Instructions to use namuunbt02/gemma_conversational with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use namuunbt02/gemma_conversational with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-3n-E4B-it") model = PeftModel.from_pretrained(base_model, "namuunbt02/gemma_conversational") - Transformers
How to use namuunbt02/gemma_conversational with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="namuunbt02/gemma_conversational") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("namuunbt02/gemma_conversational", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use namuunbt02/gemma_conversational with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "namuunbt02/gemma_conversational" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "namuunbt02/gemma_conversational", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/namuunbt02/gemma_conversational
- SGLang
How to use namuunbt02/gemma_conversational 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 "namuunbt02/gemma_conversational" \ --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": "namuunbt02/gemma_conversational", "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 "namuunbt02/gemma_conversational" \ --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": "namuunbt02/gemma_conversational", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use namuunbt02/gemma_conversational with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for namuunbt02/gemma_conversational to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for namuunbt02/gemma_conversational to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for namuunbt02/gemma_conversational to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="namuunbt02/gemma_conversational", max_seq_length=2048, ) - Docker Model Runner
How to use namuunbt02/gemma_conversational with Docker Model Runner:
docker model run hf.co/namuunbt02/gemma_conversational
| { | |
| "best_global_step": 1842, | |
| "best_metric": 1.0541821718215942, | |
| "best_model_checkpoint": "/home/astgpu3/workspace/znamuun/gemma_unsloth/output/conversational_v1_30k/checkpoint-1842", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 1842, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0054333061668024995, | |
| "grad_norm": 94.05772399902344, | |
| "learning_rate": 0.00016, | |
| "loss": 5.5664, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010866612333604999, | |
| "grad_norm": 13.2901029586792, | |
| "learning_rate": 0.00019970993473531544, | |
| "loss": 2.3616, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016299918500407497, | |
| "grad_norm": 7.427643775939941, | |
| "learning_rate": 0.00019934735315445975, | |
| "loss": 1.9261, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021733224667209998, | |
| "grad_norm": 5.632727146148682, | |
| "learning_rate": 0.00019898477157360406, | |
| "loss": 1.7626, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.027166530834012496, | |
| "grad_norm": 4.494379997253418, | |
| "learning_rate": 0.00019862218999274836, | |
| "loss": 1.6662, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.032599837000814993, | |
| "grad_norm": 4.2322516441345215, | |
| "learning_rate": 0.00019825960841189267, | |
| "loss": 1.5438, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.038033143167617495, | |
| "grad_norm": 3.744213104248047, | |
| "learning_rate": 0.00019789702683103698, | |
| "loss": 1.5352, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.043466449334419996, | |
| "grad_norm": 3.162693738937378, | |
| "learning_rate": 0.0001975344452501813, | |
| "loss": 1.4912, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0488997555012225, | |
| "grad_norm": 2.6240363121032715, | |
| "learning_rate": 0.00019717186366932562, | |
| "loss": 1.4284, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05433306166802499, | |
| "grad_norm": 2.9256842136383057, | |
| "learning_rate": 0.00019680928208846993, | |
| "loss": 1.4817, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05976636783482749, | |
| "grad_norm": 2.765918493270874, | |
| "learning_rate": 0.00019644670050761423, | |
| "loss": 1.4454, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.06519967400162999, | |
| "grad_norm": 2.6395816802978516, | |
| "learning_rate": 0.00019608411892675854, | |
| "loss": 1.3469, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07063298016843249, | |
| "grad_norm": 2.685492753982544, | |
| "learning_rate": 0.00019572153734590285, | |
| "loss": 1.3815, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.07606628633523499, | |
| "grad_norm": 2.7929065227508545, | |
| "learning_rate": 0.00019535895576504715, | |
| "loss": 1.3455, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08149959250203749, | |
| "grad_norm": 2.353255271911621, | |
| "learning_rate": 0.00019499637418419146, | |
| "loss": 1.3715, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.08693289866883999, | |
| "grad_norm": 2.219590902328491, | |
| "learning_rate": 0.00019463379260333577, | |
| "loss": 1.3263, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0923662048356425, | |
| "grad_norm": 2.428845167160034, | |
| "learning_rate": 0.00019427121102248007, | |
| "loss": 1.3271, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.097799511002445, | |
| "grad_norm": 2.2855656147003174, | |
| "learning_rate": 0.00019390862944162438, | |
| "loss": 1.2585, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.10323281716924748, | |
| "grad_norm": 1.8471496105194092, | |
| "learning_rate": 0.00019354604786076869, | |
| "loss": 1.3017, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.10866612333604998, | |
| "grad_norm": 1.90038001537323, | |
| "learning_rate": 0.000193183466279913, | |
| "loss": 1.3322, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11409942950285248, | |
| "grad_norm": 2.1164159774780273, | |
| "learning_rate": 0.0001928208846990573, | |
| "loss": 1.2592, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.11953273566965499, | |
| "grad_norm": 1.8444099426269531, | |
| "learning_rate": 0.0001924583031182016, | |
| "loss": 1.2927, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.12496604183645749, | |
| "grad_norm": 1.9745773077011108, | |
| "learning_rate": 0.0001920957215373459, | |
| "loss": 1.2741, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.13039934800325997, | |
| "grad_norm": 2.013883113861084, | |
| "learning_rate": 0.00019173313995649022, | |
| "loss": 1.3218, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.1358326541700625, | |
| "grad_norm": 2.1666481494903564, | |
| "learning_rate": 0.00019137055837563453, | |
| "loss": 1.3297, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.14126596033686498, | |
| "grad_norm": 2.155470371246338, | |
| "learning_rate": 0.00019100797679477883, | |
| "loss": 1.2874, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1466992665036675, | |
| "grad_norm": 1.8312768936157227, | |
| "learning_rate": 0.00019064539521392314, | |
| "loss": 1.2409, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.15213257267046998, | |
| "grad_norm": 2.063589096069336, | |
| "learning_rate": 0.00019028281363306745, | |
| "loss": 1.2179, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1575658788372725, | |
| "grad_norm": 1.747312068939209, | |
| "learning_rate": 0.00018992023205221175, | |
| "loss": 1.3022, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.16299918500407498, | |
| "grad_norm": 1.7806073427200317, | |
| "learning_rate": 0.0001895576504713561, | |
| "loss": 1.217, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16843249117087747, | |
| "grad_norm": 1.837993860244751, | |
| "learning_rate": 0.0001891950688905004, | |
| "loss": 1.2132, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.17386579733767998, | |
| "grad_norm": 1.7257343530654907, | |
| "learning_rate": 0.0001888324873096447, | |
| "loss": 1.2665, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.17929910350448247, | |
| "grad_norm": 1.8893738985061646, | |
| "learning_rate": 0.00018846990572878898, | |
| "loss": 1.2344, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.184732409671285, | |
| "grad_norm": 1.6077213287353516, | |
| "learning_rate": 0.0001881073241479333, | |
| "loss": 1.1938, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.19016571583808747, | |
| "grad_norm": 1.6754542589187622, | |
| "learning_rate": 0.0001877447425670776, | |
| "loss": 1.1868, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.19559902200489, | |
| "grad_norm": 1.7836875915527344, | |
| "learning_rate": 0.0001873821609862219, | |
| "loss": 1.2142, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.20103232817169248, | |
| "grad_norm": 1.6601991653442383, | |
| "learning_rate": 0.0001870195794053662, | |
| "loss": 1.2607, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.20646563433849496, | |
| "grad_norm": 1.870048999786377, | |
| "learning_rate": 0.00018665699782451051, | |
| "loss": 1.2084, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.21189894050529748, | |
| "grad_norm": 1.7718192338943481, | |
| "learning_rate": 0.00018629441624365482, | |
| "loss": 1.2659, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.21733224667209997, | |
| "grad_norm": 1.585939645767212, | |
| "learning_rate": 0.00018593183466279913, | |
| "loss": 1.1891, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22276555283890248, | |
| "grad_norm": 1.764376163482666, | |
| "learning_rate": 0.00018556925308194343, | |
| "loss": 1.1859, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.22819885900570497, | |
| "grad_norm": 1.412095546722412, | |
| "learning_rate": 0.00018520667150108774, | |
| "loss": 1.1426, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.23363216517250748, | |
| "grad_norm": 1.6154894828796387, | |
| "learning_rate": 0.00018484408992023205, | |
| "loss": 1.2003, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.23906547133930997, | |
| "grad_norm": 1.4826689958572388, | |
| "learning_rate": 0.00018448150833937635, | |
| "loss": 1.188, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.24449877750611246, | |
| "grad_norm": 1.6184778213500977, | |
| "learning_rate": 0.00018411892675852066, | |
| "loss": 1.2223, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.24993208367291497, | |
| "grad_norm": 1.756441593170166, | |
| "learning_rate": 0.00018375634517766497, | |
| "loss": 1.2589, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.25536538983971746, | |
| "grad_norm": 1.475306510925293, | |
| "learning_rate": 0.00018339376359680928, | |
| "loss": 1.1927, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.26079869600651995, | |
| "grad_norm": 1.4867374897003174, | |
| "learning_rate": 0.00018303118201595358, | |
| "loss": 1.1579, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2662320021733225, | |
| "grad_norm": 1.6788930892944336, | |
| "learning_rate": 0.00018266860043509792, | |
| "loss": 1.1589, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.271665308340125, | |
| "grad_norm": 1.4673781394958496, | |
| "learning_rate": 0.00018230601885424222, | |
| "loss": 1.1274, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.27709861450692747, | |
| "grad_norm": 1.6435223817825317, | |
| "learning_rate": 0.00018194343727338653, | |
| "loss": 1.1959, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.28253192067372995, | |
| "grad_norm": 1.4649943113327026, | |
| "learning_rate": 0.00018158085569253084, | |
| "loss": 1.1783, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.28796522684053244, | |
| "grad_norm": 1.6235178709030151, | |
| "learning_rate": 0.00018121827411167514, | |
| "loss": 1.2556, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.293398533007335, | |
| "grad_norm": 1.404118537902832, | |
| "learning_rate": 0.00018085569253081945, | |
| "loss": 1.2253, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.29883183917413747, | |
| "grad_norm": 1.3945000171661377, | |
| "learning_rate": 0.00018049311094996376, | |
| "loss": 1.1298, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.30426514534093996, | |
| "grad_norm": 1.40553879737854, | |
| "learning_rate": 0.00018013052936910806, | |
| "loss": 1.0989, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.30969845150774244, | |
| "grad_norm": 1.51361882686615, | |
| "learning_rate": 0.00017976794778825237, | |
| "loss": 1.2315, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.315131757674545, | |
| "grad_norm": 1.4282881021499634, | |
| "learning_rate": 0.00017940536620739668, | |
| "loss": 1.1301, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.3205650638413475, | |
| "grad_norm": 1.3679155111312866, | |
| "learning_rate": 0.00017904278462654098, | |
| "loss": 1.1215, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.32599837000814996, | |
| "grad_norm": 1.3678269386291504, | |
| "learning_rate": 0.0001786802030456853, | |
| "loss": 1.0858, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.33143167617495245, | |
| "grad_norm": 1.320778250694275, | |
| "learning_rate": 0.0001783176214648296, | |
| "loss": 1.142, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.33686498234175494, | |
| "grad_norm": 1.4018844366073608, | |
| "learning_rate": 0.0001779550398839739, | |
| "loss": 1.1729, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.3422982885085575, | |
| "grad_norm": 1.6065289974212646, | |
| "learning_rate": 0.0001775924583031182, | |
| "loss": 1.1491, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.34773159467535997, | |
| "grad_norm": 1.463248610496521, | |
| "learning_rate": 0.00017722987672226252, | |
| "loss": 1.1071, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.35316490084216245, | |
| "grad_norm": 1.3639869689941406, | |
| "learning_rate": 0.00017686729514140682, | |
| "loss": 1.1745, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.35859820700896494, | |
| "grad_norm": 1.5606908798217773, | |
| "learning_rate": 0.00017650471356055113, | |
| "loss": 1.1361, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.36403151317576743, | |
| "grad_norm": 1.2420063018798828, | |
| "learning_rate": 0.00017614213197969544, | |
| "loss": 1.1144, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.36946481934257, | |
| "grad_norm": 1.3263566493988037, | |
| "learning_rate": 0.00017577955039883974, | |
| "loss": 1.0744, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.37489812550937246, | |
| "grad_norm": 1.4993051290512085, | |
| "learning_rate": 0.00017541696881798405, | |
| "loss": 1.0908, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.38033143167617495, | |
| "grad_norm": 1.3254144191741943, | |
| "learning_rate": 0.00017505438723712836, | |
| "loss": 1.1584, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.38576473784297743, | |
| "grad_norm": 1.3965848684310913, | |
| "learning_rate": 0.00017469180565627266, | |
| "loss": 1.0959, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.39119804400978, | |
| "grad_norm": 1.3152015209197998, | |
| "learning_rate": 0.000174329224075417, | |
| "loss": 1.1178, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.39663135017658246, | |
| "grad_norm": 1.4309927225112915, | |
| "learning_rate": 0.0001739666424945613, | |
| "loss": 1.1177, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.40206465634338495, | |
| "grad_norm": 1.3448002338409424, | |
| "learning_rate": 0.0001736040609137056, | |
| "loss": 1.101, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.40749796251018744, | |
| "grad_norm": 1.285933256149292, | |
| "learning_rate": 0.00017324147933284992, | |
| "loss": 1.0626, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.4129312686769899, | |
| "grad_norm": 1.4348984956741333, | |
| "learning_rate": 0.00017287889775199423, | |
| "loss": 1.1462, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.41836457484379247, | |
| "grad_norm": 1.3408560752868652, | |
| "learning_rate": 0.0001725163161711385, | |
| "loss": 1.1475, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.42379788101059496, | |
| "grad_norm": 1.3782771825790405, | |
| "learning_rate": 0.0001721537345902828, | |
| "loss": 1.0875, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.42923118717739744, | |
| "grad_norm": 1.3274637460708618, | |
| "learning_rate": 0.00017179115300942712, | |
| "loss": 1.0746, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.43466449334419993, | |
| "grad_norm": 1.5006779432296753, | |
| "learning_rate": 0.00017142857142857143, | |
| "loss": 1.1149, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4400977995110024, | |
| "grad_norm": 1.3363099098205566, | |
| "learning_rate": 0.00017106598984771573, | |
| "loss": 1.0515, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.44553110567780496, | |
| "grad_norm": 1.439466953277588, | |
| "learning_rate": 0.00017070340826686004, | |
| "loss": 1.1296, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.45096441184460745, | |
| "grad_norm": 1.155349850654602, | |
| "learning_rate": 0.00017034082668600435, | |
| "loss": 1.1185, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.45639771801140994, | |
| "grad_norm": 1.1358013153076172, | |
| "learning_rate": 0.00016997824510514865, | |
| "loss": 1.1267, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.4618310241782124, | |
| "grad_norm": 1.3416662216186523, | |
| "learning_rate": 0.00016961566352429296, | |
| "loss": 1.1187, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.46726433034501497, | |
| "grad_norm": 1.2996137142181396, | |
| "learning_rate": 0.00016925308194343727, | |
| "loss": 1.0405, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.47269763651181745, | |
| "grad_norm": 1.257703185081482, | |
| "learning_rate": 0.00016889050036258157, | |
| "loss": 1.0456, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.47813094267861994, | |
| "grad_norm": 1.1873438358306885, | |
| "learning_rate": 0.00016852791878172588, | |
| "loss": 1.0442, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.48356424884542243, | |
| "grad_norm": 1.2138140201568604, | |
| "learning_rate": 0.00016816533720087019, | |
| "loss": 1.0797, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.4889975550122249, | |
| "grad_norm": 1.2529609203338623, | |
| "learning_rate": 0.00016780275562001452, | |
| "loss": 1.0624, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.49443086117902746, | |
| "grad_norm": 1.2894572019577026, | |
| "learning_rate": 0.00016744017403915883, | |
| "loss": 1.0507, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.49986416734582995, | |
| "grad_norm": 1.3366247415542603, | |
| "learning_rate": 0.00016707759245830313, | |
| "loss": 1.0792, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5052974735126324, | |
| "grad_norm": 1.1520795822143555, | |
| "learning_rate": 0.00016671501087744744, | |
| "loss": 1.0353, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.5107307796794349, | |
| "grad_norm": 1.2416119575500488, | |
| "learning_rate": 0.00016635242929659175, | |
| "loss": 1.1282, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.5161640858462374, | |
| "grad_norm": 1.1610630750656128, | |
| "learning_rate": 0.00016598984771573605, | |
| "loss": 1.0581, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5215973920130399, | |
| "grad_norm": 1.143537163734436, | |
| "learning_rate": 0.00016562726613488036, | |
| "loss": 1.0652, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5270306981798424, | |
| "grad_norm": 1.0708473920822144, | |
| "learning_rate": 0.00016526468455402467, | |
| "loss": 1.0943, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.532464004346645, | |
| "grad_norm": 1.2459930181503296, | |
| "learning_rate": 0.00016490210297316897, | |
| "loss": 1.028, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.5378973105134475, | |
| "grad_norm": 1.3345253467559814, | |
| "learning_rate": 0.00016453952139231328, | |
| "loss": 1.1056, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.54333061668025, | |
| "grad_norm": 1.270090937614441, | |
| "learning_rate": 0.0001641769398114576, | |
| "loss": 1.0562, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5487639228470524, | |
| "grad_norm": 1.1992326974868774, | |
| "learning_rate": 0.0001638143582306019, | |
| "loss": 1.0641, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.5541972290138549, | |
| "grad_norm": 1.182948350906372, | |
| "learning_rate": 0.0001634517766497462, | |
| "loss": 1.0496, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.5596305351806574, | |
| "grad_norm": 1.2159981727600098, | |
| "learning_rate": 0.0001630891950688905, | |
| "loss": 1.1103, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.5650638413474599, | |
| "grad_norm": 1.4117026329040527, | |
| "learning_rate": 0.00016272661348803481, | |
| "loss": 1.0865, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.5704971475142624, | |
| "grad_norm": 1.1276116371154785, | |
| "learning_rate": 0.00016236403190717912, | |
| "loss": 1.0844, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.5759304536810649, | |
| "grad_norm": 1.2447335720062256, | |
| "learning_rate": 0.00016200145032632343, | |
| "loss": 1.0771, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5813637598478675, | |
| "grad_norm": 1.1846734285354614, | |
| "learning_rate": 0.00016163886874546773, | |
| "loss": 1.0601, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.58679706601467, | |
| "grad_norm": 1.0874987840652466, | |
| "learning_rate": 0.00016127628716461204, | |
| "loss": 1.0539, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.5922303721814725, | |
| "grad_norm": 1.161940574645996, | |
| "learning_rate": 0.00016091370558375635, | |
| "loss": 1.0732, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.5976636783482749, | |
| "grad_norm": 1.3249943256378174, | |
| "learning_rate": 0.00016055112400290065, | |
| "loss": 1.0771, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6030969845150774, | |
| "grad_norm": 1.3140604496002197, | |
| "learning_rate": 0.00016018854242204496, | |
| "loss": 1.0611, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.6085302906818799, | |
| "grad_norm": 1.1174367666244507, | |
| "learning_rate": 0.00015982596084118927, | |
| "loss": 1.0457, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.6139635968486824, | |
| "grad_norm": 1.0260871648788452, | |
| "learning_rate": 0.0001594633792603336, | |
| "loss": 1.0164, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.6193969030154849, | |
| "grad_norm": 1.1550908088684082, | |
| "learning_rate": 0.0001591007976794779, | |
| "loss": 1.0173, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.6248302091822874, | |
| "grad_norm": 1.2019294500350952, | |
| "learning_rate": 0.00015873821609862222, | |
| "loss": 1.0284, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.63026351534909, | |
| "grad_norm": 1.2347038984298706, | |
| "learning_rate": 0.00015837563451776652, | |
| "loss": 1.0494, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.6356968215158925, | |
| "grad_norm": 1.06244957447052, | |
| "learning_rate": 0.00015801305293691083, | |
| "loss": 1.0365, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.641130127682695, | |
| "grad_norm": 1.0355654954910278, | |
| "learning_rate": 0.00015765047135605514, | |
| "loss": 1.0686, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.6465634338494974, | |
| "grad_norm": 1.1522706747055054, | |
| "learning_rate": 0.00015728788977519944, | |
| "loss": 1.0455, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.6519967400162999, | |
| "grad_norm": 1.0630000829696655, | |
| "learning_rate": 0.00015692530819434375, | |
| "loss": 1.0803, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6574300461831024, | |
| "grad_norm": 1.0645341873168945, | |
| "learning_rate": 0.00015656272661348806, | |
| "loss": 1.0453, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.6628633523499049, | |
| "grad_norm": 1.113446831703186, | |
| "learning_rate": 0.00015620014503263234, | |
| "loss": 1.0388, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.6682966585167074, | |
| "grad_norm": 1.224284291267395, | |
| "learning_rate": 0.00015583756345177664, | |
| "loss": 1.0277, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.6737299646835099, | |
| "grad_norm": 1.2570809125900269, | |
| "learning_rate": 0.00015547498187092095, | |
| "loss": 1.0811, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.6791632708503124, | |
| "grad_norm": 1.097993016242981, | |
| "learning_rate": 0.00015511240029006526, | |
| "loss": 1.0439, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.684596577017115, | |
| "grad_norm": 1.1960225105285645, | |
| "learning_rate": 0.00015474981870920956, | |
| "loss": 1.0555, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.6900298831839174, | |
| "grad_norm": 1.104408860206604, | |
| "learning_rate": 0.00015438723712835387, | |
| "loss": 1.03, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.6954631893507199, | |
| "grad_norm": 1.1032377481460571, | |
| "learning_rate": 0.00015402465554749818, | |
| "loss": 1.0474, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.7008964955175224, | |
| "grad_norm": 1.2313536405563354, | |
| "learning_rate": 0.00015366207396664248, | |
| "loss": 1.1071, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.7063298016843249, | |
| "grad_norm": 1.1079504489898682, | |
| "learning_rate": 0.0001532994923857868, | |
| "loss": 0.991, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.7117631078511274, | |
| "grad_norm": 1.1161744594573975, | |
| "learning_rate": 0.00015293691080493112, | |
| "loss": 1.0002, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.7171964140179299, | |
| "grad_norm": 1.082507610321045, | |
| "learning_rate": 0.00015257432922407543, | |
| "loss": 1.0661, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.7226297201847324, | |
| "grad_norm": 1.1152865886688232, | |
| "learning_rate": 0.00015221174764321974, | |
| "loss": 1.0414, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.7280630263515349, | |
| "grad_norm": 1.1129889488220215, | |
| "learning_rate": 0.00015184916606236404, | |
| "loss": 1.0882, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.7334963325183375, | |
| "grad_norm": 1.2625923156738281, | |
| "learning_rate": 0.00015148658448150835, | |
| "loss": 1.054, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.73892963868514, | |
| "grad_norm": 1.194080114364624, | |
| "learning_rate": 0.00015112400290065266, | |
| "loss": 0.9775, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.7443629448519424, | |
| "grad_norm": 1.1932792663574219, | |
| "learning_rate": 0.00015076142131979696, | |
| "loss": 1.039, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.7497962510187449, | |
| "grad_norm": 1.2291207313537598, | |
| "learning_rate": 0.00015039883973894127, | |
| "loss": 0.9981, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.7552295571855474, | |
| "grad_norm": 1.0410774946212769, | |
| "learning_rate": 0.00015003625815808558, | |
| "loss": 1.0136, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.7606628633523499, | |
| "grad_norm": 1.3354581594467163, | |
| "learning_rate": 0.00014967367657722988, | |
| "loss": 1.0413, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7660961695191524, | |
| "grad_norm": 1.1308538913726807, | |
| "learning_rate": 0.0001493110949963742, | |
| "loss": 1.062, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.7715294756859549, | |
| "grad_norm": 1.2079111337661743, | |
| "learning_rate": 0.0001489485134155185, | |
| "loss": 1.1237, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.7769627818527574, | |
| "grad_norm": 1.0739976167678833, | |
| "learning_rate": 0.0001485859318346628, | |
| "loss": 0.9859, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.78239608801956, | |
| "grad_norm": 0.9215412139892578, | |
| "learning_rate": 0.0001482233502538071, | |
| "loss": 0.9993, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.7878293941863624, | |
| "grad_norm": 1.1274949312210083, | |
| "learning_rate": 0.00014786076867295142, | |
| "loss": 1.0042, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.7932627003531649, | |
| "grad_norm": 1.311325192451477, | |
| "learning_rate": 0.00014749818709209573, | |
| "loss": 1.0855, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.7986960065199674, | |
| "grad_norm": 1.1324517726898193, | |
| "learning_rate": 0.00014713560551124003, | |
| "loss": 1.0675, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.8041293126867699, | |
| "grad_norm": 1.2283560037612915, | |
| "learning_rate": 0.00014677302393038434, | |
| "loss": 1.0262, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.8095626188535724, | |
| "grad_norm": 1.1866376399993896, | |
| "learning_rate": 0.00014641044234952865, | |
| "loss": 1.0767, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.8149959250203749, | |
| "grad_norm": 1.0849380493164062, | |
| "learning_rate": 0.00014604786076867295, | |
| "loss": 0.991, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.8204292311871774, | |
| "grad_norm": 1.1167508363723755, | |
| "learning_rate": 0.00014568527918781726, | |
| "loss": 0.9748, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.8258625373539799, | |
| "grad_norm": 1.0191930532455444, | |
| "learning_rate": 0.00014532269760696157, | |
| "loss": 0.9399, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.8312958435207825, | |
| "grad_norm": 1.1307344436645508, | |
| "learning_rate": 0.00014496011602610587, | |
| "loss": 0.9596, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.8367291496875849, | |
| "grad_norm": 1.0472939014434814, | |
| "learning_rate": 0.0001445975344452502, | |
| "loss": 1.0304, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.8421624558543874, | |
| "grad_norm": 1.333527684211731, | |
| "learning_rate": 0.0001442349528643945, | |
| "loss": 1.0326, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.8475957620211899, | |
| "grad_norm": 1.168447732925415, | |
| "learning_rate": 0.00014387237128353882, | |
| "loss": 1.0782, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.8530290681879924, | |
| "grad_norm": 1.1996850967407227, | |
| "learning_rate": 0.00014350978970268313, | |
| "loss": 1.0502, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.8584623743547949, | |
| "grad_norm": 1.0453308820724487, | |
| "learning_rate": 0.00014314720812182743, | |
| "loss": 1.0413, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.8638956805215974, | |
| "grad_norm": 1.0719515085220337, | |
| "learning_rate": 0.00014278462654097174, | |
| "loss": 1.0407, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.8693289866883999, | |
| "grad_norm": 1.1286976337432861, | |
| "learning_rate": 0.00014242204496011605, | |
| "loss": 0.9675, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8747622928552024, | |
| "grad_norm": 1.1395922899246216, | |
| "learning_rate": 0.00014205946337926035, | |
| "loss": 1.0504, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.8801955990220048, | |
| "grad_norm": 1.1917579174041748, | |
| "learning_rate": 0.00014169688179840466, | |
| "loss": 1.0361, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.8856289051888074, | |
| "grad_norm": 1.1743110418319702, | |
| "learning_rate": 0.00014133430021754897, | |
| "loss": 0.9684, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.8910622113556099, | |
| "grad_norm": 1.10382080078125, | |
| "learning_rate": 0.00014097171863669327, | |
| "loss": 1.0359, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.8964955175224124, | |
| "grad_norm": 1.1514308452606201, | |
| "learning_rate": 0.00014060913705583758, | |
| "loss": 1.0011, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.9019288236892149, | |
| "grad_norm": 1.2536178827285767, | |
| "learning_rate": 0.00014024655547498186, | |
| "loss": 1.0913, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.9073621298560174, | |
| "grad_norm": 1.0985808372497559, | |
| "learning_rate": 0.00013988397389412617, | |
| "loss": 0.9757, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.9127954360228199, | |
| "grad_norm": 1.042410135269165, | |
| "learning_rate": 0.00013952139231327047, | |
| "loss": 1.0196, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.9182287421896224, | |
| "grad_norm": 1.2049064636230469, | |
| "learning_rate": 0.00013915881073241478, | |
| "loss": 0.9862, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.9236620483564248, | |
| "grad_norm": 1.169303059577942, | |
| "learning_rate": 0.0001387962291515591, | |
| "loss": 0.9924, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.9290953545232273, | |
| "grad_norm": 1.1006051301956177, | |
| "learning_rate": 0.0001384336475707034, | |
| "loss": 1.037, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.9345286606900299, | |
| "grad_norm": 1.044036626815796, | |
| "learning_rate": 0.00013807106598984773, | |
| "loss": 0.9422, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.9399619668568324, | |
| "grad_norm": 1.0203227996826172, | |
| "learning_rate": 0.00013770848440899203, | |
| "loss": 1.0634, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.9453952730236349, | |
| "grad_norm": 1.1052066087722778, | |
| "learning_rate": 0.00013734590282813634, | |
| "loss": 0.989, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.9508285791904374, | |
| "grad_norm": 1.0601762533187866, | |
| "learning_rate": 0.00013698332124728065, | |
| "loss": 0.97, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.9562618853572399, | |
| "grad_norm": 1.2294491529464722, | |
| "learning_rate": 0.00013662073966642495, | |
| "loss": 1.0011, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.9616951915240424, | |
| "grad_norm": 1.0348526239395142, | |
| "learning_rate": 0.00013625815808556926, | |
| "loss": 0.9967, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.9671284976908449, | |
| "grad_norm": 1.159955620765686, | |
| "learning_rate": 0.00013589557650471357, | |
| "loss": 1.0426, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.9725618038576473, | |
| "grad_norm": 0.9879871606826782, | |
| "learning_rate": 0.00013553299492385788, | |
| "loss": 0.9393, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.9779951100244498, | |
| "grad_norm": 1.0977790355682373, | |
| "learning_rate": 0.00013517041334300218, | |
| "loss": 0.9383, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.9834284161912524, | |
| "grad_norm": 1.0443631410598755, | |
| "learning_rate": 0.0001348078317621465, | |
| "loss": 1.0478, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.9888617223580549, | |
| "grad_norm": 1.088100790977478, | |
| "learning_rate": 0.0001344452501812908, | |
| "loss": 1.0814, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.9942950285248574, | |
| "grad_norm": 1.1516419649124146, | |
| "learning_rate": 0.0001340826686004351, | |
| "loss": 1.0281, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.9997283346916599, | |
| "grad_norm": 1.0100435018539429, | |
| "learning_rate": 0.0001337200870195794, | |
| "loss": 0.9778, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.0629626512527466, | |
| "eval_runtime": 160.1638, | |
| "eval_samples_per_second": 9.678, | |
| "eval_steps_per_second": 2.423, | |
| "step": 921 | |
| }, | |
| { | |
| "epoch": 1.004346644933442, | |
| "grad_norm": 1.0621072053909302, | |
| "learning_rate": 0.00013335750543872372, | |
| "loss": 0.9633, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.0097799511002445, | |
| "grad_norm": 1.2327194213867188, | |
| "learning_rate": 0.00013299492385786802, | |
| "loss": 0.8117, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.015213257267047, | |
| "grad_norm": 1.1144647598266602, | |
| "learning_rate": 0.00013263234227701233, | |
| "loss": 0.9238, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 1.0206465634338495, | |
| "grad_norm": 1.3408534526824951, | |
| "learning_rate": 0.00013226976069615664, | |
| "loss": 0.8266, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.026079869600652, | |
| "grad_norm": 1.3345109224319458, | |
| "learning_rate": 0.00013190717911530094, | |
| "loss": 0.9091, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 1.0315131757674545, | |
| "grad_norm": 1.1732280254364014, | |
| "learning_rate": 0.00013154459753444525, | |
| "loss": 0.876, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.036946481934257, | |
| "grad_norm": 1.2480390071868896, | |
| "learning_rate": 0.00013118201595358956, | |
| "loss": 0.9055, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 1.0423797881010595, | |
| "grad_norm": 1.0195136070251465, | |
| "learning_rate": 0.00013081943437273386, | |
| "loss": 0.9262, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.047813094267862, | |
| "grad_norm": 1.1737656593322754, | |
| "learning_rate": 0.00013045685279187817, | |
| "loss": 0.9174, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 1.0532464004346644, | |
| "grad_norm": 1.087819218635559, | |
| "learning_rate": 0.00013009427121102248, | |
| "loss": 0.8892, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.058679706601467, | |
| "grad_norm": 1.0774587392807007, | |
| "learning_rate": 0.0001297316896301668, | |
| "loss": 0.8276, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.0641130127682694, | |
| "grad_norm": 1.2075201272964478, | |
| "learning_rate": 0.00012936910804931112, | |
| "loss": 0.9004, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.069546318935072, | |
| "grad_norm": 1.1365958452224731, | |
| "learning_rate": 0.00012900652646845542, | |
| "loss": 0.8428, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 1.0749796251018744, | |
| "grad_norm": 1.032224178314209, | |
| "learning_rate": 0.00012864394488759973, | |
| "loss": 0.8797, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.080412931268677, | |
| "grad_norm": 1.1515988111495972, | |
| "learning_rate": 0.00012828136330674404, | |
| "loss": 0.8756, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 1.0858462374354796, | |
| "grad_norm": 1.1434125900268555, | |
| "learning_rate": 0.00012791878172588834, | |
| "loss": 0.9153, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.091279543602282, | |
| "grad_norm": 1.4158624410629272, | |
| "learning_rate": 0.00012755620014503265, | |
| "loss": 0.8762, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 1.0967128497690846, | |
| "grad_norm": 1.069629192352295, | |
| "learning_rate": 0.00012719361856417696, | |
| "loss": 0.8729, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.102146155935887, | |
| "grad_norm": 1.1010494232177734, | |
| "learning_rate": 0.00012683103698332126, | |
| "loss": 0.8883, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 1.1075794621026895, | |
| "grad_norm": 1.4307278394699097, | |
| "learning_rate": 0.00012646845540246557, | |
| "loss": 0.8894, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.113012768269492, | |
| "grad_norm": 1.1194878816604614, | |
| "learning_rate": 0.00012610587382160988, | |
| "loss": 0.9064, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.1184460744362945, | |
| "grad_norm": 1.1481852531433105, | |
| "learning_rate": 0.00012574329224075418, | |
| "loss": 0.8716, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.123879380603097, | |
| "grad_norm": 1.0588971376419067, | |
| "learning_rate": 0.0001253807106598985, | |
| "loss": 0.92, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 1.1293126867698995, | |
| "grad_norm": 1.1482290029525757, | |
| "learning_rate": 0.0001250181290790428, | |
| "loss": 0.8431, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.1347459929367019, | |
| "grad_norm": 1.115369439125061, | |
| "learning_rate": 0.0001246555474981871, | |
| "loss": 0.8804, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 1.1401792991035045, | |
| "grad_norm": 1.1321439743041992, | |
| "learning_rate": 0.0001242929659173314, | |
| "loss": 0.8311, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.145612605270307, | |
| "grad_norm": 1.2138570547103882, | |
| "learning_rate": 0.0001239303843364757, | |
| "loss": 0.9062, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 1.1510459114371094, | |
| "grad_norm": 1.171796441078186, | |
| "learning_rate": 0.00012356780275562, | |
| "loss": 0.8656, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.156479217603912, | |
| "grad_norm": 1.277994990348816, | |
| "learning_rate": 0.0001232052211747643, | |
| "loss": 0.8735, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 1.1619125237707144, | |
| "grad_norm": 1.0549153089523315, | |
| "learning_rate": 0.00012284263959390864, | |
| "loss": 0.8959, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.167345829937517, | |
| "grad_norm": 0.9898720979690552, | |
| "learning_rate": 0.00012248005801305295, | |
| "loss": 0.8446, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.1727791361043194, | |
| "grad_norm": 1.0818243026733398, | |
| "learning_rate": 0.00012211747643219725, | |
| "loss": 0.9452, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.178212442271122, | |
| "grad_norm": 1.233089566230774, | |
| "learning_rate": 0.00012175489485134155, | |
| "loss": 0.8391, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 1.1836457484379244, | |
| "grad_norm": 1.0094175338745117, | |
| "learning_rate": 0.00012139231327048585, | |
| "loss": 0.8363, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.189079054604727, | |
| "grad_norm": 1.1545265913009644, | |
| "learning_rate": 0.00012102973168963017, | |
| "loss": 0.8744, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 1.1945123607715296, | |
| "grad_norm": 1.1529176235198975, | |
| "learning_rate": 0.00012066715010877448, | |
| "loss": 0.8819, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.199945666938332, | |
| "grad_norm": 1.1534438133239746, | |
| "learning_rate": 0.00012030456852791879, | |
| "loss": 0.8522, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 1.2053789731051345, | |
| "grad_norm": 1.146657109260559, | |
| "learning_rate": 0.00011994198694706309, | |
| "loss": 0.8919, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.210812279271937, | |
| "grad_norm": 1.2342313528060913, | |
| "learning_rate": 0.0001195794053662074, | |
| "loss": 0.8456, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 1.2162455854387395, | |
| "grad_norm": 1.398826241493225, | |
| "learning_rate": 0.0001192168237853517, | |
| "loss": 0.8727, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.2216788916055419, | |
| "grad_norm": 1.1229655742645264, | |
| "learning_rate": 0.00011885424220449601, | |
| "loss": 0.8537, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1.2271121977723445, | |
| "grad_norm": 1.1513757705688477, | |
| "learning_rate": 0.00011849166062364032, | |
| "loss": 0.9139, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.2325455039391469, | |
| "grad_norm": 1.090980052947998, | |
| "learning_rate": 0.00011812907904278463, | |
| "loss": 0.884, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 1.2379788101059495, | |
| "grad_norm": 1.2172348499298096, | |
| "learning_rate": 0.00011776649746192893, | |
| "loss": 0.8701, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.243412116272752, | |
| "grad_norm": 1.1310840845108032, | |
| "learning_rate": 0.00011740391588107324, | |
| "loss": 0.8342, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 1.2488454224395544, | |
| "grad_norm": 1.1303426027297974, | |
| "learning_rate": 0.00011704133430021755, | |
| "loss": 0.8672, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.254278728606357, | |
| "grad_norm": 1.2884100675582886, | |
| "learning_rate": 0.00011667875271936187, | |
| "loss": 0.9344, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 1.2597120347731594, | |
| "grad_norm": 1.1938570737838745, | |
| "learning_rate": 0.00011631617113850617, | |
| "loss": 0.8617, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.265145340939962, | |
| "grad_norm": 1.1624027490615845, | |
| "learning_rate": 0.00011595358955765048, | |
| "loss": 0.802, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 1.2705786471067646, | |
| "grad_norm": 1.1146856546401978, | |
| "learning_rate": 0.00011559100797679479, | |
| "loss": 0.8936, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.276011953273567, | |
| "grad_norm": 0.9942327737808228, | |
| "learning_rate": 0.0001152284263959391, | |
| "loss": 0.8782, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 1.2814452594403694, | |
| "grad_norm": 1.1722972393035889, | |
| "learning_rate": 0.0001148658448150834, | |
| "loss": 0.8808, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.286878565607172, | |
| "grad_norm": 1.2962080240249634, | |
| "learning_rate": 0.00011450326323422771, | |
| "loss": 0.853, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 1.2923118717739746, | |
| "grad_norm": 1.0645427703857422, | |
| "learning_rate": 0.00011414068165337201, | |
| "loss": 0.862, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.297745177940777, | |
| "grad_norm": 1.3279187679290771, | |
| "learning_rate": 0.00011377810007251632, | |
| "loss": 0.9193, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 1.3031784841075795, | |
| "grad_norm": 0.99788898229599, | |
| "learning_rate": 0.00011341551849166063, | |
| "loss": 0.848, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.308611790274382, | |
| "grad_norm": 1.0723084211349487, | |
| "learning_rate": 0.00011305293691080493, | |
| "loss": 0.793, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 1.3140450964411845, | |
| "grad_norm": 1.1458420753479004, | |
| "learning_rate": 0.00011269035532994925, | |
| "loss": 0.8531, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.3194784026079869, | |
| "grad_norm": 1.1347026824951172, | |
| "learning_rate": 0.00011232777374909356, | |
| "loss": 0.846, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 1.3249117087747895, | |
| "grad_norm": 1.0811132192611694, | |
| "learning_rate": 0.00011196519216823787, | |
| "loss": 0.8587, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.3303450149415919, | |
| "grad_norm": 1.2509421110153198, | |
| "learning_rate": 0.00011160261058738218, | |
| "loss": 0.8441, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 1.3357783211083945, | |
| "grad_norm": 1.0099766254425049, | |
| "learning_rate": 0.00011124002900652648, | |
| "loss": 0.8737, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.341211627275197, | |
| "grad_norm": 1.1766360998153687, | |
| "learning_rate": 0.00011087744742567079, | |
| "loss": 0.9182, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 1.3466449334419994, | |
| "grad_norm": 1.0566556453704834, | |
| "learning_rate": 0.0001105148658448151, | |
| "loss": 0.8829, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.352078239608802, | |
| "grad_norm": 1.3091182708740234, | |
| "learning_rate": 0.0001101522842639594, | |
| "loss": 0.9399, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 1.3575115457756044, | |
| "grad_norm": 1.35448157787323, | |
| "learning_rate": 0.00010978970268310371, | |
| "loss": 0.8651, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.362944851942407, | |
| "grad_norm": 1.1222350597381592, | |
| "learning_rate": 0.00010942712110224802, | |
| "loss": 0.864, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 1.3683781581092094, | |
| "grad_norm": 0.9896799921989441, | |
| "learning_rate": 0.00010906453952139232, | |
| "loss": 0.8638, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.373811464276012, | |
| "grad_norm": 1.214143991470337, | |
| "learning_rate": 0.00010870195794053664, | |
| "loss": 0.8961, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 1.3792447704428143, | |
| "grad_norm": 1.1640385389328003, | |
| "learning_rate": 0.00010833937635968095, | |
| "loss": 0.8818, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.384678076609617, | |
| "grad_norm": 1.1086711883544922, | |
| "learning_rate": 0.00010797679477882523, | |
| "loss": 0.8502, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 1.3901113827764195, | |
| "grad_norm": 1.1714527606964111, | |
| "learning_rate": 0.00010761421319796954, | |
| "loss": 0.8456, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.395544688943222, | |
| "grad_norm": 1.0106830596923828, | |
| "learning_rate": 0.00010725163161711384, | |
| "loss": 0.8588, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 1.4009779951100245, | |
| "grad_norm": 1.2438123226165771, | |
| "learning_rate": 0.00010688905003625815, | |
| "loss": 0.9012, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.406411301276827, | |
| "grad_norm": 1.055284023284912, | |
| "learning_rate": 0.00010652646845540246, | |
| "loss": 0.8724, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 1.4118446074436295, | |
| "grad_norm": 1.1548635959625244, | |
| "learning_rate": 0.00010616388687454676, | |
| "loss": 0.8323, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.4172779136104319, | |
| "grad_norm": 1.2211989164352417, | |
| "learning_rate": 0.00010580130529369108, | |
| "loss": 0.8472, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 1.4227112197772345, | |
| "grad_norm": 1.2574783563613892, | |
| "learning_rate": 0.00010543872371283539, | |
| "loss": 0.8812, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.4281445259440368, | |
| "grad_norm": 1.1512340307235718, | |
| "learning_rate": 0.0001050761421319797, | |
| "loss": 0.8231, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 1.4335778321108394, | |
| "grad_norm": 1.053491234779358, | |
| "learning_rate": 0.000104713560551124, | |
| "loss": 0.8484, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.439011138277642, | |
| "grad_norm": 0.9974244236946106, | |
| "learning_rate": 0.00010435097897026831, | |
| "loss": 0.8774, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 1.4444444444444444, | |
| "grad_norm": 1.1907140016555786, | |
| "learning_rate": 0.00010398839738941262, | |
| "loss": 0.8524, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.449877750611247, | |
| "grad_norm": 1.0929960012435913, | |
| "learning_rate": 0.00010362581580855692, | |
| "loss": 0.8793, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 1.4553110567780494, | |
| "grad_norm": 1.1883609294891357, | |
| "learning_rate": 0.00010326323422770123, | |
| "loss": 0.8784, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.460744362944852, | |
| "grad_norm": 1.0147247314453125, | |
| "learning_rate": 0.00010290065264684554, | |
| "loss": 0.8559, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 1.4661776691116544, | |
| "grad_norm": 1.0622776746749878, | |
| "learning_rate": 0.00010253807106598984, | |
| "loss": 0.9126, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.471610975278457, | |
| "grad_norm": 1.0322296619415283, | |
| "learning_rate": 0.00010217548948513415, | |
| "loss": 0.8228, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 1.4770442814452593, | |
| "grad_norm": 1.3334159851074219, | |
| "learning_rate": 0.00010181290790427847, | |
| "loss": 0.8945, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.482477587612062, | |
| "grad_norm": 1.029920220375061, | |
| "learning_rate": 0.00010145032632342278, | |
| "loss": 0.8321, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 1.4879108937788645, | |
| "grad_norm": 1.1344255208969116, | |
| "learning_rate": 0.00010108774474256708, | |
| "loss": 0.8733, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.493344199945667, | |
| "grad_norm": 1.1062661409378052, | |
| "learning_rate": 0.00010072516316171139, | |
| "loss": 0.8485, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 1.4987775061124695, | |
| "grad_norm": 0.9658976197242737, | |
| "learning_rate": 0.0001003625815808557, | |
| "loss": 0.9261, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.504210812279272, | |
| "grad_norm": 1.2899905443191528, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9171, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 1.5096441184460745, | |
| "grad_norm": 1.067159652709961, | |
| "learning_rate": 9.963741841914431e-05, | |
| "loss": 0.8402, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.515077424612877, | |
| "grad_norm": 1.211645483970642, | |
| "learning_rate": 9.927483683828862e-05, | |
| "loss": 0.8477, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 1.5205107307796795, | |
| "grad_norm": 1.385699987411499, | |
| "learning_rate": 9.891225525743293e-05, | |
| "loss": 0.9136, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.5259440369464818, | |
| "grad_norm": 1.1355695724487305, | |
| "learning_rate": 9.854967367657723e-05, | |
| "loss": 0.8304, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 1.5313773431132844, | |
| "grad_norm": 1.2345882654190063, | |
| "learning_rate": 9.818709209572154e-05, | |
| "loss": 0.8749, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.536810649280087, | |
| "grad_norm": 1.1696631908416748, | |
| "learning_rate": 9.782451051486586e-05, | |
| "loss": 0.8991, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 1.5422439554468894, | |
| "grad_norm": 1.1087141036987305, | |
| "learning_rate": 9.746192893401017e-05, | |
| "loss": 0.8925, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.5476772616136918, | |
| "grad_norm": 1.0509897470474243, | |
| "learning_rate": 9.709934735315447e-05, | |
| "loss": 0.8121, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 1.5531105677804944, | |
| "grad_norm": 1.2797741889953613, | |
| "learning_rate": 9.673676577229878e-05, | |
| "loss": 0.8782, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.558543873947297, | |
| "grad_norm": 1.1424418687820435, | |
| "learning_rate": 9.637418419144309e-05, | |
| "loss": 0.8634, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 1.5639771801140996, | |
| "grad_norm": 1.1863006353378296, | |
| "learning_rate": 9.601160261058739e-05, | |
| "loss": 0.8899, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.569410486280902, | |
| "grad_norm": 1.1050300598144531, | |
| "learning_rate": 9.564902102973169e-05, | |
| "loss": 0.8619, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 1.5748437924477043, | |
| "grad_norm": 1.1671733856201172, | |
| "learning_rate": 9.528643944887599e-05, | |
| "loss": 0.855, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.580277098614507, | |
| "grad_norm": 1.1153284311294556, | |
| "learning_rate": 9.49238578680203e-05, | |
| "loss": 0.8478, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 1.5857104047813095, | |
| "grad_norm": 0.9661588668823242, | |
| "learning_rate": 9.456127628716462e-05, | |
| "loss": 0.8411, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.591143710948112, | |
| "grad_norm": 1.2390023469924927, | |
| "learning_rate": 9.419869470630893e-05, | |
| "loss": 0.8836, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 1.5965770171149143, | |
| "grad_norm": 1.0662574768066406, | |
| "learning_rate": 9.383611312545323e-05, | |
| "loss": 0.8696, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.6020103232817169, | |
| "grad_norm": 1.2085328102111816, | |
| "learning_rate": 9.347353154459754e-05, | |
| "loss": 0.8032, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 1.6074436294485195, | |
| "grad_norm": 1.1510725021362305, | |
| "learning_rate": 9.311094996374185e-05, | |
| "loss": 0.9099, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.612876935615322, | |
| "grad_norm": 1.2687468528747559, | |
| "learning_rate": 9.274836838288615e-05, | |
| "loss": 0.8215, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 1.6183102417821245, | |
| "grad_norm": 1.2436496019363403, | |
| "learning_rate": 9.238578680203046e-05, | |
| "loss": 0.84, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.6237435479489268, | |
| "grad_norm": 1.0118858814239502, | |
| "learning_rate": 9.202320522117477e-05, | |
| "loss": 0.8481, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 1.6291768541157294, | |
| "grad_norm": 1.057982087135315, | |
| "learning_rate": 9.166062364031907e-05, | |
| "loss": 0.853, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.634610160282532, | |
| "grad_norm": 1.0575734376907349, | |
| "learning_rate": 9.129804205946338e-05, | |
| "loss": 0.9001, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 1.6400434664493344, | |
| "grad_norm": 1.119564175605774, | |
| "learning_rate": 9.093546047860769e-05, | |
| "loss": 0.8093, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.6454767726161368, | |
| "grad_norm": 1.120884895324707, | |
| "learning_rate": 9.0572878897752e-05, | |
| "loss": 0.8213, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 1.6509100787829394, | |
| "grad_norm": 1.1385974884033203, | |
| "learning_rate": 9.021029731689631e-05, | |
| "loss": 0.8877, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.656343384949742, | |
| "grad_norm": 1.1706347465515137, | |
| "learning_rate": 8.984771573604062e-05, | |
| "loss": 0.8279, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 1.6617766911165446, | |
| "grad_norm": 1.2245526313781738, | |
| "learning_rate": 8.948513415518493e-05, | |
| "loss": 0.8668, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.667209997283347, | |
| "grad_norm": 1.0326176881790161, | |
| "learning_rate": 8.912255257432923e-05, | |
| "loss": 0.8367, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 1.6726433034501493, | |
| "grad_norm": 1.1200278997421265, | |
| "learning_rate": 8.875997099347354e-05, | |
| "loss": 0.8095, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.678076609616952, | |
| "grad_norm": 1.2948065996170044, | |
| "learning_rate": 8.839738941261785e-05, | |
| "loss": 0.8287, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 1.6835099157837545, | |
| "grad_norm": 1.0283042192459106, | |
| "learning_rate": 8.803480783176215e-05, | |
| "loss": 0.8308, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.688943221950557, | |
| "grad_norm": 1.001953125, | |
| "learning_rate": 8.767222625090645e-05, | |
| "loss": 0.8586, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 1.6943765281173593, | |
| "grad_norm": 1.4033405780792236, | |
| "learning_rate": 8.730964467005075e-05, | |
| "loss": 0.9156, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.6998098342841619, | |
| "grad_norm": 1.1317863464355469, | |
| "learning_rate": 8.694706308919508e-05, | |
| "loss": 0.8126, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 1.7052431404509645, | |
| "grad_norm": 1.2173607349395752, | |
| "learning_rate": 8.658448150833938e-05, | |
| "loss": 0.8535, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 1.710676446617767, | |
| "grad_norm": 1.0661206245422363, | |
| "learning_rate": 8.622189992748369e-05, | |
| "loss": 0.8383, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 1.7161097527845695, | |
| "grad_norm": 1.0935437679290771, | |
| "learning_rate": 8.5859318346628e-05, | |
| "loss": 0.8502, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.7215430589513718, | |
| "grad_norm": 1.1766958236694336, | |
| "learning_rate": 8.54967367657723e-05, | |
| "loss": 0.8249, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 1.7269763651181744, | |
| "grad_norm": 1.1970454454421997, | |
| "learning_rate": 8.513415518491661e-05, | |
| "loss": 0.8488, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 1.732409671284977, | |
| "grad_norm": 1.0711541175842285, | |
| "learning_rate": 8.477157360406092e-05, | |
| "loss": 0.8612, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 1.7378429774517794, | |
| "grad_norm": 1.142510175704956, | |
| "learning_rate": 8.440899202320522e-05, | |
| "loss": 0.8237, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.7432762836185818, | |
| "grad_norm": 1.157728672027588, | |
| "learning_rate": 8.404641044234953e-05, | |
| "loss": 0.8693, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 1.7487095897853844, | |
| "grad_norm": 1.2358007431030273, | |
| "learning_rate": 8.368382886149384e-05, | |
| "loss": 0.8697, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 1.754142895952187, | |
| "grad_norm": 1.2696595191955566, | |
| "learning_rate": 8.332124728063814e-05, | |
| "loss": 0.8626, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 1.7595762021189894, | |
| "grad_norm": 1.2669212818145752, | |
| "learning_rate": 8.295866569978246e-05, | |
| "loss": 0.8889, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.765009508285792, | |
| "grad_norm": 1.071008324623108, | |
| "learning_rate": 8.259608411892677e-05, | |
| "loss": 0.8591, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 1.7704428144525943, | |
| "grad_norm": 1.0619854927062988, | |
| "learning_rate": 8.223350253807108e-05, | |
| "loss": 0.8183, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 1.775876120619397, | |
| "grad_norm": 1.0905566215515137, | |
| "learning_rate": 8.187092095721538e-05, | |
| "loss": 0.8569, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 1.7813094267861995, | |
| "grad_norm": 1.1269817352294922, | |
| "learning_rate": 8.150833937635969e-05, | |
| "loss": 0.9046, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.786742732953002, | |
| "grad_norm": 1.123292326927185, | |
| "learning_rate": 8.1145757795504e-05, | |
| "loss": 0.7951, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 1.7921760391198043, | |
| "grad_norm": 1.0677564144134521, | |
| "learning_rate": 8.07831762146483e-05, | |
| "loss": 0.7568, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.7976093452866069, | |
| "grad_norm": 1.3572133779525757, | |
| "learning_rate": 8.042059463379261e-05, | |
| "loss": 0.856, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 1.8030426514534095, | |
| "grad_norm": 1.0941401720046997, | |
| "learning_rate": 8.005801305293692e-05, | |
| "loss": 0.8384, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.8084759576202118, | |
| "grad_norm": 1.094785213470459, | |
| "learning_rate": 7.969543147208121e-05, | |
| "loss": 0.8504, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 1.8139092637870144, | |
| "grad_norm": 1.0520368814468384, | |
| "learning_rate": 7.933284989122553e-05, | |
| "loss": 0.8267, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 1.8193425699538168, | |
| "grad_norm": 1.0908136367797852, | |
| "learning_rate": 7.897026831036984e-05, | |
| "loss": 0.8239, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 1.8247758761206194, | |
| "grad_norm": 1.1392829418182373, | |
| "learning_rate": 7.860768672951414e-05, | |
| "loss": 0.8786, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.830209182287422, | |
| "grad_norm": 1.2346545457839966, | |
| "learning_rate": 7.824510514865845e-05, | |
| "loss": 0.8669, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 1.8356424884542244, | |
| "grad_norm": 1.131622314453125, | |
| "learning_rate": 7.788252356780276e-05, | |
| "loss": 0.8707, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 1.8410757946210268, | |
| "grad_norm": 1.2329860925674438, | |
| "learning_rate": 7.751994198694706e-05, | |
| "loss": 0.8205, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 1.8465091007878294, | |
| "grad_norm": 1.0701172351837158, | |
| "learning_rate": 7.715736040609137e-05, | |
| "loss": 0.8733, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.851942406954632, | |
| "grad_norm": 1.112290382385254, | |
| "learning_rate": 7.679477882523568e-05, | |
| "loss": 0.8, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 1.8573757131214343, | |
| "grad_norm": 1.154740571975708, | |
| "learning_rate": 7.643219724437998e-05, | |
| "loss": 0.7865, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.862809019288237, | |
| "grad_norm": 1.0539336204528809, | |
| "learning_rate": 7.606961566352429e-05, | |
| "loss": 0.8828, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 1.8682423254550393, | |
| "grad_norm": 1.034320592880249, | |
| "learning_rate": 7.57070340826686e-05, | |
| "loss": 0.8341, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.873675631621842, | |
| "grad_norm": 1.1562882661819458, | |
| "learning_rate": 7.534445250181292e-05, | |
| "loss": 0.7654, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 1.8791089377886445, | |
| "grad_norm": 1.1259301900863647, | |
| "learning_rate": 7.498187092095723e-05, | |
| "loss": 0.8479, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 1.884542243955447, | |
| "grad_norm": 1.0703877210617065, | |
| "learning_rate": 7.461928934010153e-05, | |
| "loss": 0.8129, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 1.8899755501222493, | |
| "grad_norm": 1.2072659730911255, | |
| "learning_rate": 7.425670775924584e-05, | |
| "loss": 0.8493, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.8954088562890519, | |
| "grad_norm": 1.0550438165664673, | |
| "learning_rate": 7.389412617839015e-05, | |
| "loss": 0.8305, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 1.9008421624558545, | |
| "grad_norm": 1.2068486213684082, | |
| "learning_rate": 7.353154459753445e-05, | |
| "loss": 0.814, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.9062754686226568, | |
| "grad_norm": 1.1273876428604126, | |
| "learning_rate": 7.316896301667876e-05, | |
| "loss": 0.8302, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 1.9117087747894592, | |
| "grad_norm": 1.0691168308258057, | |
| "learning_rate": 7.280638143582307e-05, | |
| "loss": 0.8305, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.9171420809562618, | |
| "grad_norm": 1.1833313703536987, | |
| "learning_rate": 7.244379985496737e-05, | |
| "loss": 0.8292, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 1.9225753871230644, | |
| "grad_norm": 1.0391945838928223, | |
| "learning_rate": 7.208121827411168e-05, | |
| "loss": 0.8173, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 1.928008693289867, | |
| "grad_norm": 1.1484371423721313, | |
| "learning_rate": 7.171863669325599e-05, | |
| "loss": 0.8855, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 1.9334419994566694, | |
| "grad_norm": 1.1941226720809937, | |
| "learning_rate": 7.135605511240029e-05, | |
| "loss": 0.8908, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.9388753056234718, | |
| "grad_norm": 1.1475844383239746, | |
| "learning_rate": 7.09934735315446e-05, | |
| "loss": 0.8317, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 1.9443086117902744, | |
| "grad_norm": 1.1159197092056274, | |
| "learning_rate": 7.06308919506889e-05, | |
| "loss": 0.8222, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 1.949741917957077, | |
| "grad_norm": 1.1025739908218384, | |
| "learning_rate": 7.026831036983321e-05, | |
| "loss": 0.824, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 1.9551752241238793, | |
| "grad_norm": 1.1180258989334106, | |
| "learning_rate": 6.990572878897752e-05, | |
| "loss": 0.8362, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.9606085302906817, | |
| "grad_norm": 1.2311022281646729, | |
| "learning_rate": 6.954314720812183e-05, | |
| "loss": 0.8303, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 1.9660418364574843, | |
| "grad_norm": 1.0354889631271362, | |
| "learning_rate": 6.918056562726613e-05, | |
| "loss": 0.8128, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 1.971475142624287, | |
| "grad_norm": 1.0918065309524536, | |
| "learning_rate": 6.881798404641044e-05, | |
| "loss": 0.8402, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 1.9769084487910895, | |
| "grad_norm": 1.0534344911575317, | |
| "learning_rate": 6.845540246555475e-05, | |
| "loss": 0.835, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.9823417549578919, | |
| "grad_norm": 1.2761425971984863, | |
| "learning_rate": 6.809282088469905e-05, | |
| "loss": 0.8245, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 1.9877750611246943, | |
| "grad_norm": 1.2208045721054077, | |
| "learning_rate": 6.773023930384337e-05, | |
| "loss": 0.814, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 1.9932083672914969, | |
| "grad_norm": 1.1697189807891846, | |
| "learning_rate": 6.736765772298768e-05, | |
| "loss": 0.7971, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 1.9986416734582995, | |
| "grad_norm": 1.2008514404296875, | |
| "learning_rate": 6.700507614213199e-05, | |
| "loss": 0.8403, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.0541821718215942, | |
| "eval_runtime": 152.5101, | |
| "eval_samples_per_second": 10.163, | |
| "eval_steps_per_second": 2.544, | |
| "step": 1842 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 2763, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 8.490251112814382e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |