Instructions to use Kaipengm2/tttw1003m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Kaipengm2/tttw1003m with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/inspire/hdd/global_user/zhengkaipeng-240108120123/models/OneReason-0.8B-pretrain-competition") model = PeftModel.from_pretrained(base_model, "Kaipengm2/tttw1003m") - Transformers
How to use Kaipengm2/tttw1003m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Kaipengm2/tttw1003m") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Kaipengm2/tttw1003m", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Kaipengm2/tttw1003m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Kaipengm2/tttw1003m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Kaipengm2/tttw1003m", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Kaipengm2/tttw1003m
- SGLang
How to use Kaipengm2/tttw1003m 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 "Kaipengm2/tttw1003m" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Kaipengm2/tttw1003m", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Kaipengm2/tttw1003m" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Kaipengm2/tttw1003m", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Kaipengm2/tttw1003m with Docker Model Runner:
docker model run hf.co/Kaipengm2/tttw1003m
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7587973062695628, | |
| "eval_steps": 500, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001896993265673907, | |
| "grad_norm": 1.4615155458450317, | |
| "learning_rate": 1e-05, | |
| "loss": 2.7559625625610353, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003793986531347814, | |
| "grad_norm": 0.7979579567909241, | |
| "learning_rate": 2.25e-05, | |
| "loss": 2.8092529296875, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005690979797021721, | |
| "grad_norm": 0.36581236124038696, | |
| "learning_rate": 3.5e-05, | |
| "loss": 2.6555248260498048, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007587973062695628, | |
| "grad_norm": 0.30574315786361694, | |
| "learning_rate": 4.75e-05, | |
| "loss": 2.5058727264404297, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009484966328369534, | |
| "grad_norm": 0.335353285074234, | |
| "learning_rate": 6e-05, | |
| "loss": 2.4662797927856444, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011381959594043442, | |
| "grad_norm": 0.22822999954223633, | |
| "learning_rate": 7.25e-05, | |
| "loss": 2.296770477294922, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013278952859717348, | |
| "grad_norm": 0.19895921647548676, | |
| "learning_rate": 8.5e-05, | |
| "loss": 2.1864345550537108, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.015175946125391256, | |
| "grad_norm": 0.18998849391937256, | |
| "learning_rate": 9.75e-05, | |
| "loss": 2.13150634765625, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01707293939106516, | |
| "grad_norm": 0.23324304819107056, | |
| "learning_rate": 0.00011000000000000002, | |
| "loss": 2.0964550018310546, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.018969932656739068, | |
| "grad_norm": 0.19142404198646545, | |
| "learning_rate": 0.00012250000000000002, | |
| "loss": 1.9552787780761718, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.020866925922412974, | |
| "grad_norm": 0.22066965699195862, | |
| "learning_rate": 0.00013500000000000003, | |
| "loss": 1.9052619934082031, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.022763919188086883, | |
| "grad_norm": 0.2379477471113205, | |
| "learning_rate": 0.0001475, | |
| "loss": 1.9066146850585937, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02466091245376079, | |
| "grad_norm": 0.22160284221172333, | |
| "learning_rate": 0.00016, | |
| "loss": 1.8553531646728516, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.026557905719434696, | |
| "grad_norm": 0.19776837527751923, | |
| "learning_rate": 0.00017250000000000002, | |
| "loss": 1.794830322265625, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0284548989851086, | |
| "grad_norm": 0.2028709501028061, | |
| "learning_rate": 0.00018500000000000002, | |
| "loss": 1.8074737548828126, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.03035189225078251, | |
| "grad_norm": 0.19441711902618408, | |
| "learning_rate": 0.00019750000000000003, | |
| "loss": 1.743231201171875, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03224888551645642, | |
| "grad_norm": 0.2005140483379364, | |
| "learning_rate": 0.00019999879144294303, | |
| "loss": 1.7226619720458984, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.03414587878213032, | |
| "grad_norm": 0.20957030355930328, | |
| "learning_rate": 0.00019999388172996495, | |
| "loss": 1.6900768280029297, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03604287204780423, | |
| "grad_norm": 0.20512907207012177, | |
| "learning_rate": 0.00019998519551153393, | |
| "loss": 1.7062498092651368, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.037939865313478136, | |
| "grad_norm": 0.22446870803833008, | |
| "learning_rate": 0.00019997273311570557, | |
| "loss": 1.6975416183471679, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03983685857915204, | |
| "grad_norm": 0.26710525155067444, | |
| "learning_rate": 0.0001999564950131517, | |
| "loss": 1.675743865966797, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.04173385184482595, | |
| "grad_norm": 0.21244746446609497, | |
| "learning_rate": 0.00019993648181714272, | |
| "loss": 1.6485740661621093, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.04363084511049986, | |
| "grad_norm": 0.2397415190935135, | |
| "learning_rate": 0.00019991269428352431, | |
| "loss": 1.6613985061645509, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.04552783837617377, | |
| "grad_norm": 0.2303868532180786, | |
| "learning_rate": 0.0001998851333106889, | |
| "loss": 1.649810218811035, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.04742483164184767, | |
| "grad_norm": 0.2253895401954651, | |
| "learning_rate": 0.00019985379993954182, | |
| "loss": 1.618267822265625, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.04932182490752158, | |
| "grad_norm": 0.2139357030391693, | |
| "learning_rate": 0.000199818695353462, | |
| "loss": 1.5947548866271972, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.051218818173195485, | |
| "grad_norm": 0.2045314759016037, | |
| "learning_rate": 0.00019977982087825713, | |
| "loss": 1.5944395065307617, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.05311581143886939, | |
| "grad_norm": 0.21028991043567657, | |
| "learning_rate": 0.00019973717798211368, | |
| "loss": 1.582909107208252, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0550128047045433, | |
| "grad_norm": 0.23554696142673492, | |
| "learning_rate": 0.00019969076827554153, | |
| "loss": 1.6185903549194336, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.0569097979702172, | |
| "grad_norm": 0.20526519417762756, | |
| "learning_rate": 0.000199640593511313, | |
| "loss": 1.5607417106628418, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05880679123589111, | |
| "grad_norm": 0.22022901475429535, | |
| "learning_rate": 0.00019958665558439672, | |
| "loss": 1.5784404754638672, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.06070378450156502, | |
| "grad_norm": 0.22664952278137207, | |
| "learning_rate": 0.0001995289565318861, | |
| "loss": 1.5773786544799804, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.06260077776723892, | |
| "grad_norm": 0.20170505344867706, | |
| "learning_rate": 0.00019946749853292232, | |
| "loss": 1.6092945098876954, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.06449777103291283, | |
| "grad_norm": 0.20320254564285278, | |
| "learning_rate": 0.0001994022839086121, | |
| "loss": 1.6189882278442382, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.06639476429858673, | |
| "grad_norm": 0.19554108381271362, | |
| "learning_rate": 0.0001993333151219399, | |
| "loss": 1.583411407470703, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.06829175756426065, | |
| "grad_norm": 0.24571268260478973, | |
| "learning_rate": 0.0001992605947776752, | |
| "loss": 1.5937853813171388, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.07018875082993456, | |
| "grad_norm": 0.24477900564670563, | |
| "learning_rate": 0.0001991841256222737, | |
| "loss": 1.567392921447754, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.07208574409560846, | |
| "grad_norm": 0.19675961136817932, | |
| "learning_rate": 0.00019910391054377393, | |
| "loss": 1.535955810546875, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.07398273736128237, | |
| "grad_norm": 0.24165809154510498, | |
| "learning_rate": 0.00019901995257168807, | |
| "loss": 1.5504512786865234, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.07587973062695627, | |
| "grad_norm": 0.2039577066898346, | |
| "learning_rate": 0.00019893225487688758, | |
| "loss": 1.5700265884399414, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07777672389263018, | |
| "grad_norm": 0.19671933352947235, | |
| "learning_rate": 0.00019884082077148324, | |
| "loss": 1.545316505432129, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.07967371715830408, | |
| "grad_norm": 0.19404149055480957, | |
| "learning_rate": 0.00019874565370870038, | |
| "loss": 1.5161818504333495, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.081570710423978, | |
| "grad_norm": 0.18738074600696564, | |
| "learning_rate": 0.00019864675728274814, | |
| "loss": 1.5074141502380372, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.0834677036896519, | |
| "grad_norm": 0.1795588582754135, | |
| "learning_rate": 0.000198544135228684, | |
| "loss": 1.5091622352600098, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.08536469695532581, | |
| "grad_norm": 0.1913215070962906, | |
| "learning_rate": 0.00019843779142227256, | |
| "loss": 1.5260107040405273, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.08726169022099972, | |
| "grad_norm": 0.2229178100824356, | |
| "learning_rate": 0.0001983277298798392, | |
| "loss": 1.5580297470092774, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.08915868348667362, | |
| "grad_norm": 0.18856383860111237, | |
| "learning_rate": 0.00019821395475811839, | |
| "loss": 1.5683236122131348, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.09105567675234753, | |
| "grad_norm": 0.25202229619026184, | |
| "learning_rate": 0.00019809647035409672, | |
| "loss": 1.4854307174682617, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.09295267001802143, | |
| "grad_norm": 0.21348656713962555, | |
| "learning_rate": 0.00019797528110485053, | |
| "loss": 1.5003705978393556, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.09484966328369535, | |
| "grad_norm": 0.20500370860099792, | |
| "learning_rate": 0.00019785039158737853, | |
| "loss": 1.4969975471496582, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.09674665654936924, | |
| "grad_norm": 0.22715307772159576, | |
| "learning_rate": 0.0001977218065184287, | |
| "loss": 1.4629117965698242, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.09864364981504316, | |
| "grad_norm": 0.221677765250206, | |
| "learning_rate": 0.0001975895307543203, | |
| "loss": 1.4972817420959472, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.10054064308071706, | |
| "grad_norm": 0.2100268453359604, | |
| "learning_rate": 0.00019745356929076042, | |
| "loss": 1.4953039169311524, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.10243763634639097, | |
| "grad_norm": 0.1992482990026474, | |
| "learning_rate": 0.00019731392726265537, | |
| "loss": 1.5101714134216309, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.10433462961206488, | |
| "grad_norm": 0.21750272810459137, | |
| "learning_rate": 0.00019717060994391657, | |
| "loss": 1.5082414627075196, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.10623162287773878, | |
| "grad_norm": 0.20638105273246765, | |
| "learning_rate": 0.00019702362274726158, | |
| "loss": 1.5074645042419434, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.1081286161434127, | |
| "grad_norm": 0.22058691084384918, | |
| "learning_rate": 0.0001968729712240095, | |
| "loss": 1.5629194259643555, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.1100256094090866, | |
| "grad_norm": 0.2238057255744934, | |
| "learning_rate": 0.00019671866106387147, | |
| "loss": 1.4418581008911133, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.11192260267476051, | |
| "grad_norm": 0.19935020804405212, | |
| "learning_rate": 0.00019656069809473564, | |
| "loss": 1.4758859634399415, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.1138195959404344, | |
| "grad_norm": 0.17538389563560486, | |
| "learning_rate": 0.00019639908828244718, | |
| "loss": 1.5230995178222657, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.11571658920610832, | |
| "grad_norm": 0.18660707771778107, | |
| "learning_rate": 0.00019623383773058288, | |
| "loss": 1.4746660232543944, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.11761358247178222, | |
| "grad_norm": 0.1905367523431778, | |
| "learning_rate": 0.00019606495268022068, | |
| "loss": 1.4676092147827149, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.11951057573745613, | |
| "grad_norm": 0.20304426550865173, | |
| "learning_rate": 0.00019589243950970402, | |
| "loss": 1.4641122817993164, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.12140756900313004, | |
| "grad_norm": 0.1871313452720642, | |
| "learning_rate": 0.00019571630473440074, | |
| "loss": 1.489812469482422, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.12330456226880394, | |
| "grad_norm": 0.2092784345149994, | |
| "learning_rate": 0.0001955365550064573, | |
| "loss": 1.5035149574279785, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.12520155553447784, | |
| "grad_norm": 0.2320139855146408, | |
| "learning_rate": 0.00019535319711454728, | |
| "loss": 1.4577213287353517, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.12709854880015176, | |
| "grad_norm": 0.2011769413948059, | |
| "learning_rate": 0.00019516623798361516, | |
| "loss": 1.4284071922302246, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.12899554206582567, | |
| "grad_norm": 0.19615046679973602, | |
| "learning_rate": 0.00019497568467461473, | |
| "loss": 1.463198471069336, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.13089253533149958, | |
| "grad_norm": 0.19227343797683716, | |
| "learning_rate": 0.0001947815443842424, | |
| "loss": 1.4854132652282714, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.13278952859717347, | |
| "grad_norm": 0.2020893692970276, | |
| "learning_rate": 0.00019458382444466544, | |
| "loss": 1.4305970191955566, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.13468652186284738, | |
| "grad_norm": 0.22684313356876373, | |
| "learning_rate": 0.00019438253232324502, | |
| "loss": 1.4427383422851563, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.1365835151285213, | |
| "grad_norm": 0.16865643858909607, | |
| "learning_rate": 0.0001941776756222542, | |
| "loss": 1.4518535614013672, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.1384805083941952, | |
| "grad_norm": 0.21425198018550873, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 1.4950151443481445, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.14037750165986912, | |
| "grad_norm": 0.19497911632061005, | |
| "learning_rate": 0.00019375729956348537, | |
| "loss": 1.4560523986816407, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.142274494925543, | |
| "grad_norm": 0.2193925976753235, | |
| "learning_rate": 0.00019354179608220348, | |
| "loss": 1.4269789695739745, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.14417148819121692, | |
| "grad_norm": 0.17809733748435974, | |
| "learning_rate": 0.00019332275977374387, | |
| "loss": 1.4138547897338867, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.14606848145689083, | |
| "grad_norm": 0.20328114926815033, | |
| "learning_rate": 0.00019310019891053082, | |
| "loss": 1.4529046058654784, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.14796547472256474, | |
| "grad_norm": 0.19923736155033112, | |
| "learning_rate": 0.00019287412189810172, | |
| "loss": 1.4495321273803712, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.14986246798823863, | |
| "grad_norm": 0.19772541522979736, | |
| "learning_rate": 0.0001926445372747897, | |
| "loss": 1.3972710609436034, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.15175946125391254, | |
| "grad_norm": 0.17566776275634766, | |
| "learning_rate": 0.00019241145371140105, | |
| "loss": 1.4670235633850097, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.15365645451958646, | |
| "grad_norm": 0.22061137855052948, | |
| "learning_rate": 0.00019217488001088784, | |
| "loss": 1.425436305999756, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.15555344778526037, | |
| "grad_norm": 0.21640822291374207, | |
| "learning_rate": 0.00019193482510801546, | |
| "loss": 1.4518651962280273, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.15745044105093428, | |
| "grad_norm": 0.24494676291942596, | |
| "learning_rate": 0.00019169129806902505, | |
| "loss": 1.4755540847778321, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.15934743431660817, | |
| "grad_norm": 0.19018127024173737, | |
| "learning_rate": 0.00019144430809129128, | |
| "loss": 1.4319318771362304, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.16124442758228208, | |
| "grad_norm": 0.18564416468143463, | |
| "learning_rate": 0.00019119386450297486, | |
| "loss": 1.3837791442871095, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.163141420847956, | |
| "grad_norm": 0.18966543674468994, | |
| "learning_rate": 0.0001909399767626702, | |
| "loss": 1.4053851127624513, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.1650384141136299, | |
| "grad_norm": 0.1813315451145172, | |
| "learning_rate": 0.00019068265445904836, | |
| "loss": 1.3960668563842773, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.1669354073793038, | |
| "grad_norm": 0.18846842646598816, | |
| "learning_rate": 0.00019042190731049477, | |
| "loss": 1.4422532081604005, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.1688324006449777, | |
| "grad_norm": 0.20645295083522797, | |
| "learning_rate": 0.00019015774516474224, | |
| "loss": 1.476173210144043, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.17072939391065162, | |
| "grad_norm": 0.19793649017810822, | |
| "learning_rate": 0.00018989017799849896, | |
| "loss": 1.4135783195495606, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.17262638717632553, | |
| "grad_norm": 0.2279992252588272, | |
| "learning_rate": 0.00018961921591707182, | |
| "loss": 1.427664089202881, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.17452338044199944, | |
| "grad_norm": 0.1988634616136551, | |
| "learning_rate": 0.00018934486915398477, | |
| "loss": 1.4047898292541503, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.17642037370767333, | |
| "grad_norm": 0.20837819576263428, | |
| "learning_rate": 0.00018906714807059218, | |
| "loss": 1.4206146240234374, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.17831736697334724, | |
| "grad_norm": 0.20084981620311737, | |
| "learning_rate": 0.00018878606315568766, | |
| "loss": 1.3507210731506347, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.18021436023902115, | |
| "grad_norm": 0.2089376449584961, | |
| "learning_rate": 0.00018850162502510783, | |
| "loss": 1.4360587120056152, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.18211135350469507, | |
| "grad_norm": 0.16152583062648773, | |
| "learning_rate": 0.00018821384442133145, | |
| "loss": 1.4121583938598632, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.18400834677036895, | |
| "grad_norm": 0.1924440562725067, | |
| "learning_rate": 0.00018792273221307374, | |
| "loss": 1.3684646606445312, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.18590534003604287, | |
| "grad_norm": 0.2439498007297516, | |
| "learning_rate": 0.00018762829939487577, | |
| "loss": 1.3523134231567382, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.18780233330171678, | |
| "grad_norm": 0.23674866557121277, | |
| "learning_rate": 0.00018733055708668926, | |
| "loss": 1.409406852722168, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.1896993265673907, | |
| "grad_norm": 0.1905030459165573, | |
| "learning_rate": 0.00018702951653345684, | |
| "loss": 1.3924416542053222, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1915963198330646, | |
| "grad_norm": 0.19121725857257843, | |
| "learning_rate": 0.00018672518910468693, | |
| "loss": 1.34664945602417, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.1934933130987385, | |
| "grad_norm": 0.2581895589828491, | |
| "learning_rate": 0.00018641758629402467, | |
| "loss": 1.4004868507385253, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.1953903063644124, | |
| "grad_norm": 0.17350085079669952, | |
| "learning_rate": 0.0001861067197188179, | |
| "loss": 1.4116735458374023, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.19728729963008632, | |
| "grad_norm": 0.16260506212711334, | |
| "learning_rate": 0.00018579260111967793, | |
| "loss": 1.3844106674194336, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.19918429289576023, | |
| "grad_norm": 0.1741265058517456, | |
| "learning_rate": 0.00018547524236003674, | |
| "loss": 1.4474384307861328, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.20108128616143411, | |
| "grad_norm": 0.22188177704811096, | |
| "learning_rate": 0.00018515465542569848, | |
| "loss": 1.3683212280273438, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.20297827942710803, | |
| "grad_norm": 0.2057981789112091, | |
| "learning_rate": 0.00018483085242438697, | |
| "loss": 1.3719690322875977, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.20487527269278194, | |
| "grad_norm": 0.2003759741783142, | |
| "learning_rate": 0.00018450384558528845, | |
| "loss": 1.4022501945495605, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.20677226595845585, | |
| "grad_norm": 0.17929714918136597, | |
| "learning_rate": 0.00018417364725858968, | |
| "loss": 1.3739409446716309, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.20866925922412977, | |
| "grad_norm": 0.18638336658477783, | |
| "learning_rate": 0.0001838402699150114, | |
| "loss": 1.4015314102172851, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.21056625248980365, | |
| "grad_norm": 0.17437921464443207, | |
| "learning_rate": 0.00018350372614533753, | |
| "loss": 1.393330192565918, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.21246324575547756, | |
| "grad_norm": 0.18839673697948456, | |
| "learning_rate": 0.00018316402865993956, | |
| "loss": 1.3550561904907226, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.21436023902115148, | |
| "grad_norm": 0.18419015407562256, | |
| "learning_rate": 0.0001828211902882965, | |
| "loss": 1.3907146453857422, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.2162572322868254, | |
| "grad_norm": 0.20525352656841278, | |
| "learning_rate": 0.00018247522397851028, | |
| "loss": 1.4013847351074218, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.21815422555249928, | |
| "grad_norm": 0.16023705899715424, | |
| "learning_rate": 0.00018212614279681697, | |
| "loss": 1.3651066780090333, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.2200512188181732, | |
| "grad_norm": 0.19111956655979156, | |
| "learning_rate": 0.00018177395992709298, | |
| "loss": 1.3793062210083007, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.2219482120838471, | |
| "grad_norm": 0.18793532252311707, | |
| "learning_rate": 0.00018141868867035745, | |
| "loss": 1.4061149597167968, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.22384520534952101, | |
| "grad_norm": 0.21913006901741028, | |
| "learning_rate": 0.00018106034244426961, | |
| "loss": 1.4185336112976075, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.22574219861519493, | |
| "grad_norm": 0.17782795429229736, | |
| "learning_rate": 0.00018069893478262237, | |
| "loss": 1.3441279411315918, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.2276391918808688, | |
| "grad_norm": 0.16852033138275146, | |
| "learning_rate": 0.00018033447933483076, | |
| "loss": 1.3879838943481446, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.22953618514654273, | |
| "grad_norm": 0.18952517211437225, | |
| "learning_rate": 0.00017996698986541692, | |
| "loss": 1.3373958587646484, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.23143317841221664, | |
| "grad_norm": 0.19198372960090637, | |
| "learning_rate": 0.00017959648025348977, | |
| "loss": 1.3663469314575196, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.23333017167789055, | |
| "grad_norm": 0.19318172335624695, | |
| "learning_rate": 0.0001792229644922212, | |
| "loss": 1.3733086585998535, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.23522716494356444, | |
| "grad_norm": 0.18178334832191467, | |
| "learning_rate": 0.00017884645668831737, | |
| "loss": 1.4156621932983398, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.23712415820923835, | |
| "grad_norm": 0.162654310464859, | |
| "learning_rate": 0.000178466971061486, | |
| "loss": 1.4097686767578126, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.23902115147491226, | |
| "grad_norm": 0.22468340396881104, | |
| "learning_rate": 0.0001780845219438994, | |
| "loss": 1.4339370727539062, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.24091814474058618, | |
| "grad_norm": 0.19972585141658783, | |
| "learning_rate": 0.00017769912377965303, | |
| "loss": 1.3868285179138184, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.2428151380062601, | |
| "grad_norm": 0.17477339506149292, | |
| "learning_rate": 0.00017731079112422017, | |
| "loss": 1.3814733505249024, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.24471213127193397, | |
| "grad_norm": 0.21417972445487976, | |
| "learning_rate": 0.00017691953864390207, | |
| "loss": 1.3325740814208984, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.2466091245376079, | |
| "grad_norm": 0.2106507569551468, | |
| "learning_rate": 0.00017652538111527402, | |
| "loss": 1.348374080657959, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.2485061178032818, | |
| "grad_norm": 0.18388742208480835, | |
| "learning_rate": 0.00017612833342462732, | |
| "loss": 1.3540283203125, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.2504031110689557, | |
| "grad_norm": 0.19554397463798523, | |
| "learning_rate": 0.00017572841056740722, | |
| "loss": 1.3880966186523438, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.2523001043346296, | |
| "grad_norm": 0.1951630413532257, | |
| "learning_rate": 0.00017532562764764622, | |
| "loss": 1.3285910606384277, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.2541970976003035, | |
| "grad_norm": 0.19997210800647736, | |
| "learning_rate": 0.00017491999987739407, | |
| "loss": 1.3560134887695312, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.25609409086597745, | |
| "grad_norm": 0.15151430666446686, | |
| "learning_rate": 0.00017451154257614287, | |
| "loss": 1.3579360961914062, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.25799108413165134, | |
| "grad_norm": 0.1861380785703659, | |
| "learning_rate": 0.0001741002711702487, | |
| "loss": 1.3282907485961915, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.2598880773973252, | |
| "grad_norm": 0.21051962673664093, | |
| "learning_rate": 0.00017368620119234896, | |
| "loss": 1.3513029098510743, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.26178507066299916, | |
| "grad_norm": 0.20640310645103455, | |
| "learning_rate": 0.00017326934828077573, | |
| "loss": 1.3803365707397461, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.26368206392867305, | |
| "grad_norm": 0.2142738252878189, | |
| "learning_rate": 0.00017284972817896522, | |
| "loss": 1.3414445877075196, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.26557905719434693, | |
| "grad_norm": 0.20645789802074432, | |
| "learning_rate": 0.000172427356734863, | |
| "loss": 1.3097976684570312, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.2674760504600209, | |
| "grad_norm": 0.18269935250282288, | |
| "learning_rate": 0.00017200224990032576, | |
| "loss": 1.3330297470092773, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.26937304372569476, | |
| "grad_norm": 0.20840169489383698, | |
| "learning_rate": 0.0001715744237305185, | |
| "loss": 1.3247990608215332, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.2712700369913687, | |
| "grad_norm": 0.18385033309459686, | |
| "learning_rate": 0.00017114389438330847, | |
| "loss": 1.3525686264038086, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.2731670302570426, | |
| "grad_norm": 0.2120097428560257, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.2947080612182618, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.27506402352271647, | |
| "grad_norm": 0.1786690503358841, | |
| "learning_rate": 0.0001702747912979943, | |
| "loss": 1.3325854301452638, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.2769610167883904, | |
| "grad_norm": 0.16804367303848267, | |
| "learning_rate": 0.0001698362503836238, | |
| "loss": 1.3193418502807617, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.2788580100540643, | |
| "grad_norm": 0.22369125485420227, | |
| "learning_rate": 0.0001693950719380782, | |
| "loss": 1.334280776977539, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.28075500331973824, | |
| "grad_norm": 0.1752845048904419, | |
| "learning_rate": 0.0001689512726235049, | |
| "loss": 1.3591064453125, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.2826519965854121, | |
| "grad_norm": 0.1956092268228531, | |
| "learning_rate": 0.00016850486920103478, | |
| "loss": 1.3456398010253907, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.284548989851086, | |
| "grad_norm": 0.196893110871315, | |
| "learning_rate": 0.00016805587853014895, | |
| "loss": 1.299994659423828, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.28644598311675995, | |
| "grad_norm": 0.22995737195014954, | |
| "learning_rate": 0.00016760431756804203, | |
| "loss": 1.3202781677246094, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.28834297638243384, | |
| "grad_norm": 0.2316529005765915, | |
| "learning_rate": 0.0001671502033689818, | |
| "loss": 1.3736864089965821, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.2902399696481078, | |
| "grad_norm": 0.17965248227119446, | |
| "learning_rate": 0.0001666935530836651, | |
| "loss": 1.3004459381103515, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.29213696291378166, | |
| "grad_norm": 0.1987454891204834, | |
| "learning_rate": 0.00016623438395857, | |
| "loss": 1.296003246307373, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.29403395617945555, | |
| "grad_norm": 0.21007826924324036, | |
| "learning_rate": 0.00016577271333530463, | |
| "loss": 1.2934464454650878, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.2959309494451295, | |
| "grad_norm": 0.21379446983337402, | |
| "learning_rate": 0.00016530855864995195, | |
| "loss": 1.3648219108581543, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.2978279427108034, | |
| "grad_norm": 0.2304612696170807, | |
| "learning_rate": 0.00016484193743241155, | |
| "loss": 1.3684311866760255, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.29972493597647726, | |
| "grad_norm": 0.2060135006904602, | |
| "learning_rate": 0.00016437286730573732, | |
| "loss": 1.307310199737549, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.3016219292421512, | |
| "grad_norm": 0.23283755779266357, | |
| "learning_rate": 0.00016390136598547217, | |
| "loss": 1.2853206634521483, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.3035189225078251, | |
| "grad_norm": 0.25028491020202637, | |
| "learning_rate": 0.00016342745127897855, | |
| "loss": 1.2227279663085937, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.305415915773499, | |
| "grad_norm": 0.1912398636341095, | |
| "learning_rate": 0.00016295114108476634, | |
| "loss": 1.2827722549438476, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.3073129090391729, | |
| "grad_norm": 0.201055109500885, | |
| "learning_rate": 0.00016247245339181662, | |
| "loss": 1.4329465866088866, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.3092099023048468, | |
| "grad_norm": 0.19105757772922516, | |
| "learning_rate": 0.00016199140627890226, | |
| "loss": 1.3207405090332032, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.31110689557052074, | |
| "grad_norm": 0.17966996133327484, | |
| "learning_rate": 0.00016150801791390532, | |
| "loss": 1.361721134185791, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.3130038888361946, | |
| "grad_norm": 0.21430671215057373, | |
| "learning_rate": 0.00016102230655313076, | |
| "loss": 1.352975845336914, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.31490088210186856, | |
| "grad_norm": 0.20482604205608368, | |
| "learning_rate": 0.00016053429054061687, | |
| "loss": 1.3699129104614258, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.31679787536754245, | |
| "grad_norm": 0.22587953507900238, | |
| "learning_rate": 0.00016004398830744268, | |
| "loss": 1.2764925956726074, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.31869486863321633, | |
| "grad_norm": 0.2138352394104004, | |
| "learning_rate": 0.00015955141837103168, | |
| "loss": 1.3355313301086427, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.3205918618988903, | |
| "grad_norm": 0.20189088582992554, | |
| "learning_rate": 0.0001590565993344526, | |
| "loss": 1.3690929412841797, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.32248885516456416, | |
| "grad_norm": 0.20826689898967743, | |
| "learning_rate": 0.0001585595498857167, | |
| "loss": 1.3091952323913574, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.3243858484302381, | |
| "grad_norm": 0.2140590399503708, | |
| "learning_rate": 0.0001580602887970721, | |
| "loss": 1.3622547149658204, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.326282841695912, | |
| "grad_norm": 0.20611706376075745, | |
| "learning_rate": 0.0001575588349242946, | |
| "loss": 1.3146515846252442, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.32817983496158587, | |
| "grad_norm": 0.18523219227790833, | |
| "learning_rate": 0.0001570552072059758, | |
| "loss": 1.283697509765625, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.3300768282272598, | |
| "grad_norm": 0.17493973672389984, | |
| "learning_rate": 0.0001565494246628077, | |
| "loss": 1.3162271499633789, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.3319738214929337, | |
| "grad_norm": 0.18968380987644196, | |
| "learning_rate": 0.00015604150639686435, | |
| "loss": 1.2837004661560059, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.3338708147586076, | |
| "grad_norm": 0.17936478555202484, | |
| "learning_rate": 0.00015553147159088035, | |
| "loss": 1.2965280532836914, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.3357678080242815, | |
| "grad_norm": 0.1989327371120453, | |
| "learning_rate": 0.00015501933950752656, | |
| "loss": 1.297536849975586, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.3376648012899554, | |
| "grad_norm": 0.18209834396839142, | |
| "learning_rate": 0.0001545051294886824, | |
| "loss": 1.2731256484985352, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.33956179455562935, | |
| "grad_norm": 0.20465397834777832, | |
| "learning_rate": 0.00015398886095470548, | |
| "loss": 1.267664909362793, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.34145878782130323, | |
| "grad_norm": 0.18621164560317993, | |
| "learning_rate": 0.00015347055340369804, | |
| "loss": 1.3370386123657227, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.3433557810869771, | |
| "grad_norm": 0.21731416881084442, | |
| "learning_rate": 0.00015295022641077072, | |
| "loss": 1.3455377578735352, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.34525277435265106, | |
| "grad_norm": 0.20505161583423615, | |
| "learning_rate": 0.00015242789962730305, | |
| "loss": 1.3124773979187012, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.34714976761832494, | |
| "grad_norm": 0.2548351585865021, | |
| "learning_rate": 0.0001519035927802015, | |
| "loss": 1.3816186904907226, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.3490467608839989, | |
| "grad_norm": 0.19469887018203735, | |
| "learning_rate": 0.0001513773256711542, | |
| "loss": 1.2894102096557618, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.35094375414967277, | |
| "grad_norm": 0.20962540805339813, | |
| "learning_rate": 0.00015084911817588327, | |
| "loss": 1.3270418167114257, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.35284074741534666, | |
| "grad_norm": 0.1830635815858841, | |
| "learning_rate": 0.00015031899024339415, | |
| "loss": 1.2324066162109375, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.3547377406810206, | |
| "grad_norm": 0.22402457892894745, | |
| "learning_rate": 0.0001497869618952221, | |
| "loss": 1.2613957405090332, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.3566347339466945, | |
| "grad_norm": 0.20581883192062378, | |
| "learning_rate": 0.000149253053224676, | |
| "loss": 1.2442885398864747, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.3585317272123684, | |
| "grad_norm": 0.2548545300960541, | |
| "learning_rate": 0.00014871728439607966, | |
| "loss": 1.3380386352539062, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.3604287204780423, | |
| "grad_norm": 0.24616223573684692, | |
| "learning_rate": 0.0001481796756440101, | |
| "loss": 1.2693334579467774, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.3623257137437162, | |
| "grad_norm": 0.1899973303079605, | |
| "learning_rate": 0.00014764024727253344, | |
| "loss": 1.304777240753174, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.36422270700939013, | |
| "grad_norm": 0.2007388025522232, | |
| "learning_rate": 0.00014709901965443794, | |
| "loss": 1.2871871948242188, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.366119700275064, | |
| "grad_norm": 0.2086300253868103, | |
| "learning_rate": 0.00014655601323046476, | |
| "loss": 1.3016556739807128, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.3680166935407379, | |
| "grad_norm": 0.17843444645404816, | |
| "learning_rate": 0.00014601124850853586, | |
| "loss": 1.2881378173828124, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.36991368680641185, | |
| "grad_norm": 0.2051367312669754, | |
| "learning_rate": 0.0001454647460629795, | |
| "loss": 1.2788877487182617, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.37181068007208573, | |
| "grad_norm": 0.2431752234697342, | |
| "learning_rate": 0.00014491652653375305, | |
| "loss": 1.3235971450805664, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.37370767333775967, | |
| "grad_norm": 0.18031497299671173, | |
| "learning_rate": 0.0001443666106256638, | |
| "loss": 1.2953450202941894, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.37560466660343356, | |
| "grad_norm": 0.2388775646686554, | |
| "learning_rate": 0.00014381501910758662, | |
| "loss": 1.2675777435302735, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.37750165986910744, | |
| "grad_norm": 0.19682824611663818, | |
| "learning_rate": 0.00014326177281167985, | |
| "loss": 1.2624688148498535, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.3793986531347814, | |
| "grad_norm": 0.18745169043540955, | |
| "learning_rate": 0.00014270689263259846, | |
| "loss": 1.322650146484375, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.38129564640045527, | |
| "grad_norm": 0.17187544703483582, | |
| "learning_rate": 0.0001421503995267048, | |
| "loss": 1.269672966003418, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.3831926396661292, | |
| "grad_norm": 0.2526921033859253, | |
| "learning_rate": 0.00014159231451127727, | |
| "loss": 1.2577630043029786, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.3850896329318031, | |
| "grad_norm": 0.22343941032886505, | |
| "learning_rate": 0.00014103265866371648, | |
| "loss": 1.296259307861328, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.386986626197477, | |
| "grad_norm": 0.19871598482131958, | |
| "learning_rate": 0.0001404714531207492, | |
| "loss": 1.2373783111572265, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.3888836194631509, | |
| "grad_norm": 0.23841656744480133, | |
| "learning_rate": 0.00013990871907763018, | |
| "loss": 1.2999099731445312, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.3907806127288248, | |
| "grad_norm": 0.20639006793498993, | |
| "learning_rate": 0.00013934447778734158, | |
| "loss": 1.2921713829040526, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.39267760599449875, | |
| "grad_norm": 0.2078259289264679, | |
| "learning_rate": 0.00013877875055979023, | |
| "loss": 1.2720942497253418, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.39457459926017263, | |
| "grad_norm": 0.20259065926074982, | |
| "learning_rate": 0.000138211558761003, | |
| "loss": 1.2835742950439453, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.3964715925258465, | |
| "grad_norm": 0.20163212716579437, | |
| "learning_rate": 0.0001376429238123197, | |
| "loss": 1.3011070251464845, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.39836858579152046, | |
| "grad_norm": 0.2062864452600479, | |
| "learning_rate": 0.00013707286718958413, | |
| "loss": 1.2368831634521484, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.40026557905719434, | |
| "grad_norm": 0.181606262922287, | |
| "learning_rate": 0.00013650141042233297, | |
| "loss": 1.281895351409912, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.40216257232286823, | |
| "grad_norm": 0.20585131645202637, | |
| "learning_rate": 0.00013592857509298268, | |
| "loss": 1.3360076904296876, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.40405956558854217, | |
| "grad_norm": 0.1852632313966751, | |
| "learning_rate": 0.00013535438283601435, | |
| "loss": 1.2859407424926759, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.40595655885421605, | |
| "grad_norm": 0.20051412284374237, | |
| "learning_rate": 0.00013477885533715668, | |
| "loss": 1.249165153503418, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.40785355211989, | |
| "grad_norm": 0.2008315920829773, | |
| "learning_rate": 0.00013420201433256689, | |
| "loss": 1.269383430480957, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.4097505453855639, | |
| "grad_norm": 0.17607596516609192, | |
| "learning_rate": 0.0001336238816080099, | |
| "loss": 1.2492810249328614, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.41164753865123777, | |
| "grad_norm": 0.18373461067676544, | |
| "learning_rate": 0.00013304447899803549, | |
| "loss": 1.3219100952148437, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.4135445319169117, | |
| "grad_norm": 0.22188381850719452, | |
| "learning_rate": 0.00013246382838515367, | |
| "loss": 1.3046795845031738, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.4154415251825856, | |
| "grad_norm": 0.23975761234760284, | |
| "learning_rate": 0.00013188195169900813, | |
| "loss": 1.2554540634155273, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.41733851844825953, | |
| "grad_norm": 0.18879424035549164, | |
| "learning_rate": 0.0001312988709155483, | |
| "loss": 1.2557123184204102, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.4192355117139334, | |
| "grad_norm": 0.19745565950870514, | |
| "learning_rate": 0.000130714608056199, | |
| "loss": 1.282470703125, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.4211325049796073, | |
| "grad_norm": 0.18979977071285248, | |
| "learning_rate": 0.00013012918518702914, | |
| "loss": 1.3009231567382813, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.42302949824528124, | |
| "grad_norm": 0.20928719639778137, | |
| "learning_rate": 0.0001295426244179179, | |
| "loss": 1.2097282409667969, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.42492649151095513, | |
| "grad_norm": 0.21866299211978912, | |
| "learning_rate": 0.00012895494790172025, | |
| "loss": 1.2436193466186523, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.42682348477662907, | |
| "grad_norm": 0.1949414312839508, | |
| "learning_rate": 0.0001283661778334297, | |
| "loss": 1.2641895294189454, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.42872047804230295, | |
| "grad_norm": 0.23283155262470245, | |
| "learning_rate": 0.00012777633644934047, | |
| "loss": 1.2731650352478028, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.43061747130797684, | |
| "grad_norm": 0.21802668273448944, | |
| "learning_rate": 0.0001271854460262076, | |
| "loss": 1.2623106002807618, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 0.4325144645736508, | |
| "grad_norm": 0.22303332388401031, | |
| "learning_rate": 0.00012659352888040547, | |
| "loss": 1.2655641555786132, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.43441145783932467, | |
| "grad_norm": 0.22781869769096375, | |
| "learning_rate": 0.0001260006073670851, | |
| "loss": 1.2422977447509767, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 0.43630845110499855, | |
| "grad_norm": 0.22849875688552856, | |
| "learning_rate": 0.0001254067038793299, | |
| "loss": 1.21691837310791, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.4382054443706725, | |
| "grad_norm": 0.17269012331962585, | |
| "learning_rate": 0.00012481184084730976, | |
| "loss": 1.2927635192871094, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.4401024376363464, | |
| "grad_norm": 0.2079879343509674, | |
| "learning_rate": 0.00012421604073743414, | |
| "loss": 1.276127243041992, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.4419994309020203, | |
| "grad_norm": 0.21967045962810516, | |
| "learning_rate": 0.0001236193260515033, | |
| "loss": 1.2668575286865233, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 0.4438964241676942, | |
| "grad_norm": 0.1871863603591919, | |
| "learning_rate": 0.00012302171932585885, | |
| "loss": 1.2879966735839843, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.4457934174333681, | |
| "grad_norm": 0.20915549993515015, | |
| "learning_rate": 0.00012242324313053212, | |
| "loss": 1.213623046875, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.44769041069904203, | |
| "grad_norm": 0.19788159430027008, | |
| "learning_rate": 0.00012182392006839231, | |
| "loss": 1.2968476295471192, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.4495874039647159, | |
| "grad_norm": 0.1836550533771515, | |
| "learning_rate": 0.00012122377277429231, | |
| "loss": 1.3275569915771483, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 0.45148439723038986, | |
| "grad_norm": 0.20611557364463806, | |
| "learning_rate": 0.00012062282391421422, | |
| "loss": 1.2274017333984375, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.45338139049606374, | |
| "grad_norm": 0.20401445031166077, | |
| "learning_rate": 0.0001200210961844131, | |
| "loss": 1.2610235214233398, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 0.4552783837617376, | |
| "grad_norm": 0.19555248320102692, | |
| "learning_rate": 0.00011941861231055994, | |
| "loss": 1.2480643272399903, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.45717537702741157, | |
| "grad_norm": 0.2255406379699707, | |
| "learning_rate": 0.00011881539504688315, | |
| "loss": 1.3372369766235352, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 0.45907237029308545, | |
| "grad_norm": 0.18010838329792023, | |
| "learning_rate": 0.00011821146717530957, | |
| "loss": 1.320176887512207, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.4609693635587594, | |
| "grad_norm": 0.26260077953338623, | |
| "learning_rate": 0.00011760685150460362, | |
| "loss": 1.3166605949401855, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 0.4628663568244333, | |
| "grad_norm": 0.21866309642791748, | |
| "learning_rate": 0.00011700157086950622, | |
| "loss": 1.284672737121582, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.46476335009010716, | |
| "grad_norm": 0.1923605352640152, | |
| "learning_rate": 0.00011639564812987213, | |
| "loss": 1.286249542236328, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.4666603433557811, | |
| "grad_norm": 0.21495236456394196, | |
| "learning_rate": 0.00011578910616980683, | |
| "loss": 1.3092803001403808, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.468557336621455, | |
| "grad_norm": 0.20779795944690704, | |
| "learning_rate": 0.00011518196789680201, | |
| "loss": 1.265378761291504, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 0.4704543298871289, | |
| "grad_norm": 0.2454712986946106, | |
| "learning_rate": 0.00011457425624087057, | |
| "loss": 1.2207672119140625, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.4723513231528028, | |
| "grad_norm": 0.19775822758674622, | |
| "learning_rate": 0.00011396599415368061, | |
| "loss": 1.2256649017333985, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 0.4742483164184767, | |
| "grad_norm": 0.2307257503271103, | |
| "learning_rate": 0.00011335720460768855, | |
| "loss": 1.231745147705078, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.47614530968415064, | |
| "grad_norm": 0.2515580952167511, | |
| "learning_rate": 0.0001127479105952715, | |
| "loss": 1.2185787200927733, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 0.4780423029498245, | |
| "grad_norm": 0.24548013508319855, | |
| "learning_rate": 0.00011213813512785898, | |
| "loss": 1.2365056991577148, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.4799392962154984, | |
| "grad_norm": 0.2566676437854767, | |
| "learning_rate": 0.00011152790123506374, | |
| "loss": 1.2476604461669922, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 0.48183628948117235, | |
| "grad_norm": 0.27034300565719604, | |
| "learning_rate": 0.00011091723196381214, | |
| "loss": 1.1881632804870605, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.48373328274684624, | |
| "grad_norm": 0.22327835857868195, | |
| "learning_rate": 0.00011030615037747353, | |
| "loss": 1.2311485290527344, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.4856302760125202, | |
| "grad_norm": 0.24171949923038483, | |
| "learning_rate": 0.00010969467955498947, | |
| "loss": 1.2696138381958009, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.48752726927819406, | |
| "grad_norm": 0.19679434597492218, | |
| "learning_rate": 0.00010908284259000173, | |
| "loss": 1.2908681869506835, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 0.48942426254386795, | |
| "grad_norm": 0.23002123832702637, | |
| "learning_rate": 0.00010847066258998053, | |
| "loss": 1.2322309494018555, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.4913212558095419, | |
| "grad_norm": 0.17921766638755798, | |
| "learning_rate": 0.00010785816267535144, | |
| "loss": 1.206237506866455, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.4932182490752158, | |
| "grad_norm": 0.19494792819023132, | |
| "learning_rate": 0.00010724536597862254, | |
| "loss": 1.2545565605163573, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.4951152423408897, | |
| "grad_norm": 0.19780462980270386, | |
| "learning_rate": 0.00010663229564351041, | |
| "loss": 1.239597702026367, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 0.4970122356065636, | |
| "grad_norm": 0.18496356904506683, | |
| "learning_rate": 0.00010601897482406633, | |
| "loss": 1.2728466987609863, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.4989092288722375, | |
| "grad_norm": 0.24206936359405518, | |
| "learning_rate": 0.00010540542668380173, | |
| "loss": 1.2206164360046388, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 0.5008062221379114, | |
| "grad_norm": 0.20516863465309143, | |
| "learning_rate": 0.00010479167439481328, | |
| "loss": 1.170132827758789, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.5027032154035853, | |
| "grad_norm": 0.20329366624355316, | |
| "learning_rate": 0.00010417774113690788, | |
| "loss": 1.2430803298950195, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.5046002086692593, | |
| "grad_norm": 0.17009533941745758, | |
| "learning_rate": 0.00010356365009672705, | |
| "loss": 1.217410945892334, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.5064972019349331, | |
| "grad_norm": 0.21874478459358215, | |
| "learning_rate": 0.00010294942446687146, | |
| "loss": 1.2362728118896484, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 0.508394195200607, | |
| "grad_norm": 0.2179032862186432, | |
| "learning_rate": 0.00010233508744502476, | |
| "loss": 1.207392692565918, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.510291188466281, | |
| "grad_norm": 0.21991856396198273, | |
| "learning_rate": 0.00010172066223307768, | |
| "loss": 1.288995361328125, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 0.5121881817319549, | |
| "grad_norm": 0.3171321451663971, | |
| "learning_rate": 0.0001011061720362516, | |
| "loss": 1.2908376693725585, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.5140851749976287, | |
| "grad_norm": 0.17339341342449188, | |
| "learning_rate": 0.00010049164006222217, | |
| "loss": 1.179736042022705, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 0.5159821682633027, | |
| "grad_norm": 0.20369172096252441, | |
| "learning_rate": 9.9877089520243e-05, | |
| "loss": 1.2046426773071288, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.5178791615289766, | |
| "grad_norm": 0.21214434504508972, | |
| "learning_rate": 9.926254362026875e-05, | |
| "loss": 1.1913909912109375, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.5197761547946504, | |
| "grad_norm": 0.20788206160068512, | |
| "learning_rate": 9.864802557207898e-05, | |
| "loss": 1.155370330810547, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.5216731480603244, | |
| "grad_norm": 0.23401576280593872, | |
| "learning_rate": 9.803355858440123e-05, | |
| "loss": 1.1851793289184571, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.5235701413259983, | |
| "grad_norm": 0.20830301940441132, | |
| "learning_rate": 9.741916586403465e-05, | |
| "loss": 1.1580560684204102, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.5254671345916722, | |
| "grad_norm": 0.1879931539297104, | |
| "learning_rate": 9.680487061497347e-05, | |
| "loss": 1.2905543327331543, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 0.5273641278573461, | |
| "grad_norm": 0.19841326773166656, | |
| "learning_rate": 9.619069603753077e-05, | |
| "loss": 1.2813724517822265, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.52926112112302, | |
| "grad_norm": 0.20493440330028534, | |
| "learning_rate": 9.557666532746213e-05, | |
| "loss": 1.2323316574096679, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 0.5311581143886939, | |
| "grad_norm": 0.1874491572380066, | |
| "learning_rate": 9.496280167508965e-05, | |
| "loss": 1.1689970016479492, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.5330551076543678, | |
| "grad_norm": 0.2185971438884735, | |
| "learning_rate": 9.434912826442605e-05, | |
| "loss": 1.23783597946167, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 0.5349521009200418, | |
| "grad_norm": 0.20173834264278412, | |
| "learning_rate": 9.373566827229923e-05, | |
| "loss": 1.236037826538086, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.5368490941857157, | |
| "grad_norm": 0.19091500341892242, | |
| "learning_rate": 9.312244486747675e-05, | |
| "loss": 1.220543384552002, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 0.5387460874513895, | |
| "grad_norm": 0.1970510482788086, | |
| "learning_rate": 9.250948120979092e-05, | |
| "loss": 1.2294425964355469, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.5406430807170635, | |
| "grad_norm": 0.2414364516735077, | |
| "learning_rate": 9.1896800449264e-05, | |
| "loss": 1.2571044921875, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.5425400739827374, | |
| "grad_norm": 0.21326732635498047, | |
| "learning_rate": 9.128442572523417e-05, | |
| "loss": 1.1620418548583984, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.5444370672484112, | |
| "grad_norm": 0.2089395374059677, | |
| "learning_rate": 9.067238016548125e-05, | |
| "loss": 1.240686798095703, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.5463340605140852, | |
| "grad_norm": 0.2580561637878418, | |
| "learning_rate": 9.006068688535342e-05, | |
| "loss": 1.2514863967895509, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.5482310537797591, | |
| "grad_norm": 0.27072176337242126, | |
| "learning_rate": 8.944936898689418e-05, | |
| "loss": 1.2550253868103027, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 0.5501280470454329, | |
| "grad_norm": 0.2212870866060257, | |
| "learning_rate": 8.883844955796994e-05, | |
| "loss": 1.145805549621582, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.5520250403111069, | |
| "grad_norm": 0.2034735232591629, | |
| "learning_rate": 8.822795167139788e-05, | |
| "loss": 1.1998319625854492, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 0.5539220335767808, | |
| "grad_norm": 0.22531533241271973, | |
| "learning_rate": 8.761789838407465e-05, | |
| "loss": 1.20664644241333, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.5558190268424547, | |
| "grad_norm": 0.2536487281322479, | |
| "learning_rate": 8.700831273610553e-05, | |
| "loss": 1.2653702735900878, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 0.5577160201081286, | |
| "grad_norm": 0.1997285932302475, | |
| "learning_rate": 8.639921774993439e-05, | |
| "loss": 1.2373212814331054, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.5596130133738025, | |
| "grad_norm": 0.19519779086112976, | |
| "learning_rate": 8.579063642947404e-05, | |
| "loss": 1.1584996223449706, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.5615100066394765, | |
| "grad_norm": 0.2115306258201599, | |
| "learning_rate": 8.518259175923746e-05, | |
| "loss": 1.2177144050598145, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.5634069999051503, | |
| "grad_norm": 0.20149481296539307, | |
| "learning_rate": 8.457510670346976e-05, | |
| "loss": 1.2159102439880372, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 0.5653039931708242, | |
| "grad_norm": 0.21905744075775146, | |
| "learning_rate": 8.3968204205281e-05, | |
| "loss": 1.2001914978027344, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.5672009864364982, | |
| "grad_norm": 0.24004018306732178, | |
| "learning_rate": 8.336190718577944e-05, | |
| "loss": 1.2156314849853516, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 0.569097979702172, | |
| "grad_norm": 0.20072941482067108, | |
| "learning_rate": 8.275623854320608e-05, | |
| "loss": 1.2034540176391602, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.570994972967846, | |
| "grad_norm": 0.24886475503444672, | |
| "learning_rate": 8.215122115206971e-05, | |
| "loss": 1.2257415771484375, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.5728919662335199, | |
| "grad_norm": 0.20359426736831665, | |
| "learning_rate": 8.154687786228319e-05, | |
| "loss": 1.1787508010864258, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.5747889594991937, | |
| "grad_norm": 0.252313494682312, | |
| "learning_rate": 8.094323149830023e-05, | |
| "loss": 1.2890241622924805, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 0.5766859527648677, | |
| "grad_norm": 0.23567771911621094, | |
| "learning_rate": 8.034030485825354e-05, | |
| "loss": 1.2202719688415526, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.5785829460305416, | |
| "grad_norm": 0.22669225931167603, | |
| "learning_rate": 7.973812071309371e-05, | |
| "loss": 1.2457989692687987, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.5804799392962156, | |
| "grad_norm": 0.22211532294750214, | |
| "learning_rate": 7.913670180572936e-05, | |
| "loss": 1.1853873252868652, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.5823769325618894, | |
| "grad_norm": 0.24924324452877045, | |
| "learning_rate": 7.853607085016801e-05, | |
| "loss": 1.1637990951538086, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 0.5842739258275633, | |
| "grad_norm": 0.21107666194438934, | |
| "learning_rate": 7.793625053065832e-05, | |
| "loss": 1.2016304016113282, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.5861709190932373, | |
| "grad_norm": 0.2091253399848938, | |
| "learning_rate": 7.733726350083332e-05, | |
| "loss": 1.184238815307617, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 0.5880679123589111, | |
| "grad_norm": 0.23442722856998444, | |
| "learning_rate": 7.673913238285502e-05, | |
| "loss": 1.2217123985290528, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.589964905624585, | |
| "grad_norm": 0.20284633338451385, | |
| "learning_rate": 7.61418797665598e-05, | |
| "loss": 1.160600471496582, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 0.591861898890259, | |
| "grad_norm": 0.31940528750419617, | |
| "learning_rate": 7.554552820860534e-05, | |
| "loss": 1.2467886924743652, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.5937588921559328, | |
| "grad_norm": 0.23765164613723755, | |
| "learning_rate": 7.495010023161872e-05, | |
| "loss": 1.172896957397461, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 0.5956558854216067, | |
| "grad_norm": 0.18498869240283966, | |
| "learning_rate": 7.435561832334587e-05, | |
| "loss": 1.234382724761963, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.5975528786872807, | |
| "grad_norm": 0.24276462197303772, | |
| "learning_rate": 7.376210493580212e-05, | |
| "loss": 1.2198051452636718, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.5994498719529545, | |
| "grad_norm": 0.22352980077266693, | |
| "learning_rate": 7.316958248442433e-05, | |
| "loss": 1.2549384117126465, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.6013468652186285, | |
| "grad_norm": 0.2909923195838928, | |
| "learning_rate": 7.257807334722433e-05, | |
| "loss": 1.2120649337768554, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 0.6032438584843024, | |
| "grad_norm": 0.21732081472873688, | |
| "learning_rate": 7.198759986394381e-05, | |
| "loss": 1.2131582260131837, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.6051408517499763, | |
| "grad_norm": 0.21774332225322723, | |
| "learning_rate": 7.139818433521044e-05, | |
| "loss": 1.1869283676147462, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 0.6070378450156502, | |
| "grad_norm": 0.20163221657276154, | |
| "learning_rate": 7.080984902169577e-05, | |
| "loss": 1.1882305145263672, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.6089348382813241, | |
| "grad_norm": 0.21289895474910736, | |
| "learning_rate": 7.022261614327448e-05, | |
| "loss": 1.1871913909912108, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 0.610831831546998, | |
| "grad_norm": 0.22363829612731934, | |
| "learning_rate": 6.96365078781851e-05, | |
| "loss": 1.1149802207946777, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.6127288248126719, | |
| "grad_norm": 0.2320428341627121, | |
| "learning_rate": 6.905154636219264e-05, | |
| "loss": 1.2263916015625, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 0.6146258180783458, | |
| "grad_norm": 0.21106109023094177, | |
| "learning_rate": 6.84677536877523e-05, | |
| "loss": 1.1639060020446776, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.6165228113440198, | |
| "grad_norm": 0.23515655100345612, | |
| "learning_rate": 6.788515190317522e-05, | |
| "loss": 1.129255199432373, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.6184198046096936, | |
| "grad_norm": 0.19230219721794128, | |
| "learning_rate": 6.730376301179578e-05, | |
| "loss": 1.175193977355957, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.6203167978753675, | |
| "grad_norm": 0.18914490938186646, | |
| "learning_rate": 6.672360897114062e-05, | |
| "loss": 1.2488232612609864, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 0.6222137911410415, | |
| "grad_norm": 0.23557758331298828, | |
| "learning_rate": 6.614471169209928e-05, | |
| "loss": 1.1635530471801758, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.6241107844067153, | |
| "grad_norm": 0.18918681144714355, | |
| "learning_rate": 6.556709303809672e-05, | |
| "loss": 1.208155632019043, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.6260077776723892, | |
| "grad_norm": 0.23364251852035522, | |
| "learning_rate": 6.499077482426756e-05, | |
| "loss": 1.1174542427062988, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.6279047709380632, | |
| "grad_norm": 0.22950278222560883, | |
| "learning_rate": 6.441577881663239e-05, | |
| "loss": 1.1948451042175292, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 0.6298017642037371, | |
| "grad_norm": 0.25743988156318665, | |
| "learning_rate": 6.384212673127537e-05, | |
| "loss": 1.1608400344848633, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.631698757469411, | |
| "grad_norm": 0.21918219327926636, | |
| "learning_rate": 6.326984023352435e-05, | |
| "loss": 1.2481471061706544, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 0.6335957507350849, | |
| "grad_norm": 0.21266892552375793, | |
| "learning_rate": 6.269894093713245e-05, | |
| "loss": 1.2023887634277344, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.6354927440007588, | |
| "grad_norm": 0.3113594353199005, | |
| "learning_rate": 6.212945040346202e-05, | |
| "loss": 1.2441641807556152, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.6373897372664327, | |
| "grad_norm": 0.23668617010116577, | |
| "learning_rate": 6.156139014066999e-05, | |
| "loss": 1.191889762878418, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.6392867305321066, | |
| "grad_norm": 0.2231028825044632, | |
| "learning_rate": 6.099478160289577e-05, | |
| "loss": 1.1762910842895509, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 0.6411837237977805, | |
| "grad_norm": 0.22090765833854675, | |
| "learning_rate": 6.042964618945095e-05, | |
| "loss": 1.1695238113403321, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.6430807170634544, | |
| "grad_norm": 0.18710334599018097, | |
| "learning_rate": 5.986600524401112e-05, | |
| "loss": 1.1961393356323242, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 0.6449777103291283, | |
| "grad_norm": 0.20757536590099335, | |
| "learning_rate": 5.930388005380974e-05, | |
| "loss": 1.1660908699035644, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.6468747035948023, | |
| "grad_norm": 0.20771600306034088, | |
| "learning_rate": 5.874329184883416e-05, | |
| "loss": 1.1397218704223633, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 0.6487716968604762, | |
| "grad_norm": 0.20164109766483307, | |
| "learning_rate": 5.818426180102382e-05, | |
| "loss": 1.2242679595947266, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.65066869012615, | |
| "grad_norm": 0.24878183007240295, | |
| "learning_rate": 5.762681102347079e-05, | |
| "loss": 1.1493138313293456, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 0.652565683391824, | |
| "grad_norm": 0.2662266492843628, | |
| "learning_rate": 5.70709605696222e-05, | |
| "loss": 1.2232205390930175, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.6544626766574979, | |
| "grad_norm": 0.2176043540239334, | |
| "learning_rate": 5.651673143248508e-05, | |
| "loss": 1.232991600036621, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.6563596699231717, | |
| "grad_norm": 0.18709635734558105, | |
| "learning_rate": 5.5964144543833704e-05, | |
| "loss": 1.2249370574951173, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.6582566631888457, | |
| "grad_norm": 0.20305493474006653, | |
| "learning_rate": 5.5413220773418996e-05, | |
| "loss": 1.2118049621582032, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 0.6601536564545196, | |
| "grad_norm": 0.2667617201805115, | |
| "learning_rate": 5.48639809281801e-05, | |
| "loss": 1.270402717590332, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.6620506497201935, | |
| "grad_norm": 0.2805268168449402, | |
| "learning_rate": 5.4316445751458944e-05, | |
| "loss": 1.235429573059082, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 0.6639476429858674, | |
| "grad_norm": 0.197420135140419, | |
| "learning_rate": 5.3770635922216404e-05, | |
| "loss": 1.1799503326416017, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.6658446362515413, | |
| "grad_norm": 0.2637590765953064, | |
| "learning_rate": 5.322657205425183e-05, | |
| "loss": 1.170688533782959, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 0.6677416295172152, | |
| "grad_norm": 0.24412654340267181, | |
| "learning_rate": 5.2684274695423904e-05, | |
| "loss": 1.1365674972534179, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.6696386227828891, | |
| "grad_norm": 0.22687046229839325, | |
| "learning_rate": 5.214376432687512e-05, | |
| "loss": 1.1378746032714844, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 0.671535616048563, | |
| "grad_norm": 0.24549344182014465, | |
| "learning_rate": 5.160506136225787e-05, | |
| "loss": 1.162976360321045, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.673432609314237, | |
| "grad_norm": 0.2180204689502716, | |
| "learning_rate": 5.106818614696394e-05, | |
| "loss": 1.1960285186767579, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.6753296025799108, | |
| "grad_norm": 0.21535226702690125, | |
| "learning_rate": 5.053315895735553e-05, | |
| "loss": 1.163905143737793, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.6772265958455848, | |
| "grad_norm": 0.24670955538749695, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.2332889556884765, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 0.6791235891112587, | |
| "grad_norm": 0.24074867367744446, | |
| "learning_rate": 4.94687294109064e-05, | |
| "loss": 1.1779815673828125, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.6810205823769325, | |
| "grad_norm": 0.22606389224529266, | |
| "learning_rate": 4.89393672547651e-05, | |
| "loss": 1.2121391296386719, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 0.6829175756426065, | |
| "grad_norm": 0.20511578023433685, | |
| "learning_rate": 4.841193352419003e-05, | |
| "loss": 1.1417461395263673, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.6848145689082804, | |
| "grad_norm": 0.22529472410678864, | |
| "learning_rate": 4.788644813896347e-05, | |
| "loss": 1.2243699073791503, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 0.6867115621739542, | |
| "grad_norm": 0.21975474059581757, | |
| "learning_rate": 4.736293094528393e-05, | |
| "loss": 1.1933428764343261, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.6886085554396282, | |
| "grad_norm": 0.20201043784618378, | |
| "learning_rate": 4.6841401715016463e-05, | |
| "loss": 1.142533302307129, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 0.6905055487053021, | |
| "grad_norm": 0.23882907629013062, | |
| "learning_rate": 4.632188014494604e-05, | |
| "loss": 1.1638980865478517, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.692402541970976, | |
| "grad_norm": 0.23736515641212463, | |
| "learning_rate": 4.580438585603347e-05, | |
| "loss": 1.1600072860717774, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.6942995352366499, | |
| "grad_norm": 0.24818144738674164, | |
| "learning_rate": 4.52889383926746e-05, | |
| "loss": 1.1760390281677247, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.6961965285023238, | |
| "grad_norm": 0.27509522438049316, | |
| "learning_rate": 4.477555722196204e-05, | |
| "loss": 1.236863899230957, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 0.6980935217679978, | |
| "grad_norm": 0.2285706251859665, | |
| "learning_rate": 4.426426173295002e-05, | |
| "loss": 1.1898836135864257, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.6999905150336716, | |
| "grad_norm": 0.2012941837310791, | |
| "learning_rate": 4.375507123592194e-05, | |
| "loss": 1.1771772384643555, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 0.7018875082993455, | |
| "grad_norm": 0.28851866722106934, | |
| "learning_rate": 4.32480049616613e-05, | |
| "loss": 1.158454990386963, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.7037845015650195, | |
| "grad_norm": 0.24860988557338715, | |
| "learning_rate": 4.274308206072535e-05, | |
| "loss": 1.1685667991638184, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 0.7056814948306933, | |
| "grad_norm": 0.20114919543266296, | |
| "learning_rate": 4.224032160272159e-05, | |
| "loss": 1.1596654891967773, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.7075784880963673, | |
| "grad_norm": 0.255470335483551, | |
| "learning_rate": 4.173974257558797e-05, | |
| "loss": 1.243448257446289, | |
| "step": 1865 | |
| }, | |
| { | |
| "epoch": 0.7094754813620412, | |
| "grad_norm": 0.18783412873744965, | |
| "learning_rate": 4.124136388487533e-05, | |
| "loss": 1.193150520324707, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.711372474627715, | |
| "grad_norm": 0.20374606549739838, | |
| "learning_rate": 4.074520435303383e-05, | |
| "loss": 1.1739991188049317, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.713269467893389, | |
| "grad_norm": 0.21200264990329742, | |
| "learning_rate": 4.025128271870163e-05, | |
| "loss": 1.1650808334350586, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.7151664611590629, | |
| "grad_norm": 0.20658573508262634, | |
| "learning_rate": 3.975961763599758e-05, | |
| "loss": 1.0997920989990235, | |
| "step": 1885 | |
| }, | |
| { | |
| "epoch": 0.7170634544247368, | |
| "grad_norm": 0.28224197030067444, | |
| "learning_rate": 3.927022767381634e-05, | |
| "loss": 1.158374309539795, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.7189604476904107, | |
| "grad_norm": 0.2197619080543518, | |
| "learning_rate": 3.8783131315127396e-05, | |
| "loss": 1.185719871520996, | |
| "step": 1895 | |
| }, | |
| { | |
| "epoch": 0.7208574409560846, | |
| "grad_norm": 0.23441337049007416, | |
| "learning_rate": 3.8298346956276844e-05, | |
| "loss": 1.1527414321899414, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.7227544342217586, | |
| "grad_norm": 0.24200305342674255, | |
| "learning_rate": 3.781589290629266e-05, | |
| "loss": 1.1757864952087402, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 0.7246514274874324, | |
| "grad_norm": 0.26121246814727783, | |
| "learning_rate": 3.733578738619308e-05, | |
| "loss": 1.0925329208374024, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.7265484207531063, | |
| "grad_norm": 0.21299229562282562, | |
| "learning_rate": 3.6858048528298674e-05, | |
| "loss": 1.1406631469726562, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 0.7284454140187803, | |
| "grad_norm": 0.21913844347000122, | |
| "learning_rate": 3.638269437554741e-05, | |
| "loss": 1.211923599243164, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.7303424072844541, | |
| "grad_norm": 0.2512378692626953, | |
| "learning_rate": 3.5909742880813124e-05, | |
| "loss": 1.2025384902954102, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.732239400550128, | |
| "grad_norm": 0.26503387093544006, | |
| "learning_rate": 3.543921190622773e-05, | |
| "loss": 1.1477834701538085, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.734136393815802, | |
| "grad_norm": 0.36298081278800964, | |
| "learning_rate": 3.49711192225063e-05, | |
| "loss": 1.1554058074951172, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 0.7360333870814758, | |
| "grad_norm": 0.24738597869873047, | |
| "learning_rate": 3.4505482508276324e-05, | |
| "loss": 1.1143407821655273, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.7379303803471498, | |
| "grad_norm": 0.19787810742855072, | |
| "learning_rate": 3.404231934940954e-05, | |
| "loss": 1.2013814926147461, | |
| "step": 1945 | |
| }, | |
| { | |
| "epoch": 0.7398273736128237, | |
| "grad_norm": 0.2378448247909546, | |
| "learning_rate": 3.3581647238358215e-05, | |
| "loss": 1.1420949935913085, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.7417243668784976, | |
| "grad_norm": 0.27126768231391907, | |
| "learning_rate": 3.3123483573494115e-05, | |
| "loss": 1.2647994995117187, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 0.7436213601441715, | |
| "grad_norm": 0.22936832904815674, | |
| "learning_rate": 3.266784565845186e-05, | |
| "loss": 1.1996916770935058, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.7455183534098454, | |
| "grad_norm": 0.23838719725608826, | |
| "learning_rate": 3.2214750701474874e-05, | |
| "loss": 1.2310851097106934, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 0.7474153466755193, | |
| "grad_norm": 0.22581499814987183, | |
| "learning_rate": 3.176421581476598e-05, | |
| "loss": 1.1289426803588867, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.7493123399411932, | |
| "grad_norm": 0.374156653881073, | |
| "learning_rate": 3.1316258013840703e-05, | |
| "loss": 1.1885247230529785, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 0.7512093332068671, | |
| "grad_norm": 0.2333122044801712, | |
| "learning_rate": 3.0870894216884995e-05, | |
| "loss": 1.173564338684082, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.753106326472541, | |
| "grad_norm": 0.245693638920784, | |
| "learning_rate": 3.0428141244116027e-05, | |
| "loss": 1.1663657188415528, | |
| "step": 1985 | |
| }, | |
| { | |
| "epoch": 0.7550033197382149, | |
| "grad_norm": 0.3405570983886719, | |
| "learning_rate": 2.9988015817146998e-05, | |
| "loss": 1.1686902046203613, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.7569003130038888, | |
| "grad_norm": 0.3073011040687561, | |
| "learning_rate": 2.955053455835568e-05, | |
| "loss": 1.2125859260559082, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 0.7587973062695628, | |
| "grad_norm": 0.23160114884376526, | |
| "learning_rate": 2.9115713990256564e-05, | |
| "loss": 1.1226896286010741, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 2636, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.282217855212585e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |