Instructions to use nuresens/ALL_PAD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use nuresens/ALL_PAD with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("aitf-komdigi/KomdigiITS-3B-PAD-CPT") model = PeftModel.from_pretrained(base_model, "nuresens/ALL_PAD") - Transformers
How to use nuresens/ALL_PAD with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nuresens/ALL_PAD") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nuresens/ALL_PAD", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use nuresens/ALL_PAD with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nuresens/ALL_PAD" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nuresens/ALL_PAD", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/nuresens/ALL_PAD
- SGLang
How to use nuresens/ALL_PAD 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 "nuresens/ALL_PAD" \ --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": "nuresens/ALL_PAD", "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 "nuresens/ALL_PAD" \ --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": "nuresens/ALL_PAD", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use nuresens/ALL_PAD 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 nuresens/ALL_PAD 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 nuresens/ALL_PAD to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for nuresens/ALL_PAD to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="nuresens/ALL_PAD", max_seq_length=2048, ) - Docker Model Runner
How to use nuresens/ALL_PAD with Docker Model Runner:
docker model run hf.co/nuresens/ALL_PAD
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8804270070984428, | |
| "eval_steps": 1000, | |
| "global_step": 8000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022009464069549906, | |
| "grad_norm": 1.9078384637832642, | |
| "learning_rate": 6.5934065934065935e-06, | |
| "loss": 1.8816274642944335, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004401892813909981, | |
| "grad_norm": 1.3476145267486572, | |
| "learning_rate": 1.391941391941392e-05, | |
| "loss": 1.7967029571533204, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006602839220864972, | |
| "grad_norm": 1.170466423034668, | |
| "learning_rate": 2.1245421245421246e-05, | |
| "loss": 1.715524673461914, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008803785627819962, | |
| "grad_norm": 1.3609683513641357, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 1.6288368225097656, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011004732034774953, | |
| "grad_norm": 1.151696801185608, | |
| "learning_rate": 3.58974358974359e-05, | |
| "loss": 1.4956942558288575, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013205678441729944, | |
| "grad_norm": 1.6291528940200806, | |
| "learning_rate": 4.322344322344323e-05, | |
| "loss": 1.3890839576721192, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.015406624848684934, | |
| "grad_norm": 1.4068406820297241, | |
| "learning_rate": 5.054945054945055e-05, | |
| "loss": 1.3895427703857421, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.017607571255639925, | |
| "grad_norm": 1.405369758605957, | |
| "learning_rate": 5.787545787545788e-05, | |
| "loss": 1.3423192977905274, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.019808517662594914, | |
| "grad_norm": 1.5128352642059326, | |
| "learning_rate": 6.52014652014652e-05, | |
| "loss": 1.2878559112548829, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.022009464069549907, | |
| "grad_norm": 1.572690486907959, | |
| "learning_rate": 7.252747252747253e-05, | |
| "loss": 1.2464408874511719, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.024210410476504896, | |
| "grad_norm": 1.610559105873108, | |
| "learning_rate": 7.985347985347986e-05, | |
| "loss": 1.2440325736999511, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02641135688345989, | |
| "grad_norm": 1.573136806488037, | |
| "learning_rate": 8.717948717948718e-05, | |
| "loss": 1.1872939109802245, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02861230329041488, | |
| "grad_norm": 1.6902788877487183, | |
| "learning_rate": 9.450549450549451e-05, | |
| "loss": 1.1642348289489746, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.030813249697369868, | |
| "grad_norm": 1.6654378175735474, | |
| "learning_rate": 0.00010183150183150183, | |
| "loss": 1.1244037628173829, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03301419610432486, | |
| "grad_norm": 2.193235397338867, | |
| "learning_rate": 0.00010915750915750915, | |
| "loss": 1.1596935272216797, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03521514251127985, | |
| "grad_norm": 1.470097541809082, | |
| "learning_rate": 0.0001164835164835165, | |
| "loss": 1.1412922859191894, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03741608891823484, | |
| "grad_norm": 1.3646049499511719, | |
| "learning_rate": 0.0001238095238095238, | |
| "loss": 1.1341608047485352, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03961703532518983, | |
| "grad_norm": 1.5164388418197632, | |
| "learning_rate": 0.00013113553113553114, | |
| "loss": 1.141274356842041, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.04181798173214482, | |
| "grad_norm": 1.47220778465271, | |
| "learning_rate": 0.00013846153846153847, | |
| "loss": 1.1136648178100585, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.044018928139099814, | |
| "grad_norm": 1.4043731689453125, | |
| "learning_rate": 0.00014578754578754578, | |
| "loss": 1.0726648330688477, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04621987454605481, | |
| "grad_norm": 1.2634721994400024, | |
| "learning_rate": 0.0001531135531135531, | |
| "loss": 1.0866886138916017, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.04842082095300979, | |
| "grad_norm": 1.4036515951156616, | |
| "learning_rate": 0.00016043956043956044, | |
| "loss": 1.0939341545104981, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.050621767359964785, | |
| "grad_norm": 1.2421815395355225, | |
| "learning_rate": 0.00016776556776556777, | |
| "loss": 1.0299765586853027, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.05282271376691978, | |
| "grad_norm": 1.2714147567749023, | |
| "learning_rate": 0.0001750915750915751, | |
| "loss": 1.0197788238525392, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.055023660173874764, | |
| "grad_norm": 1.3632781505584717, | |
| "learning_rate": 0.0001824175824175824, | |
| "loss": 1.0711404800415039, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.05722460658082976, | |
| "grad_norm": 1.2990729808807373, | |
| "learning_rate": 0.00018974358974358974, | |
| "loss": 1.0572866439819335, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.05942555298778475, | |
| "grad_norm": 1.1432695388793945, | |
| "learning_rate": 0.0001970695970695971, | |
| "loss": 1.0353819847106933, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.061626499394739735, | |
| "grad_norm": 1.357786774635315, | |
| "learning_rate": 0.00019999977137303472, | |
| "loss": 1.0498096466064453, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.06382744580169473, | |
| "grad_norm": 1.2086237668991089, | |
| "learning_rate": 0.0001999983742120326, | |
| "loss": 0.9976873397827148, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.06602839220864971, | |
| "grad_norm": 1.2265594005584717, | |
| "learning_rate": 0.00019999570692273363, | |
| "loss": 1.0049219131469727, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.0682293386156047, | |
| "grad_norm": 1.7034281492233276, | |
| "learning_rate": 0.00019999176953901636, | |
| "loss": 1.0101943016052246, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.0704302850225597, | |
| "grad_norm": 1.1741327047348022, | |
| "learning_rate": 0.0001999865621108914, | |
| "loss": 1.0026937484741212, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.07263123142951469, | |
| "grad_norm": 1.14133882522583, | |
| "learning_rate": 0.0001999800847045008, | |
| "loss": 1.0280275344848633, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.07483217783646968, | |
| "grad_norm": 1.053797960281372, | |
| "learning_rate": 0.0001999723374021174, | |
| "loss": 0.9998103141784668, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.07703312424342468, | |
| "grad_norm": 1.3832306861877441, | |
| "learning_rate": 0.00019996332030214337, | |
| "loss": 1.0395806312561036, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.07923407065037966, | |
| "grad_norm": 1.145727515220642, | |
| "learning_rate": 0.0001999530335191093, | |
| "loss": 0.9548494338989257, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.08143501705733465, | |
| "grad_norm": 1.096012830734253, | |
| "learning_rate": 0.00019994147718367276, | |
| "loss": 0.9871329307556153, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.08363596346428964, | |
| "grad_norm": 0.9356358051300049, | |
| "learning_rate": 0.0001999286514426163, | |
| "loss": 0.9341530799865723, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.08583690987124463, | |
| "grad_norm": 1.4062135219573975, | |
| "learning_rate": 0.00019991455645884605, | |
| "loss": 0.9540111541748046, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.08803785627819963, | |
| "grad_norm": 1.0113333463668823, | |
| "learning_rate": 0.00019989919241138925, | |
| "loss": 0.9937296867370605, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.09023880268515462, | |
| "grad_norm": 1.0309836864471436, | |
| "learning_rate": 0.00019988255949539215, | |
| "loss": 0.9602716445922852, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.09243974909210961, | |
| "grad_norm": 1.089353084564209, | |
| "learning_rate": 0.00019986465792211757, | |
| "loss": 0.9335391998291016, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.09464069549906459, | |
| "grad_norm": 1.054080843925476, | |
| "learning_rate": 0.0001998454879189422, | |
| "loss": 0.9715407371520997, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.09684164190601958, | |
| "grad_norm": 1.2168610095977783, | |
| "learning_rate": 0.00019982504972935357, | |
| "loss": 0.9322951316833497, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.09904258831297458, | |
| "grad_norm": 0.985170304775238, | |
| "learning_rate": 0.0001998033436129472, | |
| "loss": 0.98055419921875, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.10124353471992957, | |
| "grad_norm": 1.1162617206573486, | |
| "learning_rate": 0.00019978036984542307, | |
| "loss": 0.9634963035583496, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.10344448112688456, | |
| "grad_norm": 1.0027767419815063, | |
| "learning_rate": 0.00019975612871858222, | |
| "loss": 0.9526361465454102, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.10564542753383956, | |
| "grad_norm": 0.9371089935302734, | |
| "learning_rate": 0.0001997306205403231, | |
| "loss": 0.9452459335327148, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.10784637394079453, | |
| "grad_norm": 0.9952771067619324, | |
| "learning_rate": 0.00019970384563463753, | |
| "loss": 0.95389404296875, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.11004732034774953, | |
| "grad_norm": 0.9913569092750549, | |
| "learning_rate": 0.00019967580434160676, | |
| "loss": 0.9630558013916015, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.11224826675470452, | |
| "grad_norm": 0.9107245802879333, | |
| "learning_rate": 0.0001996464970173969, | |
| "loss": 0.9158695220947266, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.11444921316165951, | |
| "grad_norm": 0.9648348093032837, | |
| "learning_rate": 0.00019961592403425468, | |
| "loss": 0.9289742469787597, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.1166501595686145, | |
| "grad_norm": 0.9094238877296448, | |
| "learning_rate": 0.00019958408578050248, | |
| "loss": 0.9172938346862793, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.1188511059755695, | |
| "grad_norm": 0.8862208127975464, | |
| "learning_rate": 0.00019955098266053356, | |
| "loss": 0.9405776023864746, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.12105205238252449, | |
| "grad_norm": 0.9264389872550964, | |
| "learning_rate": 0.00019951661509480685, | |
| "loss": 0.9399794578552246, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.12325299878947947, | |
| "grad_norm": 1.0130054950714111, | |
| "learning_rate": 0.00019948098351984167, | |
| "loss": 0.8720254898071289, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.12545394519643446, | |
| "grad_norm": 0.9762976765632629, | |
| "learning_rate": 0.00019944408838821202, | |
| "loss": 0.8954718589782715, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.12765489160338947, | |
| "grad_norm": 1.001057744026184, | |
| "learning_rate": 0.00019940593016854106, | |
| "loss": 0.8816336631774903, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.12985583801034445, | |
| "grad_norm": 0.9089824557304382, | |
| "learning_rate": 0.000199366509345495, | |
| "loss": 0.8785006523132324, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.13205678441729943, | |
| "grad_norm": 0.9821614027023315, | |
| "learning_rate": 0.00019932582641977705, | |
| "loss": 0.8629944801330567, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.13425773082425443, | |
| "grad_norm": 0.8690505027770996, | |
| "learning_rate": 0.0001992838819081209, | |
| "loss": 0.8856033325195313, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.1364586772312094, | |
| "grad_norm": 0.9993884563446045, | |
| "learning_rate": 0.00019924067634328438, | |
| "loss": 0.871296501159668, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.13865962363816442, | |
| "grad_norm": 0.9565812349319458, | |
| "learning_rate": 0.0001991962102740425, | |
| "loss": 0.8619088172912598, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.1408605700451194, | |
| "grad_norm": 1.0189067125320435, | |
| "learning_rate": 0.00019915048426518054, | |
| "loss": 0.927723503112793, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.1430615164520744, | |
| "grad_norm": 0.9605172872543335, | |
| "learning_rate": 0.00019910349889748697, | |
| "loss": 0.8939146041870117, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.14526246285902938, | |
| "grad_norm": 0.9558774828910828, | |
| "learning_rate": 0.0001990552547677459, | |
| "loss": 0.9257272720336914, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.14746340926598436, | |
| "grad_norm": 1.0276355743408203, | |
| "learning_rate": 0.00019900575248872965, | |
| "loss": 0.8982614517211914, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.14966435567293937, | |
| "grad_norm": 0.9114047288894653, | |
| "learning_rate": 0.00019895499268919088, | |
| "loss": 0.8813505172729492, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.15186530207989435, | |
| "grad_norm": 0.935661256313324, | |
| "learning_rate": 0.0001989029760138547, | |
| "loss": 0.8918737411499024, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.15406624848684936, | |
| "grad_norm": 1.042932152748108, | |
| "learning_rate": 0.00019884970312341035, | |
| "loss": 0.9151006698608398, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.15626719489380433, | |
| "grad_norm": 1.0090407133102417, | |
| "learning_rate": 0.00019879517469450285, | |
| "loss": 0.8846939086914063, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.1584681413007593, | |
| "grad_norm": 0.9468204379081726, | |
| "learning_rate": 0.00019873939141972443, | |
| "loss": 0.9109236717224121, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.16066908770771432, | |
| "grad_norm": 2.099306344985962, | |
| "learning_rate": 0.00019868235400760588, | |
| "loss": 0.8627537727355957, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.1628700341146693, | |
| "grad_norm": 1.030119776725769, | |
| "learning_rate": 0.0001986240631826072, | |
| "loss": 0.8754992485046387, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.1650709805216243, | |
| "grad_norm": 0.8489016890525818, | |
| "learning_rate": 0.00019856451968510875, | |
| "loss": 0.8639801025390625, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.16727192692857928, | |
| "grad_norm": 0.8956750631332397, | |
| "learning_rate": 0.00019850372427140158, | |
| "loss": 0.8864573478698731, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.1694728733355343, | |
| "grad_norm": 0.9865322113037109, | |
| "learning_rate": 0.00019844167771367803, | |
| "loss": 0.8492755889892578, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.17167381974248927, | |
| "grad_norm": 0.9670360088348389, | |
| "learning_rate": 0.0001983783808000218, | |
| "loss": 0.8892242431640625, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.17387476614944425, | |
| "grad_norm": 0.8764406442642212, | |
| "learning_rate": 0.00019831383433439797, | |
| "loss": 0.8339031219482422, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.17607571255639926, | |
| "grad_norm": 0.9101215600967407, | |
| "learning_rate": 0.00019824803913664276, | |
| "loss": 0.8599502563476562, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.17827665896335423, | |
| "grad_norm": 0.9051525592803955, | |
| "learning_rate": 0.00019818099604245325, | |
| "loss": 0.8466466903686524, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.18047760537030924, | |
| "grad_norm": 0.990511953830719, | |
| "learning_rate": 0.00019811270590337654, | |
| "loss": 0.8185970306396484, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.18267855177726422, | |
| "grad_norm": 0.8963238000869751, | |
| "learning_rate": 0.00019804316958679913, | |
| "loss": 0.8855241775512696, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.18487949818421923, | |
| "grad_norm": 0.9547941088676453, | |
| "learning_rate": 0.00019797238797593578, | |
| "loss": 0.8937933921813965, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.1870804445911742, | |
| "grad_norm": 1.0186196565628052, | |
| "learning_rate": 0.00019790036196981842, | |
| "loss": 0.8803288459777832, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.18928139099812918, | |
| "grad_norm": 0.8781481385231018, | |
| "learning_rate": 0.00019782709248328457, | |
| "loss": 0.8143559455871582, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.1914823374050842, | |
| "grad_norm": 1.001970887184143, | |
| "learning_rate": 0.0001977525804469659, | |
| "loss": 0.8750756263732911, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.19368328381203917, | |
| "grad_norm": 1.0459098815917969, | |
| "learning_rate": 0.00019767682680727622, | |
| "loss": 0.8288005828857422, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.19588423021899418, | |
| "grad_norm": 0.9816129803657532, | |
| "learning_rate": 0.00019759983252639956, | |
| "loss": 0.7945041179656982, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.19808517662594916, | |
| "grad_norm": 0.8988497853279114, | |
| "learning_rate": 0.000197521598582278, | |
| "loss": 0.8355922698974609, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.20028612303290416, | |
| "grad_norm": 0.892160952091217, | |
| "learning_rate": 0.00019744212596859914, | |
| "loss": 0.854766845703125, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.20248706943985914, | |
| "grad_norm": 0.9523811340332031, | |
| "learning_rate": 0.00019736141569478356, | |
| "loss": 0.7782519340515137, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.20468801584681412, | |
| "grad_norm": 0.9528471827507019, | |
| "learning_rate": 0.00019727946878597195, | |
| "loss": 0.8091512680053711, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.20688896225376913, | |
| "grad_norm": 0.9524006843566895, | |
| "learning_rate": 0.00019719628628301212, | |
| "loss": 0.8312657356262207, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.2090899086607241, | |
| "grad_norm": 0.8955079913139343, | |
| "learning_rate": 0.00019711186924244574, | |
| "loss": 0.8257021903991699, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.2112908550676791, | |
| "grad_norm": 0.9080793857574463, | |
| "learning_rate": 0.00019702621873649495, | |
| "loss": 0.8441055297851563, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.2134918014746341, | |
| "grad_norm": 0.9945964813232422, | |
| "learning_rate": 0.00019693933585304877, | |
| "loss": 0.859739875793457, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.21569274788158907, | |
| "grad_norm": 0.9307037591934204, | |
| "learning_rate": 0.00019685122169564925, | |
| "loss": 0.8007944107055665, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.21789369428854408, | |
| "grad_norm": 0.8341166377067566, | |
| "learning_rate": 0.00019676187738347736, | |
| "loss": 0.8627373695373535, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.22009464069549906, | |
| "grad_norm": 0.9342769980430603, | |
| "learning_rate": 0.000196671304051339, | |
| "loss": 0.8269523620605469, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.22009464069549906, | |
| "eval_loss": 0.8339518904685974, | |
| "eval_runtime": 1054.8035, | |
| "eval_samples_per_second": 8.615, | |
| "eval_steps_per_second": 1.077, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.1111539096461784, | |
| "grad_norm": 1.318543791770935, | |
| "learning_rate": 0.00019965976481479497, | |
| "loss": 0.7344522476196289, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.11225444340505145, | |
| "grad_norm": 1.2357608079910278, | |
| "learning_rate": 0.0001996449179135936, | |
| "loss": 0.7247725486755371, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.11335497716392451, | |
| "grad_norm": 1.403720736503601, | |
| "learning_rate": 0.00019962975453062098, | |
| "loss": 0.7473694324493408, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.11445551092279756, | |
| "grad_norm": 1.3010951280593872, | |
| "learning_rate": 0.00019961427471403752, | |
| "loss": 0.7128599166870118, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.1155560446816706, | |
| "grad_norm": 1.4912559986114502, | |
| "learning_rate": 0.00019959847851300856, | |
| "loss": 0.7000036716461182, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.11665657844054367, | |
| "grad_norm": 1.476868748664856, | |
| "learning_rate": 0.00019958236597770437, | |
| "loss": 0.7557538986206055, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.11775711219941672, | |
| "grad_norm": 1.2181434631347656, | |
| "learning_rate": 0.00019956593715929986, | |
| "loss": 0.7561722755432129, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.11885764595828976, | |
| "grad_norm": 1.2714087963104248, | |
| "learning_rate": 0.00019954919210997453, | |
| "loss": 0.751192283630371, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.11995817971716283, | |
| "grad_norm": 1.3082411289215088, | |
| "learning_rate": 0.0001995321308829123, | |
| "loss": 0.771207618713379, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.12105871347603588, | |
| "grad_norm": 1.2826007604599, | |
| "learning_rate": 0.00019951475353230117, | |
| "loss": 0.7480668544769287, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.12215924723490892, | |
| "grad_norm": 1.3389414548873901, | |
| "learning_rate": 0.00019949706011333337, | |
| "loss": 0.7101992607116699, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.12325978099378199, | |
| "grad_norm": 1.3306312561035156, | |
| "learning_rate": 0.00019947905068220482, | |
| "loss": 0.6952154636383057, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.12436031475265504, | |
| "grad_norm": 1.5364283323287964, | |
| "learning_rate": 0.0001994607252961152, | |
| "loss": 0.7477862358093261, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.12546084851152808, | |
| "grad_norm": 1.5809048414230347, | |
| "learning_rate": 0.0001994420840132677, | |
| "loss": 0.681206226348877, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.12656138227040115, | |
| "grad_norm": 1.5444300174713135, | |
| "learning_rate": 0.0001994231268928688, | |
| "loss": 0.6869724750518799, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.1276619160292742, | |
| "grad_norm": 1.3037437200546265, | |
| "learning_rate": 0.00019940385399512813, | |
| "loss": 0.7233117580413818, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.12876244978814724, | |
| "grad_norm": 1.4460251331329346, | |
| "learning_rate": 0.00019938426538125827, | |
| "loss": 0.7215907573699951, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.1298629835470203, | |
| "grad_norm": 1.340132474899292, | |
| "learning_rate": 0.00019936436111347452, | |
| "loss": 0.6880172252655029, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.13096351730589337, | |
| "grad_norm": 1.358814001083374, | |
| "learning_rate": 0.0001993441412549947, | |
| "loss": 0.6970400333404541, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.1320640510647664, | |
| "grad_norm": 1.3030223846435547, | |
| "learning_rate": 0.00019932360587003906, | |
| "loss": 0.6770397663116455, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.13316458482363946, | |
| "grad_norm": 1.353985071182251, | |
| "learning_rate": 0.0001993027550238299, | |
| "loss": 0.660685396194458, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.13426511858251253, | |
| "grad_norm": 1.331395149230957, | |
| "learning_rate": 0.00019928158878259152, | |
| "loss": 0.7561236381530761, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.13536565234138556, | |
| "grad_norm": 1.6936500072479248, | |
| "learning_rate": 0.00019926010721354995, | |
| "loss": 0.6630916118621826, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.13646618610025862, | |
| "grad_norm": 1.7496025562286377, | |
| "learning_rate": 0.00019923831038493267, | |
| "loss": 0.7098928928375244, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.1375667198591317, | |
| "grad_norm": 1.4740201234817505, | |
| "learning_rate": 0.00019921619836596848, | |
| "loss": 0.7289152622222901, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.13866725361800472, | |
| "grad_norm": 1.6177831888198853, | |
| "learning_rate": 0.0001991937712268873, | |
| "loss": 0.6388457298278809, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.13976778737687778, | |
| "grad_norm": 1.436196208000183, | |
| "learning_rate": 0.0001991710290389198, | |
| "loss": 0.764772367477417, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.14086832113575085, | |
| "grad_norm": 1.770621418952942, | |
| "learning_rate": 0.00019914797187429743, | |
| "loss": 0.7233758449554444, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.14196885489462388, | |
| "grad_norm": 1.5772244930267334, | |
| "learning_rate": 0.00019912459980625183, | |
| "loss": 0.7039950370788575, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.14306938865349694, | |
| "grad_norm": 1.3709217309951782, | |
| "learning_rate": 0.00019910091290901503, | |
| "loss": 0.7573204040527344, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.14416992241237, | |
| "grad_norm": 1.3122904300689697, | |
| "learning_rate": 0.0001990769112578188, | |
| "loss": 0.6998284339904786, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.14527045617124304, | |
| "grad_norm": 1.4337154626846313, | |
| "learning_rate": 0.00019905259492889474, | |
| "loss": 0.7914797306060791, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.1463709899301161, | |
| "grad_norm": 1.5576714277267456, | |
| "learning_rate": 0.0001990279639994738, | |
| "loss": 0.6956133365631103, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.14747152368898916, | |
| "grad_norm": 1.403680443763733, | |
| "learning_rate": 0.00019900301854778617, | |
| "loss": 0.7613757133483887, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.14857205744786223, | |
| "grad_norm": 1.5148899555206299, | |
| "learning_rate": 0.00019897775865306098, | |
| "loss": 0.7047707557678222, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.14967259120673526, | |
| "grad_norm": 1.4134074449539185, | |
| "learning_rate": 0.00019895218439552602, | |
| "loss": 0.710445499420166, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.15077312496560832, | |
| "grad_norm": 1.2723708152770996, | |
| "learning_rate": 0.00019892629585640766, | |
| "loss": 0.7367370128631592, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.1518736587244814, | |
| "grad_norm": 1.4825470447540283, | |
| "learning_rate": 0.00019890009311793031, | |
| "loss": 0.7489582538604737, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.15297419248335442, | |
| "grad_norm": 1.3578537702560425, | |
| "learning_rate": 0.0001988735762633164, | |
| "loss": 0.7605162143707276, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.15407472624222748, | |
| "grad_norm": 1.4326390027999878, | |
| "learning_rate": 0.00019884674537678598, | |
| "loss": 0.7359246253967285, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.15517526000110055, | |
| "grad_norm": 1.54934561252594, | |
| "learning_rate": 0.00019881960054355652, | |
| "loss": 0.7244048118591309, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.15627579375997358, | |
| "grad_norm": 1.4539642333984375, | |
| "learning_rate": 0.00019879214184984257, | |
| "loss": 0.7321300029754638, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.15737632751884664, | |
| "grad_norm": 1.480238914489746, | |
| "learning_rate": 0.00019876436938285558, | |
| "loss": 0.7465243339538574, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.1584768612777197, | |
| "grad_norm": 1.380171775817871, | |
| "learning_rate": 0.00019873628323080359, | |
| "loss": 0.7432620525360107, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.15957739503659274, | |
| "grad_norm": 1.516487717628479, | |
| "learning_rate": 0.00019870788348289083, | |
| "loss": 0.7081382274627686, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.1606779287954658, | |
| "grad_norm": 1.4838062524795532, | |
| "learning_rate": 0.00019867917022931765, | |
| "loss": 0.7314321994781494, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.16177846255433886, | |
| "grad_norm": 1.501446008682251, | |
| "learning_rate": 0.0001986501435612801, | |
| "loss": 0.7468172073364258, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.1628789963132119, | |
| "grad_norm": 1.3697547912597656, | |
| "learning_rate": 0.0001986208035709696, | |
| "loss": 0.6616341590881347, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.16397953007208496, | |
| "grad_norm": 1.4565426111221313, | |
| "learning_rate": 0.00019859115035157285, | |
| "loss": 0.7138534545898437, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.16508006383095802, | |
| "grad_norm": 1.2693283557891846, | |
| "learning_rate": 0.0001985611839972712, | |
| "loss": 0.7095062732696533, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.16618059758983106, | |
| "grad_norm": 1.519113540649414, | |
| "learning_rate": 0.00019853090460324071, | |
| "loss": 0.6623078346252441, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.16728113134870412, | |
| "grad_norm": 1.1893036365509033, | |
| "learning_rate": 0.0001985003122656516, | |
| "loss": 0.785255765914917, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.16838166510757718, | |
| "grad_norm": 1.5294969081878662, | |
| "learning_rate": 0.00019846940708166807, | |
| "loss": 0.7090532302856445, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.16948219886645022, | |
| "grad_norm": 1.3630003929138184, | |
| "learning_rate": 0.00019843818914944795, | |
| "loss": 0.7042516708374024, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.17058273262532328, | |
| "grad_norm": 1.4818453788757324, | |
| "learning_rate": 0.00019840665856814236, | |
| "loss": 0.7102742195129395, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.17168326638419634, | |
| "grad_norm": 1.5661572217941284, | |
| "learning_rate": 0.00019837481543789542, | |
| "loss": 0.7352417469024658, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.17278380014306938, | |
| "grad_norm": 1.5921189785003662, | |
| "learning_rate": 0.00019834265985984394, | |
| "loss": 0.6786233901977539, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.17388433390194244, | |
| "grad_norm": 1.7793580293655396, | |
| "learning_rate": 0.00019831019193611716, | |
| "loss": 0.6913634300231933, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.1749848676608155, | |
| "grad_norm": 1.4666355848312378, | |
| "learning_rate": 0.00019827741176983629, | |
| "loss": 0.6923691749572753, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.17608540141968854, | |
| "grad_norm": 1.2723121643066406, | |
| "learning_rate": 0.0001982443194651142, | |
| "loss": 0.7328421592712402, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.1771859351785616, | |
| "grad_norm": 1.7125496864318848, | |
| "learning_rate": 0.00019821091512705529, | |
| "loss": 0.7273451328277588, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.17828646893743466, | |
| "grad_norm": 1.2607357501983643, | |
| "learning_rate": 0.0001981771988617549, | |
| "loss": 0.6852648258209229, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.1793870026963077, | |
| "grad_norm": 1.4323406219482422, | |
| "learning_rate": 0.0001981431707762991, | |
| "loss": 0.6527719974517823, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.18048753645518076, | |
| "grad_norm": 1.5323034524917603, | |
| "learning_rate": 0.00019810883097876435, | |
| "loss": 0.6863321781158447, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.18158807021405382, | |
| "grad_norm": 1.4771450757980347, | |
| "learning_rate": 0.00019807417957821708, | |
| "loss": 0.713313102722168, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.18268860397292688, | |
| "grad_norm": 1.4179728031158447, | |
| "learning_rate": 0.0001980392166847135, | |
| "loss": 0.7239354133605957, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.18378913773179992, | |
| "grad_norm": 1.54883873462677, | |
| "learning_rate": 0.00019800394240929907, | |
| "loss": 0.7668267726898194, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.18488967149067298, | |
| "grad_norm": 1.4585139751434326, | |
| "learning_rate": 0.0001979683568640083, | |
| "loss": 0.7013049602508545, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.18599020524954604, | |
| "grad_norm": 1.423919439315796, | |
| "learning_rate": 0.0001979324601618642, | |
| "loss": 0.7432220935821533, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.18709073900841908, | |
| "grad_norm": 1.5283218622207642, | |
| "learning_rate": 0.0001978962524168782, | |
| "loss": 0.7024415969848633, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.18819127276729214, | |
| "grad_norm": 1.4342306852340698, | |
| "learning_rate": 0.00019785973374404948, | |
| "loss": 0.6836557388305664, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.1892918065261652, | |
| "grad_norm": 1.3203076124191284, | |
| "learning_rate": 0.0001978229042593649, | |
| "loss": 0.669966173171997, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.19039234028503824, | |
| "grad_norm": 1.6151920557022095, | |
| "learning_rate": 0.0001977857640797984, | |
| "loss": 0.7203169345855713, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.1914928740439113, | |
| "grad_norm": 1.5594950914382935, | |
| "learning_rate": 0.00019774831332331072, | |
| "loss": 0.7175643444061279, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.19259340780278436, | |
| "grad_norm": 1.275919795036316, | |
| "learning_rate": 0.000197710552108849, | |
| "loss": 0.7080940246582031, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.1936939415616574, | |
| "grad_norm": 1.559988021850586, | |
| "learning_rate": 0.00019767248055634656, | |
| "loss": 0.6943031311035156, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.19479447532053046, | |
| "grad_norm": 1.4960150718688965, | |
| "learning_rate": 0.0001976340987867222, | |
| "loss": 0.6438261032104492, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.19589500907940352, | |
| "grad_norm": 1.3384159803390503, | |
| "learning_rate": 0.00019759540692188015, | |
| "loss": 0.6569961547851563, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.19699554283827655, | |
| "grad_norm": 1.6143518686294556, | |
| "learning_rate": 0.00019755640508470942, | |
| "loss": 0.6640120029449463, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.19809607659714962, | |
| "grad_norm": 1.533369779586792, | |
| "learning_rate": 0.00019751709339908352, | |
| "loss": 0.709033203125, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.19919661035602268, | |
| "grad_norm": 1.3830273151397705, | |
| "learning_rate": 0.00019747747198986025, | |
| "loss": 0.7042165279388428, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.20029714411489571, | |
| "grad_norm": 1.5432374477386475, | |
| "learning_rate": 0.00019743754098288087, | |
| "loss": 0.7099340438842774, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.20139767787376878, | |
| "grad_norm": 1.8186261653900146, | |
| "learning_rate": 0.00019739730050497012, | |
| "loss": 0.5920440673828125, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.20249821163264184, | |
| "grad_norm": 1.2721370458602905, | |
| "learning_rate": 0.0001973567506839356, | |
| "loss": 0.6752917766571045, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.20359874539151487, | |
| "grad_norm": 1.5037890672683716, | |
| "learning_rate": 0.00019731589164856742, | |
| "loss": 0.6958805084228515, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.20469927915038794, | |
| "grad_norm": 1.4381048679351807, | |
| "learning_rate": 0.00019727472352863774, | |
| "loss": 0.6831310749053955, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.205799812909261, | |
| "grad_norm": 1.4521901607513428, | |
| "learning_rate": 0.00019723324645490043, | |
| "loss": 0.6515075206756592, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.20690034666813403, | |
| "grad_norm": 1.4317247867584229, | |
| "learning_rate": 0.00019719146055909072, | |
| "loss": 0.7445472240447998, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.2080008804270071, | |
| "grad_norm": 1.3491274118423462, | |
| "learning_rate": 0.00019714936597392454, | |
| "loss": 0.6975584030151367, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.20910141418588016, | |
| "grad_norm": 1.6799184083938599, | |
| "learning_rate": 0.00019710696283309828, | |
| "loss": 0.663750171661377, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.2102019479447532, | |
| "grad_norm": 1.5508129596710205, | |
| "learning_rate": 0.00019706425127128844, | |
| "loss": 0.7214709281921386, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.21130248170362625, | |
| "grad_norm": 1.507115364074707, | |
| "learning_rate": 0.000197021231424151, | |
| "loss": 0.6937719345092773, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.21240301546249932, | |
| "grad_norm": 1.5276693105697632, | |
| "learning_rate": 0.00019697790342832104, | |
| "loss": 0.6974040985107421, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.21350354922137235, | |
| "grad_norm": 1.5013867616653442, | |
| "learning_rate": 0.00019693426742141244, | |
| "loss": 0.7391683101654053, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.21460408298024541, | |
| "grad_norm": 1.6396576166152954, | |
| "learning_rate": 0.00019689032354201736, | |
| "loss": 0.6841801166534424, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.21570461673911848, | |
| "grad_norm": 1.480556845664978, | |
| "learning_rate": 0.00019684607192970574, | |
| "loss": 0.6711002349853515, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.21680515049799154, | |
| "grad_norm": 1.2973003387451172, | |
| "learning_rate": 0.0001968015127250249, | |
| "loss": 0.7282744884490967, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.21790568425686457, | |
| "grad_norm": 1.5058932304382324, | |
| "learning_rate": 0.00019675664606949914, | |
| "loss": 0.7393957138061523, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.21900621801573764, | |
| "grad_norm": 1.6734826564788818, | |
| "learning_rate": 0.00019671147210562927, | |
| "loss": 0.6838624477386475, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.2201067517746107, | |
| "grad_norm": 1.7731140851974487, | |
| "learning_rate": 0.00019666599097689207, | |
| "loss": 0.7038939952850342, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2201067517746107, | |
| "eval_loss": 0.8496589064598083, | |
| "eval_runtime": 933.6965, | |
| "eval_samples_per_second": 9.732, | |
| "eval_steps_per_second": 2.433, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.22120728553348373, | |
| "grad_norm": 1.6997652053833008, | |
| "learning_rate": 0.00019662020282773995, | |
| "loss": 0.8130602836608887, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.2223078192923568, | |
| "grad_norm": 1.617069125175476, | |
| "learning_rate": 0.00019657410780360047, | |
| "loss": 0.8593770027160644, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.22340835305122986, | |
| "grad_norm": 1.435889482498169, | |
| "learning_rate": 0.0001965277060508758, | |
| "loss": 0.8794844627380372, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.2245088868101029, | |
| "grad_norm": 1.593628168106079, | |
| "learning_rate": 0.00019648099771694236, | |
| "loss": 0.8761175155639649, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.22560942056897595, | |
| "grad_norm": 1.4817216396331787, | |
| "learning_rate": 0.00019643398295015026, | |
| "loss": 0.8747184753417969, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.22670995432784902, | |
| "grad_norm": 1.2658919095993042, | |
| "learning_rate": 0.0001963866618998229, | |
| "loss": 0.8425754547119141, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.22781048808672205, | |
| "grad_norm": 1.549432396888733, | |
| "learning_rate": 0.00019633903471625645, | |
| "loss": 0.8407624244689942, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.22891102184559511, | |
| "grad_norm": 1.2967861890792847, | |
| "learning_rate": 0.00019629110155071938, | |
| "loss": 0.8481991767883301, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.23001155560446818, | |
| "grad_norm": 1.4197816848754883, | |
| "learning_rate": 0.00019624286255545199, | |
| "loss": 0.8669241905212403, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.2311120893633412, | |
| "grad_norm": 1.2624856233596802, | |
| "learning_rate": 0.00019619431788366596, | |
| "loss": 0.8022339820861817, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.23221262312221427, | |
| "grad_norm": 1.6743338108062744, | |
| "learning_rate": 0.0001961454676895438, | |
| "loss": 0.8768888473510742, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.23331315688108734, | |
| "grad_norm": 2.0868279933929443, | |
| "learning_rate": 0.0001960963121282384, | |
| "loss": 0.8667360305786133, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.23441369063996037, | |
| "grad_norm": 1.4186112880706787, | |
| "learning_rate": 0.00019604685135587245, | |
| "loss": 0.8278182029724122, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.23551422439883343, | |
| "grad_norm": 1.2936203479766846, | |
| "learning_rate": 0.00019599708552953815, | |
| "loss": 0.812893009185791, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.2366147581577065, | |
| "grad_norm": 1.2756561040878296, | |
| "learning_rate": 0.0001959470148072965, | |
| "loss": 0.8358366012573242, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.23771529191657953, | |
| "grad_norm": 1.3688085079193115, | |
| "learning_rate": 0.00019589663934817687, | |
| "loss": 0.7904013633728028, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.2388158256754526, | |
| "grad_norm": 1.317444920539856, | |
| "learning_rate": 0.0001958459593121766, | |
| "loss": 0.8964195251464844, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.23991635943432565, | |
| "grad_norm": 1.294002890586853, | |
| "learning_rate": 0.00019579497486026023, | |
| "loss": 0.8562044143676758, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.2410168931931987, | |
| "grad_norm": 1.2761428356170654, | |
| "learning_rate": 0.0001957436861543593, | |
| "loss": 0.8061718940734863, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.24211742695207175, | |
| "grad_norm": 1.4096399545669556, | |
| "learning_rate": 0.0001956920933573716, | |
| "loss": 0.8700193405151367, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.2432179607109448, | |
| "grad_norm": 1.2484604120254517, | |
| "learning_rate": 0.0001956401966331608, | |
| "loss": 0.8373005867004395, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.24431849446981785, | |
| "grad_norm": 1.4023255109786987, | |
| "learning_rate": 0.00019558799614655586, | |
| "loss": 0.7784786224365234, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.2454190282286909, | |
| "grad_norm": 1.3306242227554321, | |
| "learning_rate": 0.00019553549206335048, | |
| "loss": 0.8288736343383789, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.24651956198756397, | |
| "grad_norm": 1.3334354162216187, | |
| "learning_rate": 0.00019548268455030267, | |
| "loss": 0.815639591217041, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.24762009574643704, | |
| "grad_norm": 1.2042546272277832, | |
| "learning_rate": 0.00019542957377513412, | |
| "loss": 0.8448248863220215, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.24872062950531007, | |
| "grad_norm": 1.4218223094940186, | |
| "learning_rate": 0.0001953761599065297, | |
| "loss": 0.8586576461791993, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.24982116326418313, | |
| "grad_norm": 1.326367735862732, | |
| "learning_rate": 0.00019532244311413704, | |
| "loss": 0.7699498176574707, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.25092169702305617, | |
| "grad_norm": 1.414927363395691, | |
| "learning_rate": 0.00019526842356856568, | |
| "loss": 0.8183151245117187, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.25202223078192926, | |
| "grad_norm": 1.638340950012207, | |
| "learning_rate": 0.00019521410144138693, | |
| "loss": 0.8281731605529785, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.2531227645408023, | |
| "grad_norm": 1.4947667121887207, | |
| "learning_rate": 0.00019515947690513304, | |
| "loss": 0.8409298896789551, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.2542232982996753, | |
| "grad_norm": 1.5608994960784912, | |
| "learning_rate": 0.00019510455013329673, | |
| "loss": 0.8110830307006835, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.2553238320585484, | |
| "grad_norm": 1.3185389041900635, | |
| "learning_rate": 0.00019504932130033067, | |
| "loss": 0.8009634971618652, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.25642436581742145, | |
| "grad_norm": 1.246773600578308, | |
| "learning_rate": 0.00019499379058164694, | |
| "loss": 0.8565659523010254, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.2575248995762945, | |
| "grad_norm": 1.3509032726287842, | |
| "learning_rate": 0.00019493795815361638, | |
| "loss": 0.8486443519592285, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.2586254333351676, | |
| "grad_norm": 1.330709457397461, | |
| "learning_rate": 0.0001948818241935681, | |
| "loss": 0.8198354721069336, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.2597259670940406, | |
| "grad_norm": 1.200380802154541, | |
| "learning_rate": 0.00019482538887978894, | |
| "loss": 0.8310845375061036, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.26082650085291365, | |
| "grad_norm": 1.3873624801635742, | |
| "learning_rate": 0.00019476865239152283, | |
| "loss": 0.8995956420898438, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.26192703461178674, | |
| "grad_norm": 1.5119566917419434, | |
| "learning_rate": 0.00019471161490897029, | |
| "loss": 0.828061580657959, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.26302756837065977, | |
| "grad_norm": 1.461253046989441, | |
| "learning_rate": 0.0001946542766132878, | |
| "loss": 0.8718130111694335, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.2641281021295328, | |
| "grad_norm": 1.5901751518249512, | |
| "learning_rate": 0.00019459663768658722, | |
| "loss": 0.8477680206298828, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.2652286358884059, | |
| "grad_norm": 1.2325890064239502, | |
| "learning_rate": 0.00019453869831193536, | |
| "loss": 0.8439332008361816, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.26632916964727893, | |
| "grad_norm": 1.3299224376678467, | |
| "learning_rate": 0.00019448045867335315, | |
| "loss": 0.8034492492675781, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.26742970340615196, | |
| "grad_norm": 1.4191641807556152, | |
| "learning_rate": 0.00019442191895581524, | |
| "loss": 0.8057695388793945, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.26853023716502505, | |
| "grad_norm": 1.2450047731399536, | |
| "learning_rate": 0.0001943630793452494, | |
| "loss": 0.7739078521728515, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.2696307709238981, | |
| "grad_norm": 1.2834359407424927, | |
| "learning_rate": 0.0001943039400285358, | |
| "loss": 0.8015741348266602, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.2707313046827711, | |
| "grad_norm": 1.4579415321350098, | |
| "learning_rate": 0.0001942445011935066, | |
| "loss": 0.8276127815246582, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.2718318384416442, | |
| "grad_norm": 1.2527804374694824, | |
| "learning_rate": 0.0001941847630289452, | |
| "loss": 0.8028785705566406, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.27293237220051725, | |
| "grad_norm": 1.6216117143630981, | |
| "learning_rate": 0.00019412472572458568, | |
| "loss": 0.8052440643310547, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.2740329059593903, | |
| "grad_norm": 1.3080998659133911, | |
| "learning_rate": 0.00019406438947111232, | |
| "loss": 0.7991613388061524, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.2751334397182634, | |
| "grad_norm": 1.2693983316421509, | |
| "learning_rate": 0.00019400375446015875, | |
| "loss": 0.7874859809875489, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.2762339734771364, | |
| "grad_norm": 1.5021086931228638, | |
| "learning_rate": 0.00019394282088430758, | |
| "loss": 0.857176685333252, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.27733450723600944, | |
| "grad_norm": 1.7014224529266357, | |
| "learning_rate": 0.00019388158893708968, | |
| "loss": 0.8121908187866211, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.27843504099488253, | |
| "grad_norm": 1.2773478031158447, | |
| "learning_rate": 0.00019382005881298355, | |
| "loss": 0.83267240524292, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.27953557475375557, | |
| "grad_norm": 1.2932922840118408, | |
| "learning_rate": 0.00019375823070741472, | |
| "loss": 0.8565213203430175, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.2806361085126286, | |
| "grad_norm": 1.3514758348464966, | |
| "learning_rate": 0.00019369610481675517, | |
| "loss": 0.8068264961242676, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.2817366422715017, | |
| "grad_norm": 1.4034395217895508, | |
| "learning_rate": 0.00019363368133832264, | |
| "loss": 0.7951233863830567, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.2828371760303747, | |
| "grad_norm": 1.402474284172058, | |
| "learning_rate": 0.0001935709604703801, | |
| "loss": 0.8516476631164551, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.28393770978924776, | |
| "grad_norm": 1.2598680257797241, | |
| "learning_rate": 0.000193507942412135, | |
| "loss": 0.8248865127563476, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.28503824354812085, | |
| "grad_norm": 1.4511678218841553, | |
| "learning_rate": 0.00019344462736373865, | |
| "loss": 0.8426539421081543, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.2861387773069939, | |
| "grad_norm": 1.4446839094161987, | |
| "learning_rate": 0.00019338101552628578, | |
| "loss": 0.7813214302062989, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.2872393110658669, | |
| "grad_norm": 1.348212718963623, | |
| "learning_rate": 0.0001933171071018136, | |
| "loss": 0.8185086250305176, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.28833984482474, | |
| "grad_norm": 1.3354694843292236, | |
| "learning_rate": 0.00019325290229330134, | |
| "loss": 0.8290966033935547, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.28944037858361304, | |
| "grad_norm": 1.6722166538238525, | |
| "learning_rate": 0.00019318840130466968, | |
| "loss": 0.8179054260253906, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.2905409123424861, | |
| "grad_norm": 1.2694981098175049, | |
| "learning_rate": 0.00019312360434077985, | |
| "loss": 0.8385242462158203, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.29164144610135917, | |
| "grad_norm": 1.9272838830947876, | |
| "learning_rate": 0.00019305851160743325, | |
| "loss": 0.8141334533691407, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.2927419798602322, | |
| "grad_norm": 1.2957518100738525, | |
| "learning_rate": 0.00019299312331137055, | |
| "loss": 0.835750675201416, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.29384251361910524, | |
| "grad_norm": 1.5437421798706055, | |
| "learning_rate": 0.0001929274396602713, | |
| "loss": 0.7907589912414551, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.29494304737797833, | |
| "grad_norm": 1.487249732017517, | |
| "learning_rate": 0.00019286146086275294, | |
| "loss": 0.7967824935913086, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.29604358113685136, | |
| "grad_norm": 1.3860902786254883, | |
| "learning_rate": 0.00019279518712837052, | |
| "loss": 0.7865518093109131, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.29714411489572445, | |
| "grad_norm": 1.5004669427871704, | |
| "learning_rate": 0.00019272861866761573, | |
| "loss": 0.8506379127502441, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.2982446486545975, | |
| "grad_norm": 1.4427077770233154, | |
| "learning_rate": 0.0001926617556919163, | |
| "loss": 0.8193819999694825, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.2993451824134705, | |
| "grad_norm": 1.2161895036697388, | |
| "learning_rate": 0.00019259459841363552, | |
| "loss": 0.8297209739685059, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.3004457161723436, | |
| "grad_norm": 1.8028621673583984, | |
| "learning_rate": 0.0001925271470460712, | |
| "loss": 0.8238694190979003, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.30154624993121665, | |
| "grad_norm": 1.339763879776001, | |
| "learning_rate": 0.00019245940180345544, | |
| "loss": 0.7622324466705322, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.3026467836900897, | |
| "grad_norm": 1.3132916688919067, | |
| "learning_rate": 0.0001923913629009535, | |
| "loss": 0.7768839359283447, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.3037473174489628, | |
| "grad_norm": 1.3144910335540771, | |
| "learning_rate": 0.0001923230305546635, | |
| "loss": 0.8279050827026367, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.3048478512078358, | |
| "grad_norm": 1.1577019691467285, | |
| "learning_rate": 0.00019225440498161546, | |
| "loss": 0.7885588645935059, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.30594838496670884, | |
| "grad_norm": 1.4336917400360107, | |
| "learning_rate": 0.0001921854863997707, | |
| "loss": 0.7973155021667481, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.30704891872558193, | |
| "grad_norm": 1.363558292388916, | |
| "learning_rate": 0.00019211627502802134, | |
| "loss": 0.7967965602874756, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.30814945248445497, | |
| "grad_norm": 1.5244808197021484, | |
| "learning_rate": 0.0001920467710861892, | |
| "loss": 0.7747397422790527, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.309249986243328, | |
| "grad_norm": 1.5638800859451294, | |
| "learning_rate": 0.00019197697479502547, | |
| "loss": 0.805236530303955, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.3103505200022011, | |
| "grad_norm": 1.3312816619873047, | |
| "learning_rate": 0.00019190688637620986, | |
| "loss": 0.7381678581237793, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.3114510537610741, | |
| "grad_norm": 1.4813461303710938, | |
| "learning_rate": 0.00019183650605234984, | |
| "loss": 0.7765594005584717, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.31255158751994716, | |
| "grad_norm": 1.3135008811950684, | |
| "learning_rate": 0.00019176583404698002, | |
| "loss": 0.8520167350769043, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.31365212127882025, | |
| "grad_norm": 1.4595879316329956, | |
| "learning_rate": 0.00019169487058456148, | |
| "loss": 0.8141855239868164, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.3147526550376933, | |
| "grad_norm": 1.384316325187683, | |
| "learning_rate": 0.00019162361589048095, | |
| "loss": 0.7784629344940186, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.3158531887965663, | |
| "grad_norm": 1.1909021139144897, | |
| "learning_rate": 0.00019155207019105007, | |
| "loss": 0.8151874542236328, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.3169537225554394, | |
| "grad_norm": 1.1605905294418335, | |
| "learning_rate": 0.00019148023371350493, | |
| "loss": 0.8893998146057129, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.31805425631431244, | |
| "grad_norm": 1.6996575593948364, | |
| "learning_rate": 0.00019140810668600493, | |
| "loss": 0.8112521171569824, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.3191547900731855, | |
| "grad_norm": 1.2271260023117065, | |
| "learning_rate": 0.00019133568933763244, | |
| "loss": 0.8266308784484864, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.32025532383205857, | |
| "grad_norm": 1.7019249200820923, | |
| "learning_rate": 0.0001912629818983919, | |
| "loss": 0.7661680698394775, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.3213558575909316, | |
| "grad_norm": 1.2853891849517822, | |
| "learning_rate": 0.00019118998459920902, | |
| "loss": 0.8458981513977051, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.32245639134980464, | |
| "grad_norm": 1.4744017124176025, | |
| "learning_rate": 0.0001911166976719302, | |
| "loss": 0.7988483428955078, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.32355692510867773, | |
| "grad_norm": 1.26249098777771, | |
| "learning_rate": 0.0001910431213493218, | |
| "loss": 0.789542818069458, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.32465745886755076, | |
| "grad_norm": 1.4478040933609009, | |
| "learning_rate": 0.00019096925586506913, | |
| "loss": 0.7970124244689941, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.3257579926264238, | |
| "grad_norm": 1.465301752090454, | |
| "learning_rate": 0.00019089510145377608, | |
| "loss": 0.7939679622650146, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.3268585263852969, | |
| "grad_norm": 1.2790896892547607, | |
| "learning_rate": 0.00019082065835096412, | |
| "loss": 0.8515988349914551, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.3279590601441699, | |
| "grad_norm": 1.3531389236450195, | |
| "learning_rate": 0.00019074592679307165, | |
| "loss": 0.7504467010498047, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.32905959390304296, | |
| "grad_norm": 1.2116661071777344, | |
| "learning_rate": 0.00019067090701745327, | |
| "loss": 0.8174965858459473, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.33016012766191605, | |
| "grad_norm": 1.113641381263733, | |
| "learning_rate": 0.0001905955992623789, | |
| "loss": 0.7890684127807617, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.33016012766191605, | |
| "eval_loss": 0.790532648563385, | |
| "eval_runtime": 930.8796, | |
| "eval_samples_per_second": 9.762, | |
| "eval_steps_per_second": 2.441, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.3312606614207891, | |
| "grad_norm": 1.430518388748169, | |
| "learning_rate": 0.00019052000376703317, | |
| "loss": 0.8236588478088379, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.3323611951796621, | |
| "grad_norm": 1.4252548217773438, | |
| "learning_rate": 0.0001904441207715146, | |
| "loss": 0.847992992401123, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.3334617289385352, | |
| "grad_norm": 1.4208446741104126, | |
| "learning_rate": 0.00019036795051683483, | |
| "loss": 0.8224313735961915, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.33456226269740824, | |
| "grad_norm": 1.3954637050628662, | |
| "learning_rate": 0.00019029149324491785, | |
| "loss": 0.8087237358093262, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.3356627964562813, | |
| "grad_norm": 1.3011157512664795, | |
| "learning_rate": 0.00019021474919859926, | |
| "loss": 0.8049816131591797, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.33676333021515437, | |
| "grad_norm": 1.3143519163131714, | |
| "learning_rate": 0.00019013771862162545, | |
| "loss": 0.7496432781219482, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.3378638639740274, | |
| "grad_norm": 1.403659701347351, | |
| "learning_rate": 0.00019006040175865294, | |
| "loss": 0.7452910423278809, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.33896439773290044, | |
| "grad_norm": 1.1721720695495605, | |
| "learning_rate": 0.00018998279885524744, | |
| "loss": 0.797463321685791, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.3400649314917735, | |
| "grad_norm": 1.8334842920303345, | |
| "learning_rate": 0.00018990491015788313, | |
| "loss": 0.7963507652282715, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.34116546525064656, | |
| "grad_norm": 1.3609745502471924, | |
| "learning_rate": 0.00018982673591394207, | |
| "loss": 0.7899526596069336, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.3422659990095196, | |
| "grad_norm": 1.4191335439682007, | |
| "learning_rate": 0.00018974827637171298, | |
| "loss": 0.8170291900634765, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.3433665327683927, | |
| "grad_norm": 1.546268343925476, | |
| "learning_rate": 0.00018966953178039097, | |
| "loss": 0.7608869552612305, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.3444670665272657, | |
| "grad_norm": 1.2157829999923706, | |
| "learning_rate": 0.00018959050239007627, | |
| "loss": 0.8163496971130371, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.34556760028613875, | |
| "grad_norm": 1.4426497220993042, | |
| "learning_rate": 0.00018951118845177386, | |
| "loss": 0.7838230609893799, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.34666813404501184, | |
| "grad_norm": 1.4075052738189697, | |
| "learning_rate": 0.0001894315902173924, | |
| "loss": 0.780454158782959, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.3477686678038849, | |
| "grad_norm": 1.146291732788086, | |
| "learning_rate": 0.00018935170793974335, | |
| "loss": 0.7559466361999512, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.3488692015627579, | |
| "grad_norm": 1.1670087575912476, | |
| "learning_rate": 0.00018927154187254054, | |
| "loss": 0.7347095489501954, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.349969735321631, | |
| "grad_norm": 1.3034203052520752, | |
| "learning_rate": 0.0001891910922703991, | |
| "loss": 0.7963647365570068, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.35107026908050404, | |
| "grad_norm": 1.2328404188156128, | |
| "learning_rate": 0.0001891103593888345, | |
| "loss": 0.7840650081634521, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.3521708028393771, | |
| "grad_norm": 1.2788565158843994, | |
| "learning_rate": 0.00018902934348426223, | |
| "loss": 0.7421338081359863, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.35327133659825016, | |
| "grad_norm": 1.4272618293762207, | |
| "learning_rate": 0.0001889480448139964, | |
| "loss": 0.7635135173797607, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 0.3543718703571232, | |
| "grad_norm": 1.2253040075302124, | |
| "learning_rate": 0.0001888664636362495, | |
| "loss": 0.8046904563903808, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.35547240411599623, | |
| "grad_norm": 1.3970891237258911, | |
| "learning_rate": 0.000188784600210131, | |
| "loss": 0.7833479881286621, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 0.3565729378748693, | |
| "grad_norm": 1.3941155672073364, | |
| "learning_rate": 0.00018870245479564703, | |
| "loss": 0.8373173713684082, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.35767347163374236, | |
| "grad_norm": 1.3662322759628296, | |
| "learning_rate": 0.00018862002765369926, | |
| "loss": 0.8315282821655273, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.3587740053926154, | |
| "grad_norm": 1.5178701877593994, | |
| "learning_rate": 0.00018853731904608414, | |
| "loss": 0.7962240695953369, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.3598745391514885, | |
| "grad_norm": 1.2388792037963867, | |
| "learning_rate": 0.00018845432923549212, | |
| "loss": 0.785247802734375, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 0.3609750729103615, | |
| "grad_norm": 1.5908961296081543, | |
| "learning_rate": 0.00018837105848550672, | |
| "loss": 0.7622479915618896, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.3620756066692346, | |
| "grad_norm": 1.3947844505310059, | |
| "learning_rate": 0.00018828750706060385, | |
| "loss": 0.8159708976745605, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 0.36317614042810764, | |
| "grad_norm": 1.5420454740524292, | |
| "learning_rate": 0.00018820367522615078, | |
| "loss": 0.7608321189880372, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.3642766741869807, | |
| "grad_norm": 1.348726749420166, | |
| "learning_rate": 0.00018811956324840546, | |
| "loss": 0.7845717906951905, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 0.36537720794585377, | |
| "grad_norm": 1.3308541774749756, | |
| "learning_rate": 0.00018803517139451547, | |
| "loss": 0.7821323871612549, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.3664777417047268, | |
| "grad_norm": 1.3453469276428223, | |
| "learning_rate": 0.00018795049993251746, | |
| "loss": 0.7717282772064209, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 0.36757827546359984, | |
| "grad_norm": 1.2678643465042114, | |
| "learning_rate": 0.00018786554913133608, | |
| "loss": 0.7912368774414062, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.3686788092224729, | |
| "grad_norm": 1.2945518493652344, | |
| "learning_rate": 0.0001877803192607832, | |
| "loss": 0.8306121826171875, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.36977934298134596, | |
| "grad_norm": 1.4001387357711792, | |
| "learning_rate": 0.00018769481059155693, | |
| "loss": 0.7877901554107666, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.370879876740219, | |
| "grad_norm": 1.4055125713348389, | |
| "learning_rate": 0.00018760902339524108, | |
| "loss": 0.7993814945220947, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 0.3719804104990921, | |
| "grad_norm": 1.5058491230010986, | |
| "learning_rate": 0.0001875229579443039, | |
| "loss": 0.7562387466430665, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.3730809442579651, | |
| "grad_norm": 1.4691188335418701, | |
| "learning_rate": 0.0001874366145120975, | |
| "loss": 0.7943220615386963, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 0.37418147801683815, | |
| "grad_norm": 1.4147716760635376, | |
| "learning_rate": 0.00018734999337285686, | |
| "loss": 0.7631899356842041, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.37528201177571124, | |
| "grad_norm": 1.7002638578414917, | |
| "learning_rate": 0.000187263094801699, | |
| "loss": 0.7778403759002686, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 0.3763825455345843, | |
| "grad_norm": 1.263079285621643, | |
| "learning_rate": 0.00018717591907462208, | |
| "loss": 0.7868700981140136, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.3774830792934573, | |
| "grad_norm": 1.6632059812545776, | |
| "learning_rate": 0.0001870884664685045, | |
| "loss": 0.7900818347930908, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 0.3785836130523304, | |
| "grad_norm": 1.3724589347839355, | |
| "learning_rate": 0.00018700073726110416, | |
| "loss": 0.809692668914795, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.37968414681120344, | |
| "grad_norm": 1.6670794486999512, | |
| "learning_rate": 0.00018691273173105725, | |
| "loss": 0.7572099685668945, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.3807846805700765, | |
| "grad_norm": 1.5179470777511597, | |
| "learning_rate": 0.0001868244501578779, | |
| "loss": 0.7761201858520508, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.38188521432894956, | |
| "grad_norm": 1.4916956424713135, | |
| "learning_rate": 0.00018673589282195669, | |
| "loss": 0.7581660747528076, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 0.3829857480878226, | |
| "grad_norm": 1.42303466796875, | |
| "learning_rate": 0.00018664706000456026, | |
| "loss": 0.7460827827453613, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.38408628184669563, | |
| "grad_norm": 1.3675720691680908, | |
| "learning_rate": 0.00018655795198783005, | |
| "loss": 0.7278396606445312, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 0.3851868156055687, | |
| "grad_norm": 1.2975969314575195, | |
| "learning_rate": 0.0001864685690547817, | |
| "loss": 0.7781871318817138, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.38628734936444176, | |
| "grad_norm": 1.6625419855117798, | |
| "learning_rate": 0.00018637891148930383, | |
| "loss": 0.8365812301635742, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 0.3873878831233148, | |
| "grad_norm": 1.92893385887146, | |
| "learning_rate": 0.00018628897957615755, | |
| "loss": 0.7808390140533448, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.3884884168821879, | |
| "grad_norm": 1.4564015865325928, | |
| "learning_rate": 0.0001861987736009751, | |
| "loss": 0.8045003890991211, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 0.3895889506410609, | |
| "grad_norm": 1.3779884576797485, | |
| "learning_rate": 0.00018610829385025935, | |
| "loss": 0.8292377471923829, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.39068948439993395, | |
| "grad_norm": 1.7249268293380737, | |
| "learning_rate": 0.00018601754061138256, | |
| "loss": 0.7766525268554687, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.39179001815880704, | |
| "grad_norm": 1.2811200618743896, | |
| "learning_rate": 0.00018592651417258572, | |
| "loss": 0.7709021091461181, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.3928905519176801, | |
| "grad_norm": 1.3547565937042236, | |
| "learning_rate": 0.00018583521482297747, | |
| "loss": 0.7982177734375, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 0.3939910856765531, | |
| "grad_norm": 1.5291974544525146, | |
| "learning_rate": 0.00018574364285253326, | |
| "loss": 0.8197507858276367, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.3950916194354262, | |
| "grad_norm": 1.5480220317840576, | |
| "learning_rate": 0.0001856517985520944, | |
| "loss": 0.7673719882965088, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 0.39619215319429923, | |
| "grad_norm": 1.2931580543518066, | |
| "learning_rate": 0.0001855596822133672, | |
| "loss": 0.7790896415710449, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.39729268695317227, | |
| "grad_norm": 1.2749227285385132, | |
| "learning_rate": 0.0001854672941289219, | |
| "loss": 0.8157513618469239, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 0.39839322071204536, | |
| "grad_norm": 1.3297630548477173, | |
| "learning_rate": 0.00018537463459219187, | |
| "loss": 0.7839149475097656, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.3994937544709184, | |
| "grad_norm": 1.4063315391540527, | |
| "learning_rate": 0.00018528170389747268, | |
| "loss": 0.7640786170959473, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 0.40059428822979143, | |
| "grad_norm": 1.2009915113449097, | |
| "learning_rate": 0.0001851885023399211, | |
| "loss": 0.8061283111572266, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.4016948219886645, | |
| "grad_norm": 1.2830356359481812, | |
| "learning_rate": 0.00018509503021555407, | |
| "loss": 0.7541686058044433, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.40279535574753755, | |
| "grad_norm": 1.621762752532959, | |
| "learning_rate": 0.0001850012878212481, | |
| "loss": 0.7810799598693847, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.4038958895064106, | |
| "grad_norm": 1.5978320837020874, | |
| "learning_rate": 0.00018490727545473793, | |
| "loss": 0.7868115901947021, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 0.4049964232652837, | |
| "grad_norm": 1.465620517730713, | |
| "learning_rate": 0.00018481299341461583, | |
| "loss": 0.7783832550048828, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.4060969570241567, | |
| "grad_norm": 1.148144006729126, | |
| "learning_rate": 0.00018471844200033054, | |
| "loss": 0.7679046630859375, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 0.40719749078302975, | |
| "grad_norm": 1.4279158115386963, | |
| "learning_rate": 0.00018462362151218639, | |
| "loss": 0.7669914245605469, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.40829802454190284, | |
| "grad_norm": 1.4722813367843628, | |
| "learning_rate": 0.0001845285322513423, | |
| "loss": 0.8222566604614258, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 0.40939855830077587, | |
| "grad_norm": 1.3982079029083252, | |
| "learning_rate": 0.0001844331745198108, | |
| "loss": 0.7618198871612549, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.4104990920596489, | |
| "grad_norm": 1.6215136051177979, | |
| "learning_rate": 0.00018433754862045722, | |
| "loss": 0.7763657093048095, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 0.411599625818522, | |
| "grad_norm": 1.5549336671829224, | |
| "learning_rate": 0.00018424165485699852, | |
| "loss": 0.7253801822662354, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.41270015957739503, | |
| "grad_norm": 1.2889606952667236, | |
| "learning_rate": 0.00018414549353400238, | |
| "loss": 0.7764887332916259, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.41380069333626807, | |
| "grad_norm": 1.3491219282150269, | |
| "learning_rate": 0.00018404906495688645, | |
| "loss": 0.7364382743835449, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.41490122709514116, | |
| "grad_norm": 1.2835975885391235, | |
| "learning_rate": 0.000183952369431917, | |
| "loss": 0.7898456573486328, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 0.4160017608540142, | |
| "grad_norm": 1.3867552280426025, | |
| "learning_rate": 0.0001838554072662083, | |
| "loss": 0.817133617401123, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.4171022946128872, | |
| "grad_norm": 1.2192223072052002, | |
| "learning_rate": 0.00018375817876772145, | |
| "loss": 0.7515857219696045, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 0.4182028283717603, | |
| "grad_norm": 1.2979538440704346, | |
| "learning_rate": 0.0001836606842452634, | |
| "loss": 0.737982702255249, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.41930336213063335, | |
| "grad_norm": 1.2067734003067017, | |
| "learning_rate": 0.00018356292400848611, | |
| "loss": 0.7873512268066406, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 0.4204038958895064, | |
| "grad_norm": 1.556670069694519, | |
| "learning_rate": 0.00018346489836788542, | |
| "loss": 0.733306884765625, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.4215044296483795, | |
| "grad_norm": 1.4037160873413086, | |
| "learning_rate": 0.00018336660763480005, | |
| "loss": 0.8355989456176758, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 0.4226049634072525, | |
| "grad_norm": 1.1896283626556396, | |
| "learning_rate": 0.00018326805212141083, | |
| "loss": 0.793169355392456, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.42370549716612554, | |
| "grad_norm": 1.2549667358398438, | |
| "learning_rate": 0.00018316923214073945, | |
| "loss": 0.7088310718536377, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.42480603092499863, | |
| "grad_norm": 1.1542037725448608, | |
| "learning_rate": 0.0001830701480066476, | |
| "loss": 0.7928849697113037, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.42590656468387167, | |
| "grad_norm": 1.327624797821045, | |
| "learning_rate": 0.00018297080003383594, | |
| "loss": 0.7533132553100585, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 0.4270070984427447, | |
| "grad_norm": 1.4689446687698364, | |
| "learning_rate": 0.00018287118853784314, | |
| "loss": 0.724212646484375, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.4281076322016178, | |
| "grad_norm": 1.35456383228302, | |
| "learning_rate": 0.0001827713138350448, | |
| "loss": 0.795773983001709, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 0.42920816596049083, | |
| "grad_norm": 1.406788945198059, | |
| "learning_rate": 0.0001826711762426525, | |
| "loss": 0.7669349670410156, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.4303086997193639, | |
| "grad_norm": 1.3539007902145386, | |
| "learning_rate": 0.00018257077607871286, | |
| "loss": 0.7637516975402832, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 0.43140923347823695, | |
| "grad_norm": 1.0722286701202393, | |
| "learning_rate": 0.0001824701136621063, | |
| "loss": 0.7763535022735596, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.43250976723711, | |
| "grad_norm": 1.1297104358673096, | |
| "learning_rate": 0.00018236918931254629, | |
| "loss": 0.7475133895874023, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 0.4336103009959831, | |
| "grad_norm": 1.2874252796173096, | |
| "learning_rate": 0.00018226800335057822, | |
| "loss": 0.748918867111206, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.4347108347548561, | |
| "grad_norm": 1.317203402519226, | |
| "learning_rate": 0.00018216655609757832, | |
| "loss": 0.7373288631439209, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.43581136851372915, | |
| "grad_norm": 1.4163801670074463, | |
| "learning_rate": 0.00018206484787575283, | |
| "loss": 0.7076706886291504, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.43691190227260224, | |
| "grad_norm": 1.4905515909194946, | |
| "learning_rate": 0.00018196287900813668, | |
| "loss": 0.7911718845367431, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 0.43801243603147527, | |
| "grad_norm": 1.3535404205322266, | |
| "learning_rate": 0.00018186064981859279, | |
| "loss": 0.7962939739227295, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.4391129697903483, | |
| "grad_norm": 1.526379108428955, | |
| "learning_rate": 0.0001817581606318108, | |
| "loss": 0.8059768676757812, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 0.4402135035492214, | |
| "grad_norm": 1.1382709741592407, | |
| "learning_rate": 0.00018165541177330615, | |
| "loss": 0.7581804752349853, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.4402135035492214, | |
| "eval_loss": 0.763033926486969, | |
| "eval_runtime": 935.846, | |
| "eval_samples_per_second": 9.71, | |
| "eval_steps_per_second": 2.428, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.44131403730809443, | |
| "grad_norm": 1.4921393394470215, | |
| "learning_rate": 0.00018155240356941904, | |
| "loss": 0.7233622074127197, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 0.44241457106696747, | |
| "grad_norm": 1.2846465110778809, | |
| "learning_rate": 0.00018144913634731333, | |
| "loss": 0.7926196575164794, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.44351510482584056, | |
| "grad_norm": 1.5217868089675903, | |
| "learning_rate": 0.00018134561043497556, | |
| "loss": 0.8228995323181152, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 0.4446156385847136, | |
| "grad_norm": 1.2717784643173218, | |
| "learning_rate": 0.000181241826161214, | |
| "loss": 0.787687349319458, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.4457161723435866, | |
| "grad_norm": 1.4931477308273315, | |
| "learning_rate": 0.00018113778385565733, | |
| "loss": 0.7579782009124756, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.4468167061024597, | |
| "grad_norm": 1.167993187904358, | |
| "learning_rate": 0.00018103348384875383, | |
| "loss": 0.7449905395507812, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.44791723986133275, | |
| "grad_norm": 1.472502589225769, | |
| "learning_rate": 0.00018092892647177035, | |
| "loss": 0.7583009243011475, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 0.4490177736202058, | |
| "grad_norm": 1.3440701961517334, | |
| "learning_rate": 0.00018082411205679107, | |
| "loss": 0.8116919517517089, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.4501183073790789, | |
| "grad_norm": 1.24441397190094, | |
| "learning_rate": 0.00018071904093671656, | |
| "loss": 0.7991604804992676, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 0.4512188411379519, | |
| "grad_norm": 1.3697186708450317, | |
| "learning_rate": 0.0001806137134452627, | |
| "loss": 0.7466158866882324, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.45231937489682494, | |
| "grad_norm": 1.1649245023727417, | |
| "learning_rate": 0.00018050812991695975, | |
| "loss": 0.7050142288208008, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 0.45341990865569803, | |
| "grad_norm": 1.4361720085144043, | |
| "learning_rate": 0.00018040229068715097, | |
| "loss": 0.7678030014038086, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.45452044241457107, | |
| "grad_norm": 1.4761621952056885, | |
| "learning_rate": 0.00018029619609199196, | |
| "loss": 0.7187742710113525, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 0.4556209761734441, | |
| "grad_norm": 1.1728655099868774, | |
| "learning_rate": 0.00018018984646844919, | |
| "loss": 0.8050548553466796, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.4567215099323172, | |
| "grad_norm": 1.5159052610397339, | |
| "learning_rate": 0.00018008324215429926, | |
| "loss": 0.804990291595459, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.45782204369119023, | |
| "grad_norm": 1.4045536518096924, | |
| "learning_rate": 0.00017997638348812766, | |
| "loss": 0.7503755569458008, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.45892257745006326, | |
| "grad_norm": 1.1234439611434937, | |
| "learning_rate": 0.00017986927080932766, | |
| "loss": 0.7889124393463135, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 0.46002311120893635, | |
| "grad_norm": 1.2261425256729126, | |
| "learning_rate": 0.00017976190445809944, | |
| "loss": 0.7812236785888672, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.4611236449678094, | |
| "grad_norm": 1.181351900100708, | |
| "learning_rate": 0.0001796542847754487, | |
| "loss": 0.7701861381530761, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 0.4622241787266824, | |
| "grad_norm": 1.577356219291687, | |
| "learning_rate": 0.00017954641210318588, | |
| "loss": 0.6875332832336426, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.4633247124855555, | |
| "grad_norm": 1.2257264852523804, | |
| "learning_rate": 0.0001794382867839248, | |
| "loss": 0.742178201675415, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 0.46442524624442855, | |
| "grad_norm": 1.547837734222412, | |
| "learning_rate": 0.0001793299091610819, | |
| "loss": 0.7138393878936767, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.4655257800033016, | |
| "grad_norm": 1.6742470264434814, | |
| "learning_rate": 0.00017922127957887483, | |
| "loss": 0.7569129943847657, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 0.46662631376217467, | |
| "grad_norm": 1.3880702257156372, | |
| "learning_rate": 0.00017911239838232148, | |
| "loss": 0.7724673271179199, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.4677268475210477, | |
| "grad_norm": 1.5122058391571045, | |
| "learning_rate": 0.00017900326591723892, | |
| "loss": 0.8385299682617188, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.46882738127992074, | |
| "grad_norm": 1.491855502128601, | |
| "learning_rate": 0.00017889388253024234, | |
| "loss": 0.7509782791137696, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.46992791503879383, | |
| "grad_norm": 1.1019190549850464, | |
| "learning_rate": 0.00017878424856874371, | |
| "loss": 0.7592503547668457, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 0.47102844879766687, | |
| "grad_norm": 1.318244218826294, | |
| "learning_rate": 0.00017867436438095106, | |
| "loss": 0.7721508979797364, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.4721289825565399, | |
| "grad_norm": 1.2803703546524048, | |
| "learning_rate": 0.000178564230315867, | |
| "loss": 0.7693331718444825, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 0.473229516315413, | |
| "grad_norm": 1.4658492803573608, | |
| "learning_rate": 0.00017845384672328786, | |
| "loss": 0.7309596061706543, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.474330050074286, | |
| "grad_norm": 1.4201295375823975, | |
| "learning_rate": 0.00017834321395380248, | |
| "loss": 0.7964248657226562, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 0.47543058383315906, | |
| "grad_norm": 1.3890454769134521, | |
| "learning_rate": 0.00017823233235879105, | |
| "loss": 0.7670300960540771, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.47653111759203215, | |
| "grad_norm": 1.4585726261138916, | |
| "learning_rate": 0.00017812120229042416, | |
| "loss": 0.7615702629089356, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 0.4776316513509052, | |
| "grad_norm": 1.145139217376709, | |
| "learning_rate": 0.00017800982410166145, | |
| "loss": 0.7336215019226074, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.4787321851097782, | |
| "grad_norm": 3.134187936782837, | |
| "learning_rate": 0.00017789819814625072, | |
| "loss": 0.7543439865112305, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.4798327188686513, | |
| "grad_norm": 1.3985061645507812, | |
| "learning_rate": 0.00017778632477872668, | |
| "loss": 0.7479304313659668, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.48093325262752434, | |
| "grad_norm": 1.2374287843704224, | |
| "learning_rate": 0.00017767420435440978, | |
| "loss": 0.7452337741851807, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 0.4820337863863974, | |
| "grad_norm": 1.2880620956420898, | |
| "learning_rate": 0.00017756183722940518, | |
| "loss": 0.7773733139038086, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.48313432014527047, | |
| "grad_norm": 1.6610068082809448, | |
| "learning_rate": 0.00017744922376060167, | |
| "loss": 0.7617795944213868, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 0.4842348539041435, | |
| "grad_norm": 1.2445658445358276, | |
| "learning_rate": 0.0001773363643056703, | |
| "loss": 0.7268772125244141, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.48533538766301654, | |
| "grad_norm": 3.3761937618255615, | |
| "learning_rate": 0.0001772232592230635, | |
| "loss": 0.752207899093628, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 0.4864359214218896, | |
| "grad_norm": 1.310644507408142, | |
| "learning_rate": 0.00017710990887201384, | |
| "loss": 0.7711044788360596, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.48753645518076266, | |
| "grad_norm": 1.2487869262695312, | |
| "learning_rate": 0.00017699631361253282, | |
| "loss": 0.7602442741394043, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 0.4886369889396357, | |
| "grad_norm": 1.426648497581482, | |
| "learning_rate": 0.00017688247380540981, | |
| "loss": 0.7347400188446045, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.4897375226985088, | |
| "grad_norm": 1.3147786855697632, | |
| "learning_rate": 0.00017676838981221097, | |
| "loss": 0.7086680412292481, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.4908380564573818, | |
| "grad_norm": 1.4242682456970215, | |
| "learning_rate": 0.00017665406199527785, | |
| "loss": 0.7723946571350098, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.49193859021625486, | |
| "grad_norm": 1.2440725564956665, | |
| "learning_rate": 0.0001765394907177266, | |
| "loss": 0.7521542549133301, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 0.49303912397512795, | |
| "grad_norm": 1.3089182376861572, | |
| "learning_rate": 0.00017642467634344653, | |
| "loss": 0.7493531703948975, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.494139657734001, | |
| "grad_norm": 1.4084196090698242, | |
| "learning_rate": 0.000176309619237099, | |
| "loss": 0.7628543853759766, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 0.49524019149287407, | |
| "grad_norm": 1.2576475143432617, | |
| "learning_rate": 0.0001761943197641164, | |
| "loss": 0.8009342193603516, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.4963407252517471, | |
| "grad_norm": 1.4927014112472534, | |
| "learning_rate": 0.00017607877829070088, | |
| "loss": 0.764987850189209, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 0.49744125901062014, | |
| "grad_norm": 1.210005521774292, | |
| "learning_rate": 0.00017596299518382312, | |
| "loss": 0.7543008327484131, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.49854179276949323, | |
| "grad_norm": 1.381812334060669, | |
| "learning_rate": 0.00017584697081122138, | |
| "loss": 0.7667595863342285, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 0.49964232652836627, | |
| "grad_norm": 1.330445647239685, | |
| "learning_rate": 0.00017573070554140012, | |
| "loss": 0.7743747711181641, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.5007428602872394, | |
| "grad_norm": 1.4331225156784058, | |
| "learning_rate": 0.00017561419974362896, | |
| "loss": 0.7851823329925537, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.5018433940461123, | |
| "grad_norm": 1.4263122081756592, | |
| "learning_rate": 0.00017549745378794138, | |
| "loss": 0.7313291549682617, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.5029439278049854, | |
| "grad_norm": 1.331205129623413, | |
| "learning_rate": 0.00017538046804513376, | |
| "loss": 0.7234756946563721, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 0.5040444615638585, | |
| "grad_norm": 1.621663212776184, | |
| "learning_rate": 0.0001752632428867639, | |
| "loss": 0.7894155502319335, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.5051449953227315, | |
| "grad_norm": 1.5010970830917358, | |
| "learning_rate": 0.00017514577868515016, | |
| "loss": 0.7276608943939209, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 0.5062455290816046, | |
| "grad_norm": 1.3064217567443848, | |
| "learning_rate": 0.00017502807581337005, | |
| "loss": 0.7825868606567383, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.5073460628404777, | |
| "grad_norm": 1.4177016019821167, | |
| "learning_rate": 0.00017491013464525907, | |
| "loss": 0.7531017303466797, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 0.5084465965993507, | |
| "grad_norm": 1.5315032005310059, | |
| "learning_rate": 0.0001747919555554097, | |
| "loss": 0.7451908111572265, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.5095471303582237, | |
| "grad_norm": 1.3292468786239624, | |
| "learning_rate": 0.00017467353891916995, | |
| "loss": 0.7358492374420166, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 0.5106476641170968, | |
| "grad_norm": 1.224372386932373, | |
| "learning_rate": 0.0001745548851126424, | |
| "loss": 0.7730472564697266, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.5117481978759698, | |
| "grad_norm": 1.2024860382080078, | |
| "learning_rate": 0.00017443599451268286, | |
| "loss": 0.7512335777282715, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.5128487316348429, | |
| "grad_norm": 1.1596184968948364, | |
| "learning_rate": 0.00017431686749689923, | |
| "loss": 0.7704591274261474, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.513949265393716, | |
| "grad_norm": 1.1117010116577148, | |
| "learning_rate": 0.00017419750444365022, | |
| "loss": 0.7481093883514405, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 0.515049799152589, | |
| "grad_norm": 1.269881248474121, | |
| "learning_rate": 0.0001740779057320444, | |
| "loss": 0.7034889221191406, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.5161503329114621, | |
| "grad_norm": 1.2907774448394775, | |
| "learning_rate": 0.00017395807174193858, | |
| "loss": 0.7934452533721924, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 0.5172508666703352, | |
| "grad_norm": 1.5453121662139893, | |
| "learning_rate": 0.00017383800285393703, | |
| "loss": 0.7363879680633545, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.5183514004292081, | |
| "grad_norm": 1.2357949018478394, | |
| "learning_rate": 0.00017371769944938997, | |
| "loss": 0.7442324161529541, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 0.5194519341880812, | |
| "grad_norm": 1.1931536197662354, | |
| "learning_rate": 0.00017359716191039248, | |
| "loss": 0.7587575912475586, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.5205524679469543, | |
| "grad_norm": 1.4029440879821777, | |
| "learning_rate": 0.0001734763906197833, | |
| "loss": 0.7446390151977539, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 0.5216530017058273, | |
| "grad_norm": 1.2894697189331055, | |
| "learning_rate": 0.0001733553859611436, | |
| "loss": 0.749908447265625, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.5227535354647004, | |
| "grad_norm": 1.2883137464523315, | |
| "learning_rate": 0.00017323414831879572, | |
| "loss": 0.6804169178009033, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.5238540692235735, | |
| "grad_norm": 1.3548226356506348, | |
| "learning_rate": 0.00017311267807780198, | |
| "loss": 0.7411623001098633, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.5249546029824464, | |
| "grad_norm": 1.3655985593795776, | |
| "learning_rate": 0.00017299097562396344, | |
| "loss": 0.7595492839813233, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 0.5260551367413195, | |
| "grad_norm": 1.2662074565887451, | |
| "learning_rate": 0.00017286904134381875, | |
| "loss": 0.7716023445129394, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.5271556705001926, | |
| "grad_norm": 1.151781439781189, | |
| "learning_rate": 0.00017274687562464277, | |
| "loss": 0.764620018005371, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 0.5282562042590656, | |
| "grad_norm": 1.2629897594451904, | |
| "learning_rate": 0.00017262447885444554, | |
| "loss": 0.699459457397461, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.5293567380179387, | |
| "grad_norm": 1.3501882553100586, | |
| "learning_rate": 0.00017250185142197086, | |
| "loss": 0.7289613246917724, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 0.5304572717768118, | |
| "grad_norm": 1.4207645654678345, | |
| "learning_rate": 0.00017237899371669516, | |
| "loss": 0.7605480194091797, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.5315578055356848, | |
| "grad_norm": 1.2983626127243042, | |
| "learning_rate": 0.00017225590612882625, | |
| "loss": 0.7970122814178466, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 0.5326583392945579, | |
| "grad_norm": 1.3569053411483765, | |
| "learning_rate": 0.00017213258904930206, | |
| "loss": 0.7394134521484375, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.533758873053431, | |
| "grad_norm": 1.1259307861328125, | |
| "learning_rate": 0.0001720090428697894, | |
| "loss": 0.7425519943237304, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.5348594068123039, | |
| "grad_norm": 1.453172206878662, | |
| "learning_rate": 0.0001718852679826827, | |
| "loss": 0.8017748832702637, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.535959940571177, | |
| "grad_norm": 1.2578952312469482, | |
| "learning_rate": 0.00017176126478110287, | |
| "loss": 0.7838920593261719, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 0.5370604743300501, | |
| "grad_norm": 1.722364068031311, | |
| "learning_rate": 0.00017163703365889588, | |
| "loss": 0.7111594200134277, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.5381610080889231, | |
| "grad_norm": 1.3256832361221313, | |
| "learning_rate": 0.00017151257501063166, | |
| "loss": 0.73086576461792, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 0.5392615418477962, | |
| "grad_norm": 1.2753175497055054, | |
| "learning_rate": 0.00017138788923160277, | |
| "loss": 0.7703966617584228, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.5403620756066693, | |
| "grad_norm": 1.411819338798523, | |
| "learning_rate": 0.00017126297671782306, | |
| "loss": 0.7726946353912354, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 0.5414626093655422, | |
| "grad_norm": 1.4981974363327026, | |
| "learning_rate": 0.0001711378378660267, | |
| "loss": 0.7375073909759522, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.5425631431244153, | |
| "grad_norm": 1.4701440334320068, | |
| "learning_rate": 0.00017101247307366654, | |
| "loss": 0.7389264583587647, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 0.5436636768832884, | |
| "grad_norm": 1.4490705728530884, | |
| "learning_rate": 0.0001708868827389132, | |
| "loss": 0.7916615962982178, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.5447642106421614, | |
| "grad_norm": 1.5919363498687744, | |
| "learning_rate": 0.00017076106726065355, | |
| "loss": 0.7363606929779053, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.5458647444010345, | |
| "grad_norm": 1.5221658945083618, | |
| "learning_rate": 0.00017063502703848954, | |
| "loss": 0.756117582321167, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.5469652781599076, | |
| "grad_norm": 1.3419508934020996, | |
| "learning_rate": 0.00017050876247273698, | |
| "loss": 0.7674195766448975, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 0.5480658119187806, | |
| "grad_norm": 1.1585789918899536, | |
| "learning_rate": 0.00017038227396442415, | |
| "loss": 0.7340216159820556, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.5491663456776537, | |
| "grad_norm": 1.4809222221374512, | |
| "learning_rate": 0.00017025556191529063, | |
| "loss": 0.7714733600616455, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 0.5502668794365267, | |
| "grad_norm": 1.363792061805725, | |
| "learning_rate": 0.000170128626727786, | |
| "loss": 0.7531471252441406, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.5502668794365267, | |
| "eval_loss": 0.7419883012771606, | |
| "eval_runtime": 934.9404, | |
| "eval_samples_per_second": 9.719, | |
| "eval_steps_per_second": 2.43, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.5513674131953997, | |
| "grad_norm": 1.3879987001419067, | |
| "learning_rate": 0.00017000146880506852, | |
| "loss": 0.7755624294281006, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 0.5524679469542728, | |
| "grad_norm": 1.1908470392227173, | |
| "learning_rate": 0.00016987408855100394, | |
| "loss": 0.6974857807159424, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.5535684807131459, | |
| "grad_norm": 1.3515280485153198, | |
| "learning_rate": 0.00016974648637016403, | |
| "loss": 0.7421687126159668, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 0.5546690144720189, | |
| "grad_norm": 1.3259779214859009, | |
| "learning_rate": 0.00016961866266782555, | |
| "loss": 0.77330641746521, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.555769548230892, | |
| "grad_norm": 1.1782556772232056, | |
| "learning_rate": 0.00016949061784996876, | |
| "loss": 0.7333382129669189, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.5568700819897651, | |
| "grad_norm": 1.1794569492340088, | |
| "learning_rate": 0.0001693623523232762, | |
| "loss": 0.7309277534484864, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.557970615748638, | |
| "grad_norm": 1.4677120447158813, | |
| "learning_rate": 0.00016923386649513148, | |
| "loss": 0.7762013435363769, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 0.5590711495075111, | |
| "grad_norm": 1.354422926902771, | |
| "learning_rate": 0.00016910516077361782, | |
| "loss": 0.7435779094696044, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.5601716832663842, | |
| "grad_norm": 1.281956672668457, | |
| "learning_rate": 0.0001689762355675169, | |
| "loss": 0.7566828250885009, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 0.5612722170252572, | |
| "grad_norm": 1.7170436382293701, | |
| "learning_rate": 0.00016884709128630744, | |
| "loss": 0.7960678577423096, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.5623727507841303, | |
| "grad_norm": 1.4090797901153564, | |
| "learning_rate": 0.00016871772834016406, | |
| "loss": 0.7969419479370117, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 0.5634732845430034, | |
| "grad_norm": 1.6792510747909546, | |
| "learning_rate": 0.0001685881471399558, | |
| "loss": 0.7243700504302979, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.5645738183018764, | |
| "grad_norm": 1.589468002319336, | |
| "learning_rate": 0.0001684583480972449, | |
| "loss": 0.6752159118652343, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 0.5656743520607495, | |
| "grad_norm": 1.2133830785751343, | |
| "learning_rate": 0.00016832833162428555, | |
| "loss": 0.7530373573303223, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.5667748858196225, | |
| "grad_norm": 1.402968168258667, | |
| "learning_rate": 0.00016819809813402244, | |
| "loss": 0.7213272094726563, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.5678754195784955, | |
| "grad_norm": 1.7174259424209595, | |
| "learning_rate": 0.0001680676480400896, | |
| "loss": 0.7200131416320801, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.5689759533373686, | |
| "grad_norm": 1.206224799156189, | |
| "learning_rate": 0.00016793698175680895, | |
| "loss": 0.7772294521331787, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 0.5700764870962417, | |
| "grad_norm": 1.2895069122314453, | |
| "learning_rate": 0.0001678060996991891, | |
| "loss": 0.7059802532196044, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.5711770208551147, | |
| "grad_norm": 1.3851865530014038, | |
| "learning_rate": 0.00016767500228292395, | |
| "loss": 0.7481937408447266, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 0.5722775546139878, | |
| "grad_norm": 1.5495299100875854, | |
| "learning_rate": 0.00016754368992439144, | |
| "loss": 0.7860031604766846, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.5733780883728609, | |
| "grad_norm": 1.0802173614501953, | |
| "learning_rate": 0.0001674121630406521, | |
| "loss": 0.7575831890106202, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 0.5744786221317338, | |
| "grad_norm": 1.283719778060913, | |
| "learning_rate": 0.00016728042204944792, | |
| "loss": 0.7304069519042968, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.5755791558906069, | |
| "grad_norm": 1.291081428527832, | |
| "learning_rate": 0.00016714846736920081, | |
| "loss": 0.6965278148651123, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 0.57667968964948, | |
| "grad_norm": 2.7866170406341553, | |
| "learning_rate": 0.00016701629941901148, | |
| "loss": 0.7350920677185059, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.577780223408353, | |
| "grad_norm": 1.5153194665908813, | |
| "learning_rate": 0.00016688391861865794, | |
| "loss": 0.7063103199005127, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.5788807571672261, | |
| "grad_norm": 1.8427544832229614, | |
| "learning_rate": 0.00016675132538859425, | |
| "loss": 0.7724103450775146, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 0.5799812909260992, | |
| "grad_norm": 1.2077882289886475, | |
| "learning_rate": 0.00016661852014994918, | |
| "loss": 0.7549758434295655, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 0.5810818246849722, | |
| "grad_norm": 1.4017447233200073, | |
| "learning_rate": 0.0001664855033245248, | |
| "loss": 0.7112679481506348, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.5821823584438452, | |
| "grad_norm": 1.3323004245758057, | |
| "learning_rate": 0.00016635227533479526, | |
| "loss": 0.673241138458252, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 0.5832828922027183, | |
| "grad_norm": 1.6625175476074219, | |
| "learning_rate": 0.00016621883660390541, | |
| "loss": 0.7120931148529053, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.5843834259615913, | |
| "grad_norm": 1.3365366458892822, | |
| "learning_rate": 0.00016608518755566935, | |
| "loss": 0.726066780090332, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 0.5854839597204644, | |
| "grad_norm": 2.1613974571228027, | |
| "learning_rate": 0.00016595132861456927, | |
| "loss": 0.7196171760559082, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 0.5865844934793375, | |
| "grad_norm": 1.333061933517456, | |
| "learning_rate": 0.0001658172602057539, | |
| "loss": 0.7693576812744141, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 0.5876850272382105, | |
| "grad_norm": 1.3722368478775024, | |
| "learning_rate": 0.0001656829827550373, | |
| "loss": 0.7160601615905762, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 0.5887855609970836, | |
| "grad_norm": 2.5283138751983643, | |
| "learning_rate": 0.0001655484966888975, | |
| "loss": 0.7215074062347412, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 0.5898860947559567, | |
| "grad_norm": 1.2876371145248413, | |
| "learning_rate": 0.0001654138024344751, | |
| "loss": 0.7553225040435791, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 0.5909866285148296, | |
| "grad_norm": 1.3598158359527588, | |
| "learning_rate": 0.00016527890041957184, | |
| "loss": 0.7447906970977783, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 0.5920871622737027, | |
| "grad_norm": 1.4216128587722778, | |
| "learning_rate": 0.00016514379107264944, | |
| "loss": 0.6964402675628663, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 0.5931876960325758, | |
| "grad_norm": 1.262564778327942, | |
| "learning_rate": 0.0001650084748228281, | |
| "loss": 0.7048509120941162, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 0.5942882297914489, | |
| "grad_norm": 1.6969469785690308, | |
| "learning_rate": 0.00016487295209988511, | |
| "loss": 0.7238675117492676, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.5953887635503219, | |
| "grad_norm": 1.38680899143219, | |
| "learning_rate": 0.00016473722333425363, | |
| "loss": 0.755061674118042, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 0.596489297309195, | |
| "grad_norm": 1.3030256032943726, | |
| "learning_rate": 0.0001646012889570211, | |
| "loss": 0.7230662822723388, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 0.5975898310680681, | |
| "grad_norm": 2.8049333095550537, | |
| "learning_rate": 0.00016446514939992814, | |
| "loss": 0.7024547576904296, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 0.598690364826941, | |
| "grad_norm": 1.2925546169281006, | |
| "learning_rate": 0.00016432880509536694, | |
| "loss": 0.7584189414978028, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 0.5997908985858141, | |
| "grad_norm": 1.4285222291946411, | |
| "learning_rate": 0.00016419225647638008, | |
| "loss": 0.6970412731170654, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 0.6008914323446872, | |
| "grad_norm": 1.9083236455917358, | |
| "learning_rate": 0.0001640555039766589, | |
| "loss": 0.7205626964569092, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 0.6019919661035602, | |
| "grad_norm": 1.4175890684127808, | |
| "learning_rate": 0.00016391854803054253, | |
| "loss": 0.6843720436096191, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 0.6030924998624333, | |
| "grad_norm": 1.6256078481674194, | |
| "learning_rate": 0.00016378138907301604, | |
| "loss": 0.7570401191711426, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 0.6041930336213064, | |
| "grad_norm": 1.299574851989746, | |
| "learning_rate": 0.0001636440275397094, | |
| "loss": 0.7056687355041504, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 0.6052935673801794, | |
| "grad_norm": 1.8576395511627197, | |
| "learning_rate": 0.00016350646386689593, | |
| "loss": 0.7708197116851807, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.6063941011390525, | |
| "grad_norm": 1.2749172449111938, | |
| "learning_rate": 0.00016336869849149105, | |
| "loss": 0.7359384059906006, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 0.6074946348979255, | |
| "grad_norm": 1.502797245979309, | |
| "learning_rate": 0.00016323073185105065, | |
| "loss": 0.7268924713134766, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 0.6085951686567985, | |
| "grad_norm": 1.2893123626708984, | |
| "learning_rate": 0.00016309256438377004, | |
| "loss": 0.7836434841156006, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 0.6096957024156716, | |
| "grad_norm": 1.6940971612930298, | |
| "learning_rate": 0.0001629541965284822, | |
| "loss": 0.7172956943511963, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 0.6107962361745447, | |
| "grad_norm": 1.4099256992340088, | |
| "learning_rate": 0.0001628156287246567, | |
| "loss": 0.7529633522033692, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.6118967699334177, | |
| "grad_norm": 1.2283318042755127, | |
| "learning_rate": 0.00016267686141239812, | |
| "loss": 0.7456967830657959, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 0.6129973036922908, | |
| "grad_norm": 1.584608554840088, | |
| "learning_rate": 0.00016253789503244465, | |
| "loss": 0.7123336791992188, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 0.6140978374511639, | |
| "grad_norm": 1.2020970582962036, | |
| "learning_rate": 0.0001623987300261668, | |
| "loss": 0.7346308708190918, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 0.6151983712100368, | |
| "grad_norm": 1.375866174697876, | |
| "learning_rate": 0.00016225936683556593, | |
| "loss": 0.7147591590881348, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 0.6162989049689099, | |
| "grad_norm": 3.002707004547119, | |
| "learning_rate": 0.0001621198059032728, | |
| "loss": 0.7241267204284668, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.617399438727783, | |
| "grad_norm": 1.3746256828308105, | |
| "learning_rate": 0.0001619800476725463, | |
| "loss": 0.7762519359588623, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 0.618499972486656, | |
| "grad_norm": 2.4465384483337402, | |
| "learning_rate": 0.00016184009258727187, | |
| "loss": 0.7804543018341065, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 0.6196005062455291, | |
| "grad_norm": 1.2646642923355103, | |
| "learning_rate": 0.00016169994109196023, | |
| "loss": 0.744245958328247, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 0.6207010400044022, | |
| "grad_norm": 1.3681907653808594, | |
| "learning_rate": 0.00016155959363174592, | |
| "loss": 0.7360111713409424, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 0.6218015737632752, | |
| "grad_norm": 1.1509507894515991, | |
| "learning_rate": 0.00016141905065238587, | |
| "loss": 0.713913106918335, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 0.6229021075221483, | |
| "grad_norm": 1.4058045148849487, | |
| "learning_rate": 0.00016127831260025799, | |
| "loss": 0.7003890037536621, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 0.6240026412810213, | |
| "grad_norm": 1.3103810548782349, | |
| "learning_rate": 0.0001611373799223598, | |
| "loss": 0.7160762310028076, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 0.6251031750398943, | |
| "grad_norm": 1.4053767919540405, | |
| "learning_rate": 0.00016099625306630687, | |
| "loss": 0.7399090766906739, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 0.6262037087987674, | |
| "grad_norm": 1.4424643516540527, | |
| "learning_rate": 0.00016085493248033163, | |
| "loss": 0.7122686386108399, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 0.6273042425576405, | |
| "grad_norm": 1.495091438293457, | |
| "learning_rate": 0.0001607134186132817, | |
| "loss": 0.7723418235778808, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.6284047763165135, | |
| "grad_norm": 1.9233251810073853, | |
| "learning_rate": 0.00016057171191461868, | |
| "loss": 0.7351515769958497, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 0.6295053100753866, | |
| "grad_norm": 1.3022968769073486, | |
| "learning_rate": 0.00016042981283441655, | |
| "loss": 0.7153616428375245, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 0.6306058438342597, | |
| "grad_norm": 1.5664523839950562, | |
| "learning_rate": 0.00016028772182336034, | |
| "loss": 0.781205701828003, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 0.6317063775931326, | |
| "grad_norm": 1.485307216644287, | |
| "learning_rate": 0.00016014543933274466, | |
| "loss": 0.7299734115600586, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 0.6328069113520057, | |
| "grad_norm": 1.2536561489105225, | |
| "learning_rate": 0.00016000296581447225, | |
| "loss": 0.7220814228057861, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 0.6339074451108788, | |
| "grad_norm": 1.4910413026809692, | |
| "learning_rate": 0.00015986030172105266, | |
| "loss": 0.7590044498443603, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 0.6350079788697518, | |
| "grad_norm": 1.5727530717849731, | |
| "learning_rate": 0.00015971744750560064, | |
| "loss": 0.6608116149902343, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 0.6361085126286249, | |
| "grad_norm": 1.3321911096572876, | |
| "learning_rate": 0.00015957440362183485, | |
| "loss": 0.7006593704223633, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 0.637209046387498, | |
| "grad_norm": 1.6716225147247314, | |
| "learning_rate": 0.00015943117052407625, | |
| "loss": 0.759761381149292, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 0.638309580146371, | |
| "grad_norm": 1.342505693435669, | |
| "learning_rate": 0.0001592877486672469, | |
| "loss": 0.7411152362823487, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.639410113905244, | |
| "grad_norm": 1.4138150215148926, | |
| "learning_rate": 0.00015914413850686828, | |
| "loss": 0.7032299995422363, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 0.6405106476641171, | |
| "grad_norm": 1.3087942600250244, | |
| "learning_rate": 0.00015900034049905993, | |
| "loss": 0.6844950199127198, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 0.6416111814229901, | |
| "grad_norm": 1.1978130340576172, | |
| "learning_rate": 0.0001588563551005381, | |
| "loss": 0.7046521186828614, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 0.6427117151818632, | |
| "grad_norm": 1.4054518938064575, | |
| "learning_rate": 0.00015871218276861416, | |
| "loss": 0.7417028427124024, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 0.6438122489407363, | |
| "grad_norm": 1.4107232093811035, | |
| "learning_rate": 0.0001585678239611932, | |
| "loss": 0.7251378536224365, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 0.6449127826996093, | |
| "grad_norm": 1.2596750259399414, | |
| "learning_rate": 0.00015842327913677252, | |
| "loss": 0.7766359329223633, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 0.6460133164584824, | |
| "grad_norm": 1.2053841352462769, | |
| "learning_rate": 0.00015827854875444036, | |
| "loss": 0.6772095203399658, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 0.6471138502173555, | |
| "grad_norm": 1.432888150215149, | |
| "learning_rate": 0.00015813363327387415, | |
| "loss": 0.772012996673584, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 0.6482143839762284, | |
| "grad_norm": 1.5003931522369385, | |
| "learning_rate": 0.00015798853315533931, | |
| "loss": 0.740192985534668, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 0.6493149177351015, | |
| "grad_norm": 1.4617244005203247, | |
| "learning_rate": 0.00015784324885968775, | |
| "loss": 0.7542769908905029, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.6504154514939746, | |
| "grad_norm": 1.3754563331604004, | |
| "learning_rate": 0.00015769778084835615, | |
| "loss": 0.7268834114074707, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 0.6515159852528476, | |
| "grad_norm": 1.3474271297454834, | |
| "learning_rate": 0.00015755212958336488, | |
| "loss": 0.7852190017700196, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 0.6526165190117207, | |
| "grad_norm": 1.2138652801513672, | |
| "learning_rate": 0.0001574062955273162, | |
| "loss": 0.7471586227416992, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 0.6537170527705938, | |
| "grad_norm": 1.2696701288223267, | |
| "learning_rate": 0.00015726027914339302, | |
| "loss": 0.667238712310791, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 0.6548175865294668, | |
| "grad_norm": 1.6794250011444092, | |
| "learning_rate": 0.00015711408089535733, | |
| "loss": 0.7339349269866944, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 0.6559181202883398, | |
| "grad_norm": 1.243056058883667, | |
| "learning_rate": 0.00015696770124754873, | |
| "loss": 0.8075173377990723, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 0.6570186540472129, | |
| "grad_norm": 1.385141134262085, | |
| "learning_rate": 0.00015682114066488292, | |
| "loss": 0.7466262817382813, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 0.6581191878060859, | |
| "grad_norm": 1.2319458723068237, | |
| "learning_rate": 0.00015667439961285028, | |
| "loss": 0.7330340385437012, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 0.659219721564959, | |
| "grad_norm": 1.4220091104507446, | |
| "learning_rate": 0.00015652747855751447, | |
| "loss": 0.73863205909729, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 0.6603202553238321, | |
| "grad_norm": 1.4125266075134277, | |
| "learning_rate": 0.00015638037796551074, | |
| "loss": 0.7317982673645019, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.6603202553238321, | |
| "eval_loss": 0.7154231071472168, | |
| "eval_runtime": 936.9703, | |
| "eval_samples_per_second": 9.698, | |
| "eval_steps_per_second": 2.425, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.6614207890827051, | |
| "grad_norm": 1.248883605003357, | |
| "learning_rate": 0.00015623309830404457, | |
| "loss": 0.709596586227417, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 0.6625213228415782, | |
| "grad_norm": 1.1572697162628174, | |
| "learning_rate": 0.00015608564004089033, | |
| "loss": 0.6387454986572265, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 0.6636218566004513, | |
| "grad_norm": 1.974361777305603, | |
| "learning_rate": 0.00015593800364438947, | |
| "loss": 0.6919140338897705, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 0.6647223903593242, | |
| "grad_norm": 1.510246753692627, | |
| "learning_rate": 0.00015579018958344928, | |
| "loss": 0.7729711532592773, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 0.6658229241181973, | |
| "grad_norm": 1.1816668510437012, | |
| "learning_rate": 0.00015564219832754135, | |
| "loss": 0.7235398292541504, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 0.6669234578770704, | |
| "grad_norm": 2.0719385147094727, | |
| "learning_rate": 0.00015549403034670003, | |
| "loss": 0.7236655712127685, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 0.6680239916359434, | |
| "grad_norm": 1.3846322298049927, | |
| "learning_rate": 0.00015534568611152096, | |
| "loss": 0.7563097953796387, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 0.6691245253948165, | |
| "grad_norm": 1.3005784749984741, | |
| "learning_rate": 0.0001551971660931596, | |
| "loss": 0.6728219509124755, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 0.6702250591536896, | |
| "grad_norm": 1.6612495183944702, | |
| "learning_rate": 0.0001550484707633297, | |
| "loss": 0.7208469867706299, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 0.6713255929125626, | |
| "grad_norm": 1.536747932434082, | |
| "learning_rate": 0.00015489960059430184, | |
| "loss": 0.7596847534179687, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.6724261266714356, | |
| "grad_norm": 1.2718262672424316, | |
| "learning_rate": 0.00015475055605890185, | |
| "loss": 0.728467607498169, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 0.6735266604303087, | |
| "grad_norm": 1.2997578382492065, | |
| "learning_rate": 0.00015460133763050947, | |
| "loss": 0.6834435939788819, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 0.6746271941891817, | |
| "grad_norm": 1.2644582986831665, | |
| "learning_rate": 0.00015445194578305658, | |
| "loss": 0.6802155017852783, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 0.6757277279480548, | |
| "grad_norm": 1.3019027709960938, | |
| "learning_rate": 0.00015430238099102601, | |
| "loss": 0.6821646213531494, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 0.6768282617069279, | |
| "grad_norm": 1.2540215253829956, | |
| "learning_rate": 0.00015415264372944983, | |
| "loss": 0.7386213302612304, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 0.6779287954658009, | |
| "grad_norm": 1.2781347036361694, | |
| "learning_rate": 0.0001540027344739078, | |
| "loss": 0.76524658203125, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 0.679029329224674, | |
| "grad_norm": 1.3025370836257935, | |
| "learning_rate": 0.0001538526537005261, | |
| "loss": 0.7432229042053222, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 0.680129862983547, | |
| "grad_norm": 1.178902506828308, | |
| "learning_rate": 0.0001537024018859756, | |
| "loss": 0.7016994953155518, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 0.68123039674242, | |
| "grad_norm": 1.3114815950393677, | |
| "learning_rate": 0.0001535519795074703, | |
| "loss": 0.731592321395874, | |
| "step": 6190 | |
| }, | |
| { | |
| "epoch": 0.6823309305012931, | |
| "grad_norm": 1.7339528799057007, | |
| "learning_rate": 0.0001534013870427662, | |
| "loss": 0.7412378787994385, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.6834314642601662, | |
| "grad_norm": 1.2772549390792847, | |
| "learning_rate": 0.00015325062497015916, | |
| "loss": 0.7278597354888916, | |
| "step": 6210 | |
| }, | |
| { | |
| "epoch": 0.6845319980190392, | |
| "grad_norm": 1.119942545890808, | |
| "learning_rate": 0.00015309969376848406, | |
| "loss": 0.6550940036773681, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 0.6856325317779123, | |
| "grad_norm": 1.7672674655914307, | |
| "learning_rate": 0.00015294859391711273, | |
| "loss": 0.6876314640045166, | |
| "step": 6230 | |
| }, | |
| { | |
| "epoch": 0.6867330655367854, | |
| "grad_norm": 1.5041821002960205, | |
| "learning_rate": 0.00015279732589595276, | |
| "loss": 0.7159430503845214, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 0.6878335992956583, | |
| "grad_norm": 1.3722065687179565, | |
| "learning_rate": 0.00015264589018544578, | |
| "loss": 0.689654541015625, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 0.6889341330545314, | |
| "grad_norm": 1.4130030870437622, | |
| "learning_rate": 0.0001524942872665661, | |
| "loss": 0.779707956314087, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 0.6900346668134045, | |
| "grad_norm": 1.3028900623321533, | |
| "learning_rate": 0.000152342517620819, | |
| "loss": 0.7033322811126709, | |
| "step": 6270 | |
| }, | |
| { | |
| "epoch": 0.6911352005722775, | |
| "grad_norm": 1.2611339092254639, | |
| "learning_rate": 0.0001521905817302395, | |
| "loss": 0.7246399402618409, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 0.6922357343311506, | |
| "grad_norm": 1.3958343267440796, | |
| "learning_rate": 0.00015203848007739034, | |
| "loss": 0.7422275543212891, | |
| "step": 6290 | |
| }, | |
| { | |
| "epoch": 0.6933362680900237, | |
| "grad_norm": 1.3530064821243286, | |
| "learning_rate": 0.00015188621314536098, | |
| "loss": 0.7618152141571045, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.6944368018488967, | |
| "grad_norm": 1.2685966491699219, | |
| "learning_rate": 0.00015173378141776568, | |
| "loss": 0.7283220767974854, | |
| "step": 6310 | |
| }, | |
| { | |
| "epoch": 0.6955373356077698, | |
| "grad_norm": 1.5027806758880615, | |
| "learning_rate": 0.0001515811853787422, | |
| "loss": 0.6772040843963623, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 0.6966378693666428, | |
| "grad_norm": 1.2491596937179565, | |
| "learning_rate": 0.0001514284255129501, | |
| "loss": 0.7292652130126953, | |
| "step": 6330 | |
| }, | |
| { | |
| "epoch": 0.6977384031255158, | |
| "grad_norm": 1.2554333209991455, | |
| "learning_rate": 0.00015127550230556932, | |
| "loss": 0.6931362628936768, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 0.6988389368843889, | |
| "grad_norm": 1.34043288230896, | |
| "learning_rate": 0.00015112241624229856, | |
| "loss": 0.7329248428344727, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 0.699939470643262, | |
| "grad_norm": 1.1904277801513672, | |
| "learning_rate": 0.00015096916780935372, | |
| "loss": 0.7226557254791259, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 0.701040004402135, | |
| "grad_norm": 1.2233314514160156, | |
| "learning_rate": 0.0001508157574934665, | |
| "loss": 0.7005710124969482, | |
| "step": 6370 | |
| }, | |
| { | |
| "epoch": 0.7021405381610081, | |
| "grad_norm": 1.4783847332000732, | |
| "learning_rate": 0.00015066218578188272, | |
| "loss": 0.7101388454437256, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 0.7032410719198812, | |
| "grad_norm": 1.2805193662643433, | |
| "learning_rate": 0.00015050845316236076, | |
| "loss": 0.7289349555969238, | |
| "step": 6390 | |
| }, | |
| { | |
| "epoch": 0.7043416056787541, | |
| "grad_norm": 1.3018475770950317, | |
| "learning_rate": 0.0001503545601231701, | |
| "loss": 0.713924503326416, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.7054421394376272, | |
| "grad_norm": 1.3639897108078003, | |
| "learning_rate": 0.00015020050715308972, | |
| "loss": 0.6581418514251709, | |
| "step": 6410 | |
| }, | |
| { | |
| "epoch": 0.7065426731965003, | |
| "grad_norm": 1.4128023386001587, | |
| "learning_rate": 0.0001500462947414066, | |
| "loss": 0.7135940074920655, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 0.7076432069553733, | |
| "grad_norm": 1.2122293710708618, | |
| "learning_rate": 0.00014989192337791404, | |
| "loss": 0.7303122997283935, | |
| "step": 6430 | |
| }, | |
| { | |
| "epoch": 0.7087437407142464, | |
| "grad_norm": 1.1786285638809204, | |
| "learning_rate": 0.00014973739355291022, | |
| "loss": 0.7025662422180176, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 0.7098442744731195, | |
| "grad_norm": 1.3302885293960571, | |
| "learning_rate": 0.00014958270575719668, | |
| "loss": 0.7187159538269043, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 0.7109448082319925, | |
| "grad_norm": 1.4084340333938599, | |
| "learning_rate": 0.00014942786048207656, | |
| "loss": 0.725886344909668, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 0.7120453419908656, | |
| "grad_norm": 1.2113697528839111, | |
| "learning_rate": 0.0001492728582193532, | |
| "loss": 0.7125999450683593, | |
| "step": 6470 | |
| }, | |
| { | |
| "epoch": 0.7131458757497386, | |
| "grad_norm": 1.41702401638031, | |
| "learning_rate": 0.0001491176994613287, | |
| "loss": 0.6910535335540772, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 0.7142464095086116, | |
| "grad_norm": 1.6196422576904297, | |
| "learning_rate": 0.00014896238470080196, | |
| "loss": 0.7285680770874023, | |
| "step": 6490 | |
| }, | |
| { | |
| "epoch": 0.7153469432674847, | |
| "grad_norm": 1.186160922050476, | |
| "learning_rate": 0.00014880691443106762, | |
| "loss": 0.7270355701446534, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.7164474770263578, | |
| "grad_norm": 1.3876869678497314, | |
| "learning_rate": 0.00014865128914591397, | |
| "loss": 0.6556861877441407, | |
| "step": 6510 | |
| }, | |
| { | |
| "epoch": 0.7175480107852308, | |
| "grad_norm": 1.2404990196228027, | |
| "learning_rate": 0.00014849550933962186, | |
| "loss": 0.6614561557769776, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 0.7186485445441039, | |
| "grad_norm": 1.5126335620880127, | |
| "learning_rate": 0.00014833957550696277, | |
| "loss": 0.6966361045837403, | |
| "step": 6530 | |
| }, | |
| { | |
| "epoch": 0.719749078302977, | |
| "grad_norm": 1.2630326747894287, | |
| "learning_rate": 0.00014818348814319747, | |
| "loss": 0.7556998252868652, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 0.7208496120618499, | |
| "grad_norm": 1.3583987951278687, | |
| "learning_rate": 0.00014802724774407432, | |
| "loss": 0.707868242263794, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 0.721950145820723, | |
| "grad_norm": 1.3609402179718018, | |
| "learning_rate": 0.00014787085480582772, | |
| "loss": 0.7230880737304688, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 0.7230506795795961, | |
| "grad_norm": 1.1819531917572021, | |
| "learning_rate": 0.00014771430982517662, | |
| "loss": 0.6786688804626465, | |
| "step": 6570 | |
| }, | |
| { | |
| "epoch": 0.7241512133384692, | |
| "grad_norm": 1.2774471044540405, | |
| "learning_rate": 0.00014755761329932274, | |
| "loss": 0.7156373977661132, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 0.7252517470973422, | |
| "grad_norm": 1.375931739807129, | |
| "learning_rate": 0.0001474007657259493, | |
| "loss": 0.7217991828918457, | |
| "step": 6590 | |
| }, | |
| { | |
| "epoch": 0.7263522808562153, | |
| "grad_norm": 1.1880601644515991, | |
| "learning_rate": 0.0001472437676032191, | |
| "loss": 0.7250751495361328, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.7274528146150884, | |
| "grad_norm": 2.0583808422088623, | |
| "learning_rate": 0.0001470866194297732, | |
| "loss": 0.6847675800323486, | |
| "step": 6610 | |
| }, | |
| { | |
| "epoch": 0.7285533483739614, | |
| "grad_norm": 1.3453950881958008, | |
| "learning_rate": 0.0001469293217047292, | |
| "loss": 0.7251123428344727, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 0.7296538821328344, | |
| "grad_norm": 1.527479887008667, | |
| "learning_rate": 0.00014677187492767964, | |
| "loss": 0.6714204311370849, | |
| "step": 6630 | |
| }, | |
| { | |
| "epoch": 0.7307544158917075, | |
| "grad_norm": 1.5210182666778564, | |
| "learning_rate": 0.00014661427959869057, | |
| "loss": 0.6623645782470703, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 0.7318549496505805, | |
| "grad_norm": 1.4670600891113281, | |
| "learning_rate": 0.00014645653621829977, | |
| "loss": 0.6705510139465332, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 0.7329554834094536, | |
| "grad_norm": 1.5107208490371704, | |
| "learning_rate": 0.00014629864528751526, | |
| "loss": 0.6907163619995117, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 0.7340560171683267, | |
| "grad_norm": 1.3847161531448364, | |
| "learning_rate": 0.00014614060730781377, | |
| "loss": 0.6747828960418701, | |
| "step": 6670 | |
| }, | |
| { | |
| "epoch": 0.7351565509271997, | |
| "grad_norm": 1.7698922157287598, | |
| "learning_rate": 0.00014598242278113897, | |
| "loss": 0.7515909194946289, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 0.7362570846860728, | |
| "grad_norm": 1.2080354690551758, | |
| "learning_rate": 0.0001458240922099, | |
| "loss": 0.7281320571899415, | |
| "step": 6690 | |
| }, | |
| { | |
| "epoch": 0.7373576184449459, | |
| "grad_norm": 1.295284628868103, | |
| "learning_rate": 0.00014566561609696986, | |
| "loss": 0.699878454208374, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.7384581522038188, | |
| "grad_norm": 1.39139986038208, | |
| "learning_rate": 0.00014550699494568384, | |
| "loss": 0.7556473731994628, | |
| "step": 6710 | |
| }, | |
| { | |
| "epoch": 0.7395586859626919, | |
| "grad_norm": 1.4971297979354858, | |
| "learning_rate": 0.0001453482292598379, | |
| "loss": 0.6911003112792968, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 0.740659219721565, | |
| "grad_norm": 1.5792361497879028, | |
| "learning_rate": 0.00014518931954368694, | |
| "loss": 0.7027464389801026, | |
| "step": 6730 | |
| }, | |
| { | |
| "epoch": 0.741759753480438, | |
| "grad_norm": 1.2973233461380005, | |
| "learning_rate": 0.0001450302663019434, | |
| "loss": 0.7206850528717041, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 0.7428602872393111, | |
| "grad_norm": 1.3215023279190063, | |
| "learning_rate": 0.0001448710700397756, | |
| "loss": 0.7368278980255127, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 0.7439608209981842, | |
| "grad_norm": 1.1171671152114868, | |
| "learning_rate": 0.00014471173126280606, | |
| "loss": 0.66349196434021, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 0.7450613547570571, | |
| "grad_norm": 1.2632873058319092, | |
| "learning_rate": 0.00014455225047710989, | |
| "loss": 0.6891120910644531, | |
| "step": 6770 | |
| }, | |
| { | |
| "epoch": 0.7461618885159302, | |
| "grad_norm": 1.3787199258804321, | |
| "learning_rate": 0.00014439262818921334, | |
| "loss": 0.6997201442718506, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 0.7472624222748033, | |
| "grad_norm": 1.269120693206787, | |
| "learning_rate": 0.00014423286490609203, | |
| "loss": 0.7099348068237304, | |
| "step": 6790 | |
| }, | |
| { | |
| "epoch": 0.7483629560336763, | |
| "grad_norm": 1.2346347570419312, | |
| "learning_rate": 0.00014407296113516934, | |
| "loss": 0.735411548614502, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.7494634897925494, | |
| "grad_norm": 1.6132004261016846, | |
| "learning_rate": 0.000143912917384315, | |
| "loss": 0.7112602233886719, | |
| "step": 6810 | |
| }, | |
| { | |
| "epoch": 0.7505640235514225, | |
| "grad_norm": 1.3072880506515503, | |
| "learning_rate": 0.00014375273416184322, | |
| "loss": 0.6661246299743653, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 0.7516645573102955, | |
| "grad_norm": 1.301348090171814, | |
| "learning_rate": 0.00014359241197651112, | |
| "loss": 0.6509958267211914, | |
| "step": 6830 | |
| }, | |
| { | |
| "epoch": 0.7527650910691686, | |
| "grad_norm": 1.1231361627578735, | |
| "learning_rate": 0.00014343195133751738, | |
| "loss": 0.6790677547454834, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 0.7538656248280416, | |
| "grad_norm": 1.1891106367111206, | |
| "learning_rate": 0.00014327135275450022, | |
| "loss": 0.6516884803771973, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 0.7549661585869146, | |
| "grad_norm": 1.1670225858688354, | |
| "learning_rate": 0.00014311061673753615, | |
| "loss": 0.6912143707275391, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 0.7560666923457877, | |
| "grad_norm": 1.3946342468261719, | |
| "learning_rate": 0.00014294974379713802, | |
| "loss": 0.6989268302917481, | |
| "step": 6870 | |
| }, | |
| { | |
| "epoch": 0.7571672261046608, | |
| "grad_norm": 1.179093360900879, | |
| "learning_rate": 0.00014278873444425368, | |
| "loss": 0.7307651996612549, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 0.7582677598635338, | |
| "grad_norm": 1.292688012123108, | |
| "learning_rate": 0.00014262758919026422, | |
| "loss": 0.6909995079040527, | |
| "step": 6890 | |
| }, | |
| { | |
| "epoch": 0.7593682936224069, | |
| "grad_norm": 1.2528825998306274, | |
| "learning_rate": 0.00014246630854698232, | |
| "loss": 0.7367213726043701, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.76046882738128, | |
| "grad_norm": 1.1586990356445312, | |
| "learning_rate": 0.00014230489302665073, | |
| "loss": 0.6632703304290771, | |
| "step": 6910 | |
| }, | |
| { | |
| "epoch": 0.761569361140153, | |
| "grad_norm": 1.6231518983840942, | |
| "learning_rate": 0.00014214334314194055, | |
| "loss": 0.6899041175842285, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 0.762669894899026, | |
| "grad_norm": 1.302525281906128, | |
| "learning_rate": 0.0001419816594059496, | |
| "loss": 0.7668297767639161, | |
| "step": 6930 | |
| }, | |
| { | |
| "epoch": 0.7637704286578991, | |
| "grad_norm": 1.283761978149414, | |
| "learning_rate": 0.0001418198423322009, | |
| "loss": 0.7081122398376465, | |
| "step": 6940 | |
| }, | |
| { | |
| "epoch": 0.7648709624167721, | |
| "grad_norm": 1.1314969062805176, | |
| "learning_rate": 0.0001416578924346409, | |
| "loss": 0.6925370216369628, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 0.7659714961756452, | |
| "grad_norm": 1.2459073066711426, | |
| "learning_rate": 0.00014149581022763794, | |
| "loss": 0.6523490428924561, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 0.7670720299345183, | |
| "grad_norm": 1.5697073936462402, | |
| "learning_rate": 0.00014133359622598056, | |
| "loss": 0.6504369735717773, | |
| "step": 6970 | |
| }, | |
| { | |
| "epoch": 0.7681725636933913, | |
| "grad_norm": 1.4411842823028564, | |
| "learning_rate": 0.00014117125094487596, | |
| "loss": 0.6521959781646729, | |
| "step": 6980 | |
| }, | |
| { | |
| "epoch": 0.7692730974522644, | |
| "grad_norm": 2.7891016006469727, | |
| "learning_rate": 0.0001410087748999482, | |
| "loss": 0.6588033676147461, | |
| "step": 6990 | |
| }, | |
| { | |
| "epoch": 0.7703736312111374, | |
| "grad_norm": 1.2571395635604858, | |
| "learning_rate": 0.00014084616860723676, | |
| "loss": 0.7186612606048584, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.7703736312111374, | |
| "eval_loss": 0.6988013386726379, | |
| "eval_runtime": 935.5187, | |
| "eval_samples_per_second": 9.713, | |
| "eval_steps_per_second": 2.429, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.7714741649700104, | |
| "grad_norm": 1.1871322393417358, | |
| "learning_rate": 0.00014068343258319472, | |
| "loss": 0.6798050880432129, | |
| "step": 7010 | |
| }, | |
| { | |
| "epoch": 0.7725746987288835, | |
| "grad_norm": 1.6656651496887207, | |
| "learning_rate": 0.0001405205673446872, | |
| "loss": 0.7257527351379395, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 0.7736752324877566, | |
| "grad_norm": 1.366361141204834, | |
| "learning_rate": 0.00014035757340898978, | |
| "loss": 0.6586103916168213, | |
| "step": 7030 | |
| }, | |
| { | |
| "epoch": 0.7747757662466296, | |
| "grad_norm": 1.5451475381851196, | |
| "learning_rate": 0.00014019445129378677, | |
| "loss": 0.6806992530822754, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 0.7758763000055027, | |
| "grad_norm": 1.2665611505508423, | |
| "learning_rate": 0.00014003120151716953, | |
| "loss": 0.7109615325927734, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 0.7769768337643758, | |
| "grad_norm": 1.2748724222183228, | |
| "learning_rate": 0.000139867824597635, | |
| "loss": 0.7034411430358887, | |
| "step": 7060 | |
| }, | |
| { | |
| "epoch": 0.7780773675232487, | |
| "grad_norm": 1.4949373006820679, | |
| "learning_rate": 0.00013970432105408378, | |
| "loss": 0.6983131885528564, | |
| "step": 7070 | |
| }, | |
| { | |
| "epoch": 0.7791779012821218, | |
| "grad_norm": 1.5629324913024902, | |
| "learning_rate": 0.00013954069140581884, | |
| "loss": 0.6774309635162353, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 0.7802784350409949, | |
| "grad_norm": 1.2059013843536377, | |
| "learning_rate": 0.00013937693617254351, | |
| "loss": 0.6928264141082764, | |
| "step": 7090 | |
| }, | |
| { | |
| "epoch": 0.7813789687998679, | |
| "grad_norm": 1.350574254989624, | |
| "learning_rate": 0.00013921305587436, | |
| "loss": 0.6662729740142822, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.782479502558741, | |
| "grad_norm": 1.2160134315490723, | |
| "learning_rate": 0.00013904905103176787, | |
| "loss": 0.7077804565429687, | |
| "step": 7110 | |
| }, | |
| { | |
| "epoch": 0.7835800363176141, | |
| "grad_norm": 1.2523444890975952, | |
| "learning_rate": 0.0001388849221656621, | |
| "loss": 0.7563854694366455, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 0.7846805700764871, | |
| "grad_norm": 1.2325736284255981, | |
| "learning_rate": 0.0001387206697973316, | |
| "loss": 0.6632079601287841, | |
| "step": 7130 | |
| }, | |
| { | |
| "epoch": 0.7857811038353602, | |
| "grad_norm": 1.342939853668213, | |
| "learning_rate": 0.0001385562944484577, | |
| "loss": 0.6962016105651856, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 0.7868816375942332, | |
| "grad_norm": 1.6244813203811646, | |
| "learning_rate": 0.00013839179664111204, | |
| "loss": 0.6567019939422607, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 0.7879821713531062, | |
| "grad_norm": 1.8458601236343384, | |
| "learning_rate": 0.00013822717689775547, | |
| "loss": 0.660393762588501, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 0.7890827051119793, | |
| "grad_norm": 1.518789529800415, | |
| "learning_rate": 0.00013806243574123597, | |
| "loss": 0.6897108554840088, | |
| "step": 7170 | |
| }, | |
| { | |
| "epoch": 0.7901832388708524, | |
| "grad_norm": 1.2446949481964111, | |
| "learning_rate": 0.00013789757369478715, | |
| "loss": 0.6905016422271728, | |
| "step": 7180 | |
| }, | |
| { | |
| "epoch": 0.7912837726297254, | |
| "grad_norm": 1.1706857681274414, | |
| "learning_rate": 0.00013773259128202668, | |
| "loss": 0.6798492908477783, | |
| "step": 7190 | |
| }, | |
| { | |
| "epoch": 0.7923843063885985, | |
| "grad_norm": 2.5733892917633057, | |
| "learning_rate": 0.0001375674890269544, | |
| "loss": 0.6814803600311279, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.7934848401474716, | |
| "grad_norm": 1.091080904006958, | |
| "learning_rate": 0.00013740226745395084, | |
| "loss": 0.6753903388977051, | |
| "step": 7210 | |
| }, | |
| { | |
| "epoch": 0.7945853739063445, | |
| "grad_norm": 1.5836533308029175, | |
| "learning_rate": 0.00013723692708777553, | |
| "loss": 0.6552946090698242, | |
| "step": 7220 | |
| }, | |
| { | |
| "epoch": 0.7956859076652176, | |
| "grad_norm": 1.1512203216552734, | |
| "learning_rate": 0.00013707146845356517, | |
| "loss": 0.6479218482971192, | |
| "step": 7230 | |
| }, | |
| { | |
| "epoch": 0.7967864414240907, | |
| "grad_norm": 1.2342529296875, | |
| "learning_rate": 0.00013690589207683224, | |
| "loss": 0.6967320442199707, | |
| "step": 7240 | |
| }, | |
| { | |
| "epoch": 0.7978869751829637, | |
| "grad_norm": 1.3044766187667847, | |
| "learning_rate": 0.00013674019848346309, | |
| "loss": 0.6886932849884033, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 0.7989875089418368, | |
| "grad_norm": 1.1774944067001343, | |
| "learning_rate": 0.00013657438819971644, | |
| "loss": 0.6783594608306884, | |
| "step": 7260 | |
| }, | |
| { | |
| "epoch": 0.8000880427007099, | |
| "grad_norm": 1.2176823616027832, | |
| "learning_rate": 0.00013640846175222147, | |
| "loss": 0.7020230770111084, | |
| "step": 7270 | |
| }, | |
| { | |
| "epoch": 0.8011885764595829, | |
| "grad_norm": 1.2440234422683716, | |
| "learning_rate": 0.00013624241966797657, | |
| "loss": 0.659848976135254, | |
| "step": 7280 | |
| }, | |
| { | |
| "epoch": 0.802289110218456, | |
| "grad_norm": 1.3187357187271118, | |
| "learning_rate": 0.0001360762624743471, | |
| "loss": 0.6982054710388184, | |
| "step": 7290 | |
| }, | |
| { | |
| "epoch": 0.803389643977329, | |
| "grad_norm": 1.218770146369934, | |
| "learning_rate": 0.0001359099906990643, | |
| "loss": 0.7144939422607421, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.804490177736202, | |
| "grad_norm": 1.4207760095596313, | |
| "learning_rate": 0.0001357436048702231, | |
| "loss": 0.7038421154022216, | |
| "step": 7310 | |
| }, | |
| { | |
| "epoch": 0.8055907114950751, | |
| "grad_norm": 1.2784091234207153, | |
| "learning_rate": 0.0001355771055162808, | |
| "loss": 0.7102098941802979, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 0.8066912452539482, | |
| "grad_norm": 1.3901985883712769, | |
| "learning_rate": 0.00013541049316605528, | |
| "loss": 0.7364766120910644, | |
| "step": 7330 | |
| }, | |
| { | |
| "epoch": 0.8077917790128212, | |
| "grad_norm": 1.591460108757019, | |
| "learning_rate": 0.00013524376834872322, | |
| "loss": 0.7228377819061279, | |
| "step": 7340 | |
| }, | |
| { | |
| "epoch": 0.8088923127716943, | |
| "grad_norm": 1.3788084983825684, | |
| "learning_rate": 0.00013507693159381856, | |
| "loss": 0.7458762168884278, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 0.8099928465305674, | |
| "grad_norm": 1.2996565103530884, | |
| "learning_rate": 0.0001349099834312308, | |
| "loss": 0.762279748916626, | |
| "step": 7360 | |
| }, | |
| { | |
| "epoch": 0.8110933802894403, | |
| "grad_norm": 1.245705485343933, | |
| "learning_rate": 0.00013474292439120324, | |
| "loss": 0.698921537399292, | |
| "step": 7370 | |
| }, | |
| { | |
| "epoch": 0.8121939140483134, | |
| "grad_norm": 2.505213737487793, | |
| "learning_rate": 0.00013457575500433125, | |
| "loss": 0.674662446975708, | |
| "step": 7380 | |
| }, | |
| { | |
| "epoch": 0.8132944478071865, | |
| "grad_norm": 2.3632819652557373, | |
| "learning_rate": 0.0001344084758015609, | |
| "loss": 0.7322216987609863, | |
| "step": 7390 | |
| }, | |
| { | |
| "epoch": 0.8143949815660595, | |
| "grad_norm": 1.5684608221054077, | |
| "learning_rate": 0.00013424108731418678, | |
| "loss": 0.695711612701416, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.8154955153249326, | |
| "grad_norm": 1.2372469902038574, | |
| "learning_rate": 0.00013407359007385077, | |
| "loss": 0.6515445709228516, | |
| "step": 7410 | |
| }, | |
| { | |
| "epoch": 0.8165960490838057, | |
| "grad_norm": 1.4333858489990234, | |
| "learning_rate": 0.00013390598461254013, | |
| "loss": 0.7076169013977051, | |
| "step": 7420 | |
| }, | |
| { | |
| "epoch": 0.8176965828426787, | |
| "grad_norm": 1.4251869916915894, | |
| "learning_rate": 0.00013373827146258567, | |
| "loss": 0.6859198570251465, | |
| "step": 7430 | |
| }, | |
| { | |
| "epoch": 0.8187971166015517, | |
| "grad_norm": 1.328965425491333, | |
| "learning_rate": 0.0001335704511566605, | |
| "loss": 0.6973493576049805, | |
| "step": 7440 | |
| }, | |
| { | |
| "epoch": 0.8198976503604248, | |
| "grad_norm": 1.5237798690795898, | |
| "learning_rate": 0.00013340252422777788, | |
| "loss": 0.6448246479034424, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 0.8209981841192978, | |
| "grad_norm": 1.3510645627975464, | |
| "learning_rate": 0.00013323449120928972, | |
| "loss": 0.7142490863800048, | |
| "step": 7460 | |
| }, | |
| { | |
| "epoch": 0.8220987178781709, | |
| "grad_norm": 1.3509327173233032, | |
| "learning_rate": 0.00013306635263488504, | |
| "loss": 0.6812589645385743, | |
| "step": 7470 | |
| }, | |
| { | |
| "epoch": 0.823199251637044, | |
| "grad_norm": 1.3660122156143188, | |
| "learning_rate": 0.0001328981090385879, | |
| "loss": 0.7049969673156739, | |
| "step": 7480 | |
| }, | |
| { | |
| "epoch": 0.824299785395917, | |
| "grad_norm": 1.6111016273498535, | |
| "learning_rate": 0.00013272976095475604, | |
| "loss": 0.6968174934387207, | |
| "step": 7490 | |
| }, | |
| { | |
| "epoch": 0.8254003191547901, | |
| "grad_norm": 1.4804449081420898, | |
| "learning_rate": 0.00013256130891807909, | |
| "loss": 0.6459970474243164, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.8265008529136632, | |
| "grad_norm": 1.3297840356826782, | |
| "learning_rate": 0.00013239275346357677, | |
| "loss": 0.6993029594421387, | |
| "step": 7510 | |
| }, | |
| { | |
| "epoch": 0.8276013866725361, | |
| "grad_norm": 1.4443268775939941, | |
| "learning_rate": 0.00013222409512659731, | |
| "loss": 0.7198901176452637, | |
| "step": 7520 | |
| }, | |
| { | |
| "epoch": 0.8287019204314092, | |
| "grad_norm": 1.931485891342163, | |
| "learning_rate": 0.00013205533444281565, | |
| "loss": 0.7343377113342285, | |
| "step": 7530 | |
| }, | |
| { | |
| "epoch": 0.8298024541902823, | |
| "grad_norm": 1.3457489013671875, | |
| "learning_rate": 0.00013188647194823186, | |
| "loss": 0.7027858257293701, | |
| "step": 7540 | |
| }, | |
| { | |
| "epoch": 0.8309029879491553, | |
| "grad_norm": 1.467539668083191, | |
| "learning_rate": 0.00013171750817916932, | |
| "loss": 0.6650913238525391, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 0.8320035217080284, | |
| "grad_norm": 1.6861003637313843, | |
| "learning_rate": 0.00013154844367227312, | |
| "loss": 0.7291770935058594, | |
| "step": 7560 | |
| }, | |
| { | |
| "epoch": 0.8331040554669015, | |
| "grad_norm": 1.1725903749465942, | |
| "learning_rate": 0.00013137927896450825, | |
| "loss": 0.7654675483703614, | |
| "step": 7570 | |
| }, | |
| { | |
| "epoch": 0.8342045892257745, | |
| "grad_norm": 1.3469438552856445, | |
| "learning_rate": 0.000131210014593158, | |
| "loss": 0.6373929500579834, | |
| "step": 7580 | |
| }, | |
| { | |
| "epoch": 0.8353051229846475, | |
| "grad_norm": 1.3646994829177856, | |
| "learning_rate": 0.00013104065109582216, | |
| "loss": 0.6589652061462402, | |
| "step": 7590 | |
| }, | |
| { | |
| "epoch": 0.8364056567435206, | |
| "grad_norm": 1.4819387197494507, | |
| "learning_rate": 0.0001308711890104153, | |
| "loss": 0.7560039520263672, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.8375061905023936, | |
| "grad_norm": 2.5454657077789307, | |
| "learning_rate": 0.00013070162887516526, | |
| "loss": 0.7073025226593017, | |
| "step": 7610 | |
| }, | |
| { | |
| "epoch": 0.8386067242612667, | |
| "grad_norm": 1.3752559423446655, | |
| "learning_rate": 0.00013053197122861118, | |
| "loss": 0.6591440677642822, | |
| "step": 7620 | |
| }, | |
| { | |
| "epoch": 0.8397072580201398, | |
| "grad_norm": 1.2405189275741577, | |
| "learning_rate": 0.00013036221660960197, | |
| "loss": 0.6888460636138916, | |
| "step": 7630 | |
| }, | |
| { | |
| "epoch": 0.8408077917790128, | |
| "grad_norm": 1.35996413230896, | |
| "learning_rate": 0.00013019236555729448, | |
| "loss": 0.7027706146240235, | |
| "step": 7640 | |
| }, | |
| { | |
| "epoch": 0.8419083255378859, | |
| "grad_norm": 1.7200969457626343, | |
| "learning_rate": 0.00013002241861115186, | |
| "loss": 0.6196746349334716, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 0.843008859296759, | |
| "grad_norm": 1.377030372619629, | |
| "learning_rate": 0.00012985237631094187, | |
| "loss": 0.627590274810791, | |
| "step": 7660 | |
| }, | |
| { | |
| "epoch": 0.8441093930556319, | |
| "grad_norm": 1.4566055536270142, | |
| "learning_rate": 0.00012968223919673503, | |
| "loss": 0.6607007026672364, | |
| "step": 7670 | |
| }, | |
| { | |
| "epoch": 0.845209926814505, | |
| "grad_norm": 1.4451576471328735, | |
| "learning_rate": 0.0001295120078089031, | |
| "loss": 0.7037580013275146, | |
| "step": 7680 | |
| }, | |
| { | |
| "epoch": 0.8463104605733781, | |
| "grad_norm": 1.415389060974121, | |
| "learning_rate": 0.00012934168268811719, | |
| "loss": 0.7002586364746094, | |
| "step": 7690 | |
| }, | |
| { | |
| "epoch": 0.8474109943322511, | |
| "grad_norm": 1.4278415441513062, | |
| "learning_rate": 0.0001291712643753462, | |
| "loss": 0.7121758460998535, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.8485115280911242, | |
| "grad_norm": 1.371798038482666, | |
| "learning_rate": 0.00012900075341185487, | |
| "loss": 0.6606307029724121, | |
| "step": 7710 | |
| }, | |
| { | |
| "epoch": 0.8496120618499973, | |
| "grad_norm": 1.5357285737991333, | |
| "learning_rate": 0.00012883015033920235, | |
| "loss": 0.6908731460571289, | |
| "step": 7720 | |
| }, | |
| { | |
| "epoch": 0.8507125956088702, | |
| "grad_norm": 1.506842851638794, | |
| "learning_rate": 0.0001286594556992403, | |
| "loss": 0.6720726966857911, | |
| "step": 7730 | |
| }, | |
| { | |
| "epoch": 0.8518131293677433, | |
| "grad_norm": 1.4170438051223755, | |
| "learning_rate": 0.00012848867003411116, | |
| "loss": 0.6788636207580566, | |
| "step": 7740 | |
| }, | |
| { | |
| "epoch": 0.8529136631266164, | |
| "grad_norm": 1.1453160047531128, | |
| "learning_rate": 0.0001283177938862465, | |
| "loss": 0.6716455936431884, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 0.8540141968854894, | |
| "grad_norm": 1.438539981842041, | |
| "learning_rate": 0.0001281468277983653, | |
| "loss": 0.7212297439575195, | |
| "step": 7760 | |
| }, | |
| { | |
| "epoch": 0.8551147306443625, | |
| "grad_norm": 1.373718500137329, | |
| "learning_rate": 0.00012797577231347216, | |
| "loss": 0.6638013839721679, | |
| "step": 7770 | |
| }, | |
| { | |
| "epoch": 0.8562152644032356, | |
| "grad_norm": 1.2419517040252686, | |
| "learning_rate": 0.00012780462797485563, | |
| "loss": 0.6845217227935791, | |
| "step": 7780 | |
| }, | |
| { | |
| "epoch": 0.8573157981621087, | |
| "grad_norm": 1.5489189624786377, | |
| "learning_rate": 0.0001276333953260865, | |
| "loss": 0.6920717239379883, | |
| "step": 7790 | |
| }, | |
| { | |
| "epoch": 0.8584163319209817, | |
| "grad_norm": 1.2467175722122192, | |
| "learning_rate": 0.00012746207491101596, | |
| "loss": 0.66603102684021, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.8595168656798547, | |
| "grad_norm": 1.4268126487731934, | |
| "learning_rate": 0.000127290667273774, | |
| "loss": 0.6849881649017334, | |
| "step": 7810 | |
| }, | |
| { | |
| "epoch": 0.8606173994387278, | |
| "grad_norm": 1.495902419090271, | |
| "learning_rate": 0.0001271191729587677, | |
| "loss": 0.6129237174987793, | |
| "step": 7820 | |
| }, | |
| { | |
| "epoch": 0.8617179331976008, | |
| "grad_norm": 1.6803451776504517, | |
| "learning_rate": 0.0001269475925106793, | |
| "loss": 0.6143646240234375, | |
| "step": 7830 | |
| }, | |
| { | |
| "epoch": 0.8628184669564739, | |
| "grad_norm": 1.113897442817688, | |
| "learning_rate": 0.00012677592647446472, | |
| "loss": 0.6867623805999756, | |
| "step": 7840 | |
| }, | |
| { | |
| "epoch": 0.863919000715347, | |
| "grad_norm": 1.457037329673767, | |
| "learning_rate": 0.0001266041753953517, | |
| "loss": 0.6972255229949951, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 0.86501953447422, | |
| "grad_norm": 1.371835470199585, | |
| "learning_rate": 0.00012643233981883805, | |
| "loss": 0.6636334896087647, | |
| "step": 7860 | |
| }, | |
| { | |
| "epoch": 0.8661200682330931, | |
| "grad_norm": 1.516221523284912, | |
| "learning_rate": 0.0001262604202906899, | |
| "loss": 0.6858119964599609, | |
| "step": 7870 | |
| }, | |
| { | |
| "epoch": 0.8672206019919662, | |
| "grad_norm": 1.3317691087722778, | |
| "learning_rate": 0.00012608841735694016, | |
| "loss": 0.6870519161224365, | |
| "step": 7880 | |
| }, | |
| { | |
| "epoch": 0.8683211357508391, | |
| "grad_norm": 1.4758000373840332, | |
| "learning_rate": 0.00012591633156388654, | |
| "loss": 0.7490305423736572, | |
| "step": 7890 | |
| }, | |
| { | |
| "epoch": 0.8694216695097122, | |
| "grad_norm": 1.363806962966919, | |
| "learning_rate": 0.00012574416345808995, | |
| "loss": 0.7155299186706543, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.8705222032685853, | |
| "grad_norm": 1.3234132528305054, | |
| "learning_rate": 0.0001255719135863727, | |
| "loss": 0.7069467544555664, | |
| "step": 7910 | |
| }, | |
| { | |
| "epoch": 0.8716227370274583, | |
| "grad_norm": 1.5334231853485107, | |
| "learning_rate": 0.00012539958249581688, | |
| "loss": 0.6356239795684815, | |
| "step": 7920 | |
| }, | |
| { | |
| "epoch": 0.8727232707863314, | |
| "grad_norm": 2.0638036727905273, | |
| "learning_rate": 0.0001252271707337624, | |
| "loss": 0.6625099182128906, | |
| "step": 7930 | |
| }, | |
| { | |
| "epoch": 0.8738238045452045, | |
| "grad_norm": 1.4381542205810547, | |
| "learning_rate": 0.0001250546788478056, | |
| "loss": 0.6540022373199463, | |
| "step": 7940 | |
| }, | |
| { | |
| "epoch": 0.8749243383040775, | |
| "grad_norm": 1.5481128692626953, | |
| "learning_rate": 0.00012488210738579707, | |
| "loss": 0.7181411266326905, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 0.8760248720629505, | |
| "grad_norm": 1.4068529605865479, | |
| "learning_rate": 0.00012470945689584028, | |
| "loss": 0.7064788818359375, | |
| "step": 7960 | |
| }, | |
| { | |
| "epoch": 0.8771254058218236, | |
| "grad_norm": 1.434870958328247, | |
| "learning_rate": 0.00012453672792628968, | |
| "loss": 0.6818098545074462, | |
| "step": 7970 | |
| }, | |
| { | |
| "epoch": 0.8782259395806966, | |
| "grad_norm": 1.3886451721191406, | |
| "learning_rate": 0.00012436392102574894, | |
| "loss": 0.7107852458953857, | |
| "step": 7980 | |
| }, | |
| { | |
| "epoch": 0.8793264733395697, | |
| "grad_norm": 1.203020453453064, | |
| "learning_rate": 0.00012419103674306928, | |
| "loss": 0.6583857536315918, | |
| "step": 7990 | |
| }, | |
| { | |
| "epoch": 0.8804270070984428, | |
| "grad_norm": 1.9182116985321045, | |
| "learning_rate": 0.00012401807562734772, | |
| "loss": 0.659544849395752, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.8804270070984428, | |
| "eval_loss": 0.6778551340103149, | |
| "eval_runtime": 932.9618, | |
| "eval_samples_per_second": 9.74, | |
| "eval_steps_per_second": 2.435, | |
| "step": 8000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 18174, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9426659175242056e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |