| "tokens_per_s": 2364633.6862561074 | |
| }, | |
| { | |
| "step": 10450, | |
| "loss": 3.5896295166015624, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017263940470781888, | |
| "tokens_per_s": 2364596.305752937 | |
| }, | |
| { | |
| "step": 10500, | |
| "loss": 3.5917376708984374, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017238884593577845, | |
| "tokens_per_s": 2364594.1367804054 | |
| }, | |
| { | |
| "step": 10550, | |
| "loss": 3.582034912109375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001721373528170261, | |
| "tokens_per_s": 2364595.302064731 | |
| }, | |
| { | |
| "step": 10600, | |
| "loss": 3.5925473022460936, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017188492911796862, | |
| "tokens_per_s": 2364597.3314079526 | |
| }, | |
| { | |
| "step": 10650, | |
| "loss": 3.594691162109375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017163157861894926, | |
| "tokens_per_s": 2364574.474201118 | |
| }, | |
| { | |
| "step": 10700, | |
| "loss": 3.585426025390625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017137730511419117, | |
| "tokens_per_s": 2364575.646574995 | |
| }, | |
| { | |
| "step": 10750, | |
| "loss": 3.5925192260742187, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017112211241174066, | |
| "tokens_per_s": 2364556.3072662908 | |
| }, | |
| { | |
| "step": 10800, | |
| "loss": 3.588118896484375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017086600433341011, | |
| "tokens_per_s": 2364558.2057752106 | |
| }, | |
| { | |
| "step": 10850, | |
| "loss": 3.5715011596679687, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017060898471472064, | |
| "tokens_per_s": 2364561.5315569006 | |
| }, | |
| { | |
| "step": 10900, | |
| "loss": 3.5959091186523438, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001703510574048449, | |
| "tokens_per_s": 2364527.3759424533 | |
| }, | |
| { | |
| "step": 10950, | |
| "loss": 3.5825439453125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0017009222626654923, | |
| "tokens_per_s": 2364529.764392938 | |
| }, | |
| { | |
| "step": 11000, | |
| "loss": 3.5883978271484374, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016983249517613585, | |
| "tokens_per_s": 2364535.723304881 | |
| }, | |
| { | |
| "step": 11050, | |
| "loss": 3.5922412109375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016957186802338483, | |
| "tokens_per_s": 2364535.21520825 | |
| }, | |
| { | |
| "step": 11100, | |
| "loss": 3.5863275146484375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016931034871149587, | |
| "tokens_per_s": 2364539.7716639037 | |
| }, | |
| { | |
| "step": 11150, | |
| "loss": 3.590816650390625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016904794115702975, | |
| "tokens_per_s": 2364543.2754312498 | |
| }, | |
| { | |
| "step": 11200, | |
| "loss": 3.575264587402344, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001687846492898498, | |
| "tokens_per_s": 2364520.1049385443 | |
| }, | |
| { | |
| "step": 11250, | |
| "loss": 3.5897125244140624, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016852047705306296, | |
| "tokens_per_s": 2364519.0967425047 | |
| }, | |
| { | |
| "step": 11300, | |
| "loss": 3.5808901977539063, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016825542840296064, | |
| "tokens_per_s": 2364519.535052073 | |
| }, | |
| { | |
| "step": 11350, | |
| "loss": 3.588467712402344, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016798950730895974, | |
| "tokens_per_s": 2364519.1260418473 | |
| }, | |
| { | |
| "step": 11400, | |
| "loss": 3.572989807128906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016772271775354298, | |
| "tokens_per_s": 2364523.05739595 | |
| }, | |
| { | |
| "step": 11450, | |
| "loss": 3.58401123046875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016745506373219924, | |
| "tokens_per_s": 2364492.2628333867 | |
| }, | |
| { | |
| "step": 11500, | |
| "loss": 3.5739675903320314, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016718654925336385, | |
| "tokens_per_s": 2364455.9547486575 | |
| }, | |
| { | |
| "step": 11550, | |
| "loss": 3.5822259521484376, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016691717833835858, | |
| "tokens_per_s": 2364461.6978353625 | |
| }, | |
| { | |
| "step": 11600, | |
| "loss": 3.5779901123046876, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016664695502133125, | |
| "tokens_per_s": 2364463.6275863596 | |
| }, | |
| { | |
| "step": 11650, | |
| "loss": 3.5769583129882814, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016637588334919543, | |
| "tokens_per_s": 2364464.1999847554 | |
| }, | |
| { | |
| "step": 11700, | |
| "loss": 3.5774386596679686, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016610396738156983, | |
| "tokens_per_s": 2364430.4365166263 | |
| }, | |
| { | |
| "step": 11750, | |
| "loss": 3.5856033325195313, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016583121119071748, | |
| "tokens_per_s": 2364432.670778018 | |
| }, | |
| { | |
| "step": 11800, | |
| "loss": 3.578681640625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016555761886148472, | |
| "tokens_per_s": 2364433.2199775204 | |
| }, | |
| { | |
| "step": 11850, | |
| "loss": 3.5592086791992186, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016528319449124005, | |
| "tokens_per_s": 2364432.5059148963 | |
| }, | |
| { | |
| "step": 11900, | |
| "loss": 3.55782470703125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016500794218981282, | |
| "tokens_per_s": 2364430.3394244346 | |
| }, | |
| { | |
| "step": 11950, | |
| "loss": 3.5758621215820314, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016473186607943162, | |
| "tokens_per_s": 2364428.2591451653 | |
| }, | |
| { | |
| "step": 12000, | |
| "loss": 3.5809661865234377, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016445497029466244, | |
| "tokens_per_s": 2364432.559807022 | |
| }, | |
| { | |
| "step": 12050, | |
| "loss": 3.5732562255859377, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016417725898234701, | |
| "tokens_per_s": 2364409.797328372 | |
| }, | |
| { | |
| "step": 12100, | |
| "loss": 3.5762158203125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001638987363015405, | |
| "tokens_per_s": 2364411.848270312 | |
| }, | |
| { | |
| "step": 12150, | |
| "loss": 3.5660626220703127, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016361940642344926, | |
| "tokens_per_s": 2364415.7950529377 | |
| }, | |
| { | |
| "step": 12200, | |
| "loss": 3.571099853515625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001633392735313683, | |
| "tokens_per_s": 2364423.868247423 | |
| }, | |
| { | |
| "step": 12250, | |
| "loss": 3.5705807495117186, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016305834182061892, | |
| "tokens_per_s": 2364429.568932023 | |
| }, | |
| { | |
| "step": 12300, | |
| "loss": 3.56845947265625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016277661549848551, | |
| "tokens_per_s": 2364440.1022981284 | |
| }, | |
| { | |
| "step": 12350, | |
| "loss": 3.5802548217773436, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016249409878415272, | |
| "tokens_per_s": 2364447.076718962 | |
| }, | |
| { | |
| "step": 12400, | |
| "loss": 3.577550048828125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001622107959086423, | |
| "tokens_per_s": 2364451.8976514465 | |
| }, | |
| { | |
| "step": 12450, | |
| "loss": 3.572491455078125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016192671111474966, | |
| "tokens_per_s": 2364424.676425467 | |
| }, | |
| { | |
| "step": 12500, | |
| "loss": 3.576234130859375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001616418486569804, | |
| "tokens_per_s": 2364427.463499286 | |
| }, | |
| { | |
| "step": 12550, | |
| "loss": 3.574979553222656, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016135621280148657, | |
| "tokens_per_s": 2364434.063741631 | |
| }, | |
| { | |
| "step": 12600, | |
| "loss": 3.56525390625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016106980782600265, | |
| "tokens_per_s": 2364405.9249353437 | |
| }, | |
| { | |
| "step": 12650, | |
| "loss": 3.5671127319335936, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016078263801978172, | |
| "tokens_per_s": 2364382.9587971363 | |
| }, | |
| { | |
| "step": 12700, | |
| "loss": 3.5707806396484374, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016049470768353107, | |
| "tokens_per_s": 2364391.30013632 | |
| }, | |
| { | |
| "step": 12750, | |
| "loss": 3.5693258666992187, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0016020602112934781, | |
| "tokens_per_s": 2364399.6781987003 | |
| }, | |
| { | |
| "step": 12800, | |
| "loss": 3.5557077026367185, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015991658268065432, | |
| "tokens_per_s": 2364407.480301528 | |
| }, | |
| { | |
| "step": 12850, | |
| "loss": 3.5649639892578127, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015962639667213353, | |
| "tokens_per_s": 2364412.077402423 | |
| }, | |
| { | |
| "step": 12900, | |
| "loss": 3.5791412353515626, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015933546744966384, | |
| "tokens_per_s": 2364417.1097591957 | |
| }, | |
| { | |
| "step": 12950, | |
| "loss": 3.5680227661132813, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015904379937025427, | |
| "tokens_per_s": 2364421.2782368273 | |
| }, | |
| { | |
| "step": 13000, | |
| "loss": 3.5711679077148437, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015875139680197907, | |
| "tokens_per_s": 2364425.2561305296 | |
| }, | |
| { | |
| "step": 13050, | |
| "loss": 3.5824591064453126, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015845826412391234, | |
| "tokens_per_s": 2364427.813388818 | |
| }, | |
| { | |
| "step": 13100, | |
| "loss": 3.5715289306640625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015816440572606236, | |
| "tokens_per_s": 2364433.4582793736 | |
| }, | |
| { | |
| "step": 13150, | |
| "loss": 3.5651315307617186, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015786982600930605, | |
| "tokens_per_s": 2364437.9961783206 | |
| }, | |
| { | |
| "step": 13200, | |
| "loss": 3.561279602050781, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015757452938532281, | |
| "tokens_per_s": 2364443.752893853 | |
| }, | |
| { | |
| "step": 13250, | |
| "loss": 3.5546798706054688, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015727852027652867, | |
| "tokens_per_s": 2364448.9422484897 | |
| }, | |
| { | |
| "step": 13300, | |
| "loss": 3.5681298828125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001569818031160099, | |
| "tokens_per_s": 2364455.191608724 | |
| }, | |
| { | |
| "step": 13350, | |
| "loss": 3.5541864013671876, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015668438234745668, | |
| "tokens_per_s": 2364460.423210999 | |
| }, | |
| { | |
| "step": 13400, | |
| "loss": 3.568317565917969, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015638626242509659, | |
| "tokens_per_s": 2364464.444034929 | |
| }, | |
| { | |
| "step": 13450, | |
| "loss": 3.568704833984375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015608744781362785, | |
| "tokens_per_s": 2364479.030401394 | |
| }, | |
| { | |
| "step": 13500, | |
| "loss": 3.5567755126953124, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015578794298815246, | |
| "tokens_per_s": 2364481.560487746 | |
| }, | |
| { | |
| "step": 13550, | |
| "loss": 3.5615283203125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015548775243410921, | |
| "tokens_per_s": 2364485.0806097663 | |
| }, | |
| { | |
| "step": 13600, | |
| "loss": 3.544371337890625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015518688064720646, | |
| "tokens_per_s": 2364469.432204897 | |
| }, | |
| { | |
| "step": 13650, | |
| "loss": 3.560160827636719, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015488533213335485, | |
| "tokens_per_s": 2364470.992164751 | |
| }, | |
| { | |
| "step": 13700, | |
| "loss": 3.552525939941406, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015458311140859981, | |
| "tokens_per_s": 2364490.2313127085 | |
| }, | |
| { | |
| "step": 13750, | |
| "loss": 3.5629592895507813, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015428022299905394, | |
| "tokens_per_s": 2364502.4869046756 | |
| }, | |
| { | |
| "step": 13800, | |
| "loss": 3.5404953002929687, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015397667144082918, | |
| "tokens_per_s": 2364521.893583951 | |
| }, | |
| { | |
| "step": 13850, | |
| "loss": 3.551219787597656, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015367246127996888, | |
| "tokens_per_s": 2364538.983012529 | |
| }, | |
| { | |
| "step": 13900, | |
| "loss": 3.570863952636719, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015336759707237984, | |
| "tokens_per_s": 2364554.2795850597 | |
| }, | |
| { | |
| "step": 13950, | |
| "loss": 3.5488177490234376, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015306208338376384, | |
| "tokens_per_s": 2364565.8058795147 | |
| }, | |
| { | |
| "step": 14000, | |
| "loss": 3.5605899047851564, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015275592478954955, | |
| "tokens_per_s": 2364577.9880337077 | |
| }, | |
| { | |
| "step": 14050, | |
| "loss": 3.545021667480469, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015244912587482377, | |
| "tokens_per_s": 2364589.5218769177 | |
| }, | |
| { | |
| "step": 14100, | |
| "loss": 3.5545281982421875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015214169123426292, | |
| "tokens_per_s": 2364602.366656633 | |
| }, | |
| { | |
| "step": 14150, | |
| "loss": 3.549293212890625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015183362547206405, | |
| "tokens_per_s": 2364609.642766092 | |
| }, | |
| { | |
| "step": 14200, | |
| "loss": 3.547585754394531, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001515249332018762, | |
| "tokens_per_s": 2364628.2302917093 | |
| }, | |
| { | |
| "step": 14250, | |
| "loss": 3.55408935546875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015121561904673092, | |
| "tokens_per_s": 2364638.7583765243 | |
| }, | |
| { | |
| "step": 14300, | |
| "loss": 3.5476739501953123, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001509056876389733, | |
| "tokens_per_s": 2364647.6045392696 | |
| }, | |
| { | |
| "step": 14350, | |
| "loss": 3.55639404296875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001505951436201925, | |
| "tokens_per_s": 2364651.947412489 | |
| }, | |
| { | |
| "step": 14400, | |
| "loss": 3.55270751953125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0015028399164115232, | |
| "tokens_per_s": 2364654.6101718904 | |
| }, | |
| { | |
| "step": 14450, | |
| "loss": 3.553960876464844, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014997223636172138, | |
| "tokens_per_s": 2364638.398179981 | |
| }, | |
| { | |
| "step": 14500, | |
| "loss": 3.5518014526367185, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001496598824508035, | |
| "tokens_per_s": 2364642.7278394364 | |
| }, | |
| { | |
| "step": 14550, | |
| "loss": 3.5458859252929686, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014934693458626771, | |
| "tokens_per_s": 2364650.165037217 | |
| }, | |
| { | |
| "step": 14600, | |
| "loss": 3.55221435546875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014903339745487819, | |
| "tokens_per_s": 2364655.1400107215 | |
| }, | |
| { | |
| "step": 14650, | |
| "loss": 3.5402435302734374, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014871927575222403, | |
| "tokens_per_s": 2364660.27173962 | |
| }, | |
| { | |
| "step": 14700, | |
| "loss": 3.5534176635742187, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014840457418264913, | |
| "tokens_per_s": 2364665.123181983 | |
| }, | |
| { | |
| "step": 14750, | |
| "loss": 3.5538287353515625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014808929745918139, | |
| "tokens_per_s": 2364671.626147072 | |
| }, | |
| { | |
| "step": 14800, | |
| "loss": 3.5455078125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014777345030346238, | |
| "tokens_per_s": 2364677.4822645457 | |
| }, | |
| { | |
| "step": 14850, | |
| "loss": 3.559847412109375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001474570374456767, | |
| "tokens_per_s": 2364681.430472998 | |
| }, | |
| { | |
| "step": 14900, | |
| "loss": 3.542239074707031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014714006362448076, | |
| "tokens_per_s": 2364683.9050042424 | |
| }, | |
| { | |
| "step": 14950, | |
| "loss": 3.5535177612304687, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014682253358693229, | |
| "tokens_per_s": 2364688.962857593 | |
| }, | |
| { | |
| "step": 15000, | |
| "loss": 3.5480502319335936, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001465044520884189, | |
| "tokens_per_s": 2364692.164302681 | |
| }, | |
| { | |
| "step": 15050, | |
| "loss": 3.5443096923828126, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014618582389258703, | |
| "tokens_per_s": 2364694.8020099634 | |
| }, | |
| { | |
| "step": 15100, | |
| "loss": 3.5397885131835936, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014586665377127048, | |
| "tokens_per_s": 2364699.6622133255 | |
| }, | |
| { | |
| "step": 15150, | |
| "loss": 3.5456619262695312, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014554694650441916, | |
| "tokens_per_s": 2364702.3293950935 | |
| }, | |
| { | |
| "step": 15200, | |
| "loss": 3.5523635864257814, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014522670688002718, | |
| "tokens_per_s": 2364706.279914898 | |
| }, | |
| { | |
| "step": 15250, | |
| "loss": 3.5431146240234375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014490593969406153, | |
| "tokens_per_s": 2364714.814753194 | |
| }, | |
| { | |
| "step": 15300, | |
| "loss": 3.540928955078125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001445846497503899, | |
| "tokens_per_s": 2364719.891805239 | |
| }, | |
| { | |
| "step": 15350, | |
| "loss": 3.5598834228515623, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014426284186070902, | |
| "tokens_per_s": 2364722.977900558 | |
| }, | |
| { | |
| "step": 15400, | |
| "loss": 3.545151672363281, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014394052084447237, | |
| "tokens_per_s": 2364724.957226373 | |
| }, | |
| { | |
| "step": 15450, | |
| "loss": 3.553248291015625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014361769152881822, | |
| "tokens_per_s": 2364730.9915405395 | |
| }, | |
| { | |
| "step": 15500, | |
| "loss": 3.544927673339844, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014329435874849705, | |
| "tokens_per_s": 2364731.7685276284 | |
| }, | |
| { | |
| "step": 15550, | |
| "loss": 3.54208740234375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014297052734579957, | |
| "tokens_per_s": 2364737.0426833895 | |
| }, | |
| { | |
| "step": 15600, | |
| "loss": 3.5472427368164063, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014264620217048366, | |
| "tokens_per_s": 2364742.7890357035 | |
| }, | |
| { | |
| "step": 15650, | |
| "loss": 3.5483197021484374, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014232138807970228, | |
| "tokens_per_s": 2364747.675417071 | |
| }, | |
| { | |
| "step": 15700, | |
| "loss": 3.539051818847656, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014199608993793029, | |
| "tokens_per_s": 2364752.8382272706 | |
| }, | |
| { | |
| "step": 15750, | |
| "loss": 3.535797424316406, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014167031261689196, | |
| "tokens_per_s": 2364755.7397135133 | |
| }, | |
| { | |
| "step": 15800, | |
| "loss": 3.5343276977539064, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014134406099548767, | |
| "tokens_per_s": 2364761.737091763 | |
| }, | |
| { | |
| "step": 15850, | |
| "loss": 3.5437777709960936, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001410173399597211, | |
| "tokens_per_s": 2364766.6664111284 | |
| }, | |
| { | |
| "step": 15900, | |
| "loss": 3.5442266845703125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014069015440262595, | |
| "tokens_per_s": 2364769.12687096 | |
| }, | |
| { | |
| "step": 15950, | |
| "loss": 3.5477496337890626, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001403625092241927, | |
| "tokens_per_s": 2364772.9120278717 | |
| }, | |
| { | |
| "step": 16000, | |
| "loss": 3.5419326782226563, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0014003440933129515, | |
| "tokens_per_s": 2364776.7905186624 | |
| }, | |
| { | |
| "step": 16050, | |
| "loss": 3.5443405151367187, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013970585963761699, | |
| "tokens_per_s": 2364784.5286522578 | |
| }, | |
| { | |
| "step": 16100, | |
| "loss": 3.5306256103515623, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013937686506357828, | |
| "tokens_per_s": 2364789.7690163646 | |
| }, | |
| { | |
| "step": 16150, | |
| "loss": 3.5452001953125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013904743053626159, | |
| "tokens_per_s": 2364794.646068541 | |
| }, | |
| { | |
| "step": 16200, | |
| "loss": 3.523923034667969, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013871756098933839, | |
| "tokens_per_s": 2364797.7097460437 | |
| }, | |
| { | |
| "step": 16250, | |
| "loss": 3.5314926147460937, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013838726136299504, | |
| "tokens_per_s": 2364800.5509233107 | |
| }, | |
| { | |
| "step": 16300, | |
| "loss": 3.5491314697265626, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001380565366038589, | |
| "tokens_per_s": 2364806.742990235 | |
| }, | |
| { | |
| "step": 16350, | |
| "loss": 3.534290466308594, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013772539166492408, | |
| "tokens_per_s": 2364811.4770215373 | |
| }, | |
| { | |
| "step": 16400, | |
| "loss": 3.5383270263671873, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013739383150547753, | |
| "tokens_per_s": 2364813.421591741 | |
| }, | |
| { | |
| "step": 16450, | |
| "loss": 3.533769226074219, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013706186109102448, | |
| "tokens_per_s": 2364818.6985732364 | |
| }, | |
| { | |
| "step": 16500, | |
| "loss": 3.5260491943359376, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013672948539321435, | |
| "tokens_per_s": 2364825.8013639 | |
| }, | |
| { | |
| "step": 16550, | |
| "loss": 3.534014892578125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013639670938976603, | |
| "tokens_per_s": 2364830.800950062 | |
| }, | |
| { | |
| "step": 16600, | |
| "loss": 3.525398864746094, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013606353806439352, | |
| "tokens_per_s": 2364835.3602667865 | |
| }, | |
| { | |
| "step": 16650, | |
| "loss": 3.5152182006835937, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013572997640673126, | |
| "tokens_per_s": 2364841.0701671243 | |
| }, | |
| { | |
| "step": 16700, | |
| "loss": 3.53513916015625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013539602941225932, | |
| "tokens_per_s": 2364845.222233505 | |
| }, | |
| { | |
| "step": 16750, | |
| "loss": 3.539285888671875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013506170208222867, | |
| "tokens_per_s": 2364849.576261172 | |
| }, | |
| { | |
| "step": 16800, | |
| "loss": 3.529910888671875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013472699942358624, | |
| "tokens_per_s": 2364856.2844932037 | |
| }, | |
| { | |
| "step": 16850, | |
| "loss": 3.5255462646484377, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013439192644890002, | |
| "tokens_per_s": 2364863.580830079 | |
| }, | |
| { | |
| "step": 16900, | |
| "loss": 3.52579833984375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001340564881762838, | |
| "tokens_per_s": 2364868.8949673716 | |
| }, | |
| { | |
| "step": 16950, | |
| "loss": 3.527019348144531, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001337206896293222, | |
| "tokens_per_s": 2364872.4108681316 | |
| }, | |
| { | |
| "step": 17000, | |
| "loss": 3.520314025878906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013338453583699545, | |
| "tokens_per_s": 2364880.2561384174 | |
| }, | |
| { | |
| "step": 17050, | |
| "loss": 3.524703369140625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013304803183360387, | |
| "tokens_per_s": 2364886.4261683915 | |
| }, | |
| { | |
| "step": 17100, | |
| "loss": 3.5166552734375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001327111826586927, | |
| "tokens_per_s": 2364892.0794548304 | |
| }, | |
| { | |
| "step": 17150, | |
| "loss": 3.522206115722656, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013237399335697638, | |
| "tokens_per_s": 2364896.21763158 | |
| }, | |
| { | |
| "step": 17200, | |
| "loss": 3.5350634765625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001320364689782634, | |
| "tokens_per_s": 2364876.187711476 | |
| }, | |
| { | |
| "step": 17250, | |
| "loss": 3.517574462890625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013169861457738023, | |
| "tokens_per_s": 2364877.0044874386 | |
| }, | |
| { | |
| "step": 17300, | |
| "loss": 3.5157424926757814, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013136043521409587, | |
| "tokens_per_s": 2364881.3572889385 | |
| }, | |
| { | |
| "step": 17350, | |
| "loss": 3.522073059082031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013102193595304601, | |
| "tokens_per_s": 2364885.004861621 | |
| }, | |
| { | |
| "step": 17400, | |
| "loss": 3.525579528808594, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001306831218636572, | |
| "tokens_per_s": 2364887.674201846 | |
| }, | |
| { | |
| "step": 17450, | |
| "loss": 3.5211441040039064, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013034399802007092, | |
| "tokens_per_s": 2364890.743335755 | |
| }, | |
| { | |
| "step": 17500, | |
| "loss": 3.5405035400390625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0013000456950106759, | |
| "tokens_per_s": 2364893.6569730043 | |
| }, | |
| { | |
| "step": 17550, | |
| "loss": 3.5232278442382814, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012966484138999042, | |
| "tokens_per_s": 2364875.9984877133 | |
| }, | |
| { | |
| "step": 17600, | |
| "loss": 3.5264984130859376, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012932481877466948, | |
| "tokens_per_s": 2364882.018605157 | |
| }, | |
| { | |
| "step": 17650, | |
| "loss": 3.520211486816406, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012898450674734534, | |
| "tokens_per_s": 2364892.7954997197 | |
| }, | |
| { | |
| "step": 17700, | |
| "loss": 3.5328128051757814, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012864391040459287, | |
| "tokens_per_s": 2364894.965392848 | |
| }, | |
| { | |
| "step": 17750, | |
| "loss": 3.535531005859375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012830303484724485, | |
| "tokens_per_s": 2364875.9310452314 | |
| }, | |
| { | |
| "step": 17800, | |
| "loss": 3.511838073730469, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012796188518031573, | |
| "tokens_per_s": 2364878.4317528186 | |
| }, | |
| { | |
| "step": 17850, | |
| "loss": 3.5089761352539064, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012762046651292496, | |
| "tokens_per_s": 2364884.3425136353 | |
| }, | |
| { | |
| "step": 17900, | |
| "loss": 3.5251666259765626, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012727878395822065, | |
| "tokens_per_s": 2364864.279042975 | |
| }, | |
| { | |
| "step": 17950, | |
| "loss": 3.5317181396484374, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012693684263330297, | |
| "tokens_per_s": 2364838.3461269913 | |
| }, | |
| { | |
| "step": 18000, | |
| "loss": 3.530771484375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012659464765914742, | |
| "tokens_per_s": 2364838.2739646314 | |
| }, | |
| { | |
| "step": 18050, | |
| "loss": 3.5215744018554687, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012625220416052816, | |
| "tokens_per_s": 2364843.215823321 | |
| }, | |
| { | |
| "step": 18100, | |
| "loss": 3.5273776245117188, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001259095172659414, | |
| "tokens_per_s": 2364848.9891788065 | |
| }, | |
| { | |
| "step": 18150, | |
| "loss": 3.5221051025390624, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012556659210752848, | |
| "tokens_per_s": 2364860.3669840097 | |
| }, | |
| { | |
| "step": 18200, | |
| "loss": 3.5287545776367186, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001252234338209989, | |
| "tokens_per_s": 2364862.3248299723 | |
| }, | |
| { | |
| "step": 18250, | |
| "loss": 3.519761047363281, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012488004754555367, | |
| "tokens_per_s": 2364866.5893192687 | |
| }, | |
| { | |
| "step": 18300, | |
| "loss": 3.5211480712890624, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012453643842380818, | |
| "tokens_per_s": 2364873.3327986277 | |
| }, | |
| { | |
| "step": 18350, | |
| "loss": 3.517532958984375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001241926116017151, | |
| "tokens_per_s": 2364878.760783681 | |
| }, | |
| { | |
| "step": 18400, | |
| "loss": 3.5208819580078123, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001238485722284875, | |
| "tokens_per_s": 2364861.9926373805 | |
| }, | |
| { | |
| "step": 18450, | |
| "loss": 3.5243911743164062, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012350432545652173, | |
| "tokens_per_s": 2364869.567102641 | |
| }, | |
| { | |
| "step": 18500, | |
| "loss": 3.524724426269531, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012315987644132005, | |
| "tokens_per_s": 2364874.8937843316 | |
| }, | |
| { | |
| "step": 18550, | |
| "loss": 3.524533996582031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001228152303414136, | |
| "tokens_per_s": 2364880.8337788237 | |
| }, | |
| { | |
| "step": 18600, | |
| "loss": 3.5142147827148436, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001224703923182851, | |
| "tokens_per_s": 2364871.7617013757 | |
| }, | |
| { | |
| "step": 18650, | |
| "loss": 3.538498840332031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012212536753629158, | |
| "tokens_per_s": 2364878.177148174 | |
| }, | |
| { | |
| "step": 18700, | |
| "loss": 3.5136566162109375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012178016116258694, | |
| "tokens_per_s": 2364882.0152504235 | |
| }, | |
| { | |
| "step": 18750, | |
| "loss": 3.5139193725585938, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012143477836704466, | |
| "tokens_per_s": 2364888.717880903 | |
| }, | |
| { | |
| "step": 18800, | |
| "loss": 3.5139068603515624, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012108922432218037, | |
| "tokens_per_s": 2364894.0400259187 | |
| }, | |
| { | |
| "step": 18850, | |
| "loss": 3.508048095703125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012074350420307434, | |
| "tokens_per_s": 2364878.480534247 | |
| }, | |
| { | |
| "step": 18900, | |
| "loss": 3.5128903198242187, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012039762318729395, | |
| "tokens_per_s": 2364873.771399023 | |
| }, | |
| { | |
| "step": 18950, | |
| "loss": 3.5089511108398437, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0012005158645481632, | |
| "tokens_per_s": 2364878.406503608 | |
| }, | |
| { | |
| "step": 19000, | |
| "loss": 3.528037414550781, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011970539918795045, | |
| "tokens_per_s": 2364880.7256286745 | |
| }, | |
| { | |
| "step": 19050, | |
| "loss": 3.512792053222656, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011935906657125992, | |
| "tokens_per_s": 2364885.580200913 | |
| }, | |
| { | |
| "step": 19100, | |
| "loss": 3.501037292480469, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00119012593791485, | |
| "tokens_per_s": 2364892.075418113 | |
| }, | |
| { | |
| "step": 19150, | |
| "loss": 3.5131405639648436, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011866598603746514, | |
| "tokens_per_s": 2364894.9923606804 | |
| }, | |
| { | |
| "step": 19200, | |
| "loss": 3.5143804931640625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011831924850006109, | |
| "tokens_per_s": 2364900.506639355 | |
| }, | |
| { | |
| "step": 19250, | |
| "loss": 3.515915832519531, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011797238637207739, | |
| "tokens_per_s": 2364903.186433562 | |
| }, | |
| { | |
| "step": 19300, | |
| "loss": 3.5028890991210937, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001176254048481843, | |
| "tokens_per_s": 2364910.4164202646 | |
| }, | |
| { | |
| "step": 19350, | |
| "loss": 3.5074734497070312, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001172783091248404, | |
| "tokens_per_s": 2364913.232031024 | |
| }, | |
| { | |
| "step": 19400, | |
| "loss": 3.5280422973632812, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011693110440021428, | |
| "tokens_per_s": 2364915.4486076813 | |
| }, | |
| { | |
| "step": 19450, | |
| "loss": 3.505807189941406, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011658379587410723, | |
| "tokens_per_s": 2364920.377835977 | |
| }, | |
| { | |
| "step": 19500, | |
| "loss": 3.5260272216796875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011623638874787483, | |
| "tokens_per_s": 2364926.286275528 | |
| }, | |
| { | |
| "step": 19550, | |
| "loss": 3.5001876831054686, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011588888822434951, | |
| "tokens_per_s": 2364931.083519488 | |
| }, | |
| { | |
| "step": 19600, | |
| "loss": 3.515910949707031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011554129950776231, | |
| "tokens_per_s": 2364937.0383673767 | |
| }, | |
| { | |
| "step": 19650, | |
| "loss": 3.515985412597656, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011519362780366515, | |
| "tokens_per_s": 2364941.28133283 | |
| }, | |
| { | |
| "step": 19700, | |
| "loss": 3.4967575073242188, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001148458783188527, | |
| "tokens_per_s": 2364946.099072952 | |
| }, | |
| { | |
| "step": 19750, | |
| "loss": 3.5081820678710938, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001144980562612846, | |
| "tokens_per_s": 2364952.433675114 | |
| }, | |
| { | |
| "step": 19800, | |
| "loss": 3.4970703125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011415016684000728, | |
| "tokens_per_s": 2364968.1166770984 | |
| }, | |
| { | |
| "step": 19850, | |
| "loss": 3.4941351318359377, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011380221526507595, | |
| "tokens_per_s": 2364983.030660471 | |
| }, | |
| { | |
| "step": 19900, | |
| "loss": 3.5108740234375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011345420674747685, | |
| "tokens_per_s": 2364995.4635757534 | |
| }, | |
| { | |
| "step": 19950, | |
| "loss": 3.5072314453125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011310614649904873, | |
| "tokens_per_s": 2365002.017832295 | |
| }, | |
| { | |
| "step": 20000, | |
| "loss": 3.51745361328125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011275803973240539, | |
| "tokens_per_s": 2365012.4462108077 | |
| }, | |
| { | |
| "step": 20050, | |
| "loss": 3.504329833984375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011240989166085697, | |
| "tokens_per_s": 2365016.182638834 | |
| }, | |
| { | |
| "step": 20100, | |
| "loss": 3.5151690673828124, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011206170749833249, | |
| "tokens_per_s": 2365020.7009266205 | |
| }, | |
| { | |
| "step": 20150, | |
| "loss": 3.4942831420898437, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001117134924593012, | |
| "tokens_per_s": 2365029.626689752 | |
| }, | |
| { | |
| "step": 20200, | |
| "loss": 3.507962646484375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011136525175869502, | |
| "tokens_per_s": 2365032.304347115 | |
| }, | |
| { | |
| "step": 20250, | |
| "loss": 3.51506591796875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0011101699061183, | |
| "tokens_per_s": 2365031.6272615152 | |
| }, | |
| { | |
| "step": 20300, | |
| "loss": 3.5123248291015625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001106687142343285, | |
| "tokens_per_s": 2365041.1432089433 | |
| }, | |
| { | |
| "step": 20350, | |
| "loss": 3.496890869140625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001103204278420409, | |
| "tokens_per_s": 2365053.1443374334 | |
| }, | |
| { | |
| "step": 20400, | |
| "loss": 3.499667053222656, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010997213665096762, | |
| "tokens_per_s": 2365062.1966494224 | |
| }, | |
| { | |
| "step": 20450, | |
| "loss": 3.5097500610351564, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010962384587718088, | |
| "tokens_per_s": 2365071.488692376 | |
| }, | |
| { | |
| "step": 20500, | |
| "loss": 3.513338928222656, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010927556073674681, | |
| "tokens_per_s": 2365081.528281334 | |
| }, | |
| { | |
| "step": 20550, | |
| "loss": 3.4938507080078125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00108927286445647, | |
| "tokens_per_s": 2365098.0389152593 | |
| }, | |
| { | |
| "step": 20600, | |
| "loss": 3.492110595703125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001085790282197006, | |
| "tokens_per_s": 2365082.559409871 | |
| }, | |
| { | |
| "step": 20650, | |
| "loss": 3.4954425048828126, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001082307912744862, | |
| "tokens_per_s": 2365087.6102032447 | |
| }, | |
| { | |
| "step": 20700, | |
| "loss": 3.502156982421875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010788258082526365, | |
| "tokens_per_s": 2365097.360624905 | |
| }, | |
| { | |
| "step": 20750, | |
| "loss": 3.498072204589844, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001075344020868961, | |
| "tokens_per_s": 2365102.8156782715 | |
| }, | |
| { | |
| "step": 20800, | |
| "loss": 3.4985757446289063, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010718626027377163, | |
| "tokens_per_s": 2365104.9833335066 | |
| }, | |
| { | |
| "step": 20850, | |
| "loss": 3.499417724609375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010683816059972543, | |
| "tokens_per_s": 2365107.0221733153 | |
| }, | |
| { | |
| "step": 20900, | |
| "loss": 3.5071295166015624, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010649010827796152, | |
| "tokens_per_s": 2365112.2981638694 | |
| }, | |
| { | |
| "step": 20950, | |
| "loss": 3.510190124511719, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010614210852097493, | |
| "tokens_per_s": 2365117.6746237013 | |
| }, | |
| { | |
| "step": 21000, | |
| "loss": 3.494609680175781, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010579416654047321, | |
| "tokens_per_s": 2365120.380634972 | |
| }, | |
| { | |
| "step": 21050, | |
| "loss": 3.5057772827148437, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010544628754729892, | |
| "tokens_per_s": 2365123.228477729 | |
| }, | |
| { | |
| "step": 21100, | |
| "loss": 3.4850814819335936, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001050984767513511, | |
| "tokens_per_s": 2365127.418225456 | |
| }, | |
| { | |
| "step": 21150, | |
| "loss": 3.4918231201171874, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010475073936150757, | |
| "tokens_per_s": 2365130.3912156676 | |
| }, | |
| { | |
| "step": 21200, | |
| "loss": 3.4890936279296874, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010440308058554677, | |
| "tokens_per_s": 2365135.1113264393 | |
| }, | |
| { | |
| "step": 21250, | |
| "loss": 3.4873672485351563, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010405550563006977, | |
| "tokens_per_s": 2365144.800618524 | |
| }, | |
| { | |
| "step": 21300, | |
| "loss": 3.489290771484375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010370801970042238, | |
| "tokens_per_s": 2365127.8646931723 | |
| }, | |
| { | |
| "step": 21350, | |
| "loss": 3.49572265625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010336062800061715, | |
| "tokens_per_s": 2365131.6374158803 | |
| }, | |
| { | |
| "step": 21400, | |
| "loss": 3.4981134033203123, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010301333573325543, | |
| "tokens_per_s": 2365135.4990275768 | |
| }, | |
| { | |
| "step": 21450, | |
| "loss": 3.4998342895507815, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010266614809944933, | |
| "tokens_per_s": 2365141.128807853 | |
| }, | |
| { | |
| "step": 21500, | |
| "loss": 3.5064056396484373, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001023190702987441, | |
| "tokens_per_s": 2365145.4287326112 | |
| }, | |
| { | |
| "step": 21550, | |
| "loss": 3.492300720214844, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010197210752904006, | |
| "tokens_per_s": 2365149.0967849847 | |
| }, | |
| { | |
| "step": 21600, | |
| "loss": 3.5137738037109374, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010162526498651478, | |
| "tokens_per_s": 2365152.605914789 | |
| }, | |
| { | |
| "step": 21650, | |
| "loss": 3.4962158203125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010127854786554534, | |
| "tokens_per_s": 2365157.377229596 | |
| }, | |
| { | |
| "step": 21700, | |
| "loss": 3.498583984375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001009319613586304, | |
| "tokens_per_s": 2365161.3925709836 | |
| }, | |
| { | |
| "step": 21750, | |
| "loss": 3.4964617919921874, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0010058551065631259, | |
| "tokens_per_s": 2365164.3714531697 | |
| }, | |
| { | |
| "step": 21800, | |
| "loss": 3.5001953125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.001002392009471007, | |
| "tokens_per_s": 2365149.9146819296 | |
| }, | |
| { | |
| "step": 21850, | |
| "loss": 3.4949246215820313, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009989303741739196, | |
| "tokens_per_s": 2365147.552603776 | |
| }, | |
| { | |
| "step": 21900, | |
| "loss": 3.490021057128906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009954702525139434, | |
| "tokens_per_s": 2365149.3507257006 | |
| }, | |
| { | |
| "step": 21950, | |
| "loss": 3.483595886230469, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009920116963104905, | |
| "tokens_per_s": 2365141.1399939028 | |
| }, | |
| { | |
| "step": 22000, | |
| "loss": 3.50059326171875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009885547573595288, | |
| "tokens_per_s": 2365143.0345424507 | |
| }, | |
| { | |
| "step": 22050, | |
| "loss": 3.4934783935546876, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009850994874328045, | |
| "tokens_per_s": 2365146.277819875 | |
| }, | |
| { | |
| "step": 22100, | |
| "loss": 3.48314453125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009816459382770686, | |
| "tokens_per_s": 2365148.940419964 | |
| }, | |
| { | |
| "step": 22150, | |
| "loss": 3.4878802490234375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000978194161613302, | |
| "tokens_per_s": 2365152.5869468143 | |
| }, | |
| { | |
| "step": 22200, | |
| "loss": 3.4946859741210936, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009747442091359414, | |
| "tokens_per_s": 2365155.510589731 | |
| }, | |
| { | |
| "step": 22250, | |
| "loss": 3.4716452026367186, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009712961325121013, | |
| "tokens_per_s": 2365157.9796332642 | |
| }, | |
| { | |
| "step": 22300, | |
| "loss": 3.488453063964844, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009678499833808058, | |
| "tokens_per_s": 2365161.9439956285 | |
| }, | |
| { | |
| "step": 22350, | |
| "loss": 3.499755859375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009644058133522111, | |
| "tokens_per_s": 2365153.1417279434 | |
| }, | |
| { | |
| "step": 22400, | |
| "loss": 3.48358642578125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000960963674006835, | |
| "tokens_per_s": 2365144.7894656383 | |
| }, | |
| { | |
| "step": 22450, | |
| "loss": 3.49045166015625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009575236168947821, | |
| "tokens_per_s": 2365148.0846652514 | |
| }, | |
| { | |
| "step": 22500, | |
| "loss": 3.4919366455078125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009540856935349742, | |
| "tokens_per_s": 2365152.677317971 | |
| }, | |
| { | |
| "step": 22550, | |
| "loss": 3.4869140625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009506499554143771, | |
| "tokens_per_s": 2365140.1160172853 | |
| }, | |
| { | |
| "step": 22600, | |
| "loss": 3.48158447265625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009472164539872306, | |
| "tokens_per_s": 2365145.5019593644 | |
| }, | |
| { | |
| "step": 22650, | |
| "loss": 3.492267761230469, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009437852406742765, | |
| "tokens_per_s": 2365149.032441779 | |
| }, | |
| { | |
| "step": 22700, | |
| "loss": 3.4897137451171876, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009403563668619898, | |
| "tokens_per_s": 2365152.408722476 | |
| }, | |
| { | |
| "step": 22750, | |
| "loss": 3.4833782958984374, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009369298839018095, | |
| "tokens_per_s": 2365157.3672195836 | |
| }, | |
| { | |
| "step": 22800, | |
| "loss": 3.4793621826171877, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009335058431093672, | |
| "tokens_per_s": 2365143.5052113114 | |
| }, | |
| { | |
| "step": 22850, | |
| "loss": 3.482807922363281, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009300842957637219, | |
| "tokens_per_s": 2365150.1001891615 | |
| }, | |
| { | |
| "step": 22900, | |
| "loss": 3.4970632934570314, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009266652931065886, | |
| "tokens_per_s": 2365141.7651429456 | |
| }, | |
| { | |
| "step": 22950, | |
| "loss": 3.4861151123046876, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000923248886341574, | |
| "tokens_per_s": 2365128.26673146 | |
| }, | |
| { | |
| "step": 23000, | |
| "loss": 3.4910540771484375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009198351266334068, | |
| "tokens_per_s": 2365130.112772416 | |
| }, | |
| { | |
| "step": 23050, | |
| "loss": 3.494971923828125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000916424065107175, | |
| "tokens_per_s": 2365132.2450996027 | |
| }, | |
| { | |
| "step": 23100, | |
| "loss": 3.482679443359375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009130157528475551, | |
| "tokens_per_s": 2365135.551045869 | |
| }, | |
| { | |
| "step": 23150, | |
| "loss": 3.4744677734375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009096102408980536, | |
| "tokens_per_s": 2365140.688764926 | |
| }, | |
| { | |
| "step": 23200, | |
| "loss": 3.4877804565429686, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0009062075802602356, | |
| "tokens_per_s": 2365143.9424045538 | |
| }, | |
| { | |
| "step": 23250, | |
| "loss": 3.4820846557617187, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000902807821892968, | |
| "tokens_per_s": 2365146.369787122 | |
| }, | |
| { | |
| "step": 23300, | |
| "loss": 3.4879183959960938, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008994110167116493, | |
| "tokens_per_s": 2365151.2905520666 | |
| }, | |
| { | |
| "step": 23350, | |
| "loss": 3.473363037109375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008960172155874529, | |
| "tokens_per_s": 2365154.7562719556 | |
| }, | |
| { | |
| "step": 23400, | |
| "loss": 3.4754608154296873, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008926264693465616, | |
| "tokens_per_s": 2365157.3688098737 | |
| }, | |
| { | |
| "step": 23450, | |
| "loss": 3.4725552368164063, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008892388287694093, | |
| "tokens_per_s": 2365163.031946918 | |
| }, | |
| { | |
| "step": 23500, | |
| "loss": 3.47448486328125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008858543445899165, | |
| "tokens_per_s": 2365167.443606251 | |
| }, | |
| { | |
| "step": 23550, | |
| "loss": 3.477320556640625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008824730674947352, | |
| "tokens_per_s": 2365172.0301208515 | |
| }, | |
| { | |
| "step": 23600, | |
| "loss": 3.481239929199219, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008790950481224862, | |
| "tokens_per_s": 2365176.0050831535 | |
| }, | |
| { | |
| "step": 23650, | |
| "loss": 3.4881295776367187, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008757203370630027, | |
| "tokens_per_s": 2365179.826716569 | |
| }, | |
| { | |
| "step": 23700, | |
| "loss": 3.467179260253906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008723489848565711, | |
| "tokens_per_s": 2365184.512691456 | |
| }, | |
| { | |
| "step": 23750, | |
| "loss": 3.47642822265625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008689810419931765, | |
| "tokens_per_s": 2365188.737938442 | |
| }, | |
| { | |
| "step": 23800, | |
| "loss": 3.484112548828125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008656165589117438, | |
| "tokens_per_s": 2365191.8543415726 | |
| }, | |
| { | |
| "step": 23850, | |
| "loss": 3.4794451904296877, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008622555859993841, | |
| "tokens_per_s": 2365197.1034725895 | |
| }, | |
| { | |
| "step": 23900, | |
| "loss": 3.4725830078125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008588981735906391, | |
| "tokens_per_s": 2365200.025864046 | |
| }, | |
| { | |
| "step": 23950, | |
| "loss": 3.476612854003906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008555443719667287, | |
| "tokens_per_s": 2365203.382463012 | |
| }, | |
| { | |
| "step": 24000, | |
| "loss": 3.465234680175781, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008521942313547959, | |
| "tokens_per_s": 2365190.6350007704 | |
| }, | |
| { | |
| "step": 24050, | |
| "loss": 3.4822317504882814, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008488478019271566, | |
| "tokens_per_s": 2365194.6097968807 | |
| }, | |
| { | |
| "step": 24100, | |
| "loss": 3.479034423828125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008455051338005468, | |
| "tokens_per_s": 2365198.01189677 | |
| }, | |
| { | |
| "step": 24150, | |
| "loss": 3.479100646972656, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008421662770353726, | |
| "tokens_per_s": 2365202.2100466276 | |
| }, | |
| { | |
| "step": 24200, | |
| "loss": 3.466640625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008388312816349609, | |
| "tokens_per_s": 2365207.303601703 | |
| }, | |
| { | |
| "step": 24250, | |
| "loss": 3.4698468017578126, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008355001975448098, | |
| "tokens_per_s": 2365211.1810901063 | |
| }, | |
| { | |
| "step": 24300, | |
| "loss": 3.4776907348632813, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008321730746518408, | |
| "tokens_per_s": 2365214.3949524914 | |
| }, | |
| { | |
| "step": 24350, | |
| "loss": 3.486700134277344, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008288499627836516, | |
| "tokens_per_s": 2365218.434770441 | |
| }, | |
| { | |
| "step": 24400, | |
| "loss": 3.4796820068359375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008255309117077709, | |
| "tokens_per_s": 2365219.6232457757 | |
| }, | |
| { | |
| "step": 24450, | |
| "loss": 3.4615213012695314, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008222159711309114, | |
| "tokens_per_s": 2365206.9105389877 | |
| }, | |
| { | |
| "step": 24500, | |
| "loss": 3.4822769165039062, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008189051906982268, | |
| "tokens_per_s": 2365208.869711499 | |
| }, | |
| { | |
| "step": 24550, | |
| "loss": 3.475203552246094, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008155986199925671, | |
| "tokens_per_s": 2365213.4018265144 | |
| }, | |
| { | |
| "step": 24600, | |
| "loss": 3.478824462890625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008122963085337372, | |
| "tokens_per_s": 2365217.5228399565 | |
| }, | |
| { | |
| "step": 24650, | |
| "loss": 3.481581726074219, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008089983057777541, | |
| "tokens_per_s": 2365219.503623977 | |
| }, | |
| { | |
| "step": 24700, | |
| "loss": 3.4629388427734376, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008057046611161083, | |
| "tokens_per_s": 2365221.800483434 | |
| }, | |
| { | |
| "step": 24750, | |
| "loss": 3.4691983032226563, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0008024154238750207, | |
| "tokens_per_s": 2365223.719677372 | |
| }, | |
| { | |
| "step": 24800, | |
| "loss": 3.489212951660156, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007991306433147074, | |
| "tokens_per_s": 2365225.856538691 | |
| }, | |
| { | |
| "step": 24850, | |
| "loss": 3.4727203369140627, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007958503686286401, | |
| "tokens_per_s": 2365229.41749611 | |
| }, | |
| { | |
| "step": 24900, | |
| "loss": 3.4637997436523436, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007925746489428092, | |
| "tokens_per_s": 2365232.218739163 | |
| }, | |
| { | |
| "step": 24950, | |
| "loss": 3.4632748413085936, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007893035333149887, | |
| "tokens_per_s": 2365234.591115606 | |
| }, | |
| { | |
| "step": 25000, | |
| "loss": 3.4773428344726565, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007860370707340018, | |
| "tokens_per_s": 2365235.852280143 | |
| }, | |
| { | |
| "step": 25050, | |
| "loss": 3.4731619262695315, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007827753101189872, | |
| "tokens_per_s": 2365239.757032862 | |
| }, | |
| { | |
| "step": 25100, | |
| "loss": 3.4758746337890627, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007795183003186648, | |
| "tokens_per_s": 2365242.872154514 | |
| }, | |
| { | |
| "step": 25150, | |
| "loss": 3.4547137451171874, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007762660901106062, | |
| "tokens_per_s": 2365246.76039611 | |
| }, | |
| { | |
| "step": 25200, | |
| "loss": 3.4731298828125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007730187282005037, | |
| "tokens_per_s": 2365248.4461532314 | |
| }, | |
| { | |
| "step": 25250, | |
| "loss": 3.4768878173828126, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007697762632214402, | |
| "tokens_per_s": 2365251.0849537286 | |
| }, | |
| { | |
| "step": 25300, | |
| "loss": 3.4557916259765626, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007665387437331616, | |
| "tokens_per_s": 2365236.4544062093 | |
| }, | |
| { | |
| "step": 25350, | |
| "loss": 3.4727288818359376, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007633062182213488, | |
| "tokens_per_s": 2365224.443332569 | |
| }, | |
| { | |
| "step": 25400, | |
| "loss": 3.4774163818359374, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007600787350968919, | |
| "tokens_per_s": 2365225.876604572 | |
| }, | |
| { | |
| "step": 25450, | |
| "loss": 3.467467956542969, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007568563426951658, | |
| "tokens_per_s": 2365228.7351478273 | |
| }, | |
| { | |
| "step": 25500, | |
| "loss": 3.475078430175781, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007536390892753062, | |
| "tokens_per_s": 2365231.0770130996 | |
| }, | |
| { | |
| "step": 25550, | |
| "loss": 3.4518896484375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007504270230194852, | |
| "tokens_per_s": 2365234.623671811 | |
| }, | |
| { | |
| "step": 25600, | |
| "loss": 3.46828125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007472201920321915, | |
| "tokens_per_s": 2365236.603577883 | |
| }, | |
| { | |
| "step": 25650, | |
| "loss": 3.478263244628906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007440186443395101, | |
| "tokens_per_s": 2365238.662519482 | |
| }, | |
| { | |
| "step": 25700, | |
| "loss": 3.4622412109375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007408224278884019, | |
| "tokens_per_s": 2365240.122157951 | |
| }, | |
| { | |
| "step": 25750, | |
| "loss": 3.461891784667969, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000737631590545986, | |
| "tokens_per_s": 2365243.183229396 | |
| }, | |
| { | |
| "step": 25800, | |
| "loss": 3.483406982421875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007344461800988234, | |
| "tokens_per_s": 2365231.638851225 | |
| }, | |
| { | |
| "step": 25850, | |
| "loss": 3.4675137329101564, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007312662442522002, | |
| "tokens_per_s": 2365233.2946512997 | |
| }, | |
| { | |
| "step": 25900, | |
| "loss": 3.4667648315429687, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007280918306294153, | |
| "tokens_per_s": 2365236.327059724 | |
| }, | |
| { | |
| "step": 25950, | |
| "loss": 3.4637802124023436, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007249229867710643, | |
| "tokens_per_s": 2365223.8274475755 | |
| }, | |
| { | |
| "step": 26000, | |
| "loss": 3.457705383300781, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007217597601343297, | |
| "tokens_per_s": 2365227.4268360236 | |
| }, | |
| { | |
| "step": 26050, | |
| "loss": 3.471446533203125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000718602198092269, | |
| "tokens_per_s": 2365228.94674958 | |
| }, | |
| { | |
| "step": 26100, | |
| "loss": 3.4567535400390623, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007154503479331064, | |
| "tokens_per_s": 2365230.0480834157 | |
| }, | |
| { | |
| "step": 26150, | |
| "loss": 3.461361999511719, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007123042568595242, | |
| "tokens_per_s": 2365234.14936976 | |
| }, | |
| { | |
| "step": 26200, | |
| "loss": 3.4673977661132813, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007091639719879534, | |
| "tokens_per_s": 2365236.3644859795 | |
| }, | |
| { | |
| "step": 26250, | |
| "loss": 3.45150390625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007060295403478727, | |
| "tokens_per_s": 2365240.7131193383 | |
| }, | |
| { | |
| "step": 26300, | |
| "loss": 3.457644348144531, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0007029010088811005, | |
| "tokens_per_s": 2365242.313031177 | |
| }, | |
| { | |
| "step": 26350, | |
| "loss": 3.455341796875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006997784244410948, | |
| "tokens_per_s": 2365245.1086983676 | |
| }, | |
| { | |
| "step": 26400, | |
| "loss": 3.4632437133789065, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006966618337922463, | |
| "tokens_per_s": 2365247.2914367886 | |
| }, | |
| { | |
| "step": 26450, | |
| "loss": 3.4476272583007814, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006935512836091851, | |
| "tokens_per_s": 2365249.5038871286 | |
| }, | |
| { | |
| "step": 26500, | |
| "loss": 3.454140319824219, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006904468204760769, | |
| "tokens_per_s": 2365253.865601436 | |
| }, | |
| { | |
| "step": 26550, | |
| "loss": 3.454395446777344, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006873484908859264, | |
| "tokens_per_s": 2365258.8262051116 | |
| }, | |
| { | |
| "step": 26600, | |
| "loss": 3.451828918457031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000684256341239881, | |
| "tokens_per_s": 2365262.400121207 | |
| }, | |
| { | |
| "step": 26650, | |
| "loss": 3.4538909912109377, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000681170417846537, | |
| "tokens_per_s": 2365255.5010455353 | |
| }, | |
| { | |
| "step": 26700, | |
| "loss": 3.4567965698242187, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006780907669212453, | |
| "tokens_per_s": 2365259.211098993 | |
| }, | |
| { | |
| "step": 26750, | |
| "loss": 3.4562948608398436, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006750174345854181, | |
| "tokens_per_s": 2365247.951238871 | |
| }, | |
| { | |
| "step": 26800, | |
| "loss": 3.458800964355469, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006719504668658394, | |
| "tokens_per_s": 2365250.067749467 | |
| }, | |
| { | |
| "step": 26850, | |
| "loss": 3.459291687011719, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006688899096939767, | |
| "tokens_per_s": 2365239.5097178 | |
| }, | |
| { | |
| "step": 26900, | |
| "loss": 3.461752624511719, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006658358089052914, | |
| "tokens_per_s": 2365242.560098736 | |
| }, | |
| { | |
| "step": 26950, | |
| "loss": 3.4553628540039063, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006627882102385522, | |
| "tokens_per_s": 2365244.5328467973 | |
| }, | |
| { | |
| "step": 27000, | |
| "loss": 3.453165283203125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006597471593351514, | |
| "tokens_per_s": 2365247.4098729575 | |
| }, | |
| { | |
| "step": 27050, | |
| "loss": 3.4544491577148437, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000656712701738421, | |
| "tokens_per_s": 2365251.095881621 | |
| }, | |
| { | |
| "step": 27100, | |
| "loss": 3.454961853027344, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006536848828929505, | |
| "tokens_per_s": 2365252.911800632 | |
| }, | |
| { | |
| "step": 27150, | |
| "loss": 3.4570046997070314, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000650663748143906, | |
| "tokens_per_s": 2365256.1873084637 | |
| }, | |
| { | |
| "step": 27200, | |
| "loss": 3.45305419921875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006476493427363508, | |
| "tokens_per_s": 2365258.649653059 | |
| }, | |
| { | |
| "step": 27250, | |
| "loss": 3.4566030883789063, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006446417118145694, | |
| "tokens_per_s": 2365262.6156520634 | |
| }, | |
| { | |
| "step": 27300, | |
| "loss": 3.445639953613281, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006416409004213899, | |
| "tokens_per_s": 2365263.384279411 | |
| }, | |
| { | |
| "step": 27350, | |
| "loss": 3.4549441528320313, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006386469534975099, | |
| "tokens_per_s": 2365266.1503813923 | |
| }, | |
| { | |
| "step": 27400, | |
| "loss": 3.449703369140625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006356599158808229, | |
| "tokens_per_s": 2365268.4666582914 | |
| }, | |
| { | |
| "step": 27450, | |
| "loss": 3.435882873535156, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006326798323057483, | |
| "tokens_per_s": 2365270.653892986 | |
| }, | |
| { | |
| "step": 27500, | |
| "loss": 3.4410018920898438, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006297067474025606, | |
| "tokens_per_s": 2365275.313993377 | |
| }, | |
| { | |
| "step": 27550, | |
| "loss": 3.4477825927734376, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006267407056967196, | |
| "tokens_per_s": 2365277.07800456 | |
| }, | |
| { | |
| "step": 27600, | |
| "loss": 3.435632629394531, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006237817516082063, | |
| "tokens_per_s": 2365280.3547162055 | |
| }, | |
| { | |
| "step": 27650, | |
| "loss": 3.439797668457031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006208299294508554, | |
| "tokens_per_s": 2365283.635289479 | |
| }, | |
| { | |
| "step": 27700, | |
| "loss": 3.4449847412109373, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000617885283431693, | |
| "tokens_per_s": 2365287.1342547503 | |
| }, | |
| { | |
| "step": 27750, | |
| "loss": 3.442242431640625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006149478576502734, | |
| "tokens_per_s": 2365275.7435630686 | |
| }, | |
| { | |
| "step": 27800, | |
| "loss": 3.434183349609375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006120176960980203, | |
| "tokens_per_s": 2365278.147890627 | |
| }, | |
| { | |
| "step": 27850, | |
| "loss": 3.4394717407226563, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006090948426575662, | |
| "tokens_per_s": 2365281.8522150978 | |
| }, | |
| { | |
| "step": 27900, | |
| "loss": 3.4407919311523436, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006061793411020957, | |
| "tokens_per_s": 2365284.468483177 | |
| }, | |
| { | |
| "step": 27950, | |
| "loss": 3.4380401611328124, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006032712350946912, | |
| "tokens_per_s": 2365274.3398675546 | |
| }, | |
| { | |
| "step": 28000, | |
| "loss": 3.4359490966796873, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0006003705681876778, | |
| "tokens_per_s": 2365278.807450492 | |
| }, | |
| { | |
| "step": 28050, | |
| "loss": 3.4584530639648436, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005974773838219707, | |
| "tokens_per_s": 2365280.2822568975 | |
| }, | |
| { | |
| "step": 28100, | |
| "loss": 3.4535870361328125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005945917253264253, | |
| "tokens_per_s": 2365284.5949464077 | |
| }, | |
| { | |
| "step": 28150, | |
| "loss": 3.4370379638671875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005917136359171888, | |
| "tokens_per_s": 2365287.332537631 | |
| }, | |
| { | |
| "step": 28200, | |
| "loss": 3.434856262207031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005888431586970522, | |
| "tokens_per_s": 2365290.7022936638 | |
| }, | |
| { | |
| "step": 28250, | |
| "loss": 3.4362640380859375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005859803366548047, | |
| "tokens_per_s": 2365295.5202712067 | |
| }, | |
| { | |
| "step": 28300, | |
| "loss": 3.435060729980469, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005831252126645896, | |
| "tokens_per_s": 2365283.9726290028 | |
| }, | |
| { | |
| "step": 28350, | |
| "loss": 3.4427362060546876, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005802778294852639, | |
| "tokens_per_s": 2365287.0988236405 | |
| }, | |
| { | |
| "step": 28400, | |
| "loss": 3.4515997314453126, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005774382297597568, | |
| "tokens_per_s": 2365290.964118875 | |
| }, | |
| { | |
| "step": 28450, | |
| "loss": 3.4294314575195313, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005746064560144302, | |
| "tokens_per_s": 2365294.799624686 | |
| }, | |
| { | |
| "step": 28500, | |
| "loss": 3.4461099243164064, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005717825506584426, | |
| "tokens_per_s": 2365297.4114454454 | |
| }, | |
| { | |
| "step": 28550, | |
| "loss": 3.449992980957031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005689665559831152, | |
| "tokens_per_s": 2365300.685197197 | |
| }, | |
| { | |
| "step": 28600, | |
| "loss": 3.4374554443359373, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005661585141612969, | |
| "tokens_per_s": 2365302.7908391403 | |
| }, | |
| { | |
| "step": 28650, | |
| "loss": 3.433175354003906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005633584672467328, | |
| "tokens_per_s": 2365306.595070594 | |
| }, | |
| { | |
| "step": 28700, | |
| "loss": 3.427209777832031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005605664571734348, | |
| "tokens_per_s": 2365310.4645412983 | |
| }, | |
| { | |
| "step": 28750, | |
| "loss": 3.430868835449219, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005577825257550546, | |
| "tokens_per_s": 2365314.0874154265 | |
| }, | |
| { | |
| "step": 28800, | |
| "loss": 3.436483154296875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005550067146842555, | |
| "tokens_per_s": 2365316.835524559 | |
| }, | |
| { | |
| "step": 28850, | |
| "loss": 3.4284188842773435, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005522390655320895, | |
| "tokens_per_s": 2365319.755661954 | |
| }, | |
| { | |
| "step": 28900, | |
| "loss": 3.433955078125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005494796197473733, | |
| "tokens_per_s": 2365322.926754039 | |
| }, | |
| { | |
| "step": 28950, | |
| "loss": 3.427716064453125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005467284186560699, | |
| "tokens_per_s": 2365325.788802636 | |
| }, | |
| { | |
| "step": 29000, | |
| "loss": 3.4444024658203123, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005439855034606678, | |
| "tokens_per_s": 2365326.8058830486 | |
| }, | |
| { | |
| "step": 29050, | |
| "loss": 3.43893310546875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005412509152395637, | |
| "tokens_per_s": 2365330.933124212 | |
| }, | |
| { | |
| "step": 29100, | |
| "loss": 3.4416094970703126, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005385246949464484, | |
| "tokens_per_s": 2365332.8984414954 | |
| }, | |
| { | |
| "step": 29150, | |
| "loss": 3.435738220214844, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005358068834096933, | |
| "tokens_per_s": 2365335.6921194037 | |
| }, | |
| { | |
| "step": 29200, | |
| "loss": 3.4339947509765625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005330975213317392, | |
| "tokens_per_s": 2365339.6993274484 | |
| }, | |
| { | |
| "step": 29250, | |
| "loss": 3.4332470703125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005303966492884853, | |
| "tokens_per_s": 2365341.8529927954 | |
| }, | |
| { | |
| "step": 29300, | |
| "loss": 3.4290481567382813, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005277043077286825, | |
| "tokens_per_s": 2365344.1197218504 | |
| }, | |
| { | |
| "step": 29350, | |
| "loss": 3.4365884399414064, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005250205369733283, | |
| "tokens_per_s": 2365345.978356059 | |
| }, | |
| { | |
| "step": 29400, | |
| "loss": 3.42076904296875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005223453772150625, | |
| "tokens_per_s": 2365348.8054492376 | |
| }, | |
| { | |
| "step": 29450, | |
| "loss": 3.438873596191406, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000519678868517564, | |
| "tokens_per_s": 2365350.8424218576 | |
| }, | |
| { | |
| "step": 29500, | |
| "loss": 3.434095458984375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005170210508149522, | |
| "tokens_per_s": 2365351.0399348345 | |
| }, | |
| { | |
| "step": 29550, | |
| "loss": 3.418112487792969, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000514371963911189, | |
| "tokens_per_s": 2365352.3967214003 | |
| }, | |
| { | |
| "step": 29600, | |
| "loss": 3.426996765136719, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005117316474794824, | |
| "tokens_per_s": 2365354.3448799383 | |
| }, | |
| { | |
| "step": 29650, | |
| "loss": 3.423758239746094, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005091001410616916, | |
| "tokens_per_s": 2365356.134530006 | |
| }, | |
| { | |
| "step": 29700, | |
| "loss": 3.43627197265625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005064774840677351, | |
| "tokens_per_s": 2365359.6561459806 | |
| }, | |
| { | |
| "step": 29750, | |
| "loss": 3.4352191162109373, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005038637157750021, | |
| "tokens_per_s": 2365362.716202364 | |
| }, | |
| { | |
| "step": 29800, | |
| "loss": 3.4254525756835936, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0005012588753277619, | |
| "tokens_per_s": 2365365.7678193958 | |
| }, | |
| { | |
| "step": 29850, | |
| "loss": 3.4219461059570313, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004986630017365794, | |
| "tokens_per_s": 2365369.1438012444 | |
| }, | |
| { | |
| "step": 29900, | |
| "loss": 3.430557861328125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004960761338777296, | |
| "tokens_per_s": 2365371.8822113373 | |
| }, | |
| { | |
| "step": 29950, | |
| "loss": 3.4279446411132812, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004934983104926167, | |
| "tokens_per_s": 2365374.612390621 | |
| }, | |
| { | |
| "step": 30000, | |
| "loss": 3.4206924438476562, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004909295701871927, | |
| "tokens_per_s": 2365377.057558681 | |
| }, | |
| { | |
| "step": 30050, | |
| "loss": 3.435638427734375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004883699514313802, | |
| "tokens_per_s": 2365380.1565981065 | |
| }, | |
| { | |
| "step": 30100, | |
| "loss": 3.4259246826171874, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00048581949255849504, | |
| "tokens_per_s": 2365383.4563346803 | |
| }, | |
| { | |
| "step": 30150, | |
| "loss": 3.4144888305664063, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00048327823176467415, | |
| "tokens_per_s": 2365385.666754282 | |
| }, | |
| { | |
| "step": 30200, | |
| "loss": 3.4328179931640626, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00048074620710830115, | |
| "tokens_per_s": 2365385.963796792 | |
| }, | |
| { | |
| "step": 30250, | |
| "loss": 3.4339981079101562, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00047822345650943865, | |
| "tokens_per_s": 2365388.143031404 | |
| }, | |
| { | |
| "step": 30300, | |
| "loss": 3.410023193359375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00047571001774925813, | |
| "tokens_per_s": 2365376.930729186 | |
| }, | |
| { | |
| "step": 30350, | |
| "loss": 3.4362933349609377, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004732059284694767, | |
| "tokens_per_s": 2365380.1683508633 | |
| }, | |
| { | |
| "step": 30400, | |
| "loss": 3.424769287109375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004707112261717904, | |
| "tokens_per_s": 2365382.646316782 | |
| }, | |
| { | |
| "step": 30450, | |
| "loss": 3.423951416015625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004682259482173155, | |
| "tokens_per_s": 2365386.5270509073 | |
| }, | |
| { | |
| "step": 30500, | |
| "loss": 3.41597412109375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004657501318260265, | |
| "tokens_per_s": 2365375.479027562 | |
| }, | |
| { | |
| "step": 30550, | |
| "loss": 3.42817138671875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004632838140762009, | |
| "tokens_per_s": 2365379.533772811 | |
| }, | |
| { | |
| "step": 30600, | |
| "loss": 3.4227261352539062, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00046082703190386136, | |
| "tokens_per_s": 2365382.367307293 | |
| }, | |
| { | |
| "step": 30650, | |
| "loss": 3.432532958984375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004583798221022258, | |
| "tokens_per_s": 2365372.645494427 | |
| }, | |
| { | |
| "step": 30700, | |
| "loss": 3.422876892089844, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004559422213211527, | |
| "tokens_per_s": 2365374.9143465045 | |
| }, | |
| { | |
| "step": 30750, | |
| "loss": 3.429842224121094, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00045351426606659575, | |
| "tokens_per_s": 2365377.198771639 | |
| }, | |
| { | |
| "step": 30800, | |
| "loss": 3.426011047363281, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004510959927000542, | |
| "tokens_per_s": 2365380.8257067315 | |
| }, | |
| { | |
| "step": 30850, | |
| "loss": 3.4385476684570313, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004486874374380303, | |
| "tokens_per_s": 2365383.80221564 | |
| }, | |
| { | |
| "step": 30900, | |
| "loss": 3.4263156127929686, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004462886363514864, | |
| "tokens_per_s": 2365386.7664643764 | |
| }, | |
| { | |
| "step": 30950, | |
| "loss": 3.425262145996094, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00044389962536530385, | |
| "tokens_per_s": 2365389.9903473225 | |
| }, | |
| { | |
| "step": 31000, | |
| "loss": 3.4152154541015625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004415204402577458, | |
| "tokens_per_s": 2365393.2222243734 | |
| }, | |
| { | |
| "step": 31050, | |
| "loss": 3.4245263671875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004391511166599216, | |
| "tokens_per_s": 2365397.6586566092 | |
| }, | |
| { | |
| "step": 31100, | |
| "loss": 3.4314215087890627, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00043679169005525324, | |
| "tokens_per_s": 2365400.935029378 | |
| }, | |
| { | |
| "step": 31150, | |
| "loss": 3.424627380371094, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00043444219577894194, | |
| "tokens_per_s": 2365403.282577406 | |
| }, | |
| { | |
| "step": 31200, | |
| "loss": 3.4311758422851564, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004321026690174421, | |
| "tokens_per_s": 2365407.0518071144 | |
| }, | |
| { | |
| "step": 31250, | |
| "loss": 3.4163107299804687, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004297731448079325, | |
| "tokens_per_s": 2365410.1437283605 | |
| }, | |
| { | |
| "step": 31300, | |
| "loss": 3.435802001953125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00042745365803779196, | |
| "tokens_per_s": 2365413.694879874 | |
| }, | |
| { | |
| "step": 31350, | |
| "loss": 3.435652770996094, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004251442434440755, | |
| "tokens_per_s": 2365415.800219311 | |
| }, | |
| { | |
| "step": 31400, | |
| "loss": 3.420720520019531, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004228449356129971, | |
| "tokens_per_s": 2365417.6257259157 | |
| }, | |
| { | |
| "step": 31450, | |
| "loss": 3.404501647949219, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00042055576897940915, | |
| "tokens_per_s": 2365419.8915852746 | |
| }, | |
| { | |
| "step": 31500, | |
| "loss": 3.4316314697265624, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00041827677782628844, | |
| "tokens_per_s": 2365424.1448613205 | |
| }, | |
| { | |
| "step": 31550, | |
| "loss": 3.420281982421875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004160079962842201, | |
| "tokens_per_s": 2365426.9910851084 | |
| }, | |
| { | |
| "step": 31600, | |
| "loss": 3.4292361450195314, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00041374945833089, | |
| "tokens_per_s": 2365429.9932134454 | |
| }, | |
| { | |
| "step": 31650, | |
| "loss": 3.418418273925781, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00041150119779057395, | |
| "tokens_per_s": 2365433.3383065485 | |
| }, | |
| { | |
| "step": 31700, | |
| "loss": 3.419227294921875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004092632483336306, | |
| "tokens_per_s": 2365436.788440287 | |
| }, | |
| { | |
| "step": 31750, | |
| "loss": 3.4287643432617188, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004070356434759982, | |
| "tokens_per_s": 2365440.869694058 | |
| }, | |
| { | |
| "step": 31800, | |
| "loss": 3.4237051391601563, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004048184165786928, | |
| "tokens_per_s": 2365442.4083917057 | |
| }, | |
| { | |
| "step": 31850, | |
| "loss": 3.415086364746094, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004026116008473081, | |
| "tokens_per_s": 2365443.3593915086 | |
| }, | |
| { | |
| "step": 31900, | |
| "loss": 3.4280099487304687, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0004004152293315178, | |
| "tokens_per_s": 2365446.2761917897 | |
| }, | |
| { | |
| "step": 31950, | |
| "loss": 3.413166809082031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00039822933492458156, | |
| "tokens_per_s": 2365447.7643827884 | |
| }, | |
| { | |
| "step": 32000, | |
| "loss": 3.428000183105469, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00039605395036285183, | |
| "tokens_per_s": 2365450.3445924153 | |
| }, | |
| { | |
| "step": 32050, | |
| "loss": 3.4238455200195315, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00039388910822528417, | |
| "tokens_per_s": 2365453.7966203475 | |
| }, | |
| { | |
| "step": 32100, | |
| "loss": 3.4179556274414065, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000391734840932948, | |
| "tokens_per_s": 2365455.4690770484 | |
| }, | |
| { | |
| "step": 32150, | |
| "loss": 3.4269732666015624, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003895911807485424, | |
| "tokens_per_s": 2365456.6914379355 | |
| }, | |
| { | |
| "step": 32200, | |
| "loss": 3.4116946411132814, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00038745815977591237, | |
| "tokens_per_s": 2365447.4598378465 | |
| }, | |
| { | |
| "step": 32250, | |
| "loss": 3.40714599609375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00038533580995956876, | |
| "tokens_per_s": 2365449.354825701 | |
| }, | |
| { | |
| "step": 32300, | |
| "loss": 3.4080770874023436, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000383224163084208, | |
| "tokens_per_s": 2365438.4885577243 | |
| }, | |
| { | |
| "step": 32350, | |
| "loss": 3.4089889526367188, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003811232507742387, | |
| "tokens_per_s": 2365432.010216321 | |
| }, | |
| { | |
| "step": 32400, | |
| "loss": 3.400970458984375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00037903310449330537, | |
| "tokens_per_s": 2365434.525887477 | |
| }, | |
| { | |
| "step": 32450, | |
| "loss": 3.415177917480469, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003769537555438197, | |
| "tokens_per_s": 2365435.659629381 | |
| }, | |
| { | |
| "step": 32500, | |
| "loss": 3.424596862792969, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003748852350664894, | |
| "tokens_per_s": 2365438.6947474713 | |
| }, | |
| { | |
| "step": 32550, | |
| "loss": 3.4213604736328125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003728275740398542, | |
| "tokens_per_s": 2365440.7941749534 | |
| }, | |
| { | |
| "step": 32600, | |
| "loss": 3.425797119140625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003707808032798197, | |
| "tokens_per_s": 2365442.8372136545 | |
| }, | |
| { | |
| "step": 32650, | |
| "loss": 3.418845520019531, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00036874495343919777, | |
| "tokens_per_s": 2365432.2022077455 | |
| }, | |
| { | |
| "step": 32700, | |
| "loss": 3.4159307861328125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00036672005500724557, | |
| "tokens_per_s": 2365434.0031243567 | |
| }, | |
| { | |
| "step": 32750, | |
| "loss": 3.410948486328125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00036470613830921116, | |
| "tokens_per_s": 2365437.1410783916 | |
| }, | |
| { | |
| "step": 32800, | |
| "loss": 3.407222900390625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003627032335058771, | |
| "tokens_per_s": 2365439.9012524253 | |
| }, | |
| { | |
| "step": 32850, | |
| "loss": 3.4310650634765625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003607113705931107, | |
| "tokens_per_s": 2365441.819388896 | |
| }, | |
| { | |
| "step": 32900, | |
| "loss": 3.423568115234375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00035873057940141295, | |
| "tokens_per_s": 2365435.1984340656 | |
| }, | |
| { | |
| "step": 32950, | |
| "loss": 3.413141784667969, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003567608895954738, | |
| "tokens_per_s": 2365437.37569435 | |
| }, | |
| { | |
| "step": 33000, | |
| "loss": 3.411988525390625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00035480233067372596, | |
| "tokens_per_s": 2365440.989758715 | |
| }, | |
| { | |
| "step": 33050, | |
| "loss": 3.4133740234375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00035285493196790426, | |
| "tokens_per_s": 2365444.539520434 | |
| }, | |
| { | |
| "step": 33100, | |
| "loss": 3.4060800170898435, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00035091872264260616, | |
| "tokens_per_s": 2365445.794135327 | |
| }, | |
| { | |
| "step": 33150, | |
| "loss": 3.403880310058594, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003489937316948552, | |
| "tokens_per_s": 2365448.219029327 | |
| }, | |
| { | |
| "step": 33200, | |
| "loss": 3.4084408569335936, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000347079987953666, | |
| "tokens_per_s": 2365451.2513857204 | |
| }, | |
| { | |
| "step": 33250, | |
| "loss": 3.401578063964844, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00034517752007961295, | |
| "tokens_per_s": 2365452.876352152 | |
| }, | |
| { | |
| "step": 33300, | |
| "loss": 3.420890197753906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00034328635656440137, | |
| "tokens_per_s": 2365455.03274357 | |
| }, | |
| { | |
| "step": 33350, | |
| "loss": 3.415999450683594, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003414065257304405, | |
| "tokens_per_s": 2365457.123263433 | |
| }, | |
| { | |
| "step": 33400, | |
| "loss": 3.3944686889648437, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003395380557304187, | |
| "tokens_per_s": 2365459.1165153664 | |
| }, | |
| { | |
| "step": 33450, | |
| "loss": 3.419419860839844, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003376809745468829, | |
| "tokens_per_s": 2365460.673770418 | |
| }, | |
| { | |
| "step": 33500, | |
| "loss": 3.423117980957031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00033583530999181877, | |
| "tokens_per_s": 2365462.660640158 | |
| }, | |
| { | |
| "step": 33550, | |
| "loss": 3.4171597290039064, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00033400108970623485, | |
| "tokens_per_s": 2365451.392144709 | |
| }, | |
| { | |
| "step": 33600, | |
| "loss": 3.4003811645507813, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003321783411597479, | |
| "tokens_per_s": 2365453.4741368103 | |
| }, | |
| { | |
| "step": 33650, | |
| "loss": 3.4024484252929685, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00033036709165017175, | |
| "tokens_per_s": 2365456.911440542 | |
| }, | |
| { | |
| "step": 33700, | |
| "loss": 3.40421630859375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003285673683031087, | |
| "tokens_per_s": 2365458.433029148 | |
| }, | |
| { | |
| "step": 33750, | |
| "loss": 3.4096102905273438, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00032677919807154357, | |
| "tokens_per_s": 2365452.5315218735 | |
| }, | |
| { | |
| "step": 33800, | |
| "loss": 3.40908447265625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00032500260773543876, | |
| "tokens_per_s": 2365454.3778851232 | |
| }, | |
| { | |
| "step": 33850, | |
| "loss": 3.4068060302734375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003232376239013345, | |
| "tokens_per_s": 2365455.5188190504 | |
| }, | |
| { | |
| "step": 33900, | |
| "loss": 3.402943115234375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00032148427300195007, | |
| "tokens_per_s": 2365458.956586588 | |
| }, | |
| { | |
| "step": 33950, | |
| "loss": 3.4091455078125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003197425812957879, | |
| "tokens_per_s": 2365460.9947951115 | |
| }, | |
| { | |
| "step": 34000, | |
| "loss": 3.4201202392578125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00031801257486673977, | |
| "tokens_per_s": 2365464.295471426 | |
| }, | |
| { | |
| "step": 34050, | |
| "loss": 3.4105599975585936, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003162942796236965, | |
| "tokens_per_s": 2365466.9153006827 | |
| }, | |
| { | |
| "step": 34100, | |
| "loss": 3.4105734252929687, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003145877213001608, | |
| "tokens_per_s": 2365469.5051666694 | |
| }, | |
| { | |
| "step": 34150, | |
| "loss": 3.40491943359375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00031289292545386073, | |
| "tokens_per_s": 2365472.786856152 | |
| }, | |
| { | |
| "step": 34200, | |
| "loss": 3.402999267578125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003112099174663672, | |
| "tokens_per_s": 2365474.8082224196 | |
| }, | |
| { | |
| "step": 34250, | |
| "loss": 3.4022955322265624, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003095387225427141, | |
| "tokens_per_s": 2365476.952068372 | |
| }, | |
| { | |
| "step": 34300, | |
| "loss": 3.4010797119140626, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00030787936571102087, | |
| "tokens_per_s": 2365478.4803644866 | |
| }, | |
| { | |
| "step": 34350, | |
| "loss": 3.4092593383789063, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00030623187182211755, | |
| "tokens_per_s": 2365480.1946400604 | |
| }, | |
| { | |
| "step": 34400, | |
| "loss": 3.4045318603515624, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00030459626554917235, | |
| "tokens_per_s": 2365481.746133773 | |
| }, | |
| { | |
| "step": 34450, | |
| "loss": 3.3933139038085938, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003029725713873223, | |
| "tokens_per_s": 2365484.3921921086 | |
| }, | |
| { | |
| "step": 34500, | |
| "loss": 3.41294921875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0003013608136533069, | |
| "tokens_per_s": 2365485.6255030665 | |
| }, | |
| { | |
| "step": 34550, | |
| "loss": 3.389093322753906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00029976101648510344, | |
| "tokens_per_s": 2365475.964762409 | |
| }, | |
| { | |
| "step": 34600, | |
| "loss": 3.4111798095703123, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00029817320384156553, | |
| "tokens_per_s": 2365470.117705516 | |
| }, | |
| { | |
| "step": 34650, | |
| "loss": 3.3937008666992186, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00029659739950206376, | |
| "tokens_per_s": 2365472.9602879602 | |
| }, | |
| { | |
| "step": 34700, | |
| "loss": 3.422117919921875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002950336270661312, | |
| "tokens_per_s": 2365475.2729716985 | |
| }, | |
| { | |
| "step": 34750, | |
| "loss": 3.4079129028320314, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002934819099531086, | |
| "tokens_per_s": 2365478.1351162135 | |
| }, | |
| { | |
| "step": 34800, | |
| "loss": 3.3957650756835935, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00029194227140179357, | |
| "tokens_per_s": 2365480.365874925 | |
| }, | |
| { | |
| "step": 34850, | |
| "loss": 3.416562194824219, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00029041473447009316, | |
| "tokens_per_s": 2365481.9555008076 | |
| }, | |
| { | |
| "step": 34900, | |
| "loss": 3.4040069580078125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00028889932203467883, | |
| "tokens_per_s": 2365485.220411991 | |
| }, | |
| { | |
| "step": 34950, | |
| "loss": 3.3954092407226564, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00028739605679064276, | |
| "tokens_per_s": 2365487.6194088687 | |
| }, | |
| { | |
| "step": 35000, | |
| "loss": 3.395699768066406, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000285904961251159, | |
| "tokens_per_s": 2365482.4335465394 | |
| }, | |
| { | |
| "step": 35050, | |
| "loss": 3.3941940307617187, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002844260577471455, | |
| "tokens_per_s": 2365484.64769077 | |
| }, | |
| { | |
| "step": 35100, | |
| "loss": 3.397530517578125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00028295936842693084, | |
| "tokens_per_s": 2365487.0643147617 | |
| }, | |
| { | |
| "step": 35150, | |
| "loss": 3.413763122558594, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00028150491525592055, | |
| "tokens_per_s": 2365478.872928481 | |
| }, | |
| { | |
| "step": 35200, | |
| "loss": 3.4019461059570313, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00028006272001627054, | |
| "tokens_per_s": 2365481.610873249 | |
| }, | |
| { | |
| "step": 35250, | |
| "loss": 3.3891259765625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002786328043065589, | |
| "tokens_per_s": 2365483.4825287503 | |
| }, | |
| { | |
| "step": 35300, | |
| "loss": 3.3927096557617187, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002772151895414639, | |
| "tokens_per_s": 2365478.5941977925 | |
| }, | |
| { | |
| "step": 35350, | |
| "loss": 3.4093283081054686, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002758098969514419, | |
| "tokens_per_s": 2365481.845326304 | |
| }, | |
| { | |
| "step": 35400, | |
| "loss": 3.4001889038085937, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00027441694758241074, | |
| "tokens_per_s": 2365484.602713602 | |
| }, | |
| { | |
| "step": 35450, | |
| "loss": 3.3965966796875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00027303636229543356, | |
| "tokens_per_s": 2365488.107249136 | |
| }, | |
| { | |
| "step": 35500, | |
| "loss": 3.4024072265625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00027166816176640694, | |
| "tokens_per_s": 2365490.350333845 | |
| }, | |
| { | |
| "step": 35550, | |
| "loss": 3.4047982788085935, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00027031236648575096, | |
| "tokens_per_s": 2365493.053604671 | |
| }, | |
| { | |
| "step": 35600, | |
| "loss": 3.4009494018554687, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00026896899675810267, | |
| "tokens_per_s": 2365490.883545334 | |
| }, | |
| { | |
| "step": 35650, | |
| "loss": 3.3886007690429687, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00026763807270201157, | |
| "tokens_per_s": 2365492.6039623437 | |
| }, | |
| { | |
| "step": 35700, | |
| "loss": 3.38521240234375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00026631961424963845, | |
| "tokens_per_s": 2365494.8266707147 | |
| }, | |
| { | |
| "step": 35750, | |
| "loss": 3.3945877075195314, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002650136411464571, | |
| "tokens_per_s": 2365496.8693044977 | |
| }, | |
| { | |
| "step": 35800, | |
| "loss": 3.4033251953125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00026372017295095835, | |
| "tokens_per_s": 2365498.24284552 | |
| }, | |
| { | |
| "step": 35850, | |
| "loss": 3.385032043457031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00026243922903435756, | |
| "tokens_per_s": 2365500.287893678 | |
| }, | |
| { | |
| "step": 35900, | |
| "loss": 3.3964608764648436, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00026117082858030384, | |
| "tokens_per_s": 2365503.0530582275 | |
| }, | |
| { | |
| "step": 35950, | |
| "loss": 3.408526611328125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000259914990584593, | |
| "tokens_per_s": 2365505.541001871 | |
| }, | |
| { | |
| "step": 36000, | |
| "loss": 3.3957373046875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00025867173385488363, | |
| "tokens_per_s": 2365496.253619459 | |
| }, | |
| { | |
| "step": 36050, | |
| "loss": 3.4028173828125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002574410770104151, | |
| "tokens_per_s": 2365497.4370389916 | |
| }, | |
| { | |
| "step": 36100, | |
| "loss": 3.400078125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002562230384817278, | |
| "tokens_per_s": 2365499.5946001983 | |
| }, | |
| { | |
| "step": 36150, | |
| "loss": 3.380582580566406, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002550176365103885, | |
| "tokens_per_s": 2365500.65900682 | |
| }, | |
| { | |
| "step": 36200, | |
| "loss": 3.391004943847656, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00025382488914871677, | |
| "tokens_per_s": 2365491.8458440984 | |
| }, | |
| { | |
| "step": 36250, | |
| "loss": 3.401690673828125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002526448142595143, | |
| "tokens_per_s": 2365493.7296357276 | |
| }, | |
| { | |
| "step": 36300, | |
| "loss": 3.4001690673828127, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00025147742951579685, | |
| "tokens_per_s": 2365496.1675324007 | |
| }, | |
| { | |
| "step": 36350, | |
| "loss": 3.413360900878906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002503227524005311, | |
| "tokens_per_s": 2365497.9282006253 | |
| }, | |
| { | |
| "step": 36400, | |
| "loss": 3.3906890869140627, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00024918080020637176, | |
| "tokens_per_s": 2365497.505205605 | |
| }, | |
| { | |
| "step": 36450, | |
| "loss": 3.3942532348632812, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000248051590035403, | |
| "tokens_per_s": 2365498.9151863637 | |
| }, | |
| { | |
| "step": 36500, | |
| "loss": 3.388255920410156, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00024693513879888113, | |
| "tokens_per_s": 2365500.032037026 | |
| }, | |
| { | |
| "step": 36550, | |
| "loss": 3.3897052001953125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00024583146321698366, | |
| "tokens_per_s": 2365502.273850531 | |
| }, | |
| { | |
| "step": 36600, | |
| "loss": 3.3923068237304688, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00024474057981855685, | |
| "tokens_per_s": 2365504.0386318993 | |
| }, | |
| { | |
| "step": 36650, | |
| "loss": 3.399059143066406, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000243662504940869, | |
| "tokens_per_s": 2365505.180955713 | |
| }, | |
| { | |
| "step": 36700, | |
| "loss": 3.4055990600585937, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002425972547293656, | |
| "tokens_per_s": 2365506.50801959 | |
| }, | |
| { | |
| "step": 36750, | |
| "loss": 3.4066098022460936, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00024154484513742774, | |
| "tokens_per_s": 2365506.9887683922 | |
| }, | |
| { | |
| "step": 36800, | |
| "loss": 3.4038540649414064, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00024050529192613316, | |
| "tokens_per_s": 2365508.420406555 | |
| }, | |
| { | |
| "step": 36850, | |
| "loss": 3.3942425537109373, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00023947861066401979, | |
| "tokens_per_s": 2365511.9613675526 | |
| }, | |
| { | |
| "step": 36900, | |
| "loss": 3.3904931640625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00023846481672685306, | |
| "tokens_per_s": 2365513.925979512 | |
| }, | |
| { | |
| "step": 36950, | |
| "loss": 3.392222900390625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00023746392529739563, | |
| "tokens_per_s": 2365517.6019810024 | |
| }, | |
| { | |
| "step": 37000, | |
| "loss": 3.393274230957031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00023647595136517968, | |
| "tokens_per_s": 2365519.23969585 | |
| }, | |
| { | |
| "step": 37050, | |
| "loss": 3.3674554443359375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00023550090972628256, | |
| "tokens_per_s": 2365520.201202772 | |
| }, | |
| { | |
| "step": 37100, | |
| "loss": 3.3888958740234374, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00023453881498310537, | |
| "tokens_per_s": 2365520.993312113 | |
| }, | |
| { | |
| "step": 37150, | |
| "loss": 3.393912658691406, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00023358968154415404, | |
| "tokens_per_s": 2365521.90530402 | |
| }, | |
| { | |
| "step": 37200, | |
| "loss": 3.376514587402344, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002326535236238238, | |
| "tokens_per_s": 2365523.6940648193 | |
| }, | |
| { | |
| "step": 37250, | |
| "loss": 3.389199523925781, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002317303552421859, | |
| "tokens_per_s": 2365525.4874989158 | |
| }, | |
| { | |
| "step": 37300, | |
| "loss": 3.394179382324219, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00023082019022477833, | |
| "tokens_per_s": 2365526.7863927875 | |
| }, | |
| { | |
| "step": 37350, | |
| "loss": 3.391060485839844, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00022992304220239757, | |
| "tokens_per_s": 2365528.1646560393 | |
| }, | |
| { | |
| "step": 37400, | |
| "loss": 3.387282409667969, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00022903892461089627, | |
| "tokens_per_s": 2365529.500771211 | |
| }, | |
| { | |
| "step": 37450, | |
| "loss": 3.4006314086914062, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00022816785069097983, | |
| "tokens_per_s": 2365531.652318265 | |
| }, | |
| { | |
| "step": 37500, | |
| "loss": 3.388810119628906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00022730983348801027, | |
| "tokens_per_s": 2365533.377596897 | |
| }, | |
| { | |
| "step": 37550, | |
| "loss": 3.38219482421875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00022646488585180912, | |
| "tokens_per_s": 2365535.2529731747 | |
| }, | |
| { | |
| "step": 37600, | |
| "loss": 3.3943826293945314, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00022563302043646612, | |
| "tokens_per_s": 2365537.651065892 | |
| }, | |
| { | |
| "step": 37650, | |
| "loss": 3.3854296875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00022481424970014884, | |
| "tokens_per_s": 2365540.062980123 | |
| }, | |
| { | |
| "step": 37700, | |
| "loss": 3.4042843627929686, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002240085859049173, | |
| "tokens_per_s": 2365541.0199073413 | |
| }, | |
| { | |
| "step": 37750, | |
| "loss": 3.394325866699219, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00022321604111653882, | |
| "tokens_per_s": 2365541.9160594987 | |
| }, | |
| { | |
| "step": 37800, | |
| "loss": 3.3938919067382813, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00022243662720430852, | |
| "tokens_per_s": 2365544.277584115 | |
| }, | |
| { | |
| "step": 37850, | |
| "loss": 3.3826358032226564, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00022167035584087086, | |
| "tokens_per_s": 2365545.3779027606 | |
| }, | |
| { | |
| "step": 37900, | |
| "loss": 3.377445068359375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00022091723850204548, | |
| "tokens_per_s": 2365546.6894572824 | |
| }, | |
| { | |
| "step": 37950, | |
| "loss": 3.3974896240234376, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002201772864666545, | |
| "tokens_per_s": 2365548.5497212 | |
| }, | |
| { | |
| "step": 38000, | |
| "loss": 3.3902740478515625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00021945051081635435, | |
| "tokens_per_s": 2365549.8443684373 | |
| }, | |
| { | |
| "step": 38050, | |
| "loss": 3.3910205078125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00021873692243546948, | |
| "tokens_per_s": 2365552.0494294623 | |
| }, | |
| { | |
| "step": 38100, | |
| "loss": 3.387166748046875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00021803653201082947, | |
| "tokens_per_s": 2365553.1537087928 | |
| }, | |
| { | |
| "step": 38150, | |
| "loss": 3.3823110961914065, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00021734935003160855, | |
| "tokens_per_s": 2365555.350081687 | |
| }, | |
| { | |
| "step": 38200, | |
| "loss": 3.3826580810546876, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00021667538678916924, | |
| "tokens_per_s": 2365556.8805961614 | |
| }, | |
| { | |
| "step": 38250, | |
| "loss": 3.3956207275390624, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002160146523769076, | |
| "tokens_per_s": 2365558.1857052734 | |
| }, | |
| { | |
| "step": 38300, | |
| "loss": 3.3935015869140623, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00021536715669010276, | |
| "tokens_per_s": 2365559.1989637446 | |
| }, | |
| { | |
| "step": 38350, | |
| "loss": 3.396727294921875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00021473290942576771, | |
| "tokens_per_s": 2365549.131377122 | |
| }, | |
| { | |
| "step": 38400, | |
| "loss": 3.3915399169921874, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002141119200825049, | |
| "tokens_per_s": 2365548.8757805726 | |
| }, | |
| { | |
| "step": 38450, | |
| "loss": 3.3951040649414064, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00021350419796036386, | |
| "tokens_per_s": 2365549.078296483 | |
| }, | |
| { | |
| "step": 38500, | |
| "loss": 3.39059326171875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00021290975216070178, | |
| "tokens_per_s": 2365549.362773895 | |
| }, | |
| { | |
| "step": 38550, | |
| "loss": 3.3762356567382814, | |
| "indexer_kl": 0.0, | |
| "lr": 0.000212328591586047, | |
| "tokens_per_s": 2365549.3754322724 | |
| }, | |
| { | |
| "step": 38600, | |
| "loss": 3.378728332519531, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00021176072493996599, | |
| "tokens_per_s": 2365549.9899927382 | |
| }, | |
| { | |
| "step": 38650, | |
| "loss": 3.3529678344726563, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00021120616072693317, | |
| "tokens_per_s": 2365552.3495495366 | |
| }, | |
| { | |
| "step": 38700, | |
| "loss": 3.38170654296875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002106649072522032, | |
| "tokens_per_s": 2365553.140338392 | |
| }, | |
| { | |
| "step": 38750, | |
| "loss": 3.3904241943359374, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00021013697262168635, | |
| "tokens_per_s": 2365544.5532606714 | |
| }, | |
| { | |
| "step": 38800, | |
| "loss": 3.3856167602539062, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020962236474182793, | |
| "tokens_per_s": 2365545.1869549896 | |
| }, | |
| { | |
| "step": 38850, | |
| "loss": 3.384383544921875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002091210913194892, | |
| "tokens_per_s": 2365547.1422957005 | |
| }, | |
| { | |
| "step": 38900, | |
| "loss": 3.385108642578125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020863315986183208, | |
| "tokens_per_s": 2365547.937801769 | |
| }, | |
| { | |
| "step": 38950, | |
| "loss": 3.3881201171875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020815857767620695, | |
| "tokens_per_s": 2365549.3661198043 | |
| }, | |
| { | |
| "step": 39000, | |
| "loss": 3.3837844848632814, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020769735187004307, | |
| "tokens_per_s": 2365551.853544254 | |
| }, | |
| { | |
| "step": 39050, | |
| "loss": 3.382044677734375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020724948935074187, | |
| "tokens_per_s": 2365554.623763328 | |
| }, | |
| { | |
| "step": 39100, | |
| "loss": 3.40516845703125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020681499682557417, | |
| "tokens_per_s": 2365555.693733731 | |
| }, | |
| { | |
| "step": 39150, | |
| "loss": 3.395960693359375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002063938808015789, | |
| "tokens_per_s": 2365557.4750921633 | |
| }, | |
| { | |
| "step": 39200, | |
| "loss": 3.380354309082031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002059861475854664, | |
| "tokens_per_s": 2365558.216023141 | |
| }, | |
| { | |
| "step": 39250, | |
| "loss": 3.386961669921875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020559180328352347, | |
| "tokens_per_s": 2365559.6825830545 | |
| }, | |
| { | |
| "step": 39300, | |
| "loss": 3.385447692871094, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020521085380152226, | |
| "tokens_per_s": 2365561.2952898946 | |
| }, | |
| { | |
| "step": 39350, | |
| "loss": 3.3808663940429686, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002048433048446314, | |
| "tokens_per_s": 2365562.4562204685 | |
| }, | |
| { | |
| "step": 39400, | |
| "loss": 3.3834735107421876, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020448916191733108, | |
| "tokens_per_s": 2365563.2070510504 | |
| }, | |
| { | |
| "step": 39450, | |
| "loss": 3.37839111328125, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002041484303233302, | |
| "tokens_per_s": 2365563.808047683 | |
| }, | |
| { | |
| "step": 39500, | |
| "loss": 3.37897216796875, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020382111516548712, | |
| "tokens_per_s": 2365566.805788429 | |
| }, | |
| { | |
| "step": 39550, | |
| "loss": 3.3824636840820315, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020350722134573315, | |
| "tokens_per_s": 2365567.1570761222 | |
| }, | |
| { | |
| "step": 39600, | |
| "loss": 3.3890386962890626, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020320675356499935, | |
| "tokens_per_s": 2365568.0236191605 | |
| }, | |
| { | |
| "step": 39650, | |
| "loss": 3.384942932128906, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020291971632314585, | |
| "tokens_per_s": 2365568.205447041 | |
| }, | |
| { | |
| "step": 39700, | |
| "loss": 3.3884347534179686, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020264611391889467, | |
| "tokens_per_s": 2365569.0083201993 | |
| }, | |
| { | |
| "step": 39750, | |
| "loss": 3.386165771484375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020238595044976525, | |
| "tokens_per_s": 2365569.447939852 | |
| }, | |
| { | |
| "step": 39800, | |
| "loss": 3.386243896484375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020213922981201298, | |
| "tokens_per_s": 2365569.7630122425 | |
| }, | |
| { | |
| "step": 39850, | |
| "loss": 3.3865347290039063, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020190595570057098, | |
| "tokens_per_s": 2365570.8885429734 | |
| }, | |
| { | |
| "step": 39900, | |
| "loss": 3.3962271118164065, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020168613160899488, | |
| "tokens_per_s": 2365572.0275810123 | |
| }, | |
| { | |
| "step": 39950, | |
| "loss": 3.387021484375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020147976082941028, | |
| "tokens_per_s": 2365573.0584548744 | |
| }, | |
| { | |
| "step": 40000, | |
| "loss": 3.3888458251953124, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020128684645246355, | |
| "tokens_per_s": 2365573.735917783 | |
| }, | |
| { | |
| "step": 40050, | |
| "loss": 3.3792205810546876, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020110739136727546, | |
| "tokens_per_s": 2365574.6190810925 | |
| }, | |
| { | |
| "step": 40100, | |
| "loss": 3.3882159423828124, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020094139826139803, | |
| "tokens_per_s": 2365576.422665454 | |
| }, | |
| { | |
| "step": 40150, | |
| "loss": 3.3859133911132813, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020078886962077437, | |
| "tokens_per_s": 2365576.8770693885 | |
| }, | |
| { | |
| "step": 40200, | |
| "loss": 3.398948059082031, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020064980772970098, | |
| "tokens_per_s": 2365578.8239370845 | |
| }, | |
| { | |
| "step": 40250, | |
| "loss": 3.375940856933594, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002005242146707941, | |
| "tokens_per_s": 2365580.50700682 | |
| }, | |
| { | |
| "step": 40300, | |
| "loss": 3.3951080322265623, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002004120923249583, | |
| "tokens_per_s": 2365581.48877839 | |
| }, | |
| { | |
| "step": 40350, | |
| "loss": 3.374814147949219, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020031344237135814, | |
| "tokens_per_s": 2365582.001925761 | |
| }, | |
| { | |
| "step": 40400, | |
| "loss": 3.382310791015625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020022826628739336, | |
| "tokens_per_s": 2365583.054669233 | |
| }, | |
| { | |
| "step": 40450, | |
| "loss": 3.394410400390625, | |
| "indexer_kl": 0.0, | |
| "lr": 0.0002001565653486765, | |
| "tokens_per_s": 2365583.5464946576 | |
| }, | |
| { | |
| "step": 40500, | |
| "loss": 3.3925991821289063, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020009834062901385, | |
| "tokens_per_s": 2365585.3085234594 | |
| }, | |
| { | |
| "step": 40550, | |
| "loss": 3.3853573608398437, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020005359300038936, | |
| "tokens_per_s": 2365587.840036578 | |
| }, | |
| { | |
| "step": 40600, | |
| "loss": 3.371038818359375, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020002232313295166, | |
| "tokens_per_s": 2365587.852807129 | |
| }, | |
| { | |
| "step": 40650, | |
| "loss": 3.3825149536132812, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020000453149500406, | |
| "tokens_per_s": 2365589.551626396 | |
| }, | |
| { | |
| "step": 40690, | |
| "loss": 3.393650436401367, | |
| "indexer_kl": 0.0, | |
| "lr": 0.00020000000269571616, | |
| "tokens_per_s": 2365583.2751520397 | |
| } | |
| ] | |
| } |