Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
unsloth
sft
trl
text-generation-inference
Instructions to use Ba2han/out2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/out2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ba2han/out2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ba2han/out2") model = AutoModelForCausalLM.from_pretrained("Ba2han/out2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Ba2han/out2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ba2han/out2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/out2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Ba2han/out2
- SGLang
How to use Ba2han/out2 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 "Ba2han/out2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/out2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Ba2han/out2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/out2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Unsloth Studio
How to use Ba2han/out2 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ba2han/out2 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ba2han/out2 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Ba2han/out2 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Ba2han/out2", max_seq_length=2048, ) - Docker Model Runner
How to use Ba2han/out2 with Docker Model Runner:
docker model run hf.co/Ba2han/out2
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09007874015748031, | |
| "eval_steps": 2858, | |
| "global_step": 1716, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010498687664041995, | |
| "grad_norm": 10.849783897399902, | |
| "learning_rate": 8.421052631578948e-06, | |
| "loss": 11.336052894592285, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002099737532808399, | |
| "grad_norm": 4.206523895263672, | |
| "learning_rate": 2.5263157894736845e-05, | |
| "loss": 10.710294723510742, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00031496062992125983, | |
| "grad_norm": 2.95147705078125, | |
| "learning_rate": 4.210526315789474e-05, | |
| "loss": 10.311192512512207, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004199475065616798, | |
| "grad_norm": 7.974979400634766, | |
| "learning_rate": 5.894736842105263e-05, | |
| "loss": 9.713238716125488, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005249343832020997, | |
| "grad_norm": 2.7956748008728027, | |
| "learning_rate": 7.578947368421054e-05, | |
| "loss": 9.508157730102539, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006299212598425197, | |
| "grad_norm": 11.139887809753418, | |
| "learning_rate": 9.263157894736843e-05, | |
| "loss": 9.507661819458008, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0007349081364829396, | |
| "grad_norm": 4.121689796447754, | |
| "learning_rate": 0.00010947368421052633, | |
| "loss": 9.094792366027832, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0008398950131233596, | |
| "grad_norm": 11.641839027404785, | |
| "learning_rate": 0.0001263157894736842, | |
| "loss": 8.865646362304688, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0009448818897637795, | |
| "grad_norm": 3.2739551067352295, | |
| "learning_rate": 0.0001431578947368421, | |
| "loss": 8.6943998336792, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0010498687664041995, | |
| "grad_norm": 3.3511805534362793, | |
| "learning_rate": 0.00016, | |
| "loss": 8.40627670288086, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011548556430446195, | |
| "grad_norm": 3.8193061351776123, | |
| "learning_rate": 0.0001768421052631579, | |
| "loss": 8.06525707244873, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0012598425196850393, | |
| "grad_norm": 2.8360342979431152, | |
| "learning_rate": 0.0001936842105263158, | |
| "loss": 8.069121360778809, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0013648293963254593, | |
| "grad_norm": 2.07961368560791, | |
| "learning_rate": 0.0002105263157894737, | |
| "loss": 7.9217634201049805, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0014698162729658792, | |
| "grad_norm": 1.3632010221481323, | |
| "learning_rate": 0.0002273684210526316, | |
| "loss": 7.819206714630127, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0015748031496062992, | |
| "grad_norm": 2.2996950149536133, | |
| "learning_rate": 0.0002442105263157895, | |
| "loss": 7.806654453277588, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0016797900262467192, | |
| "grad_norm": 0.5869771242141724, | |
| "learning_rate": 0.0002610526315789474, | |
| "loss": 7.715257167816162, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.001784776902887139, | |
| "grad_norm": 0.8440877795219421, | |
| "learning_rate": 0.0002778947368421053, | |
| "loss": 7.586756229400635, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.001889763779527559, | |
| "grad_norm": 0.774182140827179, | |
| "learning_rate": 0.00029473684210526316, | |
| "loss": 7.62679386138916, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.001994750656167979, | |
| "grad_norm": 0.5010451078414917, | |
| "learning_rate": 0.00031157894736842103, | |
| "loss": 7.545993328094482, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.002099737532808399, | |
| "grad_norm": 0.6951680183410645, | |
| "learning_rate": 0.00032842105263157896, | |
| "loss": 7.461381912231445, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002204724409448819, | |
| "grad_norm": 0.8257125020027161, | |
| "learning_rate": 0.00034526315789473684, | |
| "loss": 7.4312357902526855, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.002309711286089239, | |
| "grad_norm": 0.6842756271362305, | |
| "learning_rate": 0.00036210526315789477, | |
| "loss": 7.449553489685059, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0024146981627296586, | |
| "grad_norm": 0.7420353293418884, | |
| "learning_rate": 0.00037894736842105265, | |
| "loss": 7.360008239746094, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0025196850393700786, | |
| "grad_norm": 0.5558741688728333, | |
| "learning_rate": 0.0003957894736842105, | |
| "loss": 7.450737953186035, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0026246719160104987, | |
| "grad_norm": 1.2673524618148804, | |
| "learning_rate": 0.00041263157894736845, | |
| "loss": 7.304603576660156, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0027296587926509187, | |
| "grad_norm": 1.1506381034851074, | |
| "learning_rate": 0.00042947368421052633, | |
| "loss": 7.373305797576904, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0028346456692913387, | |
| "grad_norm": 1.34714937210083, | |
| "learning_rate": 0.0004463157894736842, | |
| "loss": 7.287379264831543, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0029396325459317583, | |
| "grad_norm": 1.8458038568496704, | |
| "learning_rate": 0.00046315789473684214, | |
| "loss": 7.345888137817383, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0030446194225721783, | |
| "grad_norm": 1.229347825050354, | |
| "learning_rate": 0.00048, | |
| "loss": 7.267388343811035, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0031496062992125984, | |
| "grad_norm": 1.0520741939544678, | |
| "learning_rate": 0.0004968421052631579, | |
| "loss": 7.2191925048828125, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0032545931758530184, | |
| "grad_norm": 1.0573132038116455, | |
| "learning_rate": 0.0005136842105263158, | |
| "loss": 7.139622211456299, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0033595800524934384, | |
| "grad_norm": 0.7959205508232117, | |
| "learning_rate": 0.0005305263157894737, | |
| "loss": 7.1705827713012695, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0034645669291338585, | |
| "grad_norm": 1.0648680925369263, | |
| "learning_rate": 0.0005473684210526316, | |
| "loss": 7.059314727783203, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.003569553805774278, | |
| "grad_norm": 1.2019802331924438, | |
| "learning_rate": 0.0005642105263157894, | |
| "loss": 7.1090087890625, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.003674540682414698, | |
| "grad_norm": 0.6939458250999451, | |
| "learning_rate": 0.0005810526315789474, | |
| "loss": 7.071786880493164, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.003779527559055118, | |
| "grad_norm": 0.5002018213272095, | |
| "learning_rate": 0.0005978947368421053, | |
| "loss": 7.020046234130859, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.003884514435695538, | |
| "grad_norm": 0.5465899109840393, | |
| "learning_rate": 0.0006147368421052632, | |
| "loss": 6.96237325668335, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.003989501312335958, | |
| "grad_norm": 0.9754618406295776, | |
| "learning_rate": 0.0006315789473684211, | |
| "loss": 6.940667152404785, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.004094488188976378, | |
| "grad_norm": 1.0599706172943115, | |
| "learning_rate": 0.0006484210526315789, | |
| "loss": 6.961879730224609, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.004199475065616798, | |
| "grad_norm": 0.9335948824882507, | |
| "learning_rate": 0.0006652631578947369, | |
| "loss": 6.944250106811523, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0043044619422572174, | |
| "grad_norm": 0.9988331198692322, | |
| "learning_rate": 0.0006821052631578948, | |
| "loss": 6.911154747009277, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.004409448818897638, | |
| "grad_norm": 0.8610116243362427, | |
| "learning_rate": 0.0006989473684210527, | |
| "loss": 6.893559455871582, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.0045144356955380575, | |
| "grad_norm": 0.7761997580528259, | |
| "learning_rate": 0.0007157894736842105, | |
| "loss": 6.926453590393066, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.004619422572178478, | |
| "grad_norm": 0.825920045375824, | |
| "learning_rate": 0.0007326315789473684, | |
| "loss": 6.813850402832031, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.004724409448818898, | |
| "grad_norm": 0.8140450119972229, | |
| "learning_rate": 0.0007494736842105264, | |
| "loss": 6.821445941925049, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.004829396325459317, | |
| "grad_norm": 0.5451359748840332, | |
| "learning_rate": 0.0007663157894736842, | |
| "loss": 6.663788795471191, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.004934383202099738, | |
| "grad_norm": 0.4969961941242218, | |
| "learning_rate": 0.0007831578947368422, | |
| "loss": 6.7580647468566895, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.005039370078740157, | |
| "grad_norm": 0.5622134804725647, | |
| "learning_rate": 0.0008, | |
| "loss": 6.753166198730469, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.005144356955380578, | |
| "grad_norm": 0.45332568883895874, | |
| "learning_rate": 0.0008, | |
| "loss": 6.61945104598999, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.005249343832020997, | |
| "grad_norm": 0.6089130640029907, | |
| "learning_rate": 0.0008, | |
| "loss": 6.531531810760498, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.005354330708661417, | |
| "grad_norm": 1.5867327451705933, | |
| "learning_rate": 0.0008, | |
| "loss": 6.609947204589844, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.005459317585301837, | |
| "grad_norm": 0.8609986901283264, | |
| "learning_rate": 0.0008, | |
| "loss": 6.586551189422607, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.005564304461942257, | |
| "grad_norm": 0.682275116443634, | |
| "learning_rate": 0.0008, | |
| "loss": 6.591581344604492, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.005669291338582677, | |
| "grad_norm": 0.8488819003105164, | |
| "learning_rate": 0.0008, | |
| "loss": 6.605495452880859, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.005774278215223097, | |
| "grad_norm": 0.8200653195381165, | |
| "learning_rate": 0.0008, | |
| "loss": 6.560756206512451, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.005879265091863517, | |
| "grad_norm": 0.859346330165863, | |
| "learning_rate": 0.0008, | |
| "loss": 6.440073490142822, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.005984251968503937, | |
| "grad_norm": 1.1621174812316895, | |
| "learning_rate": 0.0008, | |
| "loss": 6.41163444519043, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.006089238845144357, | |
| "grad_norm": 0.5757318735122681, | |
| "learning_rate": 0.0008, | |
| "loss": 6.400125503540039, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.006194225721784777, | |
| "grad_norm": 0.5290873050689697, | |
| "learning_rate": 0.0008, | |
| "loss": 6.3030877113342285, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.006299212598425197, | |
| "grad_norm": 1.0253428220748901, | |
| "learning_rate": 0.0008, | |
| "loss": 6.3230977058410645, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.006404199475065617, | |
| "grad_norm": 0.6795729398727417, | |
| "learning_rate": 0.0008, | |
| "loss": 6.3237199783325195, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.006509186351706037, | |
| "grad_norm": 0.861482560634613, | |
| "learning_rate": 0.0008, | |
| "loss": 6.25187873840332, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.006614173228346456, | |
| "grad_norm": 0.7200944423675537, | |
| "learning_rate": 0.0008, | |
| "loss": 6.1981401443481445, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.006719160104986877, | |
| "grad_norm": 0.6993811726570129, | |
| "learning_rate": 0.0008, | |
| "loss": 6.191583633422852, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.0068241469816272965, | |
| "grad_norm": 0.4931415915489197, | |
| "learning_rate": 0.0008, | |
| "loss": 6.107348442077637, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.006929133858267717, | |
| "grad_norm": 0.3714856803417206, | |
| "learning_rate": 0.0008, | |
| "loss": 6.135107040405273, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.0070341207349081366, | |
| "grad_norm": 0.4941980242729187, | |
| "learning_rate": 0.0008, | |
| "loss": 6.1131463050842285, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.007139107611548556, | |
| "grad_norm": 0.5307848453521729, | |
| "learning_rate": 0.0008, | |
| "loss": 6.129576683044434, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.007244094488188977, | |
| "grad_norm": 0.4134950041770935, | |
| "learning_rate": 0.0008, | |
| "loss": 6.058399200439453, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.007349081364829396, | |
| "grad_norm": 0.5328584313392639, | |
| "learning_rate": 0.0008, | |
| "loss": 6.038764476776123, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.007454068241469817, | |
| "grad_norm": 1.15119469165802, | |
| "learning_rate": 0.0008, | |
| "loss": 5.919521808624268, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.007559055118110236, | |
| "grad_norm": 0.6950765252113342, | |
| "learning_rate": 0.0008, | |
| "loss": 5.90153694152832, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.007664041994750656, | |
| "grad_norm": 0.607292115688324, | |
| "learning_rate": 0.0008, | |
| "loss": 5.805788993835449, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.007769028871391076, | |
| "grad_norm": 0.8245534896850586, | |
| "learning_rate": 0.0008, | |
| "loss": 5.942452907562256, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.007874015748031496, | |
| "grad_norm": 0.643883228302002, | |
| "learning_rate": 0.0008, | |
| "loss": 5.859640598297119, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.007979002624671916, | |
| "grad_norm": 0.6031001806259155, | |
| "learning_rate": 0.0008, | |
| "loss": 5.771254539489746, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.008083989501312335, | |
| "grad_norm": 0.3471139967441559, | |
| "learning_rate": 0.0008, | |
| "loss": 5.825682163238525, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.008188976377952756, | |
| "grad_norm": 0.35251903533935547, | |
| "learning_rate": 0.0008, | |
| "loss": 5.824915885925293, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.008293963254593176, | |
| "grad_norm": 0.5420740842819214, | |
| "learning_rate": 0.0008, | |
| "loss": 5.735776424407959, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.008398950131233596, | |
| "grad_norm": 0.5785290002822876, | |
| "learning_rate": 0.0008, | |
| "loss": 5.71408748626709, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.008503937007874015, | |
| "grad_norm": 0.5503653287887573, | |
| "learning_rate": 0.0008, | |
| "loss": 5.681863784790039, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.008608923884514435, | |
| "grad_norm": 0.38715237379074097, | |
| "learning_rate": 0.0008, | |
| "loss": 5.627864360809326, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.008713910761154856, | |
| "grad_norm": 0.47762763500213623, | |
| "learning_rate": 0.0008, | |
| "loss": 5.623003959655762, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.008818897637795276, | |
| "grad_norm": 0.7163979411125183, | |
| "learning_rate": 0.0008, | |
| "loss": 5.694301128387451, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.008923884514435695, | |
| "grad_norm": 0.5806844830513, | |
| "learning_rate": 0.0008, | |
| "loss": 5.556089878082275, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.009028871391076115, | |
| "grad_norm": 0.39758580923080444, | |
| "learning_rate": 0.0008, | |
| "loss": 5.631988048553467, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.009133858267716535, | |
| "grad_norm": 0.4177590012550354, | |
| "learning_rate": 0.0008, | |
| "loss": 5.465466022491455, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.009238845144356956, | |
| "grad_norm": 0.3706369400024414, | |
| "learning_rate": 0.0008, | |
| "loss": 5.473786354064941, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.009343832020997376, | |
| "grad_norm": 0.3802669942378998, | |
| "learning_rate": 0.0008, | |
| "loss": 5.476729393005371, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.009448818897637795, | |
| "grad_norm": 0.44668325781822205, | |
| "learning_rate": 0.0008, | |
| "loss": 5.477040767669678, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.009553805774278215, | |
| "grad_norm": 0.2561449408531189, | |
| "learning_rate": 0.0008, | |
| "loss": 5.360054016113281, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.009658792650918634, | |
| "grad_norm": 0.3362152874469757, | |
| "learning_rate": 0.0008, | |
| "loss": 5.358182907104492, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.009763779527559056, | |
| "grad_norm": 0.2856195569038391, | |
| "learning_rate": 0.0008, | |
| "loss": 5.342494010925293, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.009868766404199475, | |
| "grad_norm": 0.5502752661705017, | |
| "learning_rate": 0.0008, | |
| "loss": 5.342869758605957, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.009973753280839895, | |
| "grad_norm": 0.7680650353431702, | |
| "learning_rate": 0.0008, | |
| "loss": 5.356422424316406, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.010078740157480314, | |
| "grad_norm": 0.5406929850578308, | |
| "learning_rate": 0.0008, | |
| "loss": 5.300556182861328, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.010183727034120734, | |
| "grad_norm": 0.3668650984764099, | |
| "learning_rate": 0.0008, | |
| "loss": 5.367114067077637, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.010288713910761155, | |
| "grad_norm": 0.4027565121650696, | |
| "learning_rate": 0.0008, | |
| "loss": 5.251592636108398, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.010393700787401575, | |
| "grad_norm": 0.40343940258026123, | |
| "learning_rate": 0.0008, | |
| "loss": 5.276173114776611, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.010498687664041995, | |
| "grad_norm": 0.4856398105621338, | |
| "learning_rate": 0.0008, | |
| "loss": 5.210047245025635, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.010603674540682414, | |
| "grad_norm": 0.26983195543289185, | |
| "learning_rate": 0.0008, | |
| "loss": 5.17520809173584, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.010708661417322834, | |
| "grad_norm": 0.25971466302871704, | |
| "learning_rate": 0.0008, | |
| "loss": 5.155277252197266, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.010813648293963255, | |
| "grad_norm": 0.2467920333147049, | |
| "learning_rate": 0.0008, | |
| "loss": 5.207974910736084, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.010918635170603675, | |
| "grad_norm": 0.27808240056037903, | |
| "learning_rate": 0.0008, | |
| "loss": 5.16036319732666, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.011023622047244094, | |
| "grad_norm": 0.287492960691452, | |
| "learning_rate": 0.0008, | |
| "loss": 5.079829692840576, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.011128608923884514, | |
| "grad_norm": 0.25132930278778076, | |
| "learning_rate": 0.0008, | |
| "loss": 5.055511474609375, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.011233595800524934, | |
| "grad_norm": 0.44570592045783997, | |
| "learning_rate": 0.0008, | |
| "loss": 5.137527942657471, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.011338582677165355, | |
| "grad_norm": 0.5238414406776428, | |
| "learning_rate": 0.0008, | |
| "loss": 5.096850872039795, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.011443569553805774, | |
| "grad_norm": 0.46957311034202576, | |
| "learning_rate": 0.0008, | |
| "loss": 5.067659378051758, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.011548556430446194, | |
| "grad_norm": 0.535942792892456, | |
| "learning_rate": 0.0008, | |
| "loss": 5.147111415863037, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.011653543307086614, | |
| "grad_norm": 0.4777580797672272, | |
| "learning_rate": 0.0008, | |
| "loss": 5.075133800506592, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.011758530183727033, | |
| "grad_norm": 0.31084227561950684, | |
| "learning_rate": 0.0008, | |
| "loss": 5.079253673553467, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.011863517060367455, | |
| "grad_norm": 0.2853791117668152, | |
| "learning_rate": 0.0008, | |
| "loss": 4.923807144165039, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.011968503937007874, | |
| "grad_norm": 0.2706334590911865, | |
| "learning_rate": 0.0008, | |
| "loss": 4.94926118850708, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.012073490813648294, | |
| "grad_norm": 0.2381977140903473, | |
| "learning_rate": 0.0008, | |
| "loss": 4.920800685882568, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.012178477690288713, | |
| "grad_norm": 0.21651628613471985, | |
| "learning_rate": 0.0008, | |
| "loss": 4.997503757476807, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.012283464566929133, | |
| "grad_norm": 0.28761589527130127, | |
| "learning_rate": 0.0008, | |
| "loss": 4.905304431915283, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.012388451443569554, | |
| "grad_norm": 0.3810858130455017, | |
| "learning_rate": 0.0008, | |
| "loss": 4.907279968261719, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.012493438320209974, | |
| "grad_norm": 0.6002088189125061, | |
| "learning_rate": 0.0008, | |
| "loss": 4.840156555175781, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.012598425196850394, | |
| "grad_norm": 0.42039456963539124, | |
| "learning_rate": 0.0008, | |
| "loss": 4.886885643005371, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.012703412073490813, | |
| "grad_norm": 0.42322126030921936, | |
| "learning_rate": 0.0008, | |
| "loss": 4.822059631347656, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.012808398950131234, | |
| "grad_norm": 0.33545973896980286, | |
| "learning_rate": 0.0008, | |
| "loss": 4.766934871673584, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.012913385826771654, | |
| "grad_norm": 0.35304394364356995, | |
| "learning_rate": 0.0008, | |
| "loss": 4.7689738273620605, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.013018372703412074, | |
| "grad_norm": 0.3135300278663635, | |
| "learning_rate": 0.0008, | |
| "loss": 4.7434821128845215, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.013123359580052493, | |
| "grad_norm": 0.2875298857688904, | |
| "learning_rate": 0.0008, | |
| "loss": 4.7837395668029785, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.013228346456692913, | |
| "grad_norm": 0.34506675601005554, | |
| "learning_rate": 0.0008, | |
| "loss": 4.787559509277344, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.013333333333333334, | |
| "grad_norm": 0.3315136730670929, | |
| "learning_rate": 0.0008, | |
| "loss": 4.751657962799072, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.013438320209973754, | |
| "grad_norm": 0.3462645709514618, | |
| "learning_rate": 0.0008, | |
| "loss": 4.821771621704102, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.013543307086614173, | |
| "grad_norm": 0.24309296905994415, | |
| "learning_rate": 0.0008, | |
| "loss": 4.689890384674072, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.013648293963254593, | |
| "grad_norm": 0.4050637185573578, | |
| "learning_rate": 0.0008, | |
| "loss": 4.697262287139893, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.013753280839895013, | |
| "grad_norm": 0.4226019084453583, | |
| "learning_rate": 0.0008, | |
| "loss": 4.713808059692383, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.013858267716535434, | |
| "grad_norm": 0.4319268763065338, | |
| "learning_rate": 0.0008, | |
| "loss": 4.579202651977539, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.013963254593175854, | |
| "grad_norm": 0.3217737078666687, | |
| "learning_rate": 0.0008, | |
| "loss": 4.692221641540527, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.014068241469816273, | |
| "grad_norm": 0.30460724234580994, | |
| "learning_rate": 0.0008, | |
| "loss": 4.656576156616211, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.014173228346456693, | |
| "grad_norm": 0.25518161058425903, | |
| "learning_rate": 0.0008, | |
| "loss": 4.592221260070801, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.014278215223097112, | |
| "grad_norm": 0.24282623827457428, | |
| "learning_rate": 0.0008, | |
| "loss": 4.648724555969238, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.014383202099737534, | |
| "grad_norm": 0.39138299226760864, | |
| "learning_rate": 0.0008, | |
| "loss": 4.606783866882324, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.014488188976377953, | |
| "grad_norm": 0.32089442014694214, | |
| "learning_rate": 0.0008, | |
| "loss": 4.516218662261963, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.014593175853018373, | |
| "grad_norm": 0.3266720473766327, | |
| "learning_rate": 0.0008, | |
| "loss": 4.552274227142334, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.014698162729658792, | |
| "grad_norm": 0.27863070368766785, | |
| "learning_rate": 0.0008, | |
| "loss": 4.488729476928711, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.014803149606299212, | |
| "grad_norm": 0.28705859184265137, | |
| "learning_rate": 0.0008, | |
| "loss": 4.477656364440918, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.014908136482939633, | |
| "grad_norm": 0.33214113116264343, | |
| "learning_rate": 0.0008, | |
| "loss": 4.430954456329346, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.015013123359580053, | |
| "grad_norm": 0.3688258230686188, | |
| "learning_rate": 0.0008, | |
| "loss": 4.452303886413574, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.015118110236220473, | |
| "grad_norm": 0.36506983637809753, | |
| "learning_rate": 0.0008, | |
| "loss": 4.543822288513184, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.015223097112860892, | |
| "grad_norm": 0.3670697808265686, | |
| "learning_rate": 0.0008, | |
| "loss": 4.436527252197266, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.015328083989501312, | |
| "grad_norm": 0.2648005187511444, | |
| "learning_rate": 0.0008, | |
| "loss": 4.4850335121154785, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.015433070866141733, | |
| "grad_norm": 0.22264482080936432, | |
| "learning_rate": 0.0008, | |
| "loss": 4.484733581542969, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.015538057742782153, | |
| "grad_norm": 0.2611202895641327, | |
| "learning_rate": 0.0008, | |
| "loss": 4.408095836639404, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.01564304461942257, | |
| "grad_norm": 0.2882183790206909, | |
| "learning_rate": 0.0008, | |
| "loss": 4.459738731384277, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.015748031496062992, | |
| "grad_norm": 0.28506702184677124, | |
| "learning_rate": 0.0008, | |
| "loss": 4.3531670570373535, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.015853018372703413, | |
| "grad_norm": 0.2589276432991028, | |
| "learning_rate": 0.0008, | |
| "loss": 4.410321235656738, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.01595800524934383, | |
| "grad_norm": 0.2526051104068756, | |
| "learning_rate": 0.0008, | |
| "loss": 4.283108711242676, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.016062992125984252, | |
| "grad_norm": 0.37200987339019775, | |
| "learning_rate": 0.0008, | |
| "loss": 4.3569817543029785, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.01616797900262467, | |
| "grad_norm": 0.307287335395813, | |
| "learning_rate": 0.0008, | |
| "loss": 4.438014507293701, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.01627296587926509, | |
| "grad_norm": 0.36766815185546875, | |
| "learning_rate": 0.0008, | |
| "loss": 4.295423984527588, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.016377952755905513, | |
| "grad_norm": 0.31193122267723083, | |
| "learning_rate": 0.0008, | |
| "loss": 4.333798885345459, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.01648293963254593, | |
| "grad_norm": 0.31765303015708923, | |
| "learning_rate": 0.0008, | |
| "loss": 4.16727352142334, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.016587926509186352, | |
| "grad_norm": 0.21497637033462524, | |
| "learning_rate": 0.0008, | |
| "loss": 4.2583441734313965, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.01669291338582677, | |
| "grad_norm": 0.26689282059669495, | |
| "learning_rate": 0.0008, | |
| "loss": 4.223230361938477, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.01679790026246719, | |
| "grad_norm": 0.27385199069976807, | |
| "learning_rate": 0.0008, | |
| "loss": 4.208255767822266, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.016902887139107613, | |
| "grad_norm": 0.2642309367656708, | |
| "learning_rate": 0.0008, | |
| "loss": 4.289506435394287, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.01700787401574803, | |
| "grad_norm": 0.2722127437591553, | |
| "learning_rate": 0.0008, | |
| "loss": 4.300339221954346, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.017112860892388452, | |
| "grad_norm": 0.38802817463874817, | |
| "learning_rate": 0.0008, | |
| "loss": 4.228229999542236, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.01721784776902887, | |
| "grad_norm": 0.2825157642364502, | |
| "learning_rate": 0.0008, | |
| "loss": 4.32781982421875, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.01732283464566929, | |
| "grad_norm": 0.3203144669532776, | |
| "learning_rate": 0.0008, | |
| "loss": 4.10207462310791, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.017427821522309712, | |
| "grad_norm": 0.2983134090900421, | |
| "learning_rate": 0.0008, | |
| "loss": 4.20668888092041, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.01753280839895013, | |
| "grad_norm": 0.33699917793273926, | |
| "learning_rate": 0.0008, | |
| "loss": 4.1426262855529785, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.01763779527559055, | |
| "grad_norm": 0.3318274915218353, | |
| "learning_rate": 0.0008, | |
| "loss": 4.161504745483398, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.01774278215223097, | |
| "grad_norm": 0.2278800904750824, | |
| "learning_rate": 0.0008, | |
| "loss": 3.990349292755127, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.01784776902887139, | |
| "grad_norm": 0.2122919112443924, | |
| "learning_rate": 0.0008, | |
| "loss": 4.127922534942627, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.017952755905511812, | |
| "grad_norm": 0.24514071643352509, | |
| "learning_rate": 0.0008, | |
| "loss": 4.193850994110107, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.01805774278215223, | |
| "grad_norm": 0.28716644644737244, | |
| "learning_rate": 0.0008, | |
| "loss": 4.070234298706055, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.01816272965879265, | |
| "grad_norm": 0.25690266489982605, | |
| "learning_rate": 0.0008, | |
| "loss": 3.966444730758667, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.01826771653543307, | |
| "grad_norm": 0.2349938452243805, | |
| "learning_rate": 0.0008, | |
| "loss": 3.9333581924438477, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.01837270341207349, | |
| "grad_norm": 0.20146915316581726, | |
| "learning_rate": 0.0008, | |
| "loss": 3.953355550765991, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.018477690288713912, | |
| "grad_norm": 0.1961042433977127, | |
| "learning_rate": 0.0008, | |
| "loss": 3.973087787628174, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.01858267716535433, | |
| "grad_norm": 0.2598169445991516, | |
| "learning_rate": 0.0008, | |
| "loss": 4.002113342285156, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.01868766404199475, | |
| "grad_norm": 0.22022010385990143, | |
| "learning_rate": 0.0008, | |
| "loss": 3.9722490310668945, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.01879265091863517, | |
| "grad_norm": 0.212201327085495, | |
| "learning_rate": 0.0008, | |
| "loss": 3.8929874897003174, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.01889763779527559, | |
| "grad_norm": 0.1991279572248459, | |
| "learning_rate": 0.0008, | |
| "loss": 3.894895076751709, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.01900262467191601, | |
| "grad_norm": 0.24566085636615753, | |
| "learning_rate": 0.0008, | |
| "loss": 3.8610589504241943, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.01910761154855643, | |
| "grad_norm": 0.2806271016597748, | |
| "learning_rate": 0.0008, | |
| "loss": 3.861912488937378, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.01921259842519685, | |
| "grad_norm": 0.2231629341840744, | |
| "learning_rate": 0.0008, | |
| "loss": 3.8544185161590576, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.01931758530183727, | |
| "grad_norm": 0.26531746983528137, | |
| "learning_rate": 0.0008, | |
| "loss": 3.8621199131011963, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.01942257217847769, | |
| "grad_norm": 0.3318291902542114, | |
| "learning_rate": 0.0008, | |
| "loss": 3.902070999145508, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.01952755905511811, | |
| "grad_norm": 0.23807932436466217, | |
| "learning_rate": 0.0008, | |
| "loss": 3.86655855178833, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.01963254593175853, | |
| "grad_norm": 0.215584397315979, | |
| "learning_rate": 0.0008, | |
| "loss": 3.773761510848999, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.01973753280839895, | |
| "grad_norm": 0.289485901594162, | |
| "learning_rate": 0.0008, | |
| "loss": 3.8897311687469482, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.01984251968503937, | |
| "grad_norm": 0.2350815236568451, | |
| "learning_rate": 0.0008, | |
| "loss": 3.787693738937378, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.01994750656167979, | |
| "grad_norm": 0.2330552637577057, | |
| "learning_rate": 0.0008, | |
| "loss": 3.7755932807922363, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.02005249343832021, | |
| "grad_norm": 0.2246251106262207, | |
| "learning_rate": 0.0008, | |
| "loss": 3.839930772781372, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.02015748031496063, | |
| "grad_norm": 0.23261497914791107, | |
| "learning_rate": 0.0008, | |
| "loss": 3.72586727142334, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.02026246719160105, | |
| "grad_norm": 0.24750104546546936, | |
| "learning_rate": 0.0008, | |
| "loss": 3.893145799636841, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.020367454068241468, | |
| "grad_norm": 0.22430314123630524, | |
| "learning_rate": 0.0008, | |
| "loss": 3.725208282470703, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.02047244094488189, | |
| "grad_norm": 0.20470485091209412, | |
| "learning_rate": 0.0008, | |
| "loss": 3.727203845977783, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.02057742782152231, | |
| "grad_norm": 0.1713440865278244, | |
| "learning_rate": 0.0008, | |
| "loss": 3.722830295562744, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.02068241469816273, | |
| "grad_norm": 0.17870037257671356, | |
| "learning_rate": 0.0008, | |
| "loss": 3.6994686126708984, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.02078740157480315, | |
| "grad_norm": 0.16635218262672424, | |
| "learning_rate": 0.0008, | |
| "loss": 3.628350257873535, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.020892388451443568, | |
| "grad_norm": 0.16065655648708344, | |
| "learning_rate": 0.0008, | |
| "loss": 3.696190357208252, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.02099737532808399, | |
| "grad_norm": 0.1648516058921814, | |
| "learning_rate": 0.0008, | |
| "loss": 3.7218990325927734, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.02110236220472441, | |
| "grad_norm": 0.2350551337003708, | |
| "learning_rate": 0.0008, | |
| "loss": 3.6114625930786133, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.02120734908136483, | |
| "grad_norm": 0.21156081557273865, | |
| "learning_rate": 0.0008, | |
| "loss": 3.6270546913146973, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.02131233595800525, | |
| "grad_norm": 0.2242772877216339, | |
| "learning_rate": 0.0008, | |
| "loss": 3.6559674739837646, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.021417322834645668, | |
| "grad_norm": 0.20296809077262878, | |
| "learning_rate": 0.0008, | |
| "loss": 3.6351869106292725, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.02152230971128609, | |
| "grad_norm": 0.21024516224861145, | |
| "learning_rate": 0.0008, | |
| "loss": 3.7134218215942383, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.02162729658792651, | |
| "grad_norm": 0.2657431662082672, | |
| "learning_rate": 0.0008, | |
| "loss": 3.675140619277954, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.021732283464566928, | |
| "grad_norm": 0.22600969672203064, | |
| "learning_rate": 0.0008, | |
| "loss": 3.6230013370513916, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.02183727034120735, | |
| "grad_norm": 0.22580362856388092, | |
| "learning_rate": 0.0008, | |
| "loss": 3.633514881134033, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.021942257217847767, | |
| "grad_norm": 0.20401369035243988, | |
| "learning_rate": 0.0008, | |
| "loss": 3.5863749980926514, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.02204724409448819, | |
| "grad_norm": 0.19097885489463806, | |
| "learning_rate": 0.0008, | |
| "loss": 3.570152521133423, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.02215223097112861, | |
| "grad_norm": 0.16916649043560028, | |
| "learning_rate": 0.0008, | |
| "loss": 3.571899175643921, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.022257217847769028, | |
| "grad_norm": 0.15503089129924774, | |
| "learning_rate": 0.0008, | |
| "loss": 3.648607015609741, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.02236220472440945, | |
| "grad_norm": 0.18933242559432983, | |
| "learning_rate": 0.0008, | |
| "loss": 3.6147239208221436, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.022467191601049867, | |
| "grad_norm": 0.1814320683479309, | |
| "learning_rate": 0.0008, | |
| "loss": 3.5678610801696777, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.02257217847769029, | |
| "grad_norm": 0.15981845557689667, | |
| "learning_rate": 0.0008, | |
| "loss": 3.4891350269317627, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.02267716535433071, | |
| "grad_norm": 0.1672240048646927, | |
| "learning_rate": 0.0008, | |
| "loss": 3.5254311561584473, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.022782152230971128, | |
| "grad_norm": 0.17923741042613983, | |
| "learning_rate": 0.0008, | |
| "loss": 3.4941389560699463, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.02288713910761155, | |
| "grad_norm": 0.20545029640197754, | |
| "learning_rate": 0.0008, | |
| "loss": 3.4603352546691895, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.022992125984251967, | |
| "grad_norm": 0.21872857213020325, | |
| "learning_rate": 0.0008, | |
| "loss": 3.4523208141326904, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.023097112860892388, | |
| "grad_norm": 0.17705431580543518, | |
| "learning_rate": 0.0008, | |
| "loss": 3.443699598312378, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.02320209973753281, | |
| "grad_norm": 0.14959222078323364, | |
| "learning_rate": 0.0008, | |
| "loss": 3.557424545288086, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.023307086614173227, | |
| "grad_norm": 0.1745806336402893, | |
| "learning_rate": 0.0008, | |
| "loss": 3.4890198707580566, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.02341207349081365, | |
| "grad_norm": 0.18317265808582306, | |
| "learning_rate": 0.0008, | |
| "loss": 3.5291688442230225, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.023517060367454067, | |
| "grad_norm": 0.1765255481004715, | |
| "learning_rate": 0.0008, | |
| "loss": 3.471801280975342, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.023622047244094488, | |
| "grad_norm": 0.1791754961013794, | |
| "learning_rate": 0.0008, | |
| "loss": 3.4235143661499023, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.02372703412073491, | |
| "grad_norm": 0.16694314777851105, | |
| "learning_rate": 0.0008, | |
| "loss": 3.5024945735931396, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.023832020997375327, | |
| "grad_norm": 0.20423193275928497, | |
| "learning_rate": 0.0008, | |
| "loss": 3.4986155033111572, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.02393700787401575, | |
| "grad_norm": 0.21046102046966553, | |
| "learning_rate": 0.0008, | |
| "loss": 3.5056910514831543, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.024041994750656166, | |
| "grad_norm": 0.18477864563465118, | |
| "learning_rate": 0.0008, | |
| "loss": 3.424469470977783, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.024146981627296588, | |
| "grad_norm": 0.17082113027572632, | |
| "learning_rate": 0.0008, | |
| "loss": 3.47847056388855, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.02425196850393701, | |
| "grad_norm": 0.17604340612888336, | |
| "learning_rate": 0.0008, | |
| "loss": 3.425982713699341, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.024356955380577427, | |
| "grad_norm": 0.16897740960121155, | |
| "learning_rate": 0.0008, | |
| "loss": 3.4730064868927, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.024461942257217848, | |
| "grad_norm": 0.1673053652048111, | |
| "learning_rate": 0.0008, | |
| "loss": 3.432903289794922, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.024566929133858266, | |
| "grad_norm": 0.17199593782424927, | |
| "learning_rate": 0.0008, | |
| "loss": 3.5054171085357666, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.024671916010498687, | |
| "grad_norm": 0.19890399277210236, | |
| "learning_rate": 0.0008, | |
| "loss": 3.4409797191619873, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.02477690288713911, | |
| "grad_norm": 0.19607073068618774, | |
| "learning_rate": 0.0008, | |
| "loss": 3.3515682220458984, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.024881889763779527, | |
| "grad_norm": 0.16958890855312347, | |
| "learning_rate": 0.0008, | |
| "loss": 3.420071840286255, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.024986876640419948, | |
| "grad_norm": 0.1964447945356369, | |
| "learning_rate": 0.0008, | |
| "loss": 3.526289224624634, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.02509186351706037, | |
| "grad_norm": 0.1786402314901352, | |
| "learning_rate": 0.0008, | |
| "loss": 3.440227746963501, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.025196850393700787, | |
| "grad_norm": 0.16233603656291962, | |
| "learning_rate": 0.0008, | |
| "loss": 3.317654609680176, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.02530183727034121, | |
| "grad_norm": 0.18433336913585663, | |
| "learning_rate": 0.0008, | |
| "loss": 3.444368839263916, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.025406824146981626, | |
| "grad_norm": 0.16506624221801758, | |
| "learning_rate": 0.0008, | |
| "loss": 3.4707281589508057, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.025511811023622048, | |
| "grad_norm": 0.1551865041255951, | |
| "learning_rate": 0.0008, | |
| "loss": 3.3682827949523926, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.02561679790026247, | |
| "grad_norm": 0.14763277769088745, | |
| "learning_rate": 0.0008, | |
| "loss": 3.325780153274536, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.025721784776902887, | |
| "grad_norm": 0.1381286233663559, | |
| "learning_rate": 0.0008, | |
| "loss": 3.426196813583374, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.025826771653543308, | |
| "grad_norm": 0.15651266276836395, | |
| "learning_rate": 0.0008, | |
| "loss": 3.38508677482605, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.025931758530183726, | |
| "grad_norm": 0.16916270554065704, | |
| "learning_rate": 0.0008, | |
| "loss": 3.394261598587036, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.026036745406824147, | |
| "grad_norm": 0.16897031664848328, | |
| "learning_rate": 0.0008, | |
| "loss": 3.278876543045044, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.02614173228346457, | |
| "grad_norm": 0.16116946935653687, | |
| "learning_rate": 0.0008, | |
| "loss": 3.3523120880126953, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.026246719160104987, | |
| "grad_norm": 0.17504142224788666, | |
| "learning_rate": 0.0008, | |
| "loss": 3.3894450664520264, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.026351706036745408, | |
| "grad_norm": 0.17068205773830414, | |
| "learning_rate": 0.0008, | |
| "loss": 3.4036076068878174, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 0.026456692913385826, | |
| "grad_norm": 0.1658509224653244, | |
| "learning_rate": 0.0008, | |
| "loss": 3.378098487854004, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.026561679790026247, | |
| "grad_norm": 0.1450873762369156, | |
| "learning_rate": 0.0008, | |
| "loss": 3.304023265838623, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 0.02666666666666667, | |
| "grad_norm": 0.18289312720298767, | |
| "learning_rate": 0.0008, | |
| "loss": 3.288076639175415, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 0.026771653543307086, | |
| "grad_norm": 0.1541556864976883, | |
| "learning_rate": 0.0008, | |
| "loss": 3.304835081100464, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.026876640419947508, | |
| "grad_norm": 0.16644538938999176, | |
| "learning_rate": 0.0008, | |
| "loss": 3.2379486560821533, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 0.026981627296587925, | |
| "grad_norm": 0.19644027948379517, | |
| "learning_rate": 0.0008, | |
| "loss": 3.3676295280456543, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 0.027086614173228347, | |
| "grad_norm": 0.20000602304935455, | |
| "learning_rate": 0.0008, | |
| "loss": 3.255898952484131, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.027191601049868768, | |
| "grad_norm": 0.17630483210086823, | |
| "learning_rate": 0.0008, | |
| "loss": 3.2831783294677734, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.027296587926509186, | |
| "grad_norm": 0.16653336584568024, | |
| "learning_rate": 0.0008, | |
| "loss": 3.388322591781616, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.027401574803149607, | |
| "grad_norm": 0.15305423736572266, | |
| "learning_rate": 0.0008, | |
| "loss": 3.3861708641052246, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 0.027506561679790025, | |
| "grad_norm": 0.15171492099761963, | |
| "learning_rate": 0.0008, | |
| "loss": 3.336448907852173, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 0.027611548556430447, | |
| "grad_norm": 0.17332474887371063, | |
| "learning_rate": 0.0008, | |
| "loss": 3.248317003250122, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 0.027716535433070868, | |
| "grad_norm": 0.14799350500106812, | |
| "learning_rate": 0.0008, | |
| "loss": 3.3303961753845215, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 0.027821522309711286, | |
| "grad_norm": 0.14763560891151428, | |
| "learning_rate": 0.0008, | |
| "loss": 3.3051490783691406, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.027926509186351707, | |
| "grad_norm": 0.1350218653678894, | |
| "learning_rate": 0.0008, | |
| "loss": 3.3351500034332275, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.028031496062992125, | |
| "grad_norm": 0.14229005575180054, | |
| "learning_rate": 0.0008, | |
| "loss": 3.2528343200683594, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.028136482939632546, | |
| "grad_norm": 0.14102040231227875, | |
| "learning_rate": 0.0008, | |
| "loss": 3.204890012741089, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 0.028241469816272968, | |
| "grad_norm": 0.14591607451438904, | |
| "learning_rate": 0.0008, | |
| "loss": 3.367074966430664, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 0.028346456692913385, | |
| "grad_norm": 0.16307151317596436, | |
| "learning_rate": 0.0008, | |
| "loss": 3.236833333969116, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.028451443569553807, | |
| "grad_norm": 0.1497374176979065, | |
| "learning_rate": 0.0008, | |
| "loss": 3.206105947494507, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 0.028556430446194225, | |
| "grad_norm": 0.1525629311800003, | |
| "learning_rate": 0.0008, | |
| "loss": 3.3076024055480957, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 0.028661417322834646, | |
| "grad_norm": 0.1597941815853119, | |
| "learning_rate": 0.0008, | |
| "loss": 3.287429094314575, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.028766404199475067, | |
| "grad_norm": 0.16407884657382965, | |
| "learning_rate": 0.0008, | |
| "loss": 3.329230785369873, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 0.028871391076115485, | |
| "grad_norm": 0.18955646455287933, | |
| "learning_rate": 0.0008, | |
| "loss": 3.29620099067688, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.028976377952755906, | |
| "grad_norm": 0.13810871541500092, | |
| "learning_rate": 0.0008, | |
| "loss": 3.22092604637146, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 0.029081364829396324, | |
| "grad_norm": 0.14122328162193298, | |
| "learning_rate": 0.0008, | |
| "loss": 3.2574150562286377, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 0.029186351706036746, | |
| "grad_norm": 0.17227867245674133, | |
| "learning_rate": 0.0008, | |
| "loss": 3.2021737098693848, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 0.029291338582677167, | |
| "grad_norm": 0.13745535910129547, | |
| "learning_rate": 0.0008, | |
| "loss": 3.2652475833892822, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.029396325459317585, | |
| "grad_norm": 0.14315351843833923, | |
| "learning_rate": 0.0008, | |
| "loss": 3.3042309284210205, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.029501312335958006, | |
| "grad_norm": 0.1505221426486969, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1302292346954346, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 0.029606299212598424, | |
| "grad_norm": 0.15946339070796967, | |
| "learning_rate": 0.0008, | |
| "loss": 3.2585742473602295, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 0.029711286089238845, | |
| "grad_norm": 0.17035390436649323, | |
| "learning_rate": 0.0008, | |
| "loss": 3.200352191925049, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 0.029816272965879267, | |
| "grad_norm": 0.14264027774333954, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1434473991394043, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 0.029921259842519685, | |
| "grad_norm": 0.14433781802654266, | |
| "learning_rate": 0.0008, | |
| "loss": 3.141904592514038, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.030026246719160106, | |
| "grad_norm": 0.13526467978954315, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0416038036346436, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.030131233595800524, | |
| "grad_norm": 0.13533855974674225, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1272072792053223, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 0.030236220472440945, | |
| "grad_norm": 0.15500874817371368, | |
| "learning_rate": 0.0008, | |
| "loss": 3.2618722915649414, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 0.030341207349081366, | |
| "grad_norm": 0.17267724871635437, | |
| "learning_rate": 0.0008, | |
| "loss": 3.2308037281036377, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 0.030446194225721784, | |
| "grad_norm": 0.1582280397415161, | |
| "learning_rate": 0.0008, | |
| "loss": 3.23921537399292, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.030551181102362206, | |
| "grad_norm": 0.13486045598983765, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1242129802703857, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.030656167979002624, | |
| "grad_norm": 0.1379910260438919, | |
| "learning_rate": 0.0008, | |
| "loss": 3.177032470703125, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 0.030761154855643045, | |
| "grad_norm": 0.14302867650985718, | |
| "learning_rate": 0.0008, | |
| "loss": 3.2286078929901123, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 0.030866141732283466, | |
| "grad_norm": 0.1382298469543457, | |
| "learning_rate": 0.0008, | |
| "loss": 3.222778797149658, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.030971128608923884, | |
| "grad_norm": 0.15394456684589386, | |
| "learning_rate": 0.0008, | |
| "loss": 3.2219724655151367, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.031076115485564305, | |
| "grad_norm": 0.13939788937568665, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1774375438690186, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 0.031181102362204723, | |
| "grad_norm": 0.1534331738948822, | |
| "learning_rate": 0.0008, | |
| "loss": 3.174874782562256, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 0.03128608923884514, | |
| "grad_norm": 0.1796104907989502, | |
| "learning_rate": 0.0008, | |
| "loss": 3.226047992706299, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 0.03139107611548556, | |
| "grad_norm": 0.13423976302146912, | |
| "learning_rate": 0.0008, | |
| "loss": 3.154773473739624, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 0.031496062992125984, | |
| "grad_norm": 0.14498203992843628, | |
| "learning_rate": 0.0008, | |
| "loss": 3.2181460857391357, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.031601049868766405, | |
| "grad_norm": 0.14076939225196838, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1480512619018555, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.031706036745406826, | |
| "grad_norm": 0.14199046790599823, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1948139667510986, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 0.03181102362204724, | |
| "grad_norm": 0.1405128389596939, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1463754177093506, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 0.03191601049868766, | |
| "grad_norm": 0.13525350391864777, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1250717639923096, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 0.032020997375328084, | |
| "grad_norm": 0.14196738600730896, | |
| "learning_rate": 0.0008, | |
| "loss": 3.2256250381469727, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.032125984251968505, | |
| "grad_norm": 0.1674332171678543, | |
| "learning_rate": 0.0008, | |
| "loss": 3.189035177230835, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 0.032230971128608926, | |
| "grad_norm": 0.19794052839279175, | |
| "learning_rate": 0.0008, | |
| "loss": 3.231616258621216, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 0.03233595800524934, | |
| "grad_norm": 0.1598575860261917, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1828837394714355, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 0.03244094488188976, | |
| "grad_norm": 0.14745914936065674, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1849329471588135, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 0.03254593175853018, | |
| "grad_norm": 0.3145313858985901, | |
| "learning_rate": 0.0008, | |
| "loss": 3.165916681289673, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.032650918635170605, | |
| "grad_norm": 0.26110589504241943, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1651082038879395, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 0.032755905511811026, | |
| "grad_norm": 0.22751542925834656, | |
| "learning_rate": 0.0008, | |
| "loss": 3.210188627243042, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.03286089238845144, | |
| "grad_norm": 0.18317535519599915, | |
| "learning_rate": 0.0008, | |
| "loss": 3.2566449642181396, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 0.03296587926509186, | |
| "grad_norm": 0.15907306969165802, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1539463996887207, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 0.03307086614173228, | |
| "grad_norm": 0.15025147795677185, | |
| "learning_rate": 0.0008, | |
| "loss": 3.142364740371704, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.033175853018372704, | |
| "grad_norm": 0.1286715716123581, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1074650287628174, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 0.033280839895013126, | |
| "grad_norm": 0.12226458638906479, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0952885150909424, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 0.03338582677165354, | |
| "grad_norm": 0.13879609107971191, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1514804363250732, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 0.03349081364829396, | |
| "grad_norm": 0.12534929811954498, | |
| "learning_rate": 0.0008, | |
| "loss": 3.139106035232544, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 0.03359580052493438, | |
| "grad_norm": 0.12349742650985718, | |
| "learning_rate": 0.0008, | |
| "loss": 3.105691909790039, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.033700787401574804, | |
| "grad_norm": 0.12220428138971329, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1019020080566406, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 0.033805774278215225, | |
| "grad_norm": 0.1326756477355957, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1477456092834473, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 0.03391076115485564, | |
| "grad_norm": 0.13377100229263306, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0433576107025146, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 0.03401574803149606, | |
| "grad_norm": 0.12178801745176315, | |
| "learning_rate": 0.0008, | |
| "loss": 3.07883620262146, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 0.03412073490813648, | |
| "grad_norm": 0.13815799355506897, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0264294147491455, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.034225721784776904, | |
| "grad_norm": 0.1332225501537323, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1015422344207764, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 0.034330708661417325, | |
| "grad_norm": 0.12200571596622467, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0805413722991943, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 0.03443569553805774, | |
| "grad_norm": 0.1238102912902832, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0576930046081543, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 0.03454068241469816, | |
| "grad_norm": 0.1291918158531189, | |
| "learning_rate": 0.0008, | |
| "loss": 3.13897967338562, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 0.03464566929133858, | |
| "grad_norm": 0.13744677603244781, | |
| "learning_rate": 0.0008, | |
| "loss": 3.164642333984375, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.034750656167979004, | |
| "grad_norm": 0.12718631327152252, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0951108932495117, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 0.034855643044619425, | |
| "grad_norm": 0.12068125605583191, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0444083213806152, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 0.03496062992125984, | |
| "grad_norm": 0.13728944957256317, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0462770462036133, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 0.03506561679790026, | |
| "grad_norm": 0.1373009830713272, | |
| "learning_rate": 0.0008, | |
| "loss": 3.086789131164551, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 0.03517060367454068, | |
| "grad_norm": 0.12281421571969986, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0893633365631104, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.0352755905511811, | |
| "grad_norm": 0.13015969097614288, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0368361473083496, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 0.035380577427821525, | |
| "grad_norm": 0.13312262296676636, | |
| "learning_rate": 0.0008, | |
| "loss": 3.122968912124634, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 0.03548556430446194, | |
| "grad_norm": 0.13073506951332092, | |
| "learning_rate": 0.0008, | |
| "loss": 3.062354326248169, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.03559055118110236, | |
| "grad_norm": 0.119827501475811, | |
| "learning_rate": 0.0008, | |
| "loss": 3.1293904781341553, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 0.03569553805774278, | |
| "grad_norm": 0.1357945054769516, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9812240600585938, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.0358005249343832, | |
| "grad_norm": 0.1311289370059967, | |
| "learning_rate": 0.0008, | |
| "loss": 2.966649293899536, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 0.035905511811023624, | |
| "grad_norm": 0.12661199271678925, | |
| "learning_rate": 0.0008, | |
| "loss": 3.031751871109009, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 0.03601049868766404, | |
| "grad_norm": 0.14154307544231415, | |
| "learning_rate": 0.0008, | |
| "loss": 3.155766248703003, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 0.03611548556430446, | |
| "grad_norm": 0.13769333064556122, | |
| "learning_rate": 0.0008, | |
| "loss": 3.064086675643921, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 0.03622047244094488, | |
| "grad_norm": 0.145602285861969, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0761966705322266, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.0363254593175853, | |
| "grad_norm": 0.12669020891189575, | |
| "learning_rate": 0.0008, | |
| "loss": 3.097874164581299, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 0.036430446194225724, | |
| "grad_norm": 0.13513895869255066, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0714070796966553, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 0.03653543307086614, | |
| "grad_norm": 0.13587389886379242, | |
| "learning_rate": 0.0008, | |
| "loss": 3.172131299972534, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 0.03664041994750656, | |
| "grad_norm": 0.130451962351799, | |
| "learning_rate": 0.0008, | |
| "loss": 3.069667100906372, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 0.03674540682414698, | |
| "grad_norm": 0.12922164797782898, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0901424884796143, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.0368503937007874, | |
| "grad_norm": 0.12978655099868774, | |
| "learning_rate": 0.0008, | |
| "loss": 3.049433708190918, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 0.036955380577427824, | |
| "grad_norm": 0.12508027255535126, | |
| "learning_rate": 0.0008, | |
| "loss": 3.00188946723938, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 0.03706036745406824, | |
| "grad_norm": 0.11734891682863235, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9634389877319336, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 0.03716535433070866, | |
| "grad_norm": 0.12137921899557114, | |
| "learning_rate": 0.0008, | |
| "loss": 2.999195098876953, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 0.03727034120734908, | |
| "grad_norm": 0.12699182331562042, | |
| "learning_rate": 0.0008, | |
| "loss": 3.018418550491333, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.0373753280839895, | |
| "grad_norm": 0.12088700383901596, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9763457775115967, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 0.037480314960629924, | |
| "grad_norm": 0.12237604707479477, | |
| "learning_rate": 0.0008, | |
| "loss": 2.962264060974121, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 0.03758530183727034, | |
| "grad_norm": 0.11808755993843079, | |
| "learning_rate": 0.0008, | |
| "loss": 2.944026470184326, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 0.03769028871391076, | |
| "grad_norm": 0.12789645791053772, | |
| "learning_rate": 0.0008, | |
| "loss": 3.062084913253784, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 0.03779527559055118, | |
| "grad_norm": 0.12254694849252701, | |
| "learning_rate": 0.0008, | |
| "loss": 3.042384386062622, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.0379002624671916, | |
| "grad_norm": 0.12937159836292267, | |
| "learning_rate": 0.0008, | |
| "loss": 2.950317859649658, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 0.03800524934383202, | |
| "grad_norm": 0.1205861046910286, | |
| "learning_rate": 0.0008, | |
| "loss": 3.043663740158081, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 0.03811023622047244, | |
| "grad_norm": 0.12075173109769821, | |
| "learning_rate": 0.0008, | |
| "loss": 3.061645269393921, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 0.03821522309711286, | |
| "grad_norm": 0.14968499541282654, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0783021450042725, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.03832020997375328, | |
| "grad_norm": 0.1275404989719391, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0341646671295166, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.0384251968503937, | |
| "grad_norm": 0.12180853635072708, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0402371883392334, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 0.03853018372703412, | |
| "grad_norm": 0.12133266776800156, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0349020957946777, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 0.03863517060367454, | |
| "grad_norm": 0.14342333376407623, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9737958908081055, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 0.03874015748031496, | |
| "grad_norm": 0.12567119300365448, | |
| "learning_rate": 0.0008, | |
| "loss": 2.999332904815674, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 0.03884514435695538, | |
| "grad_norm": 0.11701060831546783, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9920272827148438, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.0389501312335958, | |
| "grad_norm": 0.12809567153453827, | |
| "learning_rate": 0.0008, | |
| "loss": 3.047039270401001, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 0.03905511811023622, | |
| "grad_norm": 0.1611979454755783, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0390896797180176, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 0.03916010498687664, | |
| "grad_norm": 0.1428634077310562, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9358737468719482, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 0.03926509186351706, | |
| "grad_norm": 0.12375941872596741, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0470502376556396, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 0.03937007874015748, | |
| "grad_norm": 0.11091126501560211, | |
| "learning_rate": 0.0008, | |
| "loss": 3.005697250366211, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.0394750656167979, | |
| "grad_norm": 0.12000731378793716, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0071187019348145, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 0.03958005249343832, | |
| "grad_norm": 0.12539641559123993, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9291770458221436, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 0.03968503937007874, | |
| "grad_norm": 0.1304706335067749, | |
| "learning_rate": 0.0008, | |
| "loss": 2.963855266571045, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 0.03979002624671916, | |
| "grad_norm": 0.11511696130037308, | |
| "learning_rate": 0.0008, | |
| "loss": 3.024789333343506, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 0.03989501312335958, | |
| "grad_norm": 0.1253596395254135, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9894022941589355, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.11755448579788208, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0086042881011963, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 0.04010498687664042, | |
| "grad_norm": 0.12490132451057434, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0274486541748047, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 0.04020997375328084, | |
| "grad_norm": 0.1350909322500229, | |
| "learning_rate": 0.0008, | |
| "loss": 3.023331642150879, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 0.04031496062992126, | |
| "grad_norm": 0.11557217687368393, | |
| "learning_rate": 0.0008, | |
| "loss": 2.934751272201538, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 0.04041994750656168, | |
| "grad_norm": 0.11128373444080353, | |
| "learning_rate": 0.0008, | |
| "loss": 3.004828929901123, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.0405249343832021, | |
| "grad_norm": 0.11425162851810455, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0121257305145264, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 0.04062992125984252, | |
| "grad_norm": 0.11489281803369522, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9543981552124023, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 0.040734908136482936, | |
| "grad_norm": 0.11290168762207031, | |
| "learning_rate": 0.0008, | |
| "loss": 2.975158214569092, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 0.04083989501312336, | |
| "grad_norm": 0.11316516250371933, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0863113403320312, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 0.04094488188976378, | |
| "grad_norm": 0.11379840970039368, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0072288513183594, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.0410498687664042, | |
| "grad_norm": 0.10820312052965164, | |
| "learning_rate": 0.0008, | |
| "loss": 2.88815975189209, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 0.04115485564304462, | |
| "grad_norm": 0.11447291821241379, | |
| "learning_rate": 0.0008, | |
| "loss": 2.961986541748047, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 0.041259842519685036, | |
| "grad_norm": 0.11523283272981644, | |
| "learning_rate": 0.0008, | |
| "loss": 2.900437116622925, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 0.04136482939632546, | |
| "grad_norm": 0.11368467658758163, | |
| "learning_rate": 0.0008, | |
| "loss": 2.953047752380371, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 0.04146981627296588, | |
| "grad_norm": 0.12399861216545105, | |
| "learning_rate": 0.0008, | |
| "loss": 2.968926191329956, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.0415748031496063, | |
| "grad_norm": 0.11375656723976135, | |
| "learning_rate": 0.0008, | |
| "loss": 2.997025966644287, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 0.04167979002624672, | |
| "grad_norm": 0.11646395176649094, | |
| "learning_rate": 0.0008, | |
| "loss": 2.952754497528076, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 0.041784776902887136, | |
| "grad_norm": 0.1193268746137619, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9536261558532715, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 0.04188976377952756, | |
| "grad_norm": 0.1178014799952507, | |
| "learning_rate": 0.0008, | |
| "loss": 2.913003444671631, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 0.04199475065616798, | |
| "grad_norm": 0.11936375498771667, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0284841060638428, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.0420997375328084, | |
| "grad_norm": 0.11003916710615158, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9801266193389893, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 0.04220472440944882, | |
| "grad_norm": 0.20111171901226044, | |
| "learning_rate": 0.0008, | |
| "loss": 2.907733201980591, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 0.042309711286089235, | |
| "grad_norm": 0.12075945734977722, | |
| "learning_rate": 0.0008, | |
| "loss": 2.935979127883911, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 0.04241469816272966, | |
| "grad_norm": 0.11057411134243011, | |
| "learning_rate": 0.0008, | |
| "loss": 3.027822732925415, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 0.04251968503937008, | |
| "grad_norm": 0.12909549474716187, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9112420082092285, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.0426246719160105, | |
| "grad_norm": 0.11044399440288544, | |
| "learning_rate": 0.0008, | |
| "loss": 2.889822006225586, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 0.04272965879265092, | |
| "grad_norm": 0.13029007613658905, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0270438194274902, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 0.042834645669291335, | |
| "grad_norm": 0.11640318483114243, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9036266803741455, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 0.04293963254593176, | |
| "grad_norm": 0.10894198715686798, | |
| "learning_rate": 0.0008, | |
| "loss": 2.96498966217041, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 0.04304461942257218, | |
| "grad_norm": 0.11847452819347382, | |
| "learning_rate": 0.0008, | |
| "loss": 2.950117349624634, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.0431496062992126, | |
| "grad_norm": 0.1125883162021637, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9723289012908936, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 0.04325459317585302, | |
| "grad_norm": 0.11767535656690598, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0090739727020264, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 0.043359580052493435, | |
| "grad_norm": 0.11515145003795624, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8834097385406494, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 0.043464566929133856, | |
| "grad_norm": 0.1153886616230011, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8896758556365967, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 0.04356955380577428, | |
| "grad_norm": 0.12153846025466919, | |
| "learning_rate": 0.0008, | |
| "loss": 3.001197338104248, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.0436745406824147, | |
| "grad_norm": 0.11056739836931229, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9580276012420654, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 0.04377952755905512, | |
| "grad_norm": 0.1146998405456543, | |
| "learning_rate": 0.0008, | |
| "loss": 2.832361936569214, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 0.043884514435695535, | |
| "grad_norm": 0.11632180213928223, | |
| "learning_rate": 0.0008, | |
| "loss": 2.967362880706787, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 0.043989501312335956, | |
| "grad_norm": 0.11315326392650604, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9654767513275146, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 0.04409448818897638, | |
| "grad_norm": 0.11123368889093399, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0236129760742188, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.0441994750656168, | |
| "grad_norm": 0.11806689202785492, | |
| "learning_rate": 0.0008, | |
| "loss": 3.0052027702331543, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 0.04430446194225722, | |
| "grad_norm": 0.11948549002408981, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7818121910095215, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 0.044409448818897634, | |
| "grad_norm": 0.1147482842206955, | |
| "learning_rate": 0.0008, | |
| "loss": 2.926354169845581, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 0.044514435695538056, | |
| "grad_norm": 0.11350935697555542, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9837636947631836, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 0.04461942257217848, | |
| "grad_norm": 0.11554283648729324, | |
| "learning_rate": 0.0008, | |
| "loss": 2.97532320022583, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.0447244094488189, | |
| "grad_norm": 0.1130303218960762, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9679086208343506, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 0.04482939632545932, | |
| "grad_norm": 0.11595270782709122, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9420673847198486, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 0.044934383202099734, | |
| "grad_norm": 0.11009976267814636, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9262118339538574, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 0.045039370078740155, | |
| "grad_norm": 0.10903191566467285, | |
| "learning_rate": 0.0008, | |
| "loss": 2.982046365737915, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 0.04514435695538058, | |
| "grad_norm": 0.1103678047657013, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8575191497802734, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.045249343832021, | |
| "grad_norm": 0.10818672180175781, | |
| "learning_rate": 0.0008, | |
| "loss": 2.913555145263672, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 0.04535433070866142, | |
| "grad_norm": 0.1269296556711197, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9361777305603027, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 0.045459317585301834, | |
| "grad_norm": 0.11180418729782104, | |
| "learning_rate": 0.0008, | |
| "loss": 2.856563091278076, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 0.045564304461942255, | |
| "grad_norm": 0.11334341019392014, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9308438301086426, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 0.04566929133858268, | |
| "grad_norm": 0.12519557774066925, | |
| "learning_rate": 0.0008, | |
| "loss": 2.969743251800537, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.0457742782152231, | |
| "grad_norm": 0.1138872504234314, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9254794120788574, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 0.04587926509186352, | |
| "grad_norm": 0.11148543655872345, | |
| "learning_rate": 0.0008, | |
| "loss": 2.950900077819824, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 0.045984251968503934, | |
| "grad_norm": 0.10802996158599854, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9233310222625732, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 0.046089238845144355, | |
| "grad_norm": 0.107913538813591, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8875625133514404, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 0.046194225721784776, | |
| "grad_norm": 0.11127500981092453, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9353115558624268, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.0462992125984252, | |
| "grad_norm": 0.107363760471344, | |
| "learning_rate": 0.0008, | |
| "loss": 2.862389087677002, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 0.04640419947506562, | |
| "grad_norm": 0.10834158211946487, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8950586318969727, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 0.04650918635170603, | |
| "grad_norm": 0.11008019000291824, | |
| "learning_rate": 0.0008, | |
| "loss": 2.847538709640503, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 0.046614173228346455, | |
| "grad_norm": 0.10486385971307755, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8976285457611084, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 0.046719160104986876, | |
| "grad_norm": 0.10609378665685654, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9052734375, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.0468241469816273, | |
| "grad_norm": 0.10781682282686234, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8474717140197754, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 0.04692913385826772, | |
| "grad_norm": 0.11209188401699066, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8896048069000244, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 0.04703412073490813, | |
| "grad_norm": 0.11089079827070236, | |
| "learning_rate": 0.0008, | |
| "loss": 2.906379222869873, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 0.047139107611548554, | |
| "grad_norm": 0.1138719990849495, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9644546508789062, | |
| "step": 898 | |
| }, | |
| { | |
| "epoch": 0.047244094488188976, | |
| "grad_norm": 0.11188910156488419, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9156696796417236, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.0473490813648294, | |
| "grad_norm": 0.10872109234333038, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8037800788879395, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 0.04745406824146982, | |
| "grad_norm": 0.1132812425494194, | |
| "learning_rate": 0.0008, | |
| "loss": 2.88108491897583, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 0.04755905511811023, | |
| "grad_norm": 0.10931621491909027, | |
| "learning_rate": 0.0008, | |
| "loss": 2.823637008666992, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 0.047664041994750654, | |
| "grad_norm": 0.10800245404243469, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8360915184020996, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 0.047769028871391075, | |
| "grad_norm": 0.10993431508541107, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9463419914245605, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.0478740157480315, | |
| "grad_norm": 0.11326651275157928, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8706324100494385, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 0.04797900262467192, | |
| "grad_norm": 0.1067848727107048, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8948814868927, | |
| "step": 914 | |
| }, | |
| { | |
| "epoch": 0.04808398950131233, | |
| "grad_norm": 0.10832501202821732, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8744025230407715, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 0.048188976377952754, | |
| "grad_norm": 0.22046154737472534, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8172924518585205, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 0.048293963254593175, | |
| "grad_norm": 0.10513289272785187, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8799233436584473, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.048398950131233597, | |
| "grad_norm": 0.10676917433738708, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8221311569213867, | |
| "step": 922 | |
| }, | |
| { | |
| "epoch": 0.04850393700787402, | |
| "grad_norm": 0.11604278534650803, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8618123531341553, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 0.04860892388451443, | |
| "grad_norm": 0.31026268005371094, | |
| "learning_rate": 0.0008, | |
| "loss": 2.933411121368408, | |
| "step": 926 | |
| }, | |
| { | |
| "epoch": 0.048713910761154854, | |
| "grad_norm": 0.11676490306854248, | |
| "learning_rate": 0.0008, | |
| "loss": 2.900099039077759, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 0.048818897637795275, | |
| "grad_norm": 0.10813336074352264, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8783600330352783, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.048923884514435696, | |
| "grad_norm": 0.14493827521800995, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8534443378448486, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 0.04902887139107612, | |
| "grad_norm": 0.1146959587931633, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9133646488189697, | |
| "step": 934 | |
| }, | |
| { | |
| "epoch": 0.04913385826771653, | |
| "grad_norm": 0.11801094561815262, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9639992713928223, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 0.04923884514435695, | |
| "grad_norm": 0.11729086190462112, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9099583625793457, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 0.049343832020997375, | |
| "grad_norm": 0.1108347624540329, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8269410133361816, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.049448818897637796, | |
| "grad_norm": 0.107319176197052, | |
| "learning_rate": 0.0008, | |
| "loss": 2.894010066986084, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 0.04955380577427822, | |
| "grad_norm": 0.11818240582942963, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8637502193450928, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 0.04965879265091863, | |
| "grad_norm": 0.10464034974575043, | |
| "learning_rate": 0.0008, | |
| "loss": 2.848630666732788, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 0.04976377952755905, | |
| "grad_norm": 0.110150046646595, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8126089572906494, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 0.049868766404199474, | |
| "grad_norm": 0.11635616421699524, | |
| "learning_rate": 0.0008, | |
| "loss": 2.854870319366455, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.049973753280839896, | |
| "grad_norm": 0.10688231140375137, | |
| "learning_rate": 0.0008, | |
| "loss": 2.851635217666626, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 0.05007874015748032, | |
| "grad_norm": 0.10546289384365082, | |
| "learning_rate": 0.0008, | |
| "loss": 2.863751173019409, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 0.05018372703412074, | |
| "grad_norm": 0.10257919877767563, | |
| "learning_rate": 0.0008, | |
| "loss": 2.952653169631958, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 0.05028871391076115, | |
| "grad_norm": 0.10375232249498367, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8090758323669434, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 0.050393700787401574, | |
| "grad_norm": 0.12159629911184311, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9165844917297363, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.050498687664041995, | |
| "grad_norm": 0.1033838540315628, | |
| "learning_rate": 0.0008, | |
| "loss": 2.849384069442749, | |
| "step": 962 | |
| }, | |
| { | |
| "epoch": 0.05060367454068242, | |
| "grad_norm": 0.11069808155298233, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8043620586395264, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 0.05070866141732284, | |
| "grad_norm": 0.12036273628473282, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9057257175445557, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 0.05081364829396325, | |
| "grad_norm": 0.10124826431274414, | |
| "learning_rate": 0.0008, | |
| "loss": 2.830293655395508, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 0.050918635170603674, | |
| "grad_norm": 0.10840156674385071, | |
| "learning_rate": 0.0008, | |
| "loss": 2.892146110534668, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.051023622047244095, | |
| "grad_norm": 0.10134908556938171, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7851529121398926, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 0.051128608923884517, | |
| "grad_norm": 0.10375969111919403, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8426032066345215, | |
| "step": 974 | |
| }, | |
| { | |
| "epoch": 0.05123359580052494, | |
| "grad_norm": 0.10250184684991837, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8460187911987305, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 0.05133858267716535, | |
| "grad_norm": 0.10046141594648361, | |
| "learning_rate": 0.0008, | |
| "loss": 2.790334939956665, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 0.051443569553805774, | |
| "grad_norm": 0.10310408473014832, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8429830074310303, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.051548556430446195, | |
| "grad_norm": 0.10038266330957413, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8468050956726074, | |
| "step": 982 | |
| }, | |
| { | |
| "epoch": 0.051653543307086616, | |
| "grad_norm": 0.11408326029777527, | |
| "learning_rate": 0.0008, | |
| "loss": 2.869588851928711, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 0.05175853018372704, | |
| "grad_norm": 0.10076751559972763, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8215019702911377, | |
| "step": 986 | |
| }, | |
| { | |
| "epoch": 0.05186351706036745, | |
| "grad_norm": 0.11360592395067215, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8531057834625244, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 0.05196850393700787, | |
| "grad_norm": 0.1087770015001297, | |
| "learning_rate": 0.0008, | |
| "loss": 2.857332706451416, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.052073490813648295, | |
| "grad_norm": 0.09793613106012344, | |
| "learning_rate": 0.0008, | |
| "loss": 2.781360626220703, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 0.052178477690288716, | |
| "grad_norm": 0.1005278155207634, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7993361949920654, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 0.05228346456692914, | |
| "grad_norm": 0.10499605536460876, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8021810054779053, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 0.05238845144356955, | |
| "grad_norm": 0.09995300322771072, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8334829807281494, | |
| "step": 998 | |
| }, | |
| { | |
| "epoch": 0.05249343832020997, | |
| "grad_norm": 0.09899105876684189, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7776875495910645, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.052598425196850394, | |
| "grad_norm": 0.10376624763011932, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8660783767700195, | |
| "step": 1002 | |
| }, | |
| { | |
| "epoch": 0.052703412073490816, | |
| "grad_norm": 0.10802112519741058, | |
| "learning_rate": 0.0008, | |
| "loss": 2.864668369293213, | |
| "step": 1004 | |
| }, | |
| { | |
| "epoch": 0.05280839895013124, | |
| "grad_norm": 0.10298653692007065, | |
| "learning_rate": 0.0008, | |
| "loss": 2.800145387649536, | |
| "step": 1006 | |
| }, | |
| { | |
| "epoch": 0.05291338582677165, | |
| "grad_norm": 0.09753638505935669, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8046822547912598, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 0.05301837270341207, | |
| "grad_norm": 0.10928277671337128, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8910574913024902, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.053123359580052494, | |
| "grad_norm": 0.10510570555925369, | |
| "learning_rate": 0.0008, | |
| "loss": 2.772444248199463, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 0.053228346456692915, | |
| "grad_norm": 0.1018993929028511, | |
| "learning_rate": 0.0008, | |
| "loss": 2.821305990219116, | |
| "step": 1014 | |
| }, | |
| { | |
| "epoch": 0.05333333333333334, | |
| "grad_norm": 0.1073940172791481, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8084757328033447, | |
| "step": 1016 | |
| }, | |
| { | |
| "epoch": 0.05343832020997375, | |
| "grad_norm": 0.10738760232925415, | |
| "learning_rate": 0.0008, | |
| "loss": 2.780719041824341, | |
| "step": 1018 | |
| }, | |
| { | |
| "epoch": 0.05354330708661417, | |
| "grad_norm": 0.1023760661482811, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7836318016052246, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.053648293963254594, | |
| "grad_norm": 0.10736978054046631, | |
| "learning_rate": 0.0008, | |
| "loss": 2.846604108810425, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 0.053753280839895015, | |
| "grad_norm": 0.10393604636192322, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7620151042938232, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 0.053858267716535436, | |
| "grad_norm": 0.09899700433015823, | |
| "learning_rate": 0.0008, | |
| "loss": 2.773373603820801, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 0.05396325459317585, | |
| "grad_norm": 0.10414134711027145, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7963967323303223, | |
| "step": 1028 | |
| }, | |
| { | |
| "epoch": 0.05406824146981627, | |
| "grad_norm": 0.1031123548746109, | |
| "learning_rate": 0.0008, | |
| "loss": 2.845099925994873, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.054173228346456694, | |
| "grad_norm": 0.108132004737854, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8229126930236816, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 0.054278215223097115, | |
| "grad_norm": 0.11058522760868073, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8594136238098145, | |
| "step": 1034 | |
| }, | |
| { | |
| "epoch": 0.054383202099737536, | |
| "grad_norm": 0.11115548014640808, | |
| "learning_rate": 0.0008, | |
| "loss": 2.81899094581604, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 0.05448818897637795, | |
| "grad_norm": 0.1087251603603363, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7584517002105713, | |
| "step": 1038 | |
| }, | |
| { | |
| "epoch": 0.05459317585301837, | |
| "grad_norm": 0.10288669168949127, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8365824222564697, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.05469816272965879, | |
| "grad_norm": 0.10305164009332657, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8229153156280518, | |
| "step": 1042 | |
| }, | |
| { | |
| "epoch": 0.054803149606299215, | |
| "grad_norm": 0.1453515738248825, | |
| "learning_rate": 0.0008, | |
| "loss": 2.805276393890381, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 0.054908136482939636, | |
| "grad_norm": 0.10317279398441315, | |
| "learning_rate": 0.0008, | |
| "loss": 2.756784200668335, | |
| "step": 1046 | |
| }, | |
| { | |
| "epoch": 0.05501312335958005, | |
| "grad_norm": 0.09912578016519547, | |
| "learning_rate": 0.0008, | |
| "loss": 2.751218318939209, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 0.05511811023622047, | |
| "grad_norm": 0.10517663508653641, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8035247325897217, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.05522309711286089, | |
| "grad_norm": 0.20114435255527496, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7888002395629883, | |
| "step": 1052 | |
| }, | |
| { | |
| "epoch": 0.055328083989501314, | |
| "grad_norm": 0.10310180485248566, | |
| "learning_rate": 0.0008, | |
| "loss": 2.881930351257324, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 0.055433070866141736, | |
| "grad_norm": 0.09550151228904724, | |
| "learning_rate": 0.0008, | |
| "loss": 2.761927604675293, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 0.05553805774278215, | |
| "grad_norm": 0.10260967165231705, | |
| "learning_rate": 0.0008, | |
| "loss": 2.818103551864624, | |
| "step": 1058 | |
| }, | |
| { | |
| "epoch": 0.05564304461942257, | |
| "grad_norm": 0.12903259694576263, | |
| "learning_rate": 0.0008, | |
| "loss": 2.814908266067505, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.05574803149606299, | |
| "grad_norm": 0.1667206883430481, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8861734867095947, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 0.055853018372703414, | |
| "grad_norm": 0.116305872797966, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7723100185394287, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 0.055958005249343835, | |
| "grad_norm": 0.11162646859884262, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8139381408691406, | |
| "step": 1066 | |
| }, | |
| { | |
| "epoch": 0.05606299212598425, | |
| "grad_norm": 0.11301624029874802, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7693135738372803, | |
| "step": 1068 | |
| }, | |
| { | |
| "epoch": 0.05616797900262467, | |
| "grad_norm": 0.09614431113004684, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7754907608032227, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.05627296587926509, | |
| "grad_norm": 0.10846854001283646, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7906415462493896, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 0.056377952755905514, | |
| "grad_norm": 0.10793575644493103, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7774417400360107, | |
| "step": 1074 | |
| }, | |
| { | |
| "epoch": 0.056482939632545935, | |
| "grad_norm": 0.10033487528562546, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7576797008514404, | |
| "step": 1076 | |
| }, | |
| { | |
| "epoch": 0.05658792650918635, | |
| "grad_norm": 0.10204245150089264, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8064651489257812, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 0.05669291338582677, | |
| "grad_norm": 0.1339305192232132, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8269896507263184, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.05679790026246719, | |
| "grad_norm": 0.10039006918668747, | |
| "learning_rate": 0.0008, | |
| "loss": 2.785451889038086, | |
| "step": 1082 | |
| }, | |
| { | |
| "epoch": 0.056902887139107614, | |
| "grad_norm": 0.09588530659675598, | |
| "learning_rate": 0.0008, | |
| "loss": 2.751840353012085, | |
| "step": 1084 | |
| }, | |
| { | |
| "epoch": 0.057007874015748035, | |
| "grad_norm": 0.09678629785776138, | |
| "learning_rate": 0.0008, | |
| "loss": 2.820312738418579, | |
| "step": 1086 | |
| }, | |
| { | |
| "epoch": 0.05711286089238845, | |
| "grad_norm": 0.09806337207555771, | |
| "learning_rate": 0.0008, | |
| "loss": 2.735081434249878, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 0.05721784776902887, | |
| "grad_norm": 0.11089258641004562, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7608463764190674, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.05732283464566929, | |
| "grad_norm": 0.09958311170339584, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7519888877868652, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 0.05742782152230971, | |
| "grad_norm": 0.10076095163822174, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8068771362304688, | |
| "step": 1094 | |
| }, | |
| { | |
| "epoch": 0.057532808398950135, | |
| "grad_norm": 0.09349599480628967, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8188719749450684, | |
| "step": 1096 | |
| }, | |
| { | |
| "epoch": 0.05763779527559055, | |
| "grad_norm": 0.09559649974107742, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8073160648345947, | |
| "step": 1098 | |
| }, | |
| { | |
| "epoch": 0.05774278215223097, | |
| "grad_norm": 0.0973324403166771, | |
| "learning_rate": 0.0008, | |
| "loss": 2.81024432182312, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.05784776902887139, | |
| "grad_norm": 0.10361398011445999, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7769150733947754, | |
| "step": 1102 | |
| }, | |
| { | |
| "epoch": 0.05795275590551181, | |
| "grad_norm": 0.09911870211362839, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7836496829986572, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 0.058057742782152234, | |
| "grad_norm": 0.0959470123052597, | |
| "learning_rate": 0.0008, | |
| "loss": 2.824338436126709, | |
| "step": 1106 | |
| }, | |
| { | |
| "epoch": 0.05816272965879265, | |
| "grad_norm": 0.10547234117984772, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8017425537109375, | |
| "step": 1108 | |
| }, | |
| { | |
| "epoch": 0.05826771653543307, | |
| "grad_norm": 0.11770127713680267, | |
| "learning_rate": 0.0008, | |
| "loss": 2.778801918029785, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.05837270341207349, | |
| "grad_norm": 0.10263510793447495, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7272756099700928, | |
| "step": 1112 | |
| }, | |
| { | |
| "epoch": 0.05847769028871391, | |
| "grad_norm": 0.10365133732557297, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6706371307373047, | |
| "step": 1114 | |
| }, | |
| { | |
| "epoch": 0.058582677165354334, | |
| "grad_norm": 0.10239488631486893, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7648658752441406, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 0.05868766404199475, | |
| "grad_norm": 0.10074584931135178, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7860660552978516, | |
| "step": 1118 | |
| }, | |
| { | |
| "epoch": 0.05879265091863517, | |
| "grad_norm": 0.09691484272480011, | |
| "learning_rate": 0.0008, | |
| "loss": 2.776440382003784, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.05889763779527559, | |
| "grad_norm": 0.09571411460638046, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7625234127044678, | |
| "step": 1122 | |
| }, | |
| { | |
| "epoch": 0.05900262467191601, | |
| "grad_norm": 0.10247057676315308, | |
| "learning_rate": 0.0008, | |
| "loss": 2.749131679534912, | |
| "step": 1124 | |
| }, | |
| { | |
| "epoch": 0.059107611548556434, | |
| "grad_norm": 0.10407362133264542, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8207249641418457, | |
| "step": 1126 | |
| }, | |
| { | |
| "epoch": 0.05921259842519685, | |
| "grad_norm": 0.09510679543018341, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6953272819519043, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 0.05931758530183727, | |
| "grad_norm": 0.10698787122964859, | |
| "learning_rate": 0.0008, | |
| "loss": 2.795836925506592, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.05942257217847769, | |
| "grad_norm": 0.09319344162940979, | |
| "learning_rate": 0.0008, | |
| "loss": 2.751784324645996, | |
| "step": 1132 | |
| }, | |
| { | |
| "epoch": 0.05952755905511811, | |
| "grad_norm": 0.1036166325211525, | |
| "learning_rate": 0.0008, | |
| "loss": 2.768706798553467, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 0.059632545931758534, | |
| "grad_norm": 0.1037125214934349, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7052805423736572, | |
| "step": 1136 | |
| }, | |
| { | |
| "epoch": 0.05973753280839895, | |
| "grad_norm": 0.09657058864831924, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7239277362823486, | |
| "step": 1138 | |
| }, | |
| { | |
| "epoch": 0.05984251968503937, | |
| "grad_norm": 0.09930210560560226, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7407634258270264, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.05994750656167979, | |
| "grad_norm": 0.10446039587259293, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7894794940948486, | |
| "step": 1142 | |
| }, | |
| { | |
| "epoch": 0.06005249343832021, | |
| "grad_norm": 0.09340780973434448, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7534453868865967, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 0.06015748031496063, | |
| "grad_norm": 0.09551321715116501, | |
| "learning_rate": 0.0008, | |
| "loss": 2.690730571746826, | |
| "step": 1146 | |
| }, | |
| { | |
| "epoch": 0.06026246719160105, | |
| "grad_norm": 0.10366897284984589, | |
| "learning_rate": 0.0008, | |
| "loss": 2.773142099380493, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 0.06036745406824147, | |
| "grad_norm": 0.09920721501111984, | |
| "learning_rate": 0.0008, | |
| "loss": 2.736051321029663, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.06047244094488189, | |
| "grad_norm": 0.09954190999269485, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7246105670928955, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 0.06057742782152231, | |
| "grad_norm": 0.0974222794175148, | |
| "learning_rate": 0.0008, | |
| "loss": 2.731856107711792, | |
| "step": 1154 | |
| }, | |
| { | |
| "epoch": 0.06068241469816273, | |
| "grad_norm": 0.097303107380867, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7895407676696777, | |
| "step": 1156 | |
| }, | |
| { | |
| "epoch": 0.06078740157480315, | |
| "grad_norm": 0.09522704035043716, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7590274810791016, | |
| "step": 1158 | |
| }, | |
| { | |
| "epoch": 0.06089238845144357, | |
| "grad_norm": 0.09463141113519669, | |
| "learning_rate": 0.0008, | |
| "loss": 2.765191078186035, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.06099737532808399, | |
| "grad_norm": 0.09408853203058243, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7823188304901123, | |
| "step": 1162 | |
| }, | |
| { | |
| "epoch": 0.06110236220472441, | |
| "grad_norm": 0.09858901798725128, | |
| "learning_rate": 0.0008, | |
| "loss": 2.707946538925171, | |
| "step": 1164 | |
| }, | |
| { | |
| "epoch": 0.06120734908136483, | |
| "grad_norm": 0.09399278461933136, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7710776329040527, | |
| "step": 1166 | |
| }, | |
| { | |
| "epoch": 0.06131233595800525, | |
| "grad_norm": 0.09577006846666336, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7472236156463623, | |
| "step": 1168 | |
| }, | |
| { | |
| "epoch": 0.06141732283464567, | |
| "grad_norm": 0.10166503489017487, | |
| "learning_rate": 0.0008, | |
| "loss": 2.774897575378418, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.06152230971128609, | |
| "grad_norm": 0.09624114632606506, | |
| "learning_rate": 0.0008, | |
| "loss": 2.748838424682617, | |
| "step": 1172 | |
| }, | |
| { | |
| "epoch": 0.06162729658792651, | |
| "grad_norm": 0.09472914040088654, | |
| "learning_rate": 0.0008, | |
| "loss": 2.771334171295166, | |
| "step": 1174 | |
| }, | |
| { | |
| "epoch": 0.06173228346456693, | |
| "grad_norm": 0.09809508174657822, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8077011108398438, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 0.06183727034120735, | |
| "grad_norm": 0.09370114654302597, | |
| "learning_rate": 0.0008, | |
| "loss": 2.724283218383789, | |
| "step": 1178 | |
| }, | |
| { | |
| "epoch": 0.06194225721784777, | |
| "grad_norm": 0.0985821783542633, | |
| "learning_rate": 0.0008, | |
| "loss": 2.880124568939209, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.06204724409448819, | |
| "grad_norm": 0.09660397469997406, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8263754844665527, | |
| "step": 1182 | |
| }, | |
| { | |
| "epoch": 0.06215223097112861, | |
| "grad_norm": 0.09598527103662491, | |
| "learning_rate": 0.0008, | |
| "loss": 2.666367530822754, | |
| "step": 1184 | |
| }, | |
| { | |
| "epoch": 0.06225721784776903, | |
| "grad_norm": 0.09384316205978394, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7239773273468018, | |
| "step": 1186 | |
| }, | |
| { | |
| "epoch": 0.06236220472440945, | |
| "grad_norm": 0.0932997465133667, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7118349075317383, | |
| "step": 1188 | |
| }, | |
| { | |
| "epoch": 0.06246719160104987, | |
| "grad_norm": 0.09373453259468079, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7382428646087646, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.06257217847769028, | |
| "grad_norm": 0.09803857654333115, | |
| "learning_rate": 0.0008, | |
| "loss": 2.755943775177002, | |
| "step": 1192 | |
| }, | |
| { | |
| "epoch": 0.06267716535433071, | |
| "grad_norm": 0.09311717003583908, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7395267486572266, | |
| "step": 1194 | |
| }, | |
| { | |
| "epoch": 0.06278215223097112, | |
| "grad_norm": 0.09369563311338425, | |
| "learning_rate": 0.0008, | |
| "loss": 2.785970449447632, | |
| "step": 1196 | |
| }, | |
| { | |
| "epoch": 0.06288713910761155, | |
| "grad_norm": 0.09036700427532196, | |
| "learning_rate": 0.0008, | |
| "loss": 2.776278257369995, | |
| "step": 1198 | |
| }, | |
| { | |
| "epoch": 0.06299212598425197, | |
| "grad_norm": 0.09363891929388046, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7700867652893066, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.06309711286089238, | |
| "grad_norm": 0.09650267660617828, | |
| "learning_rate": 0.0008, | |
| "loss": 2.713502883911133, | |
| "step": 1202 | |
| }, | |
| { | |
| "epoch": 0.06320209973753281, | |
| "grad_norm": 0.10293524712324142, | |
| "learning_rate": 0.0008, | |
| "loss": 2.9022140502929688, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 0.06330708661417322, | |
| "grad_norm": 0.09519843757152557, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7313969135284424, | |
| "step": 1206 | |
| }, | |
| { | |
| "epoch": 0.06341207349081365, | |
| "grad_norm": 0.0950169712305069, | |
| "learning_rate": 0.0008, | |
| "loss": 2.774022340774536, | |
| "step": 1208 | |
| }, | |
| { | |
| "epoch": 0.06351706036745407, | |
| "grad_norm": 0.09091480821371078, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7015767097473145, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.06362204724409448, | |
| "grad_norm": 0.09598124027252197, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7730629444122314, | |
| "step": 1212 | |
| }, | |
| { | |
| "epoch": 0.06372703412073491, | |
| "grad_norm": 0.09794464707374573, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8449044227600098, | |
| "step": 1214 | |
| }, | |
| { | |
| "epoch": 0.06383202099737532, | |
| "grad_norm": 0.10073459148406982, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7421374320983887, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 0.06393700787401575, | |
| "grad_norm": 0.09479549527168274, | |
| "learning_rate": 0.0008, | |
| "loss": 2.726524829864502, | |
| "step": 1218 | |
| }, | |
| { | |
| "epoch": 0.06404199475065617, | |
| "grad_norm": 0.09764054417610168, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7664859294891357, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.06414698162729658, | |
| "grad_norm": 0.09193890541791916, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7090096473693848, | |
| "step": 1222 | |
| }, | |
| { | |
| "epoch": 0.06425196850393701, | |
| "grad_norm": 0.0995439738035202, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6843483448028564, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 0.06435695538057742, | |
| "grad_norm": 0.09356983751058578, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7224812507629395, | |
| "step": 1226 | |
| }, | |
| { | |
| "epoch": 0.06446194225721785, | |
| "grad_norm": 0.0965329185128212, | |
| "learning_rate": 0.0008, | |
| "loss": 2.739919900894165, | |
| "step": 1228 | |
| }, | |
| { | |
| "epoch": 0.06456692913385827, | |
| "grad_norm": 0.09178649634122849, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7742674350738525, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.06467191601049868, | |
| "grad_norm": 0.09057556837797165, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6888370513916016, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 0.06477690288713911, | |
| "grad_norm": 0.09977737814188004, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7652909755706787, | |
| "step": 1234 | |
| }, | |
| { | |
| "epoch": 0.06488188976377952, | |
| "grad_norm": 0.09570503234863281, | |
| "learning_rate": 0.0008, | |
| "loss": 2.719186782836914, | |
| "step": 1236 | |
| }, | |
| { | |
| "epoch": 0.06498687664041995, | |
| "grad_norm": 0.09464333951473236, | |
| "learning_rate": 0.0008, | |
| "loss": 2.682467460632324, | |
| "step": 1238 | |
| }, | |
| { | |
| "epoch": 0.06509186351706037, | |
| "grad_norm": 0.10610726475715637, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6956610679626465, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.06519685039370078, | |
| "grad_norm": 0.09222975373268127, | |
| "learning_rate": 0.0008, | |
| "loss": 2.741663694381714, | |
| "step": 1242 | |
| }, | |
| { | |
| "epoch": 0.06530183727034121, | |
| "grad_norm": 0.09509462118148804, | |
| "learning_rate": 0.0008, | |
| "loss": 2.739074468612671, | |
| "step": 1244 | |
| }, | |
| { | |
| "epoch": 0.06540682414698162, | |
| "grad_norm": 0.09526625275611877, | |
| "learning_rate": 0.0008, | |
| "loss": 2.716810464859009, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 0.06551181102362205, | |
| "grad_norm": 0.08917568624019623, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7790722846984863, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 0.06561679790026247, | |
| "grad_norm": 0.08985543996095657, | |
| "learning_rate": 0.0008, | |
| "loss": 2.748087167739868, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.06572178477690288, | |
| "grad_norm": 0.09263970702886581, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6896450519561768, | |
| "step": 1252 | |
| }, | |
| { | |
| "epoch": 0.06582677165354331, | |
| "grad_norm": 0.09330984950065613, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6958892345428467, | |
| "step": 1254 | |
| }, | |
| { | |
| "epoch": 0.06593175853018372, | |
| "grad_norm": 0.08814782649278641, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7310869693756104, | |
| "step": 1256 | |
| }, | |
| { | |
| "epoch": 0.06603674540682415, | |
| "grad_norm": 0.09247346967458725, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6854116916656494, | |
| "step": 1258 | |
| }, | |
| { | |
| "epoch": 0.06614173228346457, | |
| "grad_norm": 0.0904579684138298, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7304842472076416, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.06624671916010498, | |
| "grad_norm": 0.10152405500411987, | |
| "learning_rate": 0.0008, | |
| "loss": 2.702768325805664, | |
| "step": 1262 | |
| }, | |
| { | |
| "epoch": 0.06635170603674541, | |
| "grad_norm": 0.09937993437051773, | |
| "learning_rate": 0.0008, | |
| "loss": 2.766422986984253, | |
| "step": 1264 | |
| }, | |
| { | |
| "epoch": 0.06645669291338582, | |
| "grad_norm": 0.09391853213310242, | |
| "learning_rate": 0.0008, | |
| "loss": 2.707615613937378, | |
| "step": 1266 | |
| }, | |
| { | |
| "epoch": 0.06656167979002625, | |
| "grad_norm": 0.08916128426790237, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6421377658843994, | |
| "step": 1268 | |
| }, | |
| { | |
| "epoch": 0.06666666666666667, | |
| "grad_norm": 0.11973083019256592, | |
| "learning_rate": 0.0008, | |
| "loss": 2.764481782913208, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.06677165354330708, | |
| "grad_norm": 0.09177809208631516, | |
| "learning_rate": 0.0008, | |
| "loss": 2.782212972640991, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 0.06687664041994751, | |
| "grad_norm": 0.09051013737916946, | |
| "learning_rate": 0.0008, | |
| "loss": 2.728666067123413, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 0.06698162729658792, | |
| "grad_norm": 0.0887698158621788, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6825649738311768, | |
| "step": 1276 | |
| }, | |
| { | |
| "epoch": 0.06708661417322835, | |
| "grad_norm": 0.08877133578062057, | |
| "learning_rate": 0.0008, | |
| "loss": 2.770366668701172, | |
| "step": 1278 | |
| }, | |
| { | |
| "epoch": 0.06719160104986877, | |
| "grad_norm": 0.09202440083026886, | |
| "learning_rate": 0.0008, | |
| "loss": 2.774871826171875, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.06729658792650918, | |
| "grad_norm": 0.09336346387863159, | |
| "learning_rate": 0.0008, | |
| "loss": 2.733929395675659, | |
| "step": 1282 | |
| }, | |
| { | |
| "epoch": 0.06740157480314961, | |
| "grad_norm": 0.09517822414636612, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7393155097961426, | |
| "step": 1284 | |
| }, | |
| { | |
| "epoch": 0.06750656167979002, | |
| "grad_norm": 0.09316384792327881, | |
| "learning_rate": 0.0008, | |
| "loss": 2.726889133453369, | |
| "step": 1286 | |
| }, | |
| { | |
| "epoch": 0.06761154855643045, | |
| "grad_norm": 0.09062747657299042, | |
| "learning_rate": 0.0008, | |
| "loss": 2.676839590072632, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 0.06771653543307087, | |
| "grad_norm": 0.0867094025015831, | |
| "learning_rate": 0.0008, | |
| "loss": 2.712338924407959, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.06782152230971128, | |
| "grad_norm": 0.09216507524251938, | |
| "learning_rate": 0.0008, | |
| "loss": 2.76090931892395, | |
| "step": 1292 | |
| }, | |
| { | |
| "epoch": 0.06792650918635171, | |
| "grad_norm": 0.09290657192468643, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7047674655914307, | |
| "step": 1294 | |
| }, | |
| { | |
| "epoch": 0.06803149606299212, | |
| "grad_norm": 0.09055540710687637, | |
| "learning_rate": 0.0008, | |
| "loss": 2.725385904312134, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 0.06813648293963255, | |
| "grad_norm": 0.09026801586151123, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7393622398376465, | |
| "step": 1298 | |
| }, | |
| { | |
| "epoch": 0.06824146981627296, | |
| "grad_norm": 0.08923443406820297, | |
| "learning_rate": 0.0008, | |
| "loss": 2.70747709274292, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.06834645669291338, | |
| "grad_norm": 0.09018641710281372, | |
| "learning_rate": 0.0008, | |
| "loss": 2.687223434448242, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 0.06845144356955381, | |
| "grad_norm": 0.08945067226886749, | |
| "learning_rate": 0.0008, | |
| "loss": 2.758821964263916, | |
| "step": 1304 | |
| }, | |
| { | |
| "epoch": 0.06855643044619422, | |
| "grad_norm": 0.08930539339780807, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7447938919067383, | |
| "step": 1306 | |
| }, | |
| { | |
| "epoch": 0.06866141732283465, | |
| "grad_norm": 0.09555280953645706, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6633846759796143, | |
| "step": 1308 | |
| }, | |
| { | |
| "epoch": 0.06876640419947506, | |
| "grad_norm": 0.09034199267625809, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7054800987243652, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.06887139107611548, | |
| "grad_norm": 0.0911264568567276, | |
| "learning_rate": 0.0008, | |
| "loss": 2.703281879425049, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 0.06897637795275591, | |
| "grad_norm": 0.11208830028772354, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7217724323272705, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 0.06908136482939632, | |
| "grad_norm": 0.09283586591482162, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6326820850372314, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 0.06918635170603675, | |
| "grad_norm": 0.09743106365203857, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7401678562164307, | |
| "step": 1318 | |
| }, | |
| { | |
| "epoch": 0.06929133858267716, | |
| "grad_norm": 0.10332754254341125, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6880064010620117, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.06939632545931758, | |
| "grad_norm": 0.0905320793390274, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8321988582611084, | |
| "step": 1322 | |
| }, | |
| { | |
| "epoch": 0.06950131233595801, | |
| "grad_norm": 0.09661230444908142, | |
| "learning_rate": 0.0008, | |
| "loss": 2.820366144180298, | |
| "step": 1324 | |
| }, | |
| { | |
| "epoch": 0.06960629921259842, | |
| "grad_norm": 0.1010541319847107, | |
| "learning_rate": 0.0008, | |
| "loss": 2.669790506362915, | |
| "step": 1326 | |
| }, | |
| { | |
| "epoch": 0.06971128608923885, | |
| "grad_norm": 0.10069449245929718, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6688294410705566, | |
| "step": 1328 | |
| }, | |
| { | |
| "epoch": 0.06981627296587926, | |
| "grad_norm": 0.0907818153500557, | |
| "learning_rate": 0.0008, | |
| "loss": 2.711893081665039, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.06992125984251968, | |
| "grad_norm": 0.08876825869083405, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7334165573120117, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 0.0700262467191601, | |
| "grad_norm": 0.08738885074853897, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6676371097564697, | |
| "step": 1334 | |
| }, | |
| { | |
| "epoch": 0.07013123359580052, | |
| "grad_norm": 0.09067124128341675, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7439775466918945, | |
| "step": 1336 | |
| }, | |
| { | |
| "epoch": 0.07023622047244095, | |
| "grad_norm": 0.08947622030973434, | |
| "learning_rate": 0.0008, | |
| "loss": 2.773383617401123, | |
| "step": 1338 | |
| }, | |
| { | |
| "epoch": 0.07034120734908136, | |
| "grad_norm": 0.08832672238349915, | |
| "learning_rate": 0.0008, | |
| "loss": 2.684849500656128, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.07044619422572178, | |
| "grad_norm": 0.09062019735574722, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6650891304016113, | |
| "step": 1342 | |
| }, | |
| { | |
| "epoch": 0.0705511811023622, | |
| "grad_norm": 0.09270370006561279, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7085578441619873, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 0.07065616797900262, | |
| "grad_norm": 0.08942906558513641, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7183375358581543, | |
| "step": 1346 | |
| }, | |
| { | |
| "epoch": 0.07076115485564305, | |
| "grad_norm": 0.08755499869585037, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6928529739379883, | |
| "step": 1348 | |
| }, | |
| { | |
| "epoch": 0.07086614173228346, | |
| "grad_norm": 0.0885811522603035, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7188720703125, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.07097112860892388, | |
| "grad_norm": 0.08931387960910797, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6251308917999268, | |
| "step": 1352 | |
| }, | |
| { | |
| "epoch": 0.0710761154855643, | |
| "grad_norm": 0.0879686251282692, | |
| "learning_rate": 0.0008, | |
| "loss": 2.74489688873291, | |
| "step": 1354 | |
| }, | |
| { | |
| "epoch": 0.07118110236220472, | |
| "grad_norm": 0.08499078452587128, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6151463985443115, | |
| "step": 1356 | |
| }, | |
| { | |
| "epoch": 0.07128608923884515, | |
| "grad_norm": 0.08597178012132645, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6897919178009033, | |
| "step": 1358 | |
| }, | |
| { | |
| "epoch": 0.07139107611548556, | |
| "grad_norm": 0.09871555864810944, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6851541996002197, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.07149606299212598, | |
| "grad_norm": 0.08770178258419037, | |
| "learning_rate": 0.0008, | |
| "loss": 2.628960371017456, | |
| "step": 1362 | |
| }, | |
| { | |
| "epoch": 0.0716010498687664, | |
| "grad_norm": 0.09183717519044876, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6417086124420166, | |
| "step": 1364 | |
| }, | |
| { | |
| "epoch": 0.07170603674540682, | |
| "grad_norm": 0.08580727875232697, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6884584426879883, | |
| "step": 1366 | |
| }, | |
| { | |
| "epoch": 0.07181102362204725, | |
| "grad_norm": 0.08483970910310745, | |
| "learning_rate": 0.0008, | |
| "loss": 2.75624942779541, | |
| "step": 1368 | |
| }, | |
| { | |
| "epoch": 0.07191601049868766, | |
| "grad_norm": 0.09414925426244736, | |
| "learning_rate": 0.0008, | |
| "loss": 2.690917730331421, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.07202099737532808, | |
| "grad_norm": 0.0874631330370903, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6809377670288086, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 0.0721259842519685, | |
| "grad_norm": 0.09258206188678741, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6989850997924805, | |
| "step": 1374 | |
| }, | |
| { | |
| "epoch": 0.07223097112860892, | |
| "grad_norm": 0.08777697384357452, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5786826610565186, | |
| "step": 1376 | |
| }, | |
| { | |
| "epoch": 0.07233595800524935, | |
| "grad_norm": 0.09499172866344452, | |
| "learning_rate": 0.0008, | |
| "loss": 2.704826593399048, | |
| "step": 1378 | |
| }, | |
| { | |
| "epoch": 0.07244094488188976, | |
| "grad_norm": 0.08798379451036453, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6959006786346436, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.07254593175853018, | |
| "grad_norm": 0.09166393429040909, | |
| "learning_rate": 0.0008, | |
| "loss": 2.744873523712158, | |
| "step": 1382 | |
| }, | |
| { | |
| "epoch": 0.0726509186351706, | |
| "grad_norm": 0.08753436803817749, | |
| "learning_rate": 0.0008, | |
| "loss": 2.647568464279175, | |
| "step": 1384 | |
| }, | |
| { | |
| "epoch": 0.07275590551181102, | |
| "grad_norm": 0.0951622724533081, | |
| "learning_rate": 0.0008, | |
| "loss": 2.769989490509033, | |
| "step": 1386 | |
| }, | |
| { | |
| "epoch": 0.07286089238845145, | |
| "grad_norm": 0.08674084395170212, | |
| "learning_rate": 0.0008, | |
| "loss": 2.747138261795044, | |
| "step": 1388 | |
| }, | |
| { | |
| "epoch": 0.07296587926509186, | |
| "grad_norm": 0.09108833223581314, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6137795448303223, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.07307086614173228, | |
| "grad_norm": 0.08870238810777664, | |
| "learning_rate": 0.0008, | |
| "loss": 2.666318655014038, | |
| "step": 1392 | |
| }, | |
| { | |
| "epoch": 0.0731758530183727, | |
| "grad_norm": 0.08854766190052032, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6619858741760254, | |
| "step": 1394 | |
| }, | |
| { | |
| "epoch": 0.07328083989501312, | |
| "grad_norm": 0.08897228538990021, | |
| "learning_rate": 0.0008, | |
| "loss": 2.64046049118042, | |
| "step": 1396 | |
| }, | |
| { | |
| "epoch": 0.07338582677165355, | |
| "grad_norm": 0.08897323161363602, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7652525901794434, | |
| "step": 1398 | |
| }, | |
| { | |
| "epoch": 0.07349081364829396, | |
| "grad_norm": 0.08516496419906616, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5715649127960205, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.07359580052493438, | |
| "grad_norm": 0.08876385539770126, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7622568607330322, | |
| "step": 1402 | |
| }, | |
| { | |
| "epoch": 0.0737007874015748, | |
| "grad_norm": 0.08872676640748978, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7113258838653564, | |
| "step": 1404 | |
| }, | |
| { | |
| "epoch": 0.07380577427821522, | |
| "grad_norm": 0.08686773478984833, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6650986671447754, | |
| "step": 1406 | |
| }, | |
| { | |
| "epoch": 0.07391076115485565, | |
| "grad_norm": 0.09066683799028397, | |
| "learning_rate": 0.0008, | |
| "loss": 2.636753559112549, | |
| "step": 1408 | |
| }, | |
| { | |
| "epoch": 0.07401574803149606, | |
| "grad_norm": 0.08717681467533112, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6704976558685303, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.07412073490813648, | |
| "grad_norm": 0.08846788853406906, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6926631927490234, | |
| "step": 1412 | |
| }, | |
| { | |
| "epoch": 0.0742257217847769, | |
| "grad_norm": 0.09278976172208786, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6709396839141846, | |
| "step": 1414 | |
| }, | |
| { | |
| "epoch": 0.07433070866141732, | |
| "grad_norm": 0.08742888271808624, | |
| "learning_rate": 0.0008, | |
| "loss": 2.691894769668579, | |
| "step": 1416 | |
| }, | |
| { | |
| "epoch": 0.07443569553805775, | |
| "grad_norm": 0.08882424980401993, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6744706630706787, | |
| "step": 1418 | |
| }, | |
| { | |
| "epoch": 0.07454068241469816, | |
| "grad_norm": 0.09900332987308502, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6957004070281982, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.07464566929133858, | |
| "grad_norm": 0.08583637326955795, | |
| "learning_rate": 0.0008, | |
| "loss": 2.629910707473755, | |
| "step": 1422 | |
| }, | |
| { | |
| "epoch": 0.074750656167979, | |
| "grad_norm": 0.09553971141576767, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7146975994110107, | |
| "step": 1424 | |
| }, | |
| { | |
| "epoch": 0.07485564304461942, | |
| "grad_norm": 0.08393795043230057, | |
| "learning_rate": 0.0008, | |
| "loss": 2.644871234893799, | |
| "step": 1426 | |
| }, | |
| { | |
| "epoch": 0.07496062992125985, | |
| "grad_norm": 0.08811771124601364, | |
| "learning_rate": 0.0008, | |
| "loss": 2.74150013923645, | |
| "step": 1428 | |
| }, | |
| { | |
| "epoch": 0.07506561679790026, | |
| "grad_norm": 0.08552783727645874, | |
| "learning_rate": 0.0008, | |
| "loss": 2.626519203186035, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.07517060367454068, | |
| "grad_norm": 0.10242731124162674, | |
| "learning_rate": 0.0008, | |
| "loss": 2.641078472137451, | |
| "step": 1432 | |
| }, | |
| { | |
| "epoch": 0.0752755905511811, | |
| "grad_norm": 0.09166337549686432, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6449639797210693, | |
| "step": 1434 | |
| }, | |
| { | |
| "epoch": 0.07538057742782152, | |
| "grad_norm": 0.08761779218912125, | |
| "learning_rate": 0.0008, | |
| "loss": 2.677574634552002, | |
| "step": 1436 | |
| }, | |
| { | |
| "epoch": 0.07548556430446195, | |
| "grad_norm": 0.08642394095659256, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6905453205108643, | |
| "step": 1438 | |
| }, | |
| { | |
| "epoch": 0.07559055118110236, | |
| "grad_norm": 0.08333615213632584, | |
| "learning_rate": 0.0008, | |
| "loss": 2.592236280441284, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.07569553805774278, | |
| "grad_norm": 0.08484560251235962, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6854631900787354, | |
| "step": 1442 | |
| }, | |
| { | |
| "epoch": 0.0758005249343832, | |
| "grad_norm": 0.0837368294596672, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6374318599700928, | |
| "step": 1444 | |
| }, | |
| { | |
| "epoch": 0.07590551181102362, | |
| "grad_norm": 0.09100774675607681, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6125762462615967, | |
| "step": 1446 | |
| }, | |
| { | |
| "epoch": 0.07601049868766405, | |
| "grad_norm": 0.08711443096399307, | |
| "learning_rate": 0.0008, | |
| "loss": 2.597930669784546, | |
| "step": 1448 | |
| }, | |
| { | |
| "epoch": 0.07611548556430446, | |
| "grad_norm": 0.08646796643733978, | |
| "learning_rate": 0.0008, | |
| "loss": 2.648893356323242, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.07622047244094488, | |
| "grad_norm": 0.09896808862686157, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6535043716430664, | |
| "step": 1452 | |
| }, | |
| { | |
| "epoch": 0.0763254593175853, | |
| "grad_norm": 0.08856473863124847, | |
| "learning_rate": 0.0008, | |
| "loss": 2.602234363555908, | |
| "step": 1454 | |
| }, | |
| { | |
| "epoch": 0.07643044619422572, | |
| "grad_norm": 0.0864076167345047, | |
| "learning_rate": 0.0008, | |
| "loss": 2.689237594604492, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 0.07653543307086615, | |
| "grad_norm": 0.08773746341466904, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6581928730010986, | |
| "step": 1458 | |
| }, | |
| { | |
| "epoch": 0.07664041994750656, | |
| "grad_norm": 0.08633334189653397, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5990493297576904, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.07674540682414698, | |
| "grad_norm": 0.08365172892808914, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6227877140045166, | |
| "step": 1462 | |
| }, | |
| { | |
| "epoch": 0.0768503937007874, | |
| "grad_norm": 0.08256988227367401, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5598974227905273, | |
| "step": 1464 | |
| }, | |
| { | |
| "epoch": 0.07695538057742782, | |
| "grad_norm": 0.08591403067111969, | |
| "learning_rate": 0.0008, | |
| "loss": 2.673539400100708, | |
| "step": 1466 | |
| }, | |
| { | |
| "epoch": 0.07706036745406825, | |
| "grad_norm": 0.15994617342948914, | |
| "learning_rate": 0.0008, | |
| "loss": 2.664999008178711, | |
| "step": 1468 | |
| }, | |
| { | |
| "epoch": 0.07716535433070866, | |
| "grad_norm": 0.0995364636182785, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6732304096221924, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.07727034120734907, | |
| "grad_norm": 0.49649930000305176, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6371679306030273, | |
| "step": 1472 | |
| }, | |
| { | |
| "epoch": 0.0773753280839895, | |
| "grad_norm": 0.13202159106731415, | |
| "learning_rate": 0.0008, | |
| "loss": 2.666672468185425, | |
| "step": 1474 | |
| }, | |
| { | |
| "epoch": 0.07748031496062992, | |
| "grad_norm": 0.14444680511951447, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6946022510528564, | |
| "step": 1476 | |
| }, | |
| { | |
| "epoch": 0.07758530183727035, | |
| "grad_norm": 0.26887446641921997, | |
| "learning_rate": 0.0008, | |
| "loss": 2.8010661602020264, | |
| "step": 1478 | |
| }, | |
| { | |
| "epoch": 0.07769028871391076, | |
| "grad_norm": 0.1028187945485115, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7120325565338135, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.07779527559055117, | |
| "grad_norm": 0.10403750836849213, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7645153999328613, | |
| "step": 1482 | |
| }, | |
| { | |
| "epoch": 0.0779002624671916, | |
| "grad_norm": 0.097693532705307, | |
| "learning_rate": 0.0008, | |
| "loss": 2.569256067276001, | |
| "step": 1484 | |
| }, | |
| { | |
| "epoch": 0.07800524934383202, | |
| "grad_norm": 0.09556399285793304, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5498592853546143, | |
| "step": 1486 | |
| }, | |
| { | |
| "epoch": 0.07811023622047245, | |
| "grad_norm": 0.09795936942100525, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6981966495513916, | |
| "step": 1488 | |
| }, | |
| { | |
| "epoch": 0.07821522309711286, | |
| "grad_norm": 0.16835343837738037, | |
| "learning_rate": 0.0008, | |
| "loss": 2.602991819381714, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.07832020997375327, | |
| "grad_norm": 0.08939483761787415, | |
| "learning_rate": 0.0008, | |
| "loss": 2.639512062072754, | |
| "step": 1492 | |
| }, | |
| { | |
| "epoch": 0.0784251968503937, | |
| "grad_norm": 0.08930263668298721, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6877212524414062, | |
| "step": 1494 | |
| }, | |
| { | |
| "epoch": 0.07853018372703412, | |
| "grad_norm": 0.08753892779350281, | |
| "learning_rate": 0.0008, | |
| "loss": 2.748821973800659, | |
| "step": 1496 | |
| }, | |
| { | |
| "epoch": 0.07863517060367455, | |
| "grad_norm": 0.08467117697000504, | |
| "learning_rate": 0.0008, | |
| "loss": 2.636019706726074, | |
| "step": 1498 | |
| }, | |
| { | |
| "epoch": 0.07874015748031496, | |
| "grad_norm": 0.08635459095239639, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6212708950042725, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.07884514435695537, | |
| "grad_norm": 0.08619186282157898, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6356201171875, | |
| "step": 1502 | |
| }, | |
| { | |
| "epoch": 0.0789501312335958, | |
| "grad_norm": 0.08826661854982376, | |
| "learning_rate": 0.0008, | |
| "loss": 2.682232618331909, | |
| "step": 1504 | |
| }, | |
| { | |
| "epoch": 0.07905511811023622, | |
| "grad_norm": 0.08308306336402893, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6641902923583984, | |
| "step": 1506 | |
| }, | |
| { | |
| "epoch": 0.07916010498687664, | |
| "grad_norm": 0.08432268351316452, | |
| "learning_rate": 0.0008, | |
| "loss": 2.608417272567749, | |
| "step": 1508 | |
| }, | |
| { | |
| "epoch": 0.07926509186351706, | |
| "grad_norm": 0.08366723358631134, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6295907497406006, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.07937007874015747, | |
| "grad_norm": 0.08625472337007523, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6681504249572754, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 0.0794750656167979, | |
| "grad_norm": 0.08417803794145584, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6194047927856445, | |
| "step": 1514 | |
| }, | |
| { | |
| "epoch": 0.07958005249343832, | |
| "grad_norm": 0.08445578813552856, | |
| "learning_rate": 0.0008, | |
| "loss": 2.603327751159668, | |
| "step": 1516 | |
| }, | |
| { | |
| "epoch": 0.07968503937007874, | |
| "grad_norm": 0.0818251222372055, | |
| "learning_rate": 0.0008, | |
| "loss": 2.602876901626587, | |
| "step": 1518 | |
| }, | |
| { | |
| "epoch": 0.07979002624671916, | |
| "grad_norm": 0.08363281935453415, | |
| "learning_rate": 0.0008, | |
| "loss": 2.632730484008789, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.07989501312335957, | |
| "grad_norm": 0.08214236050844193, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5745739936828613, | |
| "step": 1522 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.08501773327589035, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5629425048828125, | |
| "step": 1524 | |
| }, | |
| { | |
| "epoch": 0.08010498687664042, | |
| "grad_norm": 0.0836695060133934, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6567468643188477, | |
| "step": 1526 | |
| }, | |
| { | |
| "epoch": 0.08020997375328084, | |
| "grad_norm": 0.09470122307538986, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6306705474853516, | |
| "step": 1528 | |
| }, | |
| { | |
| "epoch": 0.08031496062992126, | |
| "grad_norm": 0.08731096982955933, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6195871829986572, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.08041994750656167, | |
| "grad_norm": 0.08617392182350159, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6669445037841797, | |
| "step": 1532 | |
| }, | |
| { | |
| "epoch": 0.0805249343832021, | |
| "grad_norm": 0.09462998807430267, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6400246620178223, | |
| "step": 1534 | |
| }, | |
| { | |
| "epoch": 0.08062992125984252, | |
| "grad_norm": 0.08441915363073349, | |
| "learning_rate": 0.0008, | |
| "loss": 2.645432710647583, | |
| "step": 1536 | |
| }, | |
| { | |
| "epoch": 0.08073490813648294, | |
| "grad_norm": 0.08263417333364487, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6180851459503174, | |
| "step": 1538 | |
| }, | |
| { | |
| "epoch": 0.08083989501312336, | |
| "grad_norm": 0.08703829348087311, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5585739612579346, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.08094488188976377, | |
| "grad_norm": 0.08523893356323242, | |
| "learning_rate": 0.0008, | |
| "loss": 2.614161968231201, | |
| "step": 1542 | |
| }, | |
| { | |
| "epoch": 0.0810498687664042, | |
| "grad_norm": 0.08841872215270996, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6348488330841064, | |
| "step": 1544 | |
| }, | |
| { | |
| "epoch": 0.08115485564304462, | |
| "grad_norm": 0.08768261969089508, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6650583744049072, | |
| "step": 1546 | |
| }, | |
| { | |
| "epoch": 0.08125984251968504, | |
| "grad_norm": 0.08522971719503403, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6248960494995117, | |
| "step": 1548 | |
| }, | |
| { | |
| "epoch": 0.08136482939632546, | |
| "grad_norm": 0.08117776364088058, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5123472213745117, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.08146981627296587, | |
| "grad_norm": 0.10297319293022156, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6397876739501953, | |
| "step": 1552 | |
| }, | |
| { | |
| "epoch": 0.0815748031496063, | |
| "grad_norm": 0.08273671567440033, | |
| "learning_rate": 0.0008, | |
| "loss": 2.671487808227539, | |
| "step": 1554 | |
| }, | |
| { | |
| "epoch": 0.08167979002624672, | |
| "grad_norm": 0.08913425356149673, | |
| "learning_rate": 0.0008, | |
| "loss": 2.619361400604248, | |
| "step": 1556 | |
| }, | |
| { | |
| "epoch": 0.08178477690288714, | |
| "grad_norm": 0.08676572889089584, | |
| "learning_rate": 0.0008, | |
| "loss": 2.646219253540039, | |
| "step": 1558 | |
| }, | |
| { | |
| "epoch": 0.08188976377952756, | |
| "grad_norm": 0.08558576554059982, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6649773120880127, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.08199475065616797, | |
| "grad_norm": 0.08772425353527069, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5893633365631104, | |
| "step": 1562 | |
| }, | |
| { | |
| "epoch": 0.0820997375328084, | |
| "grad_norm": 0.0831882581114769, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6974833011627197, | |
| "step": 1564 | |
| }, | |
| { | |
| "epoch": 0.08220472440944881, | |
| "grad_norm": 0.08178865164518356, | |
| "learning_rate": 0.0008, | |
| "loss": 2.583035707473755, | |
| "step": 1566 | |
| }, | |
| { | |
| "epoch": 0.08230971128608924, | |
| "grad_norm": 0.08514456450939178, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6143856048583984, | |
| "step": 1568 | |
| }, | |
| { | |
| "epoch": 0.08241469816272966, | |
| "grad_norm": 0.0887722596526146, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6891093254089355, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.08251968503937007, | |
| "grad_norm": 0.08339700102806091, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6601476669311523, | |
| "step": 1572 | |
| }, | |
| { | |
| "epoch": 0.0826246719160105, | |
| "grad_norm": 0.09619136154651642, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7047266960144043, | |
| "step": 1574 | |
| }, | |
| { | |
| "epoch": 0.08272965879265091, | |
| "grad_norm": 0.08555737882852554, | |
| "learning_rate": 0.0008, | |
| "loss": 2.641420602798462, | |
| "step": 1576 | |
| }, | |
| { | |
| "epoch": 0.08283464566929134, | |
| "grad_norm": 0.09187690168619156, | |
| "learning_rate": 0.0008, | |
| "loss": 2.682300567626953, | |
| "step": 1578 | |
| }, | |
| { | |
| "epoch": 0.08293963254593176, | |
| "grad_norm": 0.08391961455345154, | |
| "learning_rate": 0.0008, | |
| "loss": 2.596982479095459, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.08304461942257217, | |
| "grad_norm": 0.08660521358251572, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5704190731048584, | |
| "step": 1582 | |
| }, | |
| { | |
| "epoch": 0.0831496062992126, | |
| "grad_norm": 0.09145216643810272, | |
| "learning_rate": 0.0008, | |
| "loss": 2.610621690750122, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 0.08325459317585301, | |
| "grad_norm": 0.09076787531375885, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6265766620635986, | |
| "step": 1586 | |
| }, | |
| { | |
| "epoch": 0.08335958005249344, | |
| "grad_norm": 0.08473757654428482, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5840325355529785, | |
| "step": 1588 | |
| }, | |
| { | |
| "epoch": 0.08346456692913386, | |
| "grad_norm": 0.08764895796775818, | |
| "learning_rate": 0.0008, | |
| "loss": 2.650861978530884, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.08356955380577427, | |
| "grad_norm": 0.08604638278484344, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5880215167999268, | |
| "step": 1592 | |
| }, | |
| { | |
| "epoch": 0.0836745406824147, | |
| "grad_norm": 0.08875894546508789, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5545339584350586, | |
| "step": 1594 | |
| }, | |
| { | |
| "epoch": 0.08377952755905511, | |
| "grad_norm": 0.08827130496501923, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6456351280212402, | |
| "step": 1596 | |
| }, | |
| { | |
| "epoch": 0.08388451443569554, | |
| "grad_norm": 0.08176963776350021, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5623390674591064, | |
| "step": 1598 | |
| }, | |
| { | |
| "epoch": 0.08398950131233596, | |
| "grad_norm": 0.086766816675663, | |
| "learning_rate": 0.0008, | |
| "loss": 2.7536349296569824, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.08409448818897637, | |
| "grad_norm": 0.09060511738061905, | |
| "learning_rate": 0.0008, | |
| "loss": 2.631099224090576, | |
| "step": 1602 | |
| }, | |
| { | |
| "epoch": 0.0841994750656168, | |
| "grad_norm": 0.08291477710008621, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6116275787353516, | |
| "step": 1604 | |
| }, | |
| { | |
| "epoch": 0.08430446194225721, | |
| "grad_norm": 0.08625714480876923, | |
| "learning_rate": 0.0008, | |
| "loss": 2.647369146347046, | |
| "step": 1606 | |
| }, | |
| { | |
| "epoch": 0.08440944881889764, | |
| "grad_norm": 0.08942336589097977, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6680569648742676, | |
| "step": 1608 | |
| }, | |
| { | |
| "epoch": 0.08451443569553806, | |
| "grad_norm": 0.08428546786308289, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6465890407562256, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.08461942257217847, | |
| "grad_norm": 0.08562791347503662, | |
| "learning_rate": 0.0008, | |
| "loss": 2.625067949295044, | |
| "step": 1612 | |
| }, | |
| { | |
| "epoch": 0.0847244094488189, | |
| "grad_norm": 0.0880139097571373, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5922048091888428, | |
| "step": 1614 | |
| }, | |
| { | |
| "epoch": 0.08482939632545931, | |
| "grad_norm": 0.08246537297964096, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5575156211853027, | |
| "step": 1616 | |
| }, | |
| { | |
| "epoch": 0.08493438320209974, | |
| "grad_norm": 0.0834057629108429, | |
| "learning_rate": 0.0008, | |
| "loss": 2.641045570373535, | |
| "step": 1618 | |
| }, | |
| { | |
| "epoch": 0.08503937007874016, | |
| "grad_norm": 0.08735916763544083, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5660972595214844, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.08514435695538057, | |
| "grad_norm": 0.08078532665967941, | |
| "learning_rate": 0.0008, | |
| "loss": 2.608192205429077, | |
| "step": 1622 | |
| }, | |
| { | |
| "epoch": 0.085249343832021, | |
| "grad_norm": 0.08159651607275009, | |
| "learning_rate": 0.0008, | |
| "loss": 2.628239631652832, | |
| "step": 1624 | |
| }, | |
| { | |
| "epoch": 0.08535433070866141, | |
| "grad_norm": 0.08421457558870316, | |
| "learning_rate": 0.0008, | |
| "loss": 2.590017318725586, | |
| "step": 1626 | |
| }, | |
| { | |
| "epoch": 0.08545931758530184, | |
| "grad_norm": 0.08065648376941681, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5932815074920654, | |
| "step": 1628 | |
| }, | |
| { | |
| "epoch": 0.08556430446194226, | |
| "grad_norm": 0.08451144397258759, | |
| "learning_rate": 0.0008, | |
| "loss": 2.526507616043091, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.08566929133858267, | |
| "grad_norm": 0.0815906673669815, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6585793495178223, | |
| "step": 1632 | |
| }, | |
| { | |
| "epoch": 0.0857742782152231, | |
| "grad_norm": 0.0857076346874237, | |
| "learning_rate": 0.0008, | |
| "loss": 2.603756904602051, | |
| "step": 1634 | |
| }, | |
| { | |
| "epoch": 0.08587926509186351, | |
| "grad_norm": 0.0849592387676239, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5701847076416016, | |
| "step": 1636 | |
| }, | |
| { | |
| "epoch": 0.08598425196850394, | |
| "grad_norm": 0.0825916975736618, | |
| "learning_rate": 0.0008, | |
| "loss": 2.601931095123291, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 0.08608923884514436, | |
| "grad_norm": 0.0850144624710083, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6899642944335938, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.08619422572178477, | |
| "grad_norm": 0.07960861921310425, | |
| "learning_rate": 0.0008, | |
| "loss": 2.628523349761963, | |
| "step": 1642 | |
| }, | |
| { | |
| "epoch": 0.0862992125984252, | |
| "grad_norm": 0.09087909013032913, | |
| "learning_rate": 0.0008, | |
| "loss": 2.637486457824707, | |
| "step": 1644 | |
| }, | |
| { | |
| "epoch": 0.08640419947506561, | |
| "grad_norm": 0.10057082772254944, | |
| "learning_rate": 0.0008, | |
| "loss": 2.61989688873291, | |
| "step": 1646 | |
| }, | |
| { | |
| "epoch": 0.08650918635170604, | |
| "grad_norm": 0.08616212755441666, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6472818851470947, | |
| "step": 1648 | |
| }, | |
| { | |
| "epoch": 0.08661417322834646, | |
| "grad_norm": 0.0801684781908989, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5400612354278564, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.08671916010498687, | |
| "grad_norm": 0.08322037756443024, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6284127235412598, | |
| "step": 1652 | |
| }, | |
| { | |
| "epoch": 0.0868241469816273, | |
| "grad_norm": 0.08782251924276352, | |
| "learning_rate": 0.0008, | |
| "loss": 2.571457624435425, | |
| "step": 1654 | |
| }, | |
| { | |
| "epoch": 0.08692913385826771, | |
| "grad_norm": 0.07917717844247818, | |
| "learning_rate": 0.0008, | |
| "loss": 2.583712100982666, | |
| "step": 1656 | |
| }, | |
| { | |
| "epoch": 0.08703412073490814, | |
| "grad_norm": 0.08118360489606857, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5801053047180176, | |
| "step": 1658 | |
| }, | |
| { | |
| "epoch": 0.08713910761154856, | |
| "grad_norm": 0.08316761255264282, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6475930213928223, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.08724409448818897, | |
| "grad_norm": 0.08366121351718903, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5696606636047363, | |
| "step": 1662 | |
| }, | |
| { | |
| "epoch": 0.0873490813648294, | |
| "grad_norm": 0.08328234404325485, | |
| "learning_rate": 0.0008, | |
| "loss": 2.632983922958374, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 0.08745406824146981, | |
| "grad_norm": 0.09022201597690582, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6194865703582764, | |
| "step": 1666 | |
| }, | |
| { | |
| "epoch": 0.08755905511811024, | |
| "grad_norm": 0.09023604542016983, | |
| "learning_rate": 0.0008, | |
| "loss": 2.616377592086792, | |
| "step": 1668 | |
| }, | |
| { | |
| "epoch": 0.08766404199475065, | |
| "grad_norm": 0.08536537736654282, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5466952323913574, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.08776902887139107, | |
| "grad_norm": 0.099100261926651, | |
| "learning_rate": 0.0008, | |
| "loss": 2.659147262573242, | |
| "step": 1672 | |
| }, | |
| { | |
| "epoch": 0.0878740157480315, | |
| "grad_norm": 0.08265551924705505, | |
| "learning_rate": 0.0008, | |
| "loss": 2.589916229248047, | |
| "step": 1674 | |
| }, | |
| { | |
| "epoch": 0.08797900262467191, | |
| "grad_norm": 0.09555111080408096, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6505472660064697, | |
| "step": 1676 | |
| }, | |
| { | |
| "epoch": 0.08808398950131234, | |
| "grad_norm": 0.09552125632762909, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5794239044189453, | |
| "step": 1678 | |
| }, | |
| { | |
| "epoch": 0.08818897637795275, | |
| "grad_norm": 0.08678983151912689, | |
| "learning_rate": 0.0008, | |
| "loss": 2.643092632293701, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.08829396325459317, | |
| "grad_norm": 0.08301737904548645, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6255621910095215, | |
| "step": 1682 | |
| }, | |
| { | |
| "epoch": 0.0883989501312336, | |
| "grad_norm": 0.08073344081640244, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5802159309387207, | |
| "step": 1684 | |
| }, | |
| { | |
| "epoch": 0.08850393700787401, | |
| "grad_norm": 0.08115082234144211, | |
| "learning_rate": 0.0008, | |
| "loss": 2.607386589050293, | |
| "step": 1686 | |
| }, | |
| { | |
| "epoch": 0.08860892388451444, | |
| "grad_norm": 0.0805412232875824, | |
| "learning_rate": 0.0008, | |
| "loss": 2.598745822906494, | |
| "step": 1688 | |
| }, | |
| { | |
| "epoch": 0.08871391076115485, | |
| "grad_norm": 0.08753439038991928, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6611311435699463, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.08881889763779527, | |
| "grad_norm": 0.08298667520284653, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5831384658813477, | |
| "step": 1692 | |
| }, | |
| { | |
| "epoch": 0.0889238845144357, | |
| "grad_norm": 0.08127131313085556, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6378657817840576, | |
| "step": 1694 | |
| }, | |
| { | |
| "epoch": 0.08902887139107611, | |
| "grad_norm": 0.08537666499614716, | |
| "learning_rate": 0.0008, | |
| "loss": 2.639033079147339, | |
| "step": 1696 | |
| }, | |
| { | |
| "epoch": 0.08913385826771654, | |
| "grad_norm": 0.0840623676776886, | |
| "learning_rate": 0.0008, | |
| "loss": 2.565019130706787, | |
| "step": 1698 | |
| }, | |
| { | |
| "epoch": 0.08923884514435695, | |
| "grad_norm": 0.08272294700145721, | |
| "learning_rate": 0.0008, | |
| "loss": 2.636948347091675, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.08934383202099737, | |
| "grad_norm": 0.08278897404670715, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6079483032226562, | |
| "step": 1702 | |
| }, | |
| { | |
| "epoch": 0.0894488188976378, | |
| "grad_norm": 0.0801597386598587, | |
| "learning_rate": 0.0008, | |
| "loss": 2.5585684776306152, | |
| "step": 1704 | |
| }, | |
| { | |
| "epoch": 0.08955380577427821, | |
| "grad_norm": 0.08294755220413208, | |
| "learning_rate": 0.0008, | |
| "loss": 2.572537899017334, | |
| "step": 1706 | |
| }, | |
| { | |
| "epoch": 0.08965879265091864, | |
| "grad_norm": 0.07987018674612045, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6297359466552734, | |
| "step": 1708 | |
| }, | |
| { | |
| "epoch": 0.08976377952755905, | |
| "grad_norm": 0.07916128635406494, | |
| "learning_rate": 0.0008, | |
| "loss": 2.573946952819824, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.08986876640419947, | |
| "grad_norm": 0.08582612127065659, | |
| "learning_rate": 0.0008, | |
| "loss": 2.510253429412842, | |
| "step": 1712 | |
| }, | |
| { | |
| "epoch": 0.0899737532808399, | |
| "grad_norm": 0.08121506869792938, | |
| "learning_rate": 0.0008, | |
| "loss": 2.561246395111084, | |
| "step": 1714 | |
| }, | |
| { | |
| "epoch": 0.09007874015748031, | |
| "grad_norm": 0.07797350734472275, | |
| "learning_rate": 0.0008, | |
| "loss": 2.6328437328338623, | |
| "step": 1716 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 19050, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 572, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.429426018965286e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |