Text Generation
Transformers
Safetensors
Japanese
English
llama
llm-jp
math
sft
full-parameter-finetuning
team-victory
experiment-0399
wandb
conversational
text-generation-inference
Instructions to use argo11/0399-tv-full-thinking-fp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use argo11/0399-tv-full-thinking-fp with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="argo11/0399-tv-full-thinking-fp") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("argo11/0399-tv-full-thinking-fp") model = AutoModelForCausalLM.from_pretrained("argo11/0399-tv-full-thinking-fp", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use argo11/0399-tv-full-thinking-fp with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "argo11/0399-tv-full-thinking-fp" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "argo11/0399-tv-full-thinking-fp", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/argo11/0399-tv-full-thinking-fp
- SGLang
How to use argo11/0399-tv-full-thinking-fp 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 "argo11/0399-tv-full-thinking-fp" \ --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": "argo11/0399-tv-full-thinking-fp", "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 "argo11/0399-tv-full-thinking-fp" \ --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": "argo11/0399-tv-full-thinking-fp", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use argo11/0399-tv-full-thinking-fp with Docker Model Runner:
docker model run hf.co/argo11/0399-tv-full-thinking-fp
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1171929361957708, | |
| "eval_steps": 500, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002343858723915416, | |
| "grad_norm": 7.478665351867676, | |
| "learning_rate": 1.40625e-07, | |
| "loss": 0.6732528686523438, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004687717447830832, | |
| "grad_norm": 7.584623336791992, | |
| "learning_rate": 2.96875e-07, | |
| "loss": 0.66597900390625, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007031576171746248, | |
| "grad_norm": 6.306713581085205, | |
| "learning_rate": 4.53125e-07, | |
| "loss": 0.6197677612304687, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0009375434895661664, | |
| "grad_norm": 4.607383728027344, | |
| "learning_rate": 6.09375e-07, | |
| "loss": 0.5319419860839844, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001171929361957708, | |
| "grad_norm": 2.3062853813171387, | |
| "learning_rate": 7.656250000000001e-07, | |
| "loss": 0.42061538696289064, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0014063152343492496, | |
| "grad_norm": 1.4863656759262085, | |
| "learning_rate": 9.218750000000002e-07, | |
| "loss": 0.3130531311035156, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0016407011067407912, | |
| "grad_norm": 0.8237831592559814, | |
| "learning_rate": 1.0781250000000002e-06, | |
| "loss": 0.23311138153076172, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0018750869791323327, | |
| "grad_norm": 0.6643654704093933, | |
| "learning_rate": 1.2343750000000001e-06, | |
| "loss": 0.2020857810974121, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0021094728515238742, | |
| "grad_norm": 0.5149619579315186, | |
| "learning_rate": 1.3906250000000001e-06, | |
| "loss": 0.18220624923706055, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.002343858723915416, | |
| "grad_norm": 0.5113442540168762, | |
| "learning_rate": 1.5468750000000001e-06, | |
| "loss": 0.16905088424682618, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0025782445963069577, | |
| "grad_norm": 0.5090538859367371, | |
| "learning_rate": 1.703125e-06, | |
| "loss": 0.16316838264465333, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0028126304686984993, | |
| "grad_norm": 0.4110700190067291, | |
| "learning_rate": 1.8593750000000003e-06, | |
| "loss": 0.1580258846282959, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.003047016341090041, | |
| "grad_norm": 0.5005377531051636, | |
| "learning_rate": 2.0156250000000003e-06, | |
| "loss": 0.14841842651367188, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0032814022134815823, | |
| "grad_norm": 0.4914725124835968, | |
| "learning_rate": 2.1718750000000003e-06, | |
| "loss": 0.14541361331939698, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.003515788085873124, | |
| "grad_norm": 0.5155150294303894, | |
| "learning_rate": 2.3281250000000003e-06, | |
| "loss": 0.14492216110229492, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0037501739582646654, | |
| "grad_norm": 0.4690794050693512, | |
| "learning_rate": 2.4843750000000002e-06, | |
| "loss": 0.14195268154144286, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.003984559830656207, | |
| "grad_norm": 0.50107342004776, | |
| "learning_rate": 2.640625e-06, | |
| "loss": 0.1428708553314209, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0042189457030477485, | |
| "grad_norm": 0.48859548568725586, | |
| "learning_rate": 2.796875e-06, | |
| "loss": 0.14226298332214354, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0044533315754392904, | |
| "grad_norm": 0.5123774409294128, | |
| "learning_rate": 2.953125e-06, | |
| "loss": 0.1370567798614502, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.004687717447830832, | |
| "grad_norm": 0.4833315312862396, | |
| "learning_rate": 3.109375e-06, | |
| "loss": 0.1390127420425415, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0049221033202223735, | |
| "grad_norm": 0.43915465474128723, | |
| "learning_rate": 3.265625e-06, | |
| "loss": 0.13475892543792725, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.0051564891926139155, | |
| "grad_norm": 0.46104806661605835, | |
| "learning_rate": 3.421875e-06, | |
| "loss": 0.13139626979827881, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.005390875065005457, | |
| "grad_norm": 0.5122255086898804, | |
| "learning_rate": 3.578125e-06, | |
| "loss": 0.13110661506652832, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.0056252609373969985, | |
| "grad_norm": 0.48517927527427673, | |
| "learning_rate": 3.734375e-06, | |
| "loss": 0.12811717987060547, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.00585964680978854, | |
| "grad_norm": 0.4835013449192047, | |
| "learning_rate": 3.890625e-06, | |
| "loss": 0.13097090721130372, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.006094032682180082, | |
| "grad_norm": 0.4820455312728882, | |
| "learning_rate": 4.046875e-06, | |
| "loss": 0.12818758487701415, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.006328418554571624, | |
| "grad_norm": 0.44813403487205505, | |
| "learning_rate": 4.2031250000000005e-06, | |
| "loss": 0.12801458835601806, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.006562804426963165, | |
| "grad_norm": 0.5279086232185364, | |
| "learning_rate": 4.359375e-06, | |
| "loss": 0.12751049995422364, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.006797190299354707, | |
| "grad_norm": 0.42281895875930786, | |
| "learning_rate": 4.5156250000000005e-06, | |
| "loss": 0.13442916870117189, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.007031576171746248, | |
| "grad_norm": 0.4167884588241577, | |
| "learning_rate": 4.671875e-06, | |
| "loss": 0.12415478229522706, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.00726596204413779, | |
| "grad_norm": 0.4328134059906006, | |
| "learning_rate": 4.8281250000000005e-06, | |
| "loss": 0.12891750335693358, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.007500347916529331, | |
| "grad_norm": 0.45806413888931274, | |
| "learning_rate": 4.984375e-06, | |
| "loss": 0.12102985382080078, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.007734733788920873, | |
| "grad_norm": 0.5078896880149841, | |
| "learning_rate": 5.1406250000000004e-06, | |
| "loss": 0.12243216037750244, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.007969119661312415, | |
| "grad_norm": 0.527930498123169, | |
| "learning_rate": 5.296875e-06, | |
| "loss": 0.12513620853424073, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.008203505533703956, | |
| "grad_norm": 0.431318461894989, | |
| "learning_rate": 5.453125e-06, | |
| "loss": 0.12151198387145996, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.008437891406095497, | |
| "grad_norm": 0.4996262788772583, | |
| "learning_rate": 5.609375e-06, | |
| "loss": 0.11847388744354248, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.00867227727848704, | |
| "grad_norm": 0.4818030893802643, | |
| "learning_rate": 5.765625e-06, | |
| "loss": 0.1227838158607483, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.008906663150878581, | |
| "grad_norm": 0.4577305018901825, | |
| "learning_rate": 5.921875e-06, | |
| "loss": 0.1199771523475647, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.009141049023270122, | |
| "grad_norm": 0.48360294103622437, | |
| "learning_rate": 6.078125e-06, | |
| "loss": 0.11903550624847412, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.009375434895661665, | |
| "grad_norm": 0.47577178478240967, | |
| "learning_rate": 6.234375e-06, | |
| "loss": 0.12074012756347656, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.009609820768053206, | |
| "grad_norm": 0.4833427369594574, | |
| "learning_rate": 6.390625e-06, | |
| "loss": 0.12326394319534302, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.009844206640444747, | |
| "grad_norm": 0.43909400701522827, | |
| "learning_rate": 6.546875e-06, | |
| "loss": 0.11921967267990112, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.010078592512836288, | |
| "grad_norm": 0.5028750896453857, | |
| "learning_rate": 6.703125e-06, | |
| "loss": 0.12188574075698852, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.010312978385227831, | |
| "grad_norm": 0.47389668226242065, | |
| "learning_rate": 6.859375000000001e-06, | |
| "loss": 0.1192385196685791, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.010547364257619372, | |
| "grad_norm": 0.5239953398704529, | |
| "learning_rate": 7.015625e-06, | |
| "loss": 0.11499193906784058, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.010781750130010913, | |
| "grad_norm": 0.5061202645301819, | |
| "learning_rate": 7.171875000000001e-06, | |
| "loss": 0.11584588289260864, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.011016136002402456, | |
| "grad_norm": 0.4635751247406006, | |
| "learning_rate": 7.328125e-06, | |
| "loss": 0.11434779167175294, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.011250521874793997, | |
| "grad_norm": 0.4353443682193756, | |
| "learning_rate": 7.484375000000001e-06, | |
| "loss": 0.11755821704864503, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.011484907747185538, | |
| "grad_norm": 0.41028693318367004, | |
| "learning_rate": 7.640625000000001e-06, | |
| "loss": 0.11704204082489014, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.01171929361957708, | |
| "grad_norm": 0.4426499009132385, | |
| "learning_rate": 7.796875e-06, | |
| "loss": 0.11789888143539429, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.011953679491968622, | |
| "grad_norm": 0.45650583505630493, | |
| "learning_rate": 7.953125e-06, | |
| "loss": 0.11612817049026489, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.012188065364360163, | |
| "grad_norm": 0.48528221249580383, | |
| "learning_rate": 8.109375e-06, | |
| "loss": 0.11835837364196777, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.012422451236751704, | |
| "grad_norm": 0.49201133847236633, | |
| "learning_rate": 8.265625000000001e-06, | |
| "loss": 0.11796109676361084, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.012656837109143247, | |
| "grad_norm": 0.41120538115501404, | |
| "learning_rate": 8.421875e-06, | |
| "loss": 0.11465147733688355, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.012891222981534788, | |
| "grad_norm": 0.42535409331321716, | |
| "learning_rate": 8.578125e-06, | |
| "loss": 0.11844432353973389, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.01312560885392633, | |
| "grad_norm": 0.44362396001815796, | |
| "learning_rate": 8.734375e-06, | |
| "loss": 0.11715601682662964, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.01335999472631787, | |
| "grad_norm": 0.441021203994751, | |
| "learning_rate": 8.890625000000001e-06, | |
| "loss": 0.11989809274673462, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.013594380598709413, | |
| "grad_norm": 0.4338180720806122, | |
| "learning_rate": 9.046875e-06, | |
| "loss": 0.11536179780960083, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.013828766471100954, | |
| "grad_norm": 0.43819499015808105, | |
| "learning_rate": 9.203125e-06, | |
| "loss": 0.11345911026000977, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.014063152343492496, | |
| "grad_norm": 0.4360722601413727, | |
| "learning_rate": 9.359375e-06, | |
| "loss": 0.11602315902709961, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.014297538215884038, | |
| "grad_norm": 0.4287785589694977, | |
| "learning_rate": 9.515625000000001e-06, | |
| "loss": 0.11890817880630493, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.01453192408827558, | |
| "grad_norm": 0.4322708547115326, | |
| "learning_rate": 9.671875000000001e-06, | |
| "loss": 0.11710528135299683, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.01476630996066712, | |
| "grad_norm": 0.4133163392543793, | |
| "learning_rate": 9.828125e-06, | |
| "loss": 0.11247456073760986, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.015000695833058662, | |
| "grad_norm": 0.4161861538887024, | |
| "learning_rate": 9.984375e-06, | |
| "loss": 0.1176948070526123, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.015235081705450204, | |
| "grad_norm": 0.4499410092830658, | |
| "learning_rate": 1.0140625000000003e-05, | |
| "loss": 0.11162110567092895, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.015469467577841746, | |
| "grad_norm": 0.4393712878227234, | |
| "learning_rate": 1.0296875000000001e-05, | |
| "loss": 0.11646484136581421, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.01570385345023329, | |
| "grad_norm": 0.43581581115722656, | |
| "learning_rate": 1.0453125000000002e-05, | |
| "loss": 0.11804448366165161, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.01593823932262483, | |
| "grad_norm": 0.5233722925186157, | |
| "learning_rate": 1.0609375000000002e-05, | |
| "loss": 0.11381900310516357, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.01617262519501637, | |
| "grad_norm": 0.4110233187675476, | |
| "learning_rate": 1.0765625000000002e-05, | |
| "loss": 0.11446200609207154, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.01640701106740791, | |
| "grad_norm": 0.399118036031723, | |
| "learning_rate": 1.0921875000000001e-05, | |
| "loss": 0.11271647214889527, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.016641396939799453, | |
| "grad_norm": 0.46171241998672485, | |
| "learning_rate": 1.1078125000000002e-05, | |
| "loss": 0.11184619665145874, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.016875782812190994, | |
| "grad_norm": 0.45813125371932983, | |
| "learning_rate": 1.1234375000000002e-05, | |
| "loss": 0.11524376869201661, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.01711016868458254, | |
| "grad_norm": 0.3914071023464203, | |
| "learning_rate": 1.1390625000000002e-05, | |
| "loss": 0.11292357444763183, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.01734455455697408, | |
| "grad_norm": 0.3806169033050537, | |
| "learning_rate": 1.1546875000000001e-05, | |
| "loss": 0.11865770816802979, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.01757894042936562, | |
| "grad_norm": 0.6183323264122009, | |
| "learning_rate": 1.1703125000000002e-05, | |
| "loss": 0.1167568564414978, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.017813326301757162, | |
| "grad_norm": 0.39449653029441833, | |
| "learning_rate": 1.1859375000000002e-05, | |
| "loss": 0.11325149536132813, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.018047712174148703, | |
| "grad_norm": 0.37599578499794006, | |
| "learning_rate": 1.2015625000000002e-05, | |
| "loss": 0.11163055896759033, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.018282098046540244, | |
| "grad_norm": 0.38267573714256287, | |
| "learning_rate": 1.2171875000000001e-05, | |
| "loss": 0.11489014625549317, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.018516483918931785, | |
| "grad_norm": 0.37311288714408875, | |
| "learning_rate": 1.2328125000000002e-05, | |
| "loss": 0.11194641590118408, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.01875086979132333, | |
| "grad_norm": 0.411432683467865, | |
| "learning_rate": 1.2484375000000002e-05, | |
| "loss": 0.11317495107650757, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.01898525566371487, | |
| "grad_norm": 0.43839067220687866, | |
| "learning_rate": 1.2640625000000002e-05, | |
| "loss": 0.10759581327438354, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.019219641536106412, | |
| "grad_norm": 0.3859034478664398, | |
| "learning_rate": 1.2796875000000003e-05, | |
| "loss": 0.11314148902893066, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.019454027408497953, | |
| "grad_norm": 0.4093567728996277, | |
| "learning_rate": 1.2953125000000001e-05, | |
| "loss": 0.11214956045150756, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.019688413280889494, | |
| "grad_norm": 0.4202522337436676, | |
| "learning_rate": 1.3109375000000002e-05, | |
| "loss": 0.10863385200500489, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.019922799153281035, | |
| "grad_norm": 0.37031644582748413, | |
| "learning_rate": 1.3265625000000002e-05, | |
| "loss": 0.11562912464141846, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.020157185025672576, | |
| "grad_norm": 0.372043251991272, | |
| "learning_rate": 1.3421875000000003e-05, | |
| "loss": 0.11000908613204956, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.02039157089806412, | |
| "grad_norm": 0.39329200983047485, | |
| "learning_rate": 1.3578125000000001e-05, | |
| "loss": 0.11322653293609619, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.020625956770455662, | |
| "grad_norm": 0.3731657564640045, | |
| "learning_rate": 1.3734375000000002e-05, | |
| "loss": 0.11117322444915771, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.020860342642847203, | |
| "grad_norm": 0.3705548644065857, | |
| "learning_rate": 1.3890625000000002e-05, | |
| "loss": 0.10953671932220459, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.021094728515238744, | |
| "grad_norm": 0.38085901737213135, | |
| "learning_rate": 1.4046875000000003e-05, | |
| "loss": 0.11695330142974854, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.021329114387630285, | |
| "grad_norm": 0.4012692868709564, | |
| "learning_rate": 1.4203125000000001e-05, | |
| "loss": 0.11438255310058594, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.021563500260021826, | |
| "grad_norm": 0.3757342994213104, | |
| "learning_rate": 1.4359375000000002e-05, | |
| "loss": 0.11287130117416382, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.021797886132413367, | |
| "grad_norm": 0.38042888045310974, | |
| "learning_rate": 1.4515625000000002e-05, | |
| "loss": 0.11060645580291747, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.022032272004804912, | |
| "grad_norm": 0.3464396297931671, | |
| "learning_rate": 1.4671875000000003e-05, | |
| "loss": 0.11261942386627197, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.022266657877196453, | |
| "grad_norm": 0.3607310652732849, | |
| "learning_rate": 1.4828125000000001e-05, | |
| "loss": 0.11483677625656127, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.022501043749587994, | |
| "grad_norm": 0.37492862343788147, | |
| "learning_rate": 1.4984375000000002e-05, | |
| "loss": 0.11412110328674316, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.022735429621979535, | |
| "grad_norm": 0.36724552512168884, | |
| "learning_rate": 1.5140625000000002e-05, | |
| "loss": 0.11400502920150757, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.022969815494371076, | |
| "grad_norm": 0.3513246774673462, | |
| "learning_rate": 1.5296875e-05, | |
| "loss": 0.11101123094558715, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.023204201366762617, | |
| "grad_norm": 0.39282527565956116, | |
| "learning_rate": 1.5453125e-05, | |
| "loss": 0.11446715593338012, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.02343858723915416, | |
| "grad_norm": 0.3693297505378723, | |
| "learning_rate": 1.5609375e-05, | |
| "loss": 0.11360613107681275, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.023672973111545703, | |
| "grad_norm": 0.3805910050868988, | |
| "learning_rate": 1.5765625000000002e-05, | |
| "loss": 0.1102859616279602, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.023907358983937244, | |
| "grad_norm": 0.3862535059452057, | |
| "learning_rate": 1.5921875000000002e-05, | |
| "loss": 0.11268872022628784, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.024141744856328785, | |
| "grad_norm": 0.404893696308136, | |
| "learning_rate": 1.6078125000000003e-05, | |
| "loss": 0.11359611749649048, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.024376130728720326, | |
| "grad_norm": 0.38326576352119446, | |
| "learning_rate": 1.6234375000000003e-05, | |
| "loss": 0.11227505207061768, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.024610516601111868, | |
| "grad_norm": 0.36912357807159424, | |
| "learning_rate": 1.6390625000000004e-05, | |
| "loss": 0.11599531173706054, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.02484490247350341, | |
| "grad_norm": 0.3696171045303345, | |
| "learning_rate": 1.6546875e-05, | |
| "loss": 0.11023976802825927, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.02507928834589495, | |
| "grad_norm": 0.3755769729614258, | |
| "learning_rate": 1.6703125e-05, | |
| "loss": 0.11145970821380616, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.025313674218286494, | |
| "grad_norm": 0.3687419593334198, | |
| "learning_rate": 1.6859375e-05, | |
| "loss": 0.11287758350372315, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.025548060090678035, | |
| "grad_norm": 0.33784812688827515, | |
| "learning_rate": 1.7015625000000002e-05, | |
| "loss": 0.10908894538879395, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.025782445963069577, | |
| "grad_norm": 0.3508151173591614, | |
| "learning_rate": 1.7171875000000002e-05, | |
| "loss": 0.11538139581680298, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.026016831835461118, | |
| "grad_norm": 0.36725053191185, | |
| "learning_rate": 1.7328125000000003e-05, | |
| "loss": 0.11482850313186646, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.02625121770785266, | |
| "grad_norm": 0.34291842579841614, | |
| "learning_rate": 1.7484375000000003e-05, | |
| "loss": 0.11298364400863647, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.0264856035802442, | |
| "grad_norm": 0.36184895038604736, | |
| "learning_rate": 1.7640625000000004e-05, | |
| "loss": 0.1066980242729187, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.02671998945263574, | |
| "grad_norm": 0.4020235240459442, | |
| "learning_rate": 1.7796875000000004e-05, | |
| "loss": 0.11315239667892456, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.026954375325027286, | |
| "grad_norm": 0.34352606534957886, | |
| "learning_rate": 1.7953125e-05, | |
| "loss": 0.10964906215667725, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.027188761197418827, | |
| "grad_norm": 0.4462008476257324, | |
| "learning_rate": 1.8109375e-05, | |
| "loss": 0.11428066492080688, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.027423147069810368, | |
| "grad_norm": 0.3392775058746338, | |
| "learning_rate": 1.8265625000000002e-05, | |
| "loss": 0.11005079746246338, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.02765753294220191, | |
| "grad_norm": 0.3385438621044159, | |
| "learning_rate": 1.8421875000000002e-05, | |
| "loss": 0.11102509498596191, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.02789191881459345, | |
| "grad_norm": 0.3650127649307251, | |
| "learning_rate": 1.8578125000000003e-05, | |
| "loss": 0.11523213386535644, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.02812630468698499, | |
| "grad_norm": 0.3460846245288849, | |
| "learning_rate": 1.8734375000000003e-05, | |
| "loss": 0.11034642457962036, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.028360690559376532, | |
| "grad_norm": 0.326349675655365, | |
| "learning_rate": 1.8890625000000003e-05, | |
| "loss": 0.10953868627548217, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.028595076431768077, | |
| "grad_norm": 0.34334462881088257, | |
| "learning_rate": 1.9046875000000004e-05, | |
| "loss": 0.11296612024307251, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.028829462304159618, | |
| "grad_norm": 0.33681803941726685, | |
| "learning_rate": 1.9203125e-05, | |
| "loss": 0.11056774854660034, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.02906384817655116, | |
| "grad_norm": 0.3528500199317932, | |
| "learning_rate": 1.9359375e-05, | |
| "loss": 0.10871942043304443, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.0292982340489427, | |
| "grad_norm": 0.3156096339225769, | |
| "learning_rate": 1.9515625000000002e-05, | |
| "loss": 0.1137766718864441, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.02953261992133424, | |
| "grad_norm": 0.3579378128051758, | |
| "learning_rate": 1.9671875000000002e-05, | |
| "loss": 0.11373578310012818, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.029767005793725782, | |
| "grad_norm": 0.315738707780838, | |
| "learning_rate": 1.9828125000000003e-05, | |
| "loss": 0.11297824382781982, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.030001391666117323, | |
| "grad_norm": 0.3177584111690521, | |
| "learning_rate": 1.9984375000000003e-05, | |
| "loss": 0.1135290265083313, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.030235777538508868, | |
| "grad_norm": 0.34855231642723083, | |
| "learning_rate": 1.9999997666172074e-05, | |
| "loss": 0.11188427209854127, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.03047016341090041, | |
| "grad_norm": 0.3580094575881958, | |
| "learning_rate": 1.9999989598620137e-05, | |
| "loss": 0.10642122030258179, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.03070454928329195, | |
| "grad_norm": 0.37562474608421326, | |
| "learning_rate": 1.9999975768536158e-05, | |
| "loss": 0.11398833990097046, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.03093893515568349, | |
| "grad_norm": 0.34030941128730774, | |
| "learning_rate": 1.9999956175928097e-05, | |
| "loss": 0.10998734235763549, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.031173321028075032, | |
| "grad_norm": 0.3101728856563568, | |
| "learning_rate": 1.9999930820807245e-05, | |
| "loss": 0.11209770441055297, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.03140770690046658, | |
| "grad_norm": 0.34433069825172424, | |
| "learning_rate": 1.999989970318822e-05, | |
| "loss": 0.1109668493270874, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.031642092772858114, | |
| "grad_norm": 0.32215601205825806, | |
| "learning_rate": 1.9999862823088946e-05, | |
| "loss": 0.10847405195236207, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.03187647864524966, | |
| "grad_norm": 0.32859981060028076, | |
| "learning_rate": 1.999982018053068e-05, | |
| "loss": 0.11370890140533448, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.0321108645176412, | |
| "grad_norm": 0.3100363314151764, | |
| "learning_rate": 1.999977177553799e-05, | |
| "loss": 0.1127819538116455, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.03234525039003274, | |
| "grad_norm": 0.29671692848205566, | |
| "learning_rate": 1.9999717608138778e-05, | |
| "loss": 0.10928714275360107, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.032579636262424286, | |
| "grad_norm": 0.3065207302570343, | |
| "learning_rate": 1.9999657678364252e-05, | |
| "loss": 0.10931737422943115, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.03281402213481582, | |
| "grad_norm": 0.32845526933670044, | |
| "learning_rate": 1.9999591986248947e-05, | |
| "loss": 0.1125643253326416, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.03304840800720737, | |
| "grad_norm": 0.31998366117477417, | |
| "learning_rate": 1.999952053183072e-05, | |
| "loss": 0.11007034778594971, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.033282793879598906, | |
| "grad_norm": 0.3302232623100281, | |
| "learning_rate": 1.9999443315150742e-05, | |
| "loss": 0.11075022220611572, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.03351717975199045, | |
| "grad_norm": 0.3401246964931488, | |
| "learning_rate": 1.999936033625352e-05, | |
| "loss": 0.10927612781524658, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.03375156562438199, | |
| "grad_norm": 0.31189054250717163, | |
| "learning_rate": 1.999927159518686e-05, | |
| "loss": 0.10789297819137574, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.03398595149677353, | |
| "grad_norm": 0.32660672068595886, | |
| "learning_rate": 1.9999177092001907e-05, | |
| "loss": 0.10693231821060181, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.03422033736916508, | |
| "grad_norm": 0.31303200125694275, | |
| "learning_rate": 1.9999076826753116e-05, | |
| "loss": 0.11288677453994751, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.034454723241556615, | |
| "grad_norm": 0.3008570075035095, | |
| "learning_rate": 1.9998970799498262e-05, | |
| "loss": 0.10686779022216797, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.03468910911394816, | |
| "grad_norm": 0.3439565598964691, | |
| "learning_rate": 1.9998859010298447e-05, | |
| "loss": 0.1086077332496643, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.0349234949863397, | |
| "grad_norm": 0.3342174291610718, | |
| "learning_rate": 1.9998741459218093e-05, | |
| "loss": 0.1085971713066101, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.03515788085873124, | |
| "grad_norm": 0.3462369740009308, | |
| "learning_rate": 1.999861814632493e-05, | |
| "loss": 0.11292096376419067, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.03539226673112278, | |
| "grad_norm": 0.2996586263179779, | |
| "learning_rate": 1.9998489071690024e-05, | |
| "loss": 0.1069232702255249, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.035626652603514324, | |
| "grad_norm": 0.30933356285095215, | |
| "learning_rate": 1.9998354235387758e-05, | |
| "loss": 0.11092567443847656, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.03586103847590587, | |
| "grad_norm": 0.3398067355155945, | |
| "learning_rate": 1.9998213637495824e-05, | |
| "loss": 0.10429364442825317, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.036095424348297406, | |
| "grad_norm": 0.34331822395324707, | |
| "learning_rate": 1.999806727809525e-05, | |
| "loss": 0.11222647428512574, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.03632981022068895, | |
| "grad_norm": 0.32439032196998596, | |
| "learning_rate": 1.9997915157270367e-05, | |
| "loss": 0.10828479528427123, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.03656419609308049, | |
| "grad_norm": 0.2919040322303772, | |
| "learning_rate": 1.9997757275108847e-05, | |
| "loss": 0.1067802906036377, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.03679858196547203, | |
| "grad_norm": 0.3021163046360016, | |
| "learning_rate": 1.999759363170166e-05, | |
| "loss": 0.1080705165863037, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.03703296783786357, | |
| "grad_norm": 0.309612512588501, | |
| "learning_rate": 1.9997424227143108e-05, | |
| "loss": 0.10892333984375, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.037267353710255115, | |
| "grad_norm": 0.2833057641983032, | |
| "learning_rate": 1.9997249061530814e-05, | |
| "loss": 0.11133861541748047, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.03750173958264666, | |
| "grad_norm": 0.32193875312805176, | |
| "learning_rate": 1.999706813496572e-05, | |
| "loss": 0.11482088565826416, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.0377361254550382, | |
| "grad_norm": 0.3027825653553009, | |
| "learning_rate": 1.9996881447552077e-05, | |
| "loss": 0.10923588275909424, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.03797051132742974, | |
| "grad_norm": 0.321659654378891, | |
| "learning_rate": 1.9996688999397473e-05, | |
| "loss": 0.10786941051483154, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.03820489719982128, | |
| "grad_norm": 0.31725117564201355, | |
| "learning_rate": 1.99964907906128e-05, | |
| "loss": 0.10536646842956543, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.038439283072212824, | |
| "grad_norm": 0.2907871603965759, | |
| "learning_rate": 1.9996286821312282e-05, | |
| "loss": 0.10624017715454101, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.03867366894460436, | |
| "grad_norm": 0.32546359300613403, | |
| "learning_rate": 1.9996077091613454e-05, | |
| "loss": 0.10742425918579102, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.038908054816995906, | |
| "grad_norm": 0.2799864411354065, | |
| "learning_rate": 1.9995861601637175e-05, | |
| "loss": 0.11092619895935059, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.03914244068938745, | |
| "grad_norm": 0.3120432496070862, | |
| "learning_rate": 1.9995640351507623e-05, | |
| "loss": 0.10951026678085327, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.03937682656177899, | |
| "grad_norm": 0.35961198806762695, | |
| "learning_rate": 1.9995413341352293e-05, | |
| "loss": 0.11031874418258666, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.03961121243417053, | |
| "grad_norm": 0.3039030134677887, | |
| "learning_rate": 1.9995180571301998e-05, | |
| "loss": 0.10726022720336914, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.03984559830656207, | |
| "grad_norm": 0.29744887351989746, | |
| "learning_rate": 1.9994942041490878e-05, | |
| "loss": 0.11042420864105225, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.040079984178953615, | |
| "grad_norm": 0.2774674594402313, | |
| "learning_rate": 1.9994697752056385e-05, | |
| "loss": 0.11003159284591675, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.04031437005134515, | |
| "grad_norm": 0.3363332748413086, | |
| "learning_rate": 1.9994447703139286e-05, | |
| "loss": 0.10592604875564575, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.0405487559237367, | |
| "grad_norm": 0.27715635299682617, | |
| "learning_rate": 1.999419189488368e-05, | |
| "loss": 0.10486645698547363, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.04078314179612824, | |
| "grad_norm": 0.3067134916782379, | |
| "learning_rate": 1.999393032743697e-05, | |
| "loss": 0.10921738147735596, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.04101752766851978, | |
| "grad_norm": 0.2900826632976532, | |
| "learning_rate": 1.9993663000949893e-05, | |
| "loss": 0.10426084995269776, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.041251913540911324, | |
| "grad_norm": 0.2976682186126709, | |
| "learning_rate": 1.9993389915576494e-05, | |
| "loss": 0.10740503072738647, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.04148629941330286, | |
| "grad_norm": 0.33628037571907043, | |
| "learning_rate": 1.9993111071474138e-05, | |
| "loss": 0.10685398578643798, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.041720685285694406, | |
| "grad_norm": 0.2832029461860657, | |
| "learning_rate": 1.999282646880351e-05, | |
| "loss": 0.10406830310821533, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.041955071158085944, | |
| "grad_norm": 0.29356080293655396, | |
| "learning_rate": 1.999253610772862e-05, | |
| "loss": 0.10723583698272705, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.04218945703047749, | |
| "grad_norm": 0.29421284794807434, | |
| "learning_rate": 1.9992239988416778e-05, | |
| "loss": 0.10370919704437256, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.04242384290286903, | |
| "grad_norm": 0.3112437129020691, | |
| "learning_rate": 1.999193811103863e-05, | |
| "loss": 0.10596777200698852, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.04265822877526057, | |
| "grad_norm": 0.29095956683158875, | |
| "learning_rate": 1.9991630475768136e-05, | |
| "loss": 0.10655193328857422, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.042892614647652115, | |
| "grad_norm": 0.3111267685890198, | |
| "learning_rate": 1.9991317082782572e-05, | |
| "loss": 0.1068030595779419, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.04312700052004365, | |
| "grad_norm": 0.2968071699142456, | |
| "learning_rate": 1.9990997932262525e-05, | |
| "loss": 0.10419989824295044, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.0433613863924352, | |
| "grad_norm": 0.2839556336402893, | |
| "learning_rate": 1.9990673024391914e-05, | |
| "loss": 0.10594829320907592, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.043595772264826735, | |
| "grad_norm": 0.2657758295536041, | |
| "learning_rate": 1.999034235935797e-05, | |
| "loss": 0.10265007019042968, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.04383015813721828, | |
| "grad_norm": 0.2868812084197998, | |
| "learning_rate": 1.999000593735123e-05, | |
| "loss": 0.10612194538116455, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.044064544009609824, | |
| "grad_norm": 0.2973288297653198, | |
| "learning_rate": 1.9989663758565565e-05, | |
| "loss": 0.1020740270614624, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.04429892988200136, | |
| "grad_norm": 0.33596375584602356, | |
| "learning_rate": 1.9989315823198158e-05, | |
| "loss": 0.10814613103866577, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.044533315754392906, | |
| "grad_norm": 0.30708539485931396, | |
| "learning_rate": 1.998896213144951e-05, | |
| "loss": 0.10821013450622559, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.044767701626784444, | |
| "grad_norm": 0.306995689868927, | |
| "learning_rate": 1.9988602683523427e-05, | |
| "loss": 0.10907049179077148, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.04500208749917599, | |
| "grad_norm": 0.3026825785636902, | |
| "learning_rate": 1.998823747962705e-05, | |
| "loss": 0.1026546835899353, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.045236473371567526, | |
| "grad_norm": 0.26199498772621155, | |
| "learning_rate": 1.9987866519970832e-05, | |
| "loss": 0.10394124984741211, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.04547085924395907, | |
| "grad_norm": 0.28023838996887207, | |
| "learning_rate": 1.9987489804768532e-05, | |
| "loss": 0.1040355920791626, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.045705245116350615, | |
| "grad_norm": 0.3118273913860321, | |
| "learning_rate": 1.998710733423724e-05, | |
| "loss": 0.10564100742340088, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.04593963098874215, | |
| "grad_norm": 0.28954198956489563, | |
| "learning_rate": 1.9986719108597354e-05, | |
| "loss": 0.10645655393600464, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.0461740168611337, | |
| "grad_norm": 0.33579158782958984, | |
| "learning_rate": 1.9986325128072585e-05, | |
| "loss": 0.10616481304168701, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.046408402733525235, | |
| "grad_norm": 0.2787134349346161, | |
| "learning_rate": 1.9985925392889974e-05, | |
| "loss": 0.10173577070236206, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.04664278860591678, | |
| "grad_norm": 0.29140785336494446, | |
| "learning_rate": 1.9985519903279868e-05, | |
| "loss": 0.10528752803802491, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.04687717447830832, | |
| "grad_norm": 0.2874172329902649, | |
| "learning_rate": 1.998510865947593e-05, | |
| "loss": 0.10788161754608154, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.04711156035069986, | |
| "grad_norm": 0.28292685747146606, | |
| "learning_rate": 1.998469166171514e-05, | |
| "loss": 0.1097710132598877, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.047345946223091406, | |
| "grad_norm": 0.28411567211151123, | |
| "learning_rate": 1.9984268910237797e-05, | |
| "loss": 0.10665783882141114, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.047580332095482944, | |
| "grad_norm": 0.2909773290157318, | |
| "learning_rate": 1.9983840405287507e-05, | |
| "loss": 0.10285806655883789, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.04781471796787449, | |
| "grad_norm": 0.29889369010925293, | |
| "learning_rate": 1.998340614711121e-05, | |
| "loss": 0.10465379953384399, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.048049103840266026, | |
| "grad_norm": 0.29105401039123535, | |
| "learning_rate": 1.998296613595914e-05, | |
| "loss": 0.10770035982131958, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.04828348971265757, | |
| "grad_norm": 0.2655159533023834, | |
| "learning_rate": 1.9982520372084855e-05, | |
| "loss": 0.10434014797210693, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.04851787558504911, | |
| "grad_norm": 0.24804545938968658, | |
| "learning_rate": 1.9982068855745232e-05, | |
| "loss": 0.09603033661842346, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.04875226145744065, | |
| "grad_norm": 0.27127230167388916, | |
| "learning_rate": 1.9981611587200453e-05, | |
| "loss": 0.10701797008514405, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.0489866473298322, | |
| "grad_norm": 0.3288525342941284, | |
| "learning_rate": 1.998114856671403e-05, | |
| "loss": 0.10488884449005127, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.049221033202223735, | |
| "grad_norm": 0.2957431375980377, | |
| "learning_rate": 1.998067979455277e-05, | |
| "loss": 0.10282833576202392, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.04945541907461528, | |
| "grad_norm": 0.3068355619907379, | |
| "learning_rate": 1.998020527098681e-05, | |
| "loss": 0.10160216093063354, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.04968980494700682, | |
| "grad_norm": 0.3347589075565338, | |
| "learning_rate": 1.99797249962896e-05, | |
| "loss": 0.10400426387786865, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.04992419081939836, | |
| "grad_norm": 0.30906444787979126, | |
| "learning_rate": 1.997923897073789e-05, | |
| "loss": 0.10504637956619263, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.0501585766917899, | |
| "grad_norm": 0.2961674928665161, | |
| "learning_rate": 1.9978747194611767e-05, | |
| "loss": 0.10290087461471557, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.050392962564181444, | |
| "grad_norm": 0.27527812123298645, | |
| "learning_rate": 1.9978249668194607e-05, | |
| "loss": 0.10352675914764405, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.05062734843657299, | |
| "grad_norm": 0.2558128237724304, | |
| "learning_rate": 1.9977746391773117e-05, | |
| "loss": 0.10233690738677978, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.050861734308964526, | |
| "grad_norm": 0.2849492132663727, | |
| "learning_rate": 1.9977237365637313e-05, | |
| "loss": 0.10237650871276856, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.05109612018135607, | |
| "grad_norm": 0.2671148478984833, | |
| "learning_rate": 1.997672259008052e-05, | |
| "loss": 0.10290088653564453, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.05133050605374761, | |
| "grad_norm": 0.2684539258480072, | |
| "learning_rate": 1.997620206539938e-05, | |
| "loss": 0.10364431142807007, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.05156489192613915, | |
| "grad_norm": 0.2842761278152466, | |
| "learning_rate": 1.9975675791893848e-05, | |
| "loss": 0.10434544086456299, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.05179927779853069, | |
| "grad_norm": 0.2870532274246216, | |
| "learning_rate": 1.997514376986719e-05, | |
| "loss": 0.10496325492858886, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.052033663670922235, | |
| "grad_norm": 0.295663446187973, | |
| "learning_rate": 1.997460599962599e-05, | |
| "loss": 0.1019209384918213, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.05226804954331378, | |
| "grad_norm": 0.2890377342700958, | |
| "learning_rate": 1.9974062481480136e-05, | |
| "loss": 0.1006014347076416, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.05250243541570532, | |
| "grad_norm": 0.2824719548225403, | |
| "learning_rate": 1.9973513215742836e-05, | |
| "loss": 0.10610531568527222, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.05273682128809686, | |
| "grad_norm": 0.2934313714504242, | |
| "learning_rate": 1.9972958202730602e-05, | |
| "loss": 0.10438885688781738, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.0529712071604884, | |
| "grad_norm": 0.27515366673469543, | |
| "learning_rate": 1.997239744276326e-05, | |
| "loss": 0.10107412338256835, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.053205593032879944, | |
| "grad_norm": 0.28475672006607056, | |
| "learning_rate": 1.9971830936163964e-05, | |
| "loss": 0.10238564014434814, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.05343997890527148, | |
| "grad_norm": 0.28128883242607117, | |
| "learning_rate": 1.997125868325915e-05, | |
| "loss": 0.1000057339668274, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.053674364777663026, | |
| "grad_norm": 0.2682857811450958, | |
| "learning_rate": 1.9970680684378586e-05, | |
| "loss": 0.1018843412399292, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.05390875065005457, | |
| "grad_norm": 0.27407148480415344, | |
| "learning_rate": 1.9970096939855347e-05, | |
| "loss": 0.10452917814254761, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.05414313652244611, | |
| "grad_norm": 0.28061622381210327, | |
| "learning_rate": 1.996950745002582e-05, | |
| "loss": 0.10294064283370971, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.05437752239483765, | |
| "grad_norm": 0.27093762159347534, | |
| "learning_rate": 1.9968912215229697e-05, | |
| "loss": 0.10425781011581421, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.05461190826722919, | |
| "grad_norm": 0.2750425934791565, | |
| "learning_rate": 1.9968311235809988e-05, | |
| "loss": 0.10463676452636719, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.054846294139620735, | |
| "grad_norm": 0.2728804349899292, | |
| "learning_rate": 1.9967704512113006e-05, | |
| "loss": 0.1036148190498352, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.05508068001201227, | |
| "grad_norm": 0.26616159081459045, | |
| "learning_rate": 1.996709204448838e-05, | |
| "loss": 0.10782848596572876, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.05531506588440382, | |
| "grad_norm": 0.28741851449012756, | |
| "learning_rate": 1.9966473833289047e-05, | |
| "loss": 0.10164358615875244, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.05554945175679536, | |
| "grad_norm": 0.2606866955757141, | |
| "learning_rate": 1.9965849878871254e-05, | |
| "loss": 0.1056321382522583, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.0557838376291869, | |
| "grad_norm": 0.27213457226753235, | |
| "learning_rate": 1.9965220181594555e-05, | |
| "loss": 0.1027193546295166, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.056018223501578444, | |
| "grad_norm": 0.2630506753921509, | |
| "learning_rate": 1.9964584741821814e-05, | |
| "loss": 0.09874136447906494, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.05625260937396998, | |
| "grad_norm": 0.27048349380493164, | |
| "learning_rate": 1.996394355991921e-05, | |
| "loss": 0.10071604251861573, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.05648699524636153, | |
| "grad_norm": 0.2909840941429138, | |
| "learning_rate": 1.9963296636256223e-05, | |
| "loss": 0.10374481678009033, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.056721381118753064, | |
| "grad_norm": 0.2548065781593323, | |
| "learning_rate": 1.996264397120565e-05, | |
| "loss": 0.09739646911621094, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.05695576699114461, | |
| "grad_norm": 0.25469157099723816, | |
| "learning_rate": 1.9961985565143586e-05, | |
| "loss": 0.10347042083740235, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.05719015286353615, | |
| "grad_norm": 0.27947095036506653, | |
| "learning_rate": 1.9961321418449443e-05, | |
| "loss": 0.09943625926971436, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.05742453873592769, | |
| "grad_norm": 0.2800036668777466, | |
| "learning_rate": 1.996065153150594e-05, | |
| "loss": 0.10229953527450561, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.057658924608319236, | |
| "grad_norm": 0.24105332791805267, | |
| "learning_rate": 1.9959975904699096e-05, | |
| "loss": 0.10039407014846802, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.05789331048071077, | |
| "grad_norm": 0.24678143858909607, | |
| "learning_rate": 1.995929453841825e-05, | |
| "loss": 0.1001626968383789, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.05812769635310232, | |
| "grad_norm": 0.24058112502098083, | |
| "learning_rate": 1.9958607433056035e-05, | |
| "loss": 0.1008292555809021, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.058362082225493855, | |
| "grad_norm": 0.2694501578807831, | |
| "learning_rate": 1.9957914589008405e-05, | |
| "loss": 0.09967796802520752, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.0585964680978854, | |
| "grad_norm": 0.27223488688468933, | |
| "learning_rate": 1.995721600667461e-05, | |
| "loss": 0.10117262601852417, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.058830853970276945, | |
| "grad_norm": 0.2681121528148651, | |
| "learning_rate": 1.9956511686457213e-05, | |
| "loss": 0.0976826786994934, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.05906523984266848, | |
| "grad_norm": 0.28960487246513367, | |
| "learning_rate": 1.9955801628762076e-05, | |
| "loss": 0.0989774227142334, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.05929962571506003, | |
| "grad_norm": 0.281716912984848, | |
| "learning_rate": 1.995508583399838e-05, | |
| "loss": 0.1036555290222168, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.059534011587451564, | |
| "grad_norm": 0.2516411542892456, | |
| "learning_rate": 1.9954364302578598e-05, | |
| "loss": 0.09806258678436279, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.05976839745984311, | |
| "grad_norm": 0.28333738446235657, | |
| "learning_rate": 1.9953637034918523e-05, | |
| "loss": 0.10205515623092651, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.06000278333223465, | |
| "grad_norm": 0.26888540387153625, | |
| "learning_rate": 1.9952904031437236e-05, | |
| "loss": 0.10150589942932128, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.06023716920462619, | |
| "grad_norm": 0.28422436118125916, | |
| "learning_rate": 1.9952165292557143e-05, | |
| "loss": 0.09607882499694824, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.060471555077017736, | |
| "grad_norm": 0.2646063566207886, | |
| "learning_rate": 1.9951420818703935e-05, | |
| "loss": 0.0985830307006836, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.06070594094940927, | |
| "grad_norm": 0.2686246931552887, | |
| "learning_rate": 1.9950670610306625e-05, | |
| "loss": 0.10168079137802125, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.06094032682180082, | |
| "grad_norm": 0.2655580937862396, | |
| "learning_rate": 1.994991466779752e-05, | |
| "loss": 0.10096908807754516, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.061174712694192356, | |
| "grad_norm": 0.3549988269805908, | |
| "learning_rate": 1.9949152991612236e-05, | |
| "loss": 0.10471076965332031, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.0614090985665839, | |
| "grad_norm": 0.2887643277645111, | |
| "learning_rate": 1.9948385582189695e-05, | |
| "loss": 0.09757264256477356, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.06164348443897544, | |
| "grad_norm": 0.26402509212493896, | |
| "learning_rate": 1.994761243997211e-05, | |
| "loss": 0.09927420616149903, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.06187787031136698, | |
| "grad_norm": 0.25216010212898254, | |
| "learning_rate": 1.994683356540502e-05, | |
| "loss": 0.10259475708007812, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.06211225618375853, | |
| "grad_norm": 0.2457595318555832, | |
| "learning_rate": 1.9946048958937245e-05, | |
| "loss": 0.09863827228546143, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.062346642056150064, | |
| "grad_norm": 0.24635690450668335, | |
| "learning_rate": 1.994525862102092e-05, | |
| "loss": 0.09740403294563293, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.0625810279285416, | |
| "grad_norm": 0.2770674228668213, | |
| "learning_rate": 1.9944462552111482e-05, | |
| "loss": 0.09908512234687805, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.06281541380093315, | |
| "grad_norm": 0.2662931978702545, | |
| "learning_rate": 1.9943660752667667e-05, | |
| "loss": 0.10364282131195068, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.06304979967332469, | |
| "grad_norm": 0.2732428312301636, | |
| "learning_rate": 1.9942853223151514e-05, | |
| "loss": 0.10122396945953369, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.06328418554571623, | |
| "grad_norm": 0.2957812547683716, | |
| "learning_rate": 1.994203996402837e-05, | |
| "loss": 0.09913806319236755, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.06351857141810778, | |
| "grad_norm": 0.2504137456417084, | |
| "learning_rate": 1.9941220975766874e-05, | |
| "loss": 0.10005698204040528, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.06375295729049932, | |
| "grad_norm": 0.2572518587112427, | |
| "learning_rate": 1.9940396258838966e-05, | |
| "loss": 0.09756886959075928, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.06398734316289086, | |
| "grad_norm": 0.2348632514476776, | |
| "learning_rate": 1.9939565813719906e-05, | |
| "loss": 0.09779543280601502, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.0642217290352824, | |
| "grad_norm": 0.25319570302963257, | |
| "learning_rate": 1.993872964088823e-05, | |
| "loss": 0.10350990295410156, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.06445611490767394, | |
| "grad_norm": 0.26977482438087463, | |
| "learning_rate": 1.993788774082579e-05, | |
| "loss": 0.09852898716926575, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.06469050078006548, | |
| "grad_norm": 0.27146127820014954, | |
| "learning_rate": 1.9937040114017735e-05, | |
| "loss": 0.09648056030273437, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.06492488665245702, | |
| "grad_norm": 0.2358931303024292, | |
| "learning_rate": 1.9936186760952508e-05, | |
| "loss": 0.09882181882858276, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.06515927252484857, | |
| "grad_norm": 0.272926390171051, | |
| "learning_rate": 1.9935327682121866e-05, | |
| "loss": 0.10181998014450074, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.06539365839724011, | |
| "grad_norm": 0.25403040647506714, | |
| "learning_rate": 1.9934462878020844e-05, | |
| "loss": 0.09905003309249878, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.06562804426963165, | |
| "grad_norm": 0.2518831491470337, | |
| "learning_rate": 1.99335923491478e-05, | |
| "loss": 0.10159070491790771, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.06586243014202318, | |
| "grad_norm": 0.2731393575668335, | |
| "learning_rate": 1.9932716096004375e-05, | |
| "loss": 0.0981027603149414, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.06609681601441474, | |
| "grad_norm": 0.25448721647262573, | |
| "learning_rate": 1.9931834119095513e-05, | |
| "loss": 0.10141733884811402, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.06633120188680627, | |
| "grad_norm": 0.2541082203388214, | |
| "learning_rate": 1.9930946418929457e-05, | |
| "loss": 0.10162540674209594, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.06656558775919781, | |
| "grad_norm": 0.24208639562129974, | |
| "learning_rate": 1.9930052996017748e-05, | |
| "loss": 0.10364505052566528, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.06679997363158936, | |
| "grad_norm": 0.285247802734375, | |
| "learning_rate": 1.9929153850875225e-05, | |
| "loss": 0.10242388248443604, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.0670343595039809, | |
| "grad_norm": 0.26962780952453613, | |
| "learning_rate": 1.992824898402002e-05, | |
| "loss": 0.10025610923767089, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.06726874537637244, | |
| "grad_norm": 0.24651190638542175, | |
| "learning_rate": 1.992733839597357e-05, | |
| "loss": 0.09919982552528381, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.06750313124876398, | |
| "grad_norm": 0.2675532400608063, | |
| "learning_rate": 1.9926422087260605e-05, | |
| "loss": 0.09946922659873962, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.06773751712115553, | |
| "grad_norm": 0.2714926302433014, | |
| "learning_rate": 1.9925500058409147e-05, | |
| "loss": 0.09951109886169433, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.06797190299354706, | |
| "grad_norm": 0.2618255913257599, | |
| "learning_rate": 1.9924572309950523e-05, | |
| "loss": 0.0979630172252655, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.0682062888659386, | |
| "grad_norm": 0.24111329019069672, | |
| "learning_rate": 1.992363884241935e-05, | |
| "loss": 0.09887909889221191, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.06844067473833015, | |
| "grad_norm": 0.253558874130249, | |
| "learning_rate": 1.9922699656353544e-05, | |
| "loss": 0.09874061942100525, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.06867506061072169, | |
| "grad_norm": 0.2613140046596527, | |
| "learning_rate": 1.992175475229431e-05, | |
| "loss": 0.102379310131073, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.06890944648311323, | |
| "grad_norm": 0.24305768311023712, | |
| "learning_rate": 1.9920804130786154e-05, | |
| "loss": 0.09398667812347412, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.06914383235550477, | |
| "grad_norm": 0.2555887699127197, | |
| "learning_rate": 1.9919847792376883e-05, | |
| "loss": 0.10116375684738159, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.06937821822789632, | |
| "grad_norm": 0.2499028593301773, | |
| "learning_rate": 1.991888573761758e-05, | |
| "loss": 0.10240293741226196, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.06961260410028786, | |
| "grad_norm": 0.25849130749702454, | |
| "learning_rate": 1.991791796706264e-05, | |
| "loss": 0.10004898309707641, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.0698469899726794, | |
| "grad_norm": 0.2523442804813385, | |
| "learning_rate": 1.9916944481269737e-05, | |
| "loss": 0.09540088772773743, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.07008137584507095, | |
| "grad_norm": 0.26065507531166077, | |
| "learning_rate": 1.9915965280799853e-05, | |
| "loss": 0.10101289749145508, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.07031576171746248, | |
| "grad_norm": 0.2680308222770691, | |
| "learning_rate": 1.9914980366217253e-05, | |
| "loss": 0.09616921544075012, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.07055014758985402, | |
| "grad_norm": 0.2500920295715332, | |
| "learning_rate": 1.99139897380895e-05, | |
| "loss": 0.10100579261779785, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.07078453346224556, | |
| "grad_norm": 0.25104743242263794, | |
| "learning_rate": 1.9912993396987444e-05, | |
| "loss": 0.09979425072669983, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.07101891933463711, | |
| "grad_norm": 0.2475253939628601, | |
| "learning_rate": 1.991199134348523e-05, | |
| "loss": 0.09667822122573852, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.07125330520702865, | |
| "grad_norm": 0.2536265552043915, | |
| "learning_rate": 1.99109835781603e-05, | |
| "loss": 0.09792364835739135, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.07148769107942018, | |
| "grad_norm": 0.2577130198478699, | |
| "learning_rate": 1.9909970101593378e-05, | |
| "loss": 0.09835001230239868, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.07172207695181174, | |
| "grad_norm": 0.25029686093330383, | |
| "learning_rate": 1.9908950914368487e-05, | |
| "loss": 0.09796052575111389, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.07195646282420327, | |
| "grad_norm": 0.23914887011051178, | |
| "learning_rate": 1.9907926017072932e-05, | |
| "loss": 0.0987473726272583, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.07219084869659481, | |
| "grad_norm": 0.24877937138080597, | |
| "learning_rate": 1.990689541029732e-05, | |
| "loss": 0.10078320503234864, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.07242523456898635, | |
| "grad_norm": 0.2453630566596985, | |
| "learning_rate": 1.990585909463554e-05, | |
| "loss": 0.09731289148330688, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.0726596204413779, | |
| "grad_norm": 0.26139035820961, | |
| "learning_rate": 1.9904817070684773e-05, | |
| "loss": 0.1011696696281433, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.07289400631376944, | |
| "grad_norm": 0.2525120973587036, | |
| "learning_rate": 1.990376933904549e-05, | |
| "loss": 0.09903097748756409, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.07312839218616098, | |
| "grad_norm": 0.2420421689748764, | |
| "learning_rate": 1.9902715900321446e-05, | |
| "loss": 0.09905420541763306, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.07336277805855253, | |
| "grad_norm": 0.2517470121383667, | |
| "learning_rate": 1.9901656755119694e-05, | |
| "loss": 0.09957172870635986, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.07359716393094407, | |
| "grad_norm": 0.2818022668361664, | |
| "learning_rate": 1.990059190405057e-05, | |
| "loss": 0.09472342133522034, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.0738315498033356, | |
| "grad_norm": 0.23709538578987122, | |
| "learning_rate": 1.989952134772769e-05, | |
| "loss": 0.09947357177734376, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.07406593567572714, | |
| "grad_norm": 0.22681857645511627, | |
| "learning_rate": 1.9898445086767984e-05, | |
| "loss": 0.09621384143829345, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.07430032154811869, | |
| "grad_norm": 0.27160051465034485, | |
| "learning_rate": 1.9897363121791634e-05, | |
| "loss": 0.10093357563018798, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.07453470742051023, | |
| "grad_norm": 0.24737612903118134, | |
| "learning_rate": 1.9896275453422137e-05, | |
| "loss": 0.09624905586242676, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.07476909329290177, | |
| "grad_norm": 0.2514803111553192, | |
| "learning_rate": 1.989518208228626e-05, | |
| "loss": 0.09662477970123291, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.07500347916529332, | |
| "grad_norm": 0.26822003722190857, | |
| "learning_rate": 1.9894083009014064e-05, | |
| "loss": 0.1020202398300171, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.07523786503768486, | |
| "grad_norm": 0.2461136430501938, | |
| "learning_rate": 1.98929782342389e-05, | |
| "loss": 0.10071293115615845, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 0.0754722509100764, | |
| "grad_norm": 0.25979340076446533, | |
| "learning_rate": 1.9891867758597386e-05, | |
| "loss": 0.09892451167106628, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.07570663678246793, | |
| "grad_norm": 0.26687169075012207, | |
| "learning_rate": 1.9890751582729447e-05, | |
| "loss": 0.09821947813034057, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 0.07594102265485948, | |
| "grad_norm": 0.24391818046569824, | |
| "learning_rate": 1.9889629707278287e-05, | |
| "loss": 0.09522389173507691, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.07617540852725102, | |
| "grad_norm": 0.27298569679260254, | |
| "learning_rate": 1.9888502132890382e-05, | |
| "loss": 0.0995317280292511, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.07640979439964256, | |
| "grad_norm": 0.26171112060546875, | |
| "learning_rate": 1.9887368860215505e-05, | |
| "loss": 0.0962512195110321, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.07664418027203411, | |
| "grad_norm": 0.2542007267475128, | |
| "learning_rate": 1.988622988990671e-05, | |
| "loss": 0.0960867702960968, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 0.07687856614442565, | |
| "grad_norm": 0.2614597976207733, | |
| "learning_rate": 1.988508522262033e-05, | |
| "loss": 0.10188798904418946, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.07711295201681719, | |
| "grad_norm": 0.2572106122970581, | |
| "learning_rate": 1.9883934859015984e-05, | |
| "loss": 0.1032893180847168, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 0.07734733788920872, | |
| "grad_norm": 0.23633244633674622, | |
| "learning_rate": 1.9882778799756578e-05, | |
| "loss": 0.09361481070518493, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.07758172376160027, | |
| "grad_norm": 0.2835707664489746, | |
| "learning_rate": 1.988161704550829e-05, | |
| "loss": 0.09952925443649292, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 0.07781610963399181, | |
| "grad_norm": 0.24982769787311554, | |
| "learning_rate": 1.9880449596940592e-05, | |
| "loss": 0.10030505657196045, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.07805049550638335, | |
| "grad_norm": 0.2490740567445755, | |
| "learning_rate": 1.987927645472622e-05, | |
| "loss": 0.09545428156852723, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 0.0782848813787749, | |
| "grad_norm": 0.2633962631225586, | |
| "learning_rate": 1.9878097619541216e-05, | |
| "loss": 0.09645770788192749, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.07851926725116644, | |
| "grad_norm": 0.23084695637226105, | |
| "learning_rate": 1.9876913092064873e-05, | |
| "loss": 0.09904928803443909, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.07875365312355798, | |
| "grad_norm": 0.23052991926670074, | |
| "learning_rate": 1.987572287297979e-05, | |
| "loss": 0.0964333474636078, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.07898803899594951, | |
| "grad_norm": 0.23603223264217377, | |
| "learning_rate": 1.987452696297183e-05, | |
| "loss": 0.09768587946891785, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 0.07922242486834107, | |
| "grad_norm": 0.2493145614862442, | |
| "learning_rate": 1.9873325362730144e-05, | |
| "loss": 0.09757353067398071, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.0794568107407326, | |
| "grad_norm": 0.23746788501739502, | |
| "learning_rate": 1.987211807294716e-05, | |
| "loss": 0.0977285385131836, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 0.07969119661312414, | |
| "grad_norm": 0.24295686185359955, | |
| "learning_rate": 1.9870905094318576e-05, | |
| "loss": 0.09761766195297242, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.07992558248551569, | |
| "grad_norm": 0.27508994936943054, | |
| "learning_rate": 1.9869686427543386e-05, | |
| "loss": 0.09971782565116882, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 0.08015996835790723, | |
| "grad_norm": 0.2461894452571869, | |
| "learning_rate": 1.986846207332384e-05, | |
| "loss": 0.09590293169021606, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.08039435423029877, | |
| "grad_norm": 0.24693821370601654, | |
| "learning_rate": 1.9867232032365484e-05, | |
| "loss": 0.0998963713645935, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 0.0806287401026903, | |
| "grad_norm": 0.2588333785533905, | |
| "learning_rate": 1.9865996305377134e-05, | |
| "loss": 0.09864089488983155, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.08086312597508186, | |
| "grad_norm": 0.25416141748428345, | |
| "learning_rate": 1.986475489307088e-05, | |
| "loss": 0.09738174676895142, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.0810975118474734, | |
| "grad_norm": 0.2596873641014099, | |
| "learning_rate": 1.986350779616209e-05, | |
| "loss": 0.09710718989372254, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.08133189771986493, | |
| "grad_norm": 0.24456380307674408, | |
| "learning_rate": 1.986225501536941e-05, | |
| "loss": 0.09537820219993591, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 0.08156628359225648, | |
| "grad_norm": 0.26090583205223083, | |
| "learning_rate": 1.9860996551414756e-05, | |
| "loss": 0.09760335087776184, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.08180066946464802, | |
| "grad_norm": 0.25346025824546814, | |
| "learning_rate": 1.9859732405023332e-05, | |
| "loss": 0.09759787917137146, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 0.08203505533703956, | |
| "grad_norm": 0.2648662328720093, | |
| "learning_rate": 1.98584625769236e-05, | |
| "loss": 0.09515713453292847, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.0822694412094311, | |
| "grad_norm": 0.24194453656673431, | |
| "learning_rate": 1.98571870678473e-05, | |
| "loss": 0.09653838872909545, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 0.08250382708182265, | |
| "grad_norm": 0.24655663967132568, | |
| "learning_rate": 1.9855905878529455e-05, | |
| "loss": 0.09520291686058044, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.08273821295421419, | |
| "grad_norm": 0.2518446743488312, | |
| "learning_rate": 1.9854619009708356e-05, | |
| "loss": 0.09346435070037842, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 0.08297259882660572, | |
| "grad_norm": 0.22469614446163177, | |
| "learning_rate": 1.9853326462125563e-05, | |
| "loss": 0.09370574355125427, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.08320698469899727, | |
| "grad_norm": 0.25860902667045593, | |
| "learning_rate": 1.985202823652591e-05, | |
| "loss": 0.0952832818031311, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.08344137057138881, | |
| "grad_norm": 0.24837590754032135, | |
| "learning_rate": 1.9850724333657505e-05, | |
| "loss": 0.09452325105667114, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.08367575644378035, | |
| "grad_norm": 0.24337328970432281, | |
| "learning_rate": 1.9849414754271728e-05, | |
| "loss": 0.10293822288513184, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 0.08391014231617189, | |
| "grad_norm": 0.2375827431678772, | |
| "learning_rate": 1.9848099499123235e-05, | |
| "loss": 0.09826892614364624, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.08414452818856344, | |
| "grad_norm": 0.25366494059562683, | |
| "learning_rate": 1.9846778568969938e-05, | |
| "loss": 0.09723625183105469, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 0.08437891406095498, | |
| "grad_norm": 0.23969712853431702, | |
| "learning_rate": 1.9845451964573034e-05, | |
| "loss": 0.09802864789962769, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.08461329993334651, | |
| "grad_norm": 0.23336990177631378, | |
| "learning_rate": 1.9844119686696977e-05, | |
| "loss": 0.09494391083717346, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 0.08484768580573807, | |
| "grad_norm": 0.235444575548172, | |
| "learning_rate": 1.98427817361095e-05, | |
| "loss": 0.09131643772125245, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.0850820716781296, | |
| "grad_norm": 0.23032870888710022, | |
| "learning_rate": 1.984143811358161e-05, | |
| "loss": 0.09573459029197692, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 0.08531645755052114, | |
| "grad_norm": 0.23937658965587616, | |
| "learning_rate": 1.9840088819887565e-05, | |
| "loss": 0.09996015429496766, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.08555084342291268, | |
| "grad_norm": 0.24653863906860352, | |
| "learning_rate": 1.9838733855804902e-05, | |
| "loss": 0.09477783441543579, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.08578522929530423, | |
| "grad_norm": 0.25124043226242065, | |
| "learning_rate": 1.9837373222114428e-05, | |
| "loss": 0.09672245383262634, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.08601961516769577, | |
| "grad_norm": 0.2511589229106903, | |
| "learning_rate": 1.983600691960021e-05, | |
| "loss": 0.09629061818122864, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 0.0862540010400873, | |
| "grad_norm": 0.2269066572189331, | |
| "learning_rate": 1.9834634949049586e-05, | |
| "loss": 0.0972110390663147, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.08648838691247886, | |
| "grad_norm": 0.23792436718940735, | |
| "learning_rate": 1.983325731125316e-05, | |
| "loss": 0.09729048609733582, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 0.0867227727848704, | |
| "grad_norm": 0.2454032003879547, | |
| "learning_rate": 1.98318740070048e-05, | |
| "loss": 0.09432913661003113, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.08695715865726193, | |
| "grad_norm": 0.2414274960756302, | |
| "learning_rate": 1.983048503710164e-05, | |
| "loss": 0.09333533644676209, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 0.08719154452965347, | |
| "grad_norm": 0.2480117529630661, | |
| "learning_rate": 1.982909040234408e-05, | |
| "loss": 0.09618304371833801, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.08742593040204502, | |
| "grad_norm": 0.23502829670906067, | |
| "learning_rate": 1.9827690103535787e-05, | |
| "loss": 0.09364211559295654, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 0.08766031627443656, | |
| "grad_norm": 0.24081166088581085, | |
| "learning_rate": 1.9826284141483684e-05, | |
| "loss": 0.09827250838279725, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.0878947021468281, | |
| "grad_norm": 0.2612898051738739, | |
| "learning_rate": 1.982487251699796e-05, | |
| "loss": 0.09838377237319947, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.08812908801921965, | |
| "grad_norm": 0.2390422821044922, | |
| "learning_rate": 1.9823455230892075e-05, | |
| "loss": 0.09558175802230835, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.08836347389161119, | |
| "grad_norm": 0.24075160920619965, | |
| "learning_rate": 1.9822032283982742e-05, | |
| "loss": 0.09991474747657776, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 0.08859785976400272, | |
| "grad_norm": 0.22865113615989685, | |
| "learning_rate": 1.982060367708994e-05, | |
| "loss": 0.09180349111557007, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.08883224563639426, | |
| "grad_norm": 0.3339390754699707, | |
| "learning_rate": 1.981916941103691e-05, | |
| "loss": 0.09643151164054871, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 0.08906663150878581, | |
| "grad_norm": 0.22869139909744263, | |
| "learning_rate": 1.9817729486650153e-05, | |
| "loss": 0.09396811723709106, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.08930101738117735, | |
| "grad_norm": 0.2341780811548233, | |
| "learning_rate": 1.981628390475943e-05, | |
| "loss": 0.09621808528900147, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 0.08953540325356889, | |
| "grad_norm": 0.2384805977344513, | |
| "learning_rate": 1.9814832666197765e-05, | |
| "loss": 0.09238668084144593, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.08976978912596044, | |
| "grad_norm": 0.2264566868543625, | |
| "learning_rate": 1.9813375771801437e-05, | |
| "loss": 0.09774394631385804, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 0.09000417499835198, | |
| "grad_norm": 0.23572641611099243, | |
| "learning_rate": 1.9811913222409986e-05, | |
| "loss": 0.09363995790481568, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.09023856087074351, | |
| "grad_norm": 0.2336873710155487, | |
| "learning_rate": 1.9810445018866215e-05, | |
| "loss": 0.09437603950500488, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.09047294674313505, | |
| "grad_norm": 0.24012072384357452, | |
| "learning_rate": 1.9808971162016183e-05, | |
| "loss": 0.09632388353347779, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.0907073326155266, | |
| "grad_norm": 0.21895694732666016, | |
| "learning_rate": 1.98074916527092e-05, | |
| "loss": 0.09226862192153931, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 0.09094171848791814, | |
| "grad_norm": 0.23330460488796234, | |
| "learning_rate": 1.9806006491797845e-05, | |
| "loss": 0.09779489040374756, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.09117610436030968, | |
| "grad_norm": 0.22884823381900787, | |
| "learning_rate": 1.9804515680137944e-05, | |
| "loss": 0.09680858254432678, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 0.09141049023270123, | |
| "grad_norm": 0.23938292264938354, | |
| "learning_rate": 1.9803019218588587e-05, | |
| "loss": 0.0956246554851532, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.09164487610509277, | |
| "grad_norm": 0.23141860961914062, | |
| "learning_rate": 1.9801517108012107e-05, | |
| "loss": 0.09357759952545167, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 0.0918792619774843, | |
| "grad_norm": 0.22961118817329407, | |
| "learning_rate": 1.980000934927411e-05, | |
| "loss": 0.09144994616508484, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.09211364784987584, | |
| "grad_norm": 0.2457009255886078, | |
| "learning_rate": 1.9798495943243442e-05, | |
| "loss": 0.09539741277694702, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 0.0923480337222674, | |
| "grad_norm": 0.2407168745994568, | |
| "learning_rate": 1.9796976890792212e-05, | |
| "loss": 0.09906752109527588, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.09258241959465893, | |
| "grad_norm": 0.23279158771038055, | |
| "learning_rate": 1.9795452192795777e-05, | |
| "loss": 0.0976353108882904, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.09281680546705047, | |
| "grad_norm": 0.23886136710643768, | |
| "learning_rate": 1.9793921850132754e-05, | |
| "loss": 0.09300338625907897, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.09305119133944202, | |
| "grad_norm": 0.2225753515958786, | |
| "learning_rate": 1.9792385863685008e-05, | |
| "loss": 0.09286441206932068, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 0.09328557721183356, | |
| "grad_norm": 0.25730594992637634, | |
| "learning_rate": 1.9790844234337652e-05, | |
| "loss": 0.0958833634853363, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.0935199630842251, | |
| "grad_norm": 0.2208249270915985, | |
| "learning_rate": 1.9789296962979062e-05, | |
| "loss": 0.09462381601333618, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 0.09375434895661663, | |
| "grad_norm": 0.2539410889148712, | |
| "learning_rate": 1.9787744050500854e-05, | |
| "loss": 0.0970985472202301, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.09398873482900819, | |
| "grad_norm": 0.24547065794467926, | |
| "learning_rate": 1.9786185497797905e-05, | |
| "loss": 0.09270370006561279, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 0.09422312070139972, | |
| "grad_norm": 0.21373350918293, | |
| "learning_rate": 1.978462130576833e-05, | |
| "loss": 0.09532421827316284, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.09445750657379126, | |
| "grad_norm": 0.22722873091697693, | |
| "learning_rate": 1.978305147531351e-05, | |
| "loss": 0.09954251050949096, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 0.09469189244618281, | |
| "grad_norm": 0.23587945103645325, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 0.09665398001670837, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.09492627831857435, | |
| "grad_norm": 0.2414003163576126, | |
| "learning_rate": 1.9779894902749847e-05, | |
| "loss": 0.09357191920280457, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.09516066419096589, | |
| "grad_norm": 0.20647630095481873, | |
| "learning_rate": 1.9778308162459993e-05, | |
| "loss": 0.09053308963775634, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.09539505006335743, | |
| "grad_norm": 0.23781977593898773, | |
| "learning_rate": 1.977671578738286e-05, | |
| "loss": 0.09778456687927246, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 0.09562943593574898, | |
| "grad_norm": 0.30146169662475586, | |
| "learning_rate": 1.977511777843606e-05, | |
| "loss": 0.09628196954727172, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.09586382180814051, | |
| "grad_norm": 0.2778559923171997, | |
| "learning_rate": 1.977351413654046e-05, | |
| "loss": 0.09867449402809143, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 0.09609820768053205, | |
| "grad_norm": 0.23800766468048096, | |
| "learning_rate": 1.9771904862620153e-05, | |
| "loss": 0.09480830430984497, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.0963325935529236, | |
| "grad_norm": 0.22861213982105255, | |
| "learning_rate": 1.9770289957602493e-05, | |
| "loss": 0.09864791631698608, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 0.09656697942531514, | |
| "grad_norm": 0.22815021872520447, | |
| "learning_rate": 1.976866942241808e-05, | |
| "loss": 0.09667736291885376, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.09680136529770668, | |
| "grad_norm": 0.23416341841220856, | |
| "learning_rate": 1.976704325800075e-05, | |
| "loss": 0.09581059217453003, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 0.09703575117009822, | |
| "grad_norm": 0.22242465615272522, | |
| "learning_rate": 1.9765411465287587e-05, | |
| "loss": 0.09738817811012268, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.09727013704248977, | |
| "grad_norm": 0.22200895845890045, | |
| "learning_rate": 1.9763774045218916e-05, | |
| "loss": 0.09585686922073364, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.0975045229148813, | |
| "grad_norm": 0.24173030257225037, | |
| "learning_rate": 1.9762130998738307e-05, | |
| "loss": 0.09692124128341675, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.09773890878727284, | |
| "grad_norm": 0.22302596271038055, | |
| "learning_rate": 1.9760482326792574e-05, | |
| "loss": 0.09782094955444336, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 0.0979732946596644, | |
| "grad_norm": 0.21544748544692993, | |
| "learning_rate": 1.975882803033177e-05, | |
| "loss": 0.08959999084472656, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.09820768053205593, | |
| "grad_norm": 0.2426128089427948, | |
| "learning_rate": 1.975716811030919e-05, | |
| "loss": 0.09736834764480591, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 0.09844206640444747, | |
| "grad_norm": 0.24294038116931915, | |
| "learning_rate": 1.9755502567681362e-05, | |
| "loss": 0.09966242909431458, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.09867645227683901, | |
| "grad_norm": 0.23231154680252075, | |
| "learning_rate": 1.9753831403408076e-05, | |
| "loss": 0.09645105600357055, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 0.09891083814923056, | |
| "grad_norm": 0.24394413828849792, | |
| "learning_rate": 1.975215461845233e-05, | |
| "loss": 0.09449782967567444, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.0991452240216221, | |
| "grad_norm": 0.23751017451286316, | |
| "learning_rate": 1.9750472213780393e-05, | |
| "loss": 0.09705086350440979, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 0.09937960989401363, | |
| "grad_norm": 0.23274391889572144, | |
| "learning_rate": 1.9748784190361743e-05, | |
| "loss": 0.09089593291282654, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.09961399576640519, | |
| "grad_norm": 0.25115707516670227, | |
| "learning_rate": 1.9747090549169117e-05, | |
| "loss": 0.09281798601150512, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.09984838163879672, | |
| "grad_norm": 0.22884058952331543, | |
| "learning_rate": 1.9745391291178487e-05, | |
| "loss": 0.09412742257118226, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.10008276751118826, | |
| "grad_norm": 0.23018816113471985, | |
| "learning_rate": 1.974368641736905e-05, | |
| "loss": 0.09431731700897217, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 0.1003171533835798, | |
| "grad_norm": 0.2526938319206238, | |
| "learning_rate": 1.9741975928723248e-05, | |
| "loss": 0.09406562447547913, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.10055153925597135, | |
| "grad_norm": 0.23338615894317627, | |
| "learning_rate": 1.9740259826226754e-05, | |
| "loss": 0.09766570329666138, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 0.10078592512836289, | |
| "grad_norm": 0.22235698997974396, | |
| "learning_rate": 1.9738538110868483e-05, | |
| "loss": 0.09488759636878967, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.10102031100075443, | |
| "grad_norm": 0.25075283646583557, | |
| "learning_rate": 1.973681078364058e-05, | |
| "loss": 0.09644614458084107, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 0.10125469687314598, | |
| "grad_norm": 0.21953310072422028, | |
| "learning_rate": 1.9735077845538416e-05, | |
| "loss": 0.0908882200717926, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.10148908274553751, | |
| "grad_norm": 0.24634884297847748, | |
| "learning_rate": 1.9733339297560617e-05, | |
| "loss": 0.09361082315444946, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 0.10172346861792905, | |
| "grad_norm": 0.23937328159809113, | |
| "learning_rate": 1.9731595140709014e-05, | |
| "loss": 0.0879040777683258, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.10195785449032059, | |
| "grad_norm": 0.2418578416109085, | |
| "learning_rate": 1.9729845375988694e-05, | |
| "loss": 0.09273046851158143, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.10219224036271214, | |
| "grad_norm": 0.22532379627227783, | |
| "learning_rate": 1.9728090004407957e-05, | |
| "loss": 0.09399214386940002, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.10242662623510368, | |
| "grad_norm": 0.22561515867710114, | |
| "learning_rate": 1.9726329026978352e-05, | |
| "loss": 0.0966880202293396, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 0.10266101210749522, | |
| "grad_norm": 0.2344096302986145, | |
| "learning_rate": 1.9724562444714642e-05, | |
| "loss": 0.09638426303863526, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.10289539797988677, | |
| "grad_norm": 0.225719153881073, | |
| "learning_rate": 1.972279025863483e-05, | |
| "loss": 0.09435364007949829, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 0.1031297838522783, | |
| "grad_norm": 0.2316310703754425, | |
| "learning_rate": 1.9721012469760142e-05, | |
| "loss": 0.09278578162193299, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.10336416972466984, | |
| "grad_norm": 0.32076817750930786, | |
| "learning_rate": 1.9719229079115037e-05, | |
| "loss": 0.0939367413520813, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 0.10359855559706138, | |
| "grad_norm": 0.2274835854768753, | |
| "learning_rate": 1.9717440087727204e-05, | |
| "loss": 0.09314810037612915, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.10383294146945293, | |
| "grad_norm": 0.2332312911748886, | |
| "learning_rate": 1.9715645496627548e-05, | |
| "loss": 0.09466577768325805, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 0.10406732734184447, | |
| "grad_norm": 0.2384312003850937, | |
| "learning_rate": 1.971384530685022e-05, | |
| "loss": 0.09577916860580445, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.10430171321423601, | |
| "grad_norm": 0.22498412430286407, | |
| "learning_rate": 1.9712039519432577e-05, | |
| "loss": 0.09781519174575806, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.10453609908662756, | |
| "grad_norm": 0.2251872569322586, | |
| "learning_rate": 1.9710228135415215e-05, | |
| "loss": 0.09909622669219971, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.1047704849590191, | |
| "grad_norm": 0.21877743303775787, | |
| "learning_rate": 1.970841115584195e-05, | |
| "loss": 0.09469491243362427, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 0.10500487083141063, | |
| "grad_norm": 0.22527791559696198, | |
| "learning_rate": 1.9706588581759822e-05, | |
| "loss": 0.09495667815208435, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.10523925670380217, | |
| "grad_norm": 0.22535377740859985, | |
| "learning_rate": 1.9704760414219103e-05, | |
| "loss": 0.09554814100265503, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 0.10547364257619372, | |
| "grad_norm": 0.24218642711639404, | |
| "learning_rate": 1.9702926654273268e-05, | |
| "loss": 0.09457748532295226, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.10570802844858526, | |
| "grad_norm": 0.2455141395330429, | |
| "learning_rate": 1.970108730297904e-05, | |
| "loss": 0.09385570287704467, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 0.1059424143209768, | |
| "grad_norm": 0.23144005239009857, | |
| "learning_rate": 1.9699242361396352e-05, | |
| "loss": 0.09370056986808777, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.10617680019336835, | |
| "grad_norm": 0.2208258956670761, | |
| "learning_rate": 1.9697391830588352e-05, | |
| "loss": 0.09559195041656494, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 0.10641118606575989, | |
| "grad_norm": 0.23533989489078522, | |
| "learning_rate": 1.969553571162142e-05, | |
| "loss": 0.09394575357437134, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.10664557193815143, | |
| "grad_norm": 0.23762735724449158, | |
| "learning_rate": 1.969367400556515e-05, | |
| "loss": 0.09339027404785157, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.10687995781054296, | |
| "grad_norm": 0.24431352317333221, | |
| "learning_rate": 1.9691806713492355e-05, | |
| "loss": 0.09555701017379761, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.10711434368293452, | |
| "grad_norm": 0.24158154428005219, | |
| "learning_rate": 1.9689933836479076e-05, | |
| "loss": 0.09148794412612915, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 0.10734872955532605, | |
| "grad_norm": 0.23731191456317902, | |
| "learning_rate": 1.968805537560456e-05, | |
| "loss": 0.09808973073959351, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.10758311542771759, | |
| "grad_norm": 0.24656768143177032, | |
| "learning_rate": 1.9686171331951276e-05, | |
| "loss": 0.09351555109024048, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 0.10781750130010914, | |
| "grad_norm": 0.2201780080795288, | |
| "learning_rate": 1.9684281706604912e-05, | |
| "loss": 0.09151367545127868, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.10805188717250068, | |
| "grad_norm": 0.26106929779052734, | |
| "learning_rate": 1.9682386500654377e-05, | |
| "loss": 0.09554622173309327, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 0.10828627304489222, | |
| "grad_norm": 0.24652375280857086, | |
| "learning_rate": 1.9680485715191786e-05, | |
| "loss": 0.09829449653625488, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.10852065891728375, | |
| "grad_norm": 0.21742303669452667, | |
| "learning_rate": 1.9678579351312476e-05, | |
| "loss": 0.09160538911819457, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 0.1087550447896753, | |
| "grad_norm": 0.20726215839385986, | |
| "learning_rate": 1.9676667410114993e-05, | |
| "loss": 0.09404849410057067, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.10898943066206684, | |
| "grad_norm": 0.2141851931810379, | |
| "learning_rate": 1.9674749892701105e-05, | |
| "loss": 0.09068138599395752, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.10922381653445838, | |
| "grad_norm": 0.22479958832263947, | |
| "learning_rate": 1.9672826800175786e-05, | |
| "loss": 0.09121141433715821, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.10945820240684993, | |
| "grad_norm": 0.21579064428806305, | |
| "learning_rate": 1.9670898133647226e-05, | |
| "loss": 0.08935116529464722, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 0.10969258827924147, | |
| "grad_norm": 0.20952926576137543, | |
| "learning_rate": 1.9668963894226824e-05, | |
| "loss": 0.09583397507667542, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.10992697415163301, | |
| "grad_norm": 0.20717328786849976, | |
| "learning_rate": 1.9667024083029197e-05, | |
| "loss": 0.09277876615524291, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 0.11016136002402455, | |
| "grad_norm": 0.22909605503082275, | |
| "learning_rate": 1.9665078701172165e-05, | |
| "loss": 0.09534701704978943, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.1103957458964161, | |
| "grad_norm": 0.22040508687496185, | |
| "learning_rate": 1.966312774977677e-05, | |
| "loss": 0.0920095682144165, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 0.11063013176880764, | |
| "grad_norm": 0.24977952241897583, | |
| "learning_rate": 1.966117122996724e-05, | |
| "loss": 0.0967732012271881, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.11086451764119917, | |
| "grad_norm": 0.2372177690267563, | |
| "learning_rate": 1.9659209142871037e-05, | |
| "loss": 0.09182756543159484, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 0.11109890351359072, | |
| "grad_norm": 0.21527361869812012, | |
| "learning_rate": 1.9657241489618824e-05, | |
| "loss": 0.0896917998790741, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.11133328938598226, | |
| "grad_norm": 0.22934825718402863, | |
| "learning_rate": 1.965526827134446e-05, | |
| "loss": 0.09115242958068848, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.1115676752583738, | |
| "grad_norm": 0.22352270781993866, | |
| "learning_rate": 1.9653289489185024e-05, | |
| "loss": 0.09716107845306396, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.11180206113076534, | |
| "grad_norm": 0.21478617191314697, | |
| "learning_rate": 1.96513051442808e-05, | |
| "loss": 0.08914797306060791, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 0.11203644700315689, | |
| "grad_norm": 0.24973329901695251, | |
| "learning_rate": 1.964931523777527e-05, | |
| "loss": 0.08963323831558227, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.11227083287554843, | |
| "grad_norm": 0.23024708032608032, | |
| "learning_rate": 1.9647319770815123e-05, | |
| "loss": 0.09055772423744202, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 0.11250521874793996, | |
| "grad_norm": 0.2224258929491043, | |
| "learning_rate": 1.964531874455026e-05, | |
| "loss": 0.09596869945526124, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.11273960462033152, | |
| "grad_norm": 0.2195906788110733, | |
| "learning_rate": 1.964331216013378e-05, | |
| "loss": 0.0875722348690033, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 0.11297399049272305, | |
| "grad_norm": 0.22107210755348206, | |
| "learning_rate": 1.9641300018721977e-05, | |
| "loss": 0.09211227893829346, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.11320837636511459, | |
| "grad_norm": 0.2055511176586151, | |
| "learning_rate": 1.9639282321474368e-05, | |
| "loss": 0.09224797487258911, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 0.11344276223750613, | |
| "grad_norm": 0.21249008178710938, | |
| "learning_rate": 1.9637259069553643e-05, | |
| "loss": 0.09126865863800049, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.11367714810989768, | |
| "grad_norm": 0.2206508070230484, | |
| "learning_rate": 1.9635230264125724e-05, | |
| "loss": 0.09112058877944947, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.11391153398228922, | |
| "grad_norm": 0.22011403739452362, | |
| "learning_rate": 1.9633195906359704e-05, | |
| "loss": 0.09202954173088074, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.11414591985468076, | |
| "grad_norm": 0.24389015138149261, | |
| "learning_rate": 1.96311559974279e-05, | |
| "loss": 0.09100943207740783, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 0.1143803057270723, | |
| "grad_norm": 0.2410711795091629, | |
| "learning_rate": 1.9629110538505813e-05, | |
| "loss": 0.09183706045150757, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.11461469159946384, | |
| "grad_norm": 0.22952304780483246, | |
| "learning_rate": 1.9627059530772148e-05, | |
| "loss": 0.09171746373176574, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 0.11484907747185538, | |
| "grad_norm": 0.21583250164985657, | |
| "learning_rate": 1.96250029754088e-05, | |
| "loss": 0.08891347646713257, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.11508346334424692, | |
| "grad_norm": 0.22173185646533966, | |
| "learning_rate": 1.962294087360088e-05, | |
| "loss": 0.0954024076461792, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 0.11531784921663847, | |
| "grad_norm": 0.2237253487110138, | |
| "learning_rate": 1.9620873226536668e-05, | |
| "loss": 0.08858268260955811, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.11555223508903001, | |
| "grad_norm": 0.22095924615859985, | |
| "learning_rate": 1.961880003540766e-05, | |
| "loss": 0.09283017516136169, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 0.11578662096142155, | |
| "grad_norm": 0.21108508110046387, | |
| "learning_rate": 1.9616721301408538e-05, | |
| "loss": 0.0909350872039795, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.1160210068338131, | |
| "grad_norm": 0.21895809471607208, | |
| "learning_rate": 1.9614637025737186e-05, | |
| "loss": 0.09349902272224427, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.11625539270620464, | |
| "grad_norm": 0.2372807264328003, | |
| "learning_rate": 1.961254720959467e-05, | |
| "loss": 0.09002131223678589, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.11648977857859617, | |
| "grad_norm": 0.22921942174434662, | |
| "learning_rate": 1.9610451854185253e-05, | |
| "loss": 0.09196782112121582, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 0.11672416445098771, | |
| "grad_norm": 0.21088609099388123, | |
| "learning_rate": 1.96083509607164e-05, | |
| "loss": 0.09280639290809631, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.11695855032337926, | |
| "grad_norm": 0.21362151205539703, | |
| "learning_rate": 1.9606244530398753e-05, | |
| "loss": 0.08787336349487304, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 0.1171929361957708, | |
| "grad_norm": 0.23681169748306274, | |
| "learning_rate": 1.960413256444615e-05, | |
| "loss": 0.09669545888900757, | |
| "step": 5000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 42665, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.192784443610392e+19, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |