Instructions to use shareit/chabot-supervisor-phi4rpKL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use shareit/chabot-supervisor-phi4rpKL with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/phi-4-reasoning-plus-unsloth-bnb-4bit") model = PeftModel.from_pretrained(base_model, "shareit/chabot-supervisor-phi4rpKL") - Transformers
How to use shareit/chabot-supervisor-phi4rpKL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="shareit/chabot-supervisor-phi4rpKL") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("shareit/chabot-supervisor-phi4rpKL", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use shareit/chabot-supervisor-phi4rpKL with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "shareit/chabot-supervisor-phi4rpKL" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "shareit/chabot-supervisor-phi4rpKL", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/shareit/chabot-supervisor-phi4rpKL
- SGLang
How to use shareit/chabot-supervisor-phi4rpKL 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 "shareit/chabot-supervisor-phi4rpKL" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "shareit/chabot-supervisor-phi4rpKL", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "shareit/chabot-supervisor-phi4rpKL" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "shareit/chabot-supervisor-phi4rpKL", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio new
How to use shareit/chabot-supervisor-phi4rpKL 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 shareit/chabot-supervisor-phi4rpKL 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 shareit/chabot-supervisor-phi4rpKL to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for shareit/chabot-supervisor-phi4rpKL to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="shareit/chabot-supervisor-phi4rpKL", max_seq_length=2048, ) - Docker Model Runner
How to use shareit/chabot-supervisor-phi4rpKL with Docker Model Runner:
docker model run hf.co/shareit/chabot-supervisor-phi4rpKL
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 888, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004507042253521127, | |
| "grad_norm": 0.5109427571296692, | |
| "learning_rate": 0.0, | |
| "loss": 2.8366, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009014084507042254, | |
| "grad_norm": 0.5052362084388733, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 2.9992, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013521126760563381, | |
| "grad_norm": 0.4910641610622406, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 2.8925, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.018028169014084508, | |
| "grad_norm": 0.5134980082511902, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 2.8476, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.022535211267605635, | |
| "grad_norm": 0.5817605257034302, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 2.9803, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.027042253521126762, | |
| "grad_norm": 0.7044035792350769, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 2.8277, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.031549295774647886, | |
| "grad_norm": 0.793286919593811, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 2.9407, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.036056338028169016, | |
| "grad_norm": 0.9440262317657471, | |
| "learning_rate": 5.185185185185185e-05, | |
| "loss": 2.9527, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04056338028169014, | |
| "grad_norm": 1.107783555984497, | |
| "learning_rate": 5.925925925925926e-05, | |
| "loss": 2.5235, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04507042253521127, | |
| "grad_norm": 1.3675676584243774, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.377, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.049577464788732394, | |
| "grad_norm": 1.4395591020584106, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 2.1443, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.054084507042253524, | |
| "grad_norm": 0.5429375171661377, | |
| "learning_rate": 8.148148148148148e-05, | |
| "loss": 1.8369, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05859154929577465, | |
| "grad_norm": 1.5771080255508423, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 1.9669, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06309859154929577, | |
| "grad_norm": 1.6812283992767334, | |
| "learning_rate": 9.62962962962963e-05, | |
| "loss": 1.918, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0676056338028169, | |
| "grad_norm": 1.698196530342102, | |
| "learning_rate": 0.0001037037037037037, | |
| "loss": 1.7981, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07211267605633803, | |
| "grad_norm": 1.4648041725158691, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 1.686, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07661971830985916, | |
| "grad_norm": 0.7997398972511292, | |
| "learning_rate": 0.00011851851851851852, | |
| "loss": 1.6433, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08112676056338028, | |
| "grad_norm": 0.6825237274169922, | |
| "learning_rate": 0.00012592592592592592, | |
| "loss": 1.461, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0856338028169014, | |
| "grad_norm": 0.598156213760376, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 1.3822, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09014084507042254, | |
| "grad_norm": 0.5010932683944702, | |
| "learning_rate": 0.00014074074074074076, | |
| "loss": 1.3466, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09464788732394366, | |
| "grad_norm": 0.4217166006565094, | |
| "learning_rate": 0.00014814814814814815, | |
| "loss": 1.2368, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09915492957746479, | |
| "grad_norm": 0.3251509368419647, | |
| "learning_rate": 0.00015555555555555556, | |
| "loss": 1.0822, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10366197183098591, | |
| "grad_norm": 0.28032082319259644, | |
| "learning_rate": 0.00016296296296296295, | |
| "loss": 1.0166, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10816901408450705, | |
| "grad_norm": 0.43019387125968933, | |
| "learning_rate": 0.00017037037037037037, | |
| "loss": 1.1404, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11267605633802817, | |
| "grad_norm": 0.371652215719223, | |
| "learning_rate": 0.00017777777777777779, | |
| "loss": 1.0273, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1171830985915493, | |
| "grad_norm": 0.4319760799407959, | |
| "learning_rate": 0.0001851851851851852, | |
| "loss": 1.0482, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.12169014084507042, | |
| "grad_norm": 0.4139591157436371, | |
| "learning_rate": 0.0001925925925925926, | |
| "loss": 0.9763, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12619718309859154, | |
| "grad_norm": 0.3923117220401764, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9831, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.13070422535211268, | |
| "grad_norm": 0.3156369626522064, | |
| "learning_rate": 0.00019999933432389942, | |
| "loss": 0.9356, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1352112676056338, | |
| "grad_norm": 0.23431973159313202, | |
| "learning_rate": 0.00019999733730446018, | |
| "loss": 0.912, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13971830985915493, | |
| "grad_norm": 0.2367880940437317, | |
| "learning_rate": 0.00019999400896826965, | |
| "loss": 0.8699, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.14422535211267606, | |
| "grad_norm": 0.23735183477401733, | |
| "learning_rate": 0.00019998934935963966, | |
| "loss": 0.8918, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.14873239436619717, | |
| "grad_norm": 0.21039249002933502, | |
| "learning_rate": 0.00019998335854060607, | |
| "loss": 0.8716, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1532394366197183, | |
| "grad_norm": 0.2169954627752304, | |
| "learning_rate": 0.00019997603659092773, | |
| "loss": 0.8872, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.15774647887323945, | |
| "grad_norm": 0.18319812417030334, | |
| "learning_rate": 0.00019996738360808565, | |
| "loss": 0.8339, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16225352112676056, | |
| "grad_norm": 0.16776813566684723, | |
| "learning_rate": 0.00019995739970728144, | |
| "loss": 0.882, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1667605633802817, | |
| "grad_norm": 0.1763199269771576, | |
| "learning_rate": 0.00019994608502143602, | |
| "loss": 0.8939, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1712676056338028, | |
| "grad_norm": 0.14987778663635254, | |
| "learning_rate": 0.00019993343970118766, | |
| "loss": 0.7841, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.17577464788732394, | |
| "grad_norm": 0.14466699957847595, | |
| "learning_rate": 0.00019991946391489018, | |
| "loss": 0.7943, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.18028169014084508, | |
| "grad_norm": 0.13038891553878784, | |
| "learning_rate": 0.00019990415784861047, | |
| "loss": 0.781, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1847887323943662, | |
| "grad_norm": 0.1293761432170868, | |
| "learning_rate": 0.00019988752170612618, | |
| "loss": 0.793, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.18929577464788733, | |
| "grad_norm": 0.12768785655498505, | |
| "learning_rate": 0.000199869555708923, | |
| "loss": 0.7708, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.19380281690140846, | |
| "grad_norm": 0.14372171461582184, | |
| "learning_rate": 0.0001998502600961916, | |
| "loss": 0.7788, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.19830985915492957, | |
| "grad_norm": 0.12837673723697662, | |
| "learning_rate": 0.00019982963512482453, | |
| "loss": 0.7968, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2028169014084507, | |
| "grad_norm": 0.12973128259181976, | |
| "learning_rate": 0.00019980768106941281, | |
| "loss": 0.7833, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.20732394366197182, | |
| "grad_norm": 0.11364801228046417, | |
| "learning_rate": 0.00019978439822224226, | |
| "loss": 0.78, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.21183098591549296, | |
| "grad_norm": 0.09620922058820724, | |
| "learning_rate": 0.00019975978689328958, | |
| "loss": 0.7192, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2163380281690141, | |
| "grad_norm": 0.09795072674751282, | |
| "learning_rate": 0.0001997338474102182, | |
| "loss": 0.7628, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2208450704225352, | |
| "grad_norm": 0.18416811525821686, | |
| "learning_rate": 0.00019970658011837404, | |
| "loss": 0.7298, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.22535211267605634, | |
| "grad_norm": 0.09638620167970657, | |
| "learning_rate": 0.00019967798538078076, | |
| "loss": 0.7248, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22985915492957745, | |
| "grad_norm": 0.10183525085449219, | |
| "learning_rate": 0.00019964806357813508, | |
| "loss": 0.7704, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.2343661971830986, | |
| "grad_norm": 0.09559155255556107, | |
| "learning_rate": 0.0001996168151088015, | |
| "loss": 0.7559, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.23887323943661973, | |
| "grad_norm": 0.11242512613534927, | |
| "learning_rate": 0.00019958424038880727, | |
| "loss": 0.7897, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.24338028169014084, | |
| "grad_norm": 0.09209013730287552, | |
| "learning_rate": 0.0001995503398518366, | |
| "loss": 0.7212, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.24788732394366197, | |
| "grad_norm": 0.08857212960720062, | |
| "learning_rate": 0.00019951511394922507, | |
| "loss": 0.7409, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2523943661971831, | |
| "grad_norm": 0.11040879040956497, | |
| "learning_rate": 0.00019947856314995349, | |
| "loss": 0.7288, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.25690140845070425, | |
| "grad_norm": 0.09153151512145996, | |
| "learning_rate": 0.00019944068794064174, | |
| "loss": 0.7387, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.26140845070422536, | |
| "grad_norm": 0.08312317728996277, | |
| "learning_rate": 0.0001994014888255422, | |
| "loss": 0.7295, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.26591549295774647, | |
| "grad_norm": 0.08618035167455673, | |
| "learning_rate": 0.00019936096632653324, | |
| "loss": 0.7089, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.2704225352112676, | |
| "grad_norm": 0.09828522056341171, | |
| "learning_rate": 0.00019931912098311195, | |
| "loss": 0.7105, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.27492957746478874, | |
| "grad_norm": 0.0870802253484726, | |
| "learning_rate": 0.00019927595335238733, | |
| "loss": 0.6672, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.27943661971830985, | |
| "grad_norm": 0.09070249646902084, | |
| "learning_rate": 0.00019923146400907253, | |
| "loss": 0.6541, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.28394366197183096, | |
| "grad_norm": 0.07697242498397827, | |
| "learning_rate": 0.0001991856535454774, | |
| "loss": 0.6902, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.28845070422535213, | |
| "grad_norm": 0.08537200093269348, | |
| "learning_rate": 0.00019913852257150052, | |
| "loss": 0.7073, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.29295774647887324, | |
| "grad_norm": 0.08310703933238983, | |
| "learning_rate": 0.0001990900717146212, | |
| "loss": 0.6784, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.29746478873239435, | |
| "grad_norm": 0.10847494751214981, | |
| "learning_rate": 0.00019904030161989103, | |
| "loss": 0.7397, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.3019718309859155, | |
| "grad_norm": 0.08034008741378784, | |
| "learning_rate": 0.00019898921294992516, | |
| "loss": 0.7044, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.3064788732394366, | |
| "grad_norm": 0.08679196983575821, | |
| "learning_rate": 0.00019893680638489382, | |
| "loss": 0.6948, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.31098591549295773, | |
| "grad_norm": 0.08680360019207001, | |
| "learning_rate": 0.00019888308262251285, | |
| "loss": 0.7017, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.3154929577464789, | |
| "grad_norm": 0.08481983840465546, | |
| "learning_rate": 0.00019882804237803488, | |
| "loss": 0.7111, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.07690601050853729, | |
| "learning_rate": 0.0001987716863842393, | |
| "loss": 0.6722, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.3245070422535211, | |
| "grad_norm": 0.06967870891094208, | |
| "learning_rate": 0.00019871401539142293, | |
| "loss": 0.6485, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.3290140845070422, | |
| "grad_norm": 0.0827360600233078, | |
| "learning_rate": 0.00019865503016738983, | |
| "loss": 0.698, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.3335211267605634, | |
| "grad_norm": 0.0766606405377388, | |
| "learning_rate": 0.000198594731497441, | |
| "loss": 0.691, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.3380281690140845, | |
| "grad_norm": 0.08298925310373306, | |
| "learning_rate": 0.00019853312018436417, | |
| "loss": 0.7125, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3425352112676056, | |
| "grad_norm": 0.07882972061634064, | |
| "learning_rate": 0.0001984701970484229, | |
| "loss": 0.6932, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.3470422535211268, | |
| "grad_norm": 0.08647109568119049, | |
| "learning_rate": 0.0001984059629273457, | |
| "loss": 0.6862, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.3515492957746479, | |
| "grad_norm": 0.0839175134897232, | |
| "learning_rate": 0.00019834041867631505, | |
| "loss": 0.6784, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.356056338028169, | |
| "grad_norm": 0.07932542264461517, | |
| "learning_rate": 0.0001982735651679557, | |
| "loss": 0.6707, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.36056338028169016, | |
| "grad_norm": 0.0704977959394455, | |
| "learning_rate": 0.00019820540329232333, | |
| "loss": 0.6374, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.36507042253521127, | |
| "grad_norm": 0.07499450445175171, | |
| "learning_rate": 0.0001981359339568926, | |
| "loss": 0.6452, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.3695774647887324, | |
| "grad_norm": 0.07560130953788757, | |
| "learning_rate": 0.00019806515808654498, | |
| "loss": 0.6599, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.37408450704225354, | |
| "grad_norm": 0.0893062874674797, | |
| "learning_rate": 0.0001979930766235566, | |
| "loss": 0.6745, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.37859154929577465, | |
| "grad_norm": 0.08140068501234055, | |
| "learning_rate": 0.00019791969052758562, | |
| "loss": 0.6559, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.38309859154929576, | |
| "grad_norm": 0.0829370766878128, | |
| "learning_rate": 0.00019784500077565944, | |
| "loss": 0.6857, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.38760563380281693, | |
| "grad_norm": 0.0947769358754158, | |
| "learning_rate": 0.0001977690083621617, | |
| "loss": 0.7109, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.39211267605633804, | |
| "grad_norm": 0.10486528277397156, | |
| "learning_rate": 0.00019769171429881907, | |
| "loss": 0.7033, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.39661971830985915, | |
| "grad_norm": 0.11483494937419891, | |
| "learning_rate": 0.0001976131196146878, | |
| "loss": 0.7183, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.40112676056338026, | |
| "grad_norm": 0.08664172142744064, | |
| "learning_rate": 0.0001975332253561399, | |
| "loss": 0.6734, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.4056338028169014, | |
| "grad_norm": 0.08497391641139984, | |
| "learning_rate": 0.00019745203258684938, | |
| "loss": 0.6627, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.41014084507042253, | |
| "grad_norm": 0.09175261110067368, | |
| "learning_rate": 0.00019736954238777792, | |
| "loss": 0.6678, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.41464788732394364, | |
| "grad_norm": 0.08519595116376877, | |
| "learning_rate": 0.0001972857558571606, | |
| "loss": 0.6716, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.4191549295774648, | |
| "grad_norm": 0.08249272406101227, | |
| "learning_rate": 0.0001972006741104913, | |
| "loss": 0.6607, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.4236619718309859, | |
| "grad_norm": 0.09815848618745804, | |
| "learning_rate": 0.00019711429828050769, | |
| "loss": 0.6737, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.428169014084507, | |
| "grad_norm": 0.08678440749645233, | |
| "learning_rate": 0.00019702662951717628, | |
| "loss": 0.6437, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.4326760563380282, | |
| "grad_norm": 0.07430567592382431, | |
| "learning_rate": 0.0001969376689876771, | |
| "loss": 0.6445, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.4371830985915493, | |
| "grad_norm": 0.10983766615390778, | |
| "learning_rate": 0.00019684741787638808, | |
| "loss": 0.6588, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.4416901408450704, | |
| "grad_norm": 0.07917274534702301, | |
| "learning_rate": 0.00019675587738486936, | |
| "loss": 0.6532, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.4461971830985916, | |
| "grad_norm": 0.08504049479961395, | |
| "learning_rate": 0.00019666304873184739, | |
| "loss": 0.674, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.4507042253521127, | |
| "grad_norm": 0.08401936292648315, | |
| "learning_rate": 0.00019656893315319837, | |
| "loss": 0.645, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4552112676056338, | |
| "grad_norm": 0.0813940167427063, | |
| "learning_rate": 0.00019647353190193224, | |
| "loss": 0.6491, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.4597183098591549, | |
| "grad_norm": 0.08745774626731873, | |
| "learning_rate": 0.00019637684624817554, | |
| "loss": 0.6561, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.46422535211267607, | |
| "grad_norm": 0.07857084274291992, | |
| "learning_rate": 0.00019627887747915494, | |
| "loss": 0.6419, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.4687323943661972, | |
| "grad_norm": 0.08520088344812393, | |
| "learning_rate": 0.00019617962689917975, | |
| "loss": 0.6167, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.4732394366197183, | |
| "grad_norm": 0.0916878879070282, | |
| "learning_rate": 0.00019607909582962477, | |
| "loss": 0.6165, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.47774647887323946, | |
| "grad_norm": 0.07891346514225006, | |
| "learning_rate": 0.00019597728560891264, | |
| "loss": 0.6262, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.48225352112676056, | |
| "grad_norm": 0.11444642394781113, | |
| "learning_rate": 0.00019587419759249593, | |
| "loss": 0.6252, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.4867605633802817, | |
| "grad_norm": 0.08692018687725067, | |
| "learning_rate": 0.00019576983315283922, | |
| "loss": 0.6772, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.49126760563380284, | |
| "grad_norm": 0.08438707143068314, | |
| "learning_rate": 0.0001956641936794008, | |
| "loss": 0.6159, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.49577464788732395, | |
| "grad_norm": 0.08054433017969131, | |
| "learning_rate": 0.0001955572805786141, | |
| "loss": 0.6198, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5002816901408451, | |
| "grad_norm": 0.10778526216745377, | |
| "learning_rate": 0.00019544909527386903, | |
| "loss": 0.653, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.5047887323943662, | |
| "grad_norm": 0.08686485141515732, | |
| "learning_rate": 0.00019533963920549306, | |
| "loss": 0.6349, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.5092957746478873, | |
| "grad_norm": 0.08285564184188843, | |
| "learning_rate": 0.00019522891383073196, | |
| "loss": 0.6178, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.5138028169014085, | |
| "grad_norm": 0.11247093975543976, | |
| "learning_rate": 0.00019511692062373044, | |
| "loss": 0.6482, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.5183098591549296, | |
| "grad_norm": 0.11526112258434296, | |
| "learning_rate": 0.00019500366107551252, | |
| "loss": 0.6692, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.5228169014084507, | |
| "grad_norm": 0.09112968295812607, | |
| "learning_rate": 0.00019488913669396166, | |
| "loss": 0.6262, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.5273239436619719, | |
| "grad_norm": 0.1070021390914917, | |
| "learning_rate": 0.0001947733490038008, | |
| "loss": 0.6699, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.5318309859154929, | |
| "grad_norm": 0.09726863354444504, | |
| "learning_rate": 0.00019465629954657185, | |
| "loss": 0.6468, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.5363380281690141, | |
| "grad_norm": 0.08580797910690308, | |
| "learning_rate": 0.00019453798988061535, | |
| "loss": 0.5734, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.5408450704225352, | |
| "grad_norm": 0.08846008032560349, | |
| "learning_rate": 0.00019441842158104966, | |
| "loss": 0.5958, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5453521126760563, | |
| "grad_norm": 0.08376345038414001, | |
| "learning_rate": 0.00019429759623974991, | |
| "loss": 0.6236, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.5498591549295775, | |
| "grad_norm": 0.1092655211687088, | |
| "learning_rate": 0.00019417551546532704, | |
| "loss": 0.629, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.5543661971830985, | |
| "grad_norm": 0.09457230567932129, | |
| "learning_rate": 0.00019405218088310605, | |
| "loss": 0.5955, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.5588732394366197, | |
| "grad_norm": 0.09811452776193619, | |
| "learning_rate": 0.0001939275941351046, | |
| "loss": 0.6683, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.5633802816901409, | |
| "grad_norm": 0.11004705727100372, | |
| "learning_rate": 0.00019380175688001118, | |
| "loss": 0.6381, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5678873239436619, | |
| "grad_norm": 0.0918348953127861, | |
| "learning_rate": 0.00019367467079316279, | |
| "loss": 0.6285, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.5723943661971831, | |
| "grad_norm": 0.09264164417982101, | |
| "learning_rate": 0.00019354633756652286, | |
| "loss": 0.6667, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.5769014084507043, | |
| "grad_norm": 0.08994423598051071, | |
| "learning_rate": 0.00019341675890865867, | |
| "loss": 0.5938, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.5814084507042253, | |
| "grad_norm": 0.08977948129177094, | |
| "learning_rate": 0.00019328593654471848, | |
| "loss": 0.5933, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.5859154929577465, | |
| "grad_norm": 0.10552453994750977, | |
| "learning_rate": 0.00019315387221640874, | |
| "loss": 0.6596, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5904225352112676, | |
| "grad_norm": 0.09184475243091583, | |
| "learning_rate": 0.00019302056768197076, | |
| "loss": 0.6269, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.5949295774647887, | |
| "grad_norm": 0.08900140970945358, | |
| "learning_rate": 0.00019288602471615742, | |
| "loss": 0.6168, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.5994366197183099, | |
| "grad_norm": 0.11255169659852982, | |
| "learning_rate": 0.0001927502451102095, | |
| "loss": 0.6187, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.603943661971831, | |
| "grad_norm": 0.091275654733181, | |
| "learning_rate": 0.00019261323067183166, | |
| "loss": 0.5949, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.6084507042253521, | |
| "grad_norm": 0.09162840992212296, | |
| "learning_rate": 0.00019247498322516875, | |
| "loss": 0.6069, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.6129577464788732, | |
| "grad_norm": 0.09226758778095245, | |
| "learning_rate": 0.00019233550461078113, | |
| "loss": 0.6014, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.6174647887323944, | |
| "grad_norm": 0.11824911832809448, | |
| "learning_rate": 0.00019219479668562044, | |
| "loss": 0.6126, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.6219718309859155, | |
| "grad_norm": 0.09837235510349274, | |
| "learning_rate": 0.00019205286132300468, | |
| "loss": 0.6268, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.6264788732394366, | |
| "grad_norm": 0.11063525825738907, | |
| "learning_rate": 0.00019190970041259352, | |
| "loss": 0.6101, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.6309859154929578, | |
| "grad_norm": 0.0999184399843216, | |
| "learning_rate": 0.0001917653158603628, | |
| "loss": 0.6362, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6354929577464788, | |
| "grad_norm": 0.1021515354514122, | |
| "learning_rate": 0.0001916197095885795, | |
| "loss": 0.6094, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.10452960431575775, | |
| "learning_rate": 0.00019147288353577589, | |
| "loss": 0.6178, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.6445070422535212, | |
| "grad_norm": 0.14412759244441986, | |
| "learning_rate": 0.00019132483965672386, | |
| "loss": 0.6276, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.6490140845070422, | |
| "grad_norm": 0.11471202969551086, | |
| "learning_rate": 0.00019117557992240887, | |
| "loss": 0.6176, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.6535211267605634, | |
| "grad_norm": 0.1019945964217186, | |
| "learning_rate": 0.00019102510632000363, | |
| "loss": 0.6034, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6580281690140845, | |
| "grad_norm": 0.09331919997930527, | |
| "learning_rate": 0.00019087342085284182, | |
| "loss": 0.6037, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.6625352112676056, | |
| "grad_norm": 0.1276702880859375, | |
| "learning_rate": 0.00019072052554039122, | |
| "loss": 0.623, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.6670422535211268, | |
| "grad_norm": 0.10190749168395996, | |
| "learning_rate": 0.00019056642241822692, | |
| "loss": 0.6346, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.6715492957746478, | |
| "grad_norm": 0.1176435798406601, | |
| "learning_rate": 0.00019041111353800425, | |
| "loss": 0.5865, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.676056338028169, | |
| "grad_norm": 0.12664955854415894, | |
| "learning_rate": 0.0001902546009674314, | |
| "loss": 0.5882, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6805633802816902, | |
| "grad_norm": 0.10095725208520889, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 0.5944, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.6850704225352112, | |
| "grad_norm": 0.09524551033973694, | |
| "learning_rate": 0.00018993797310616698, | |
| "loss": 0.567, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.6895774647887324, | |
| "grad_norm": 0.11315032839775085, | |
| "learning_rate": 0.00018977786203090743, | |
| "loss": 0.6368, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.6940845070422536, | |
| "grad_norm": 0.1286381185054779, | |
| "learning_rate": 0.00018961655569610557, | |
| "loss": 0.6272, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.6985915492957746, | |
| "grad_norm": 0.1185537725687027, | |
| "learning_rate": 0.00018945405624931684, | |
| "loss": 0.6102, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.7030985915492958, | |
| "grad_norm": 0.12012823671102524, | |
| "learning_rate": 0.00018929036585398122, | |
| "loss": 0.5973, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.7076056338028169, | |
| "grad_norm": 0.10544425994157791, | |
| "learning_rate": 0.00018912548668939438, | |
| "loss": 0.6194, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.712112676056338, | |
| "grad_norm": 0.1360369324684143, | |
| "learning_rate": 0.0001889594209506787, | |
| "loss": 0.625, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.7166197183098592, | |
| "grad_norm": 0.10620026290416718, | |
| "learning_rate": 0.00018879217084875408, | |
| "loss": 0.6054, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.7211267605633803, | |
| "grad_norm": 0.10198299586772919, | |
| "learning_rate": 0.00018862373861030837, | |
| "loss": 0.6489, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.7256338028169014, | |
| "grad_norm": 0.12448371946811676, | |
| "learning_rate": 0.00018845412647776794, | |
| "loss": 0.5959, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.7301408450704225, | |
| "grad_norm": 0.10388363152742386, | |
| "learning_rate": 0.00018828333670926764, | |
| "loss": 0.5915, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.7346478873239437, | |
| "grad_norm": 0.10535863786935806, | |
| "learning_rate": 0.00018811137157862082, | |
| "loss": 0.5892, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.7391549295774648, | |
| "grad_norm": 0.12875902652740479, | |
| "learning_rate": 0.000187938233375289, | |
| "loss": 0.5904, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.7436619718309859, | |
| "grad_norm": 0.10576613992452621, | |
| "learning_rate": 0.00018776392440435146, | |
| "loss": 0.616, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.7481690140845071, | |
| "grad_norm": 0.11017853021621704, | |
| "learning_rate": 0.00018758844698647456, | |
| "loss": 0.5802, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.7526760563380281, | |
| "grad_norm": 0.1325456202030182, | |
| "learning_rate": 0.00018741180345788072, | |
| "loss": 0.5984, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.7571830985915493, | |
| "grad_norm": 0.09516138583421707, | |
| "learning_rate": 0.00018723399617031751, | |
| "loss": 0.6039, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.7616901408450705, | |
| "grad_norm": 0.12991869449615479, | |
| "learning_rate": 0.0001870550274910261, | |
| "loss": 0.5868, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.7661971830985915, | |
| "grad_norm": 0.12943920493125916, | |
| "learning_rate": 0.00018687489980270998, | |
| "loss": 0.5894, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7707042253521127, | |
| "grad_norm": 0.10891859978437424, | |
| "learning_rate": 0.00018669361550350307, | |
| "loss": 0.6213, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.7752112676056339, | |
| "grad_norm": 0.18440082669258118, | |
| "learning_rate": 0.00018651117700693793, | |
| "loss": 0.5791, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.7797183098591549, | |
| "grad_norm": 0.10212352871894836, | |
| "learning_rate": 0.00018632758674191343, | |
| "loss": 0.5957, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.7842253521126761, | |
| "grad_norm": 0.12365531921386719, | |
| "learning_rate": 0.00018614284715266264, | |
| "loss": 0.6341, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.7887323943661971, | |
| "grad_norm": 0.16831544041633606, | |
| "learning_rate": 0.00018595696069872013, | |
| "loss": 0.5904, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.7932394366197183, | |
| "grad_norm": 0.10575060546398163, | |
| "learning_rate": 0.0001857699298548893, | |
| "loss": 0.574, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.7977464788732395, | |
| "grad_norm": 0.09861788153648376, | |
| "learning_rate": 0.00018558175711120946, | |
| "loss": 0.5694, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.8022535211267605, | |
| "grad_norm": 0.10814764350652695, | |
| "learning_rate": 0.00018539244497292248, | |
| "loss": 0.5881, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.8067605633802817, | |
| "grad_norm": 0.1235693171620369, | |
| "learning_rate": 0.00018520199596043976, | |
| "loss": 0.5941, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.8112676056338028, | |
| "grad_norm": 0.11930661648511887, | |
| "learning_rate": 0.0001850104126093084, | |
| "loss": 0.598, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8157746478873239, | |
| "grad_norm": 0.11203116923570633, | |
| "learning_rate": 0.00018481769747017752, | |
| "loss": 0.5903, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.8202816901408451, | |
| "grad_norm": 0.32203975319862366, | |
| "learning_rate": 0.00018462385310876443, | |
| "loss": 0.5577, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.8247887323943662, | |
| "grad_norm": 0.11607527732849121, | |
| "learning_rate": 0.00018442888210582026, | |
| "loss": 0.5881, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.8292957746478873, | |
| "grad_norm": 0.1148713156580925, | |
| "learning_rate": 0.00018423278705709573, | |
| "loss": 0.5661, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.8338028169014085, | |
| "grad_norm": 0.11103823035955429, | |
| "learning_rate": 0.00018403557057330666, | |
| "loss": 0.5772, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.8383098591549296, | |
| "grad_norm": 0.11443036794662476, | |
| "learning_rate": 0.000183837235280099, | |
| "loss": 0.5958, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.8428169014084507, | |
| "grad_norm": 0.1051875427365303, | |
| "learning_rate": 0.00018363778381801402, | |
| "loss": 0.5774, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.8473239436619718, | |
| "grad_norm": 0.10837268084287643, | |
| "learning_rate": 0.0001834372188424532, | |
| "loss": 0.6333, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.851830985915493, | |
| "grad_norm": 0.10711036622524261, | |
| "learning_rate": 0.00018323554302364272, | |
| "loss": 0.5734, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.856338028169014, | |
| "grad_norm": 0.10732840746641159, | |
| "learning_rate": 0.00018303275904659806, | |
| "loss": 0.5941, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8608450704225352, | |
| "grad_norm": 0.1174219474196434, | |
| "learning_rate": 0.00018282886961108817, | |
| "loss": 0.5983, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.8653521126760564, | |
| "grad_norm": 0.11654770374298096, | |
| "learning_rate": 0.0001826238774315995, | |
| "loss": 0.6075, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.8698591549295774, | |
| "grad_norm": 0.09939175844192505, | |
| "learning_rate": 0.00018241778523729995, | |
| "loss": 0.5731, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.8743661971830986, | |
| "grad_norm": 0.10806521773338318, | |
| "learning_rate": 0.0001822105957720025, | |
| "loss": 0.6029, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.8788732394366198, | |
| "grad_norm": 0.11704345047473907, | |
| "learning_rate": 0.0001820023117941287, | |
| "loss": 0.5376, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.8833802816901408, | |
| "grad_norm": 0.1095748320221901, | |
| "learning_rate": 0.00018179293607667178, | |
| "loss": 0.5714, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.887887323943662, | |
| "grad_norm": 0.130691796541214, | |
| "learning_rate": 0.00018158247140716004, | |
| "loss": 0.6168, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.8923943661971832, | |
| "grad_norm": 0.1149544045329094, | |
| "learning_rate": 0.0001813709205876194, | |
| "loss": 0.5928, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.8969014084507042, | |
| "grad_norm": 0.12969551980495453, | |
| "learning_rate": 0.00018115828643453647, | |
| "loss": 0.6044, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.9014084507042254, | |
| "grad_norm": 0.12071943283081055, | |
| "learning_rate": 0.00018094457177882068, | |
| "loss": 0.6057, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.9059154929577464, | |
| "grad_norm": 0.11709054559469223, | |
| "learning_rate": 0.00018072977946576678, | |
| "loss": 0.5769, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.9104225352112676, | |
| "grad_norm": 0.12902222573757172, | |
| "learning_rate": 0.00018051391235501696, | |
| "loss": 0.6006, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.9149295774647888, | |
| "grad_norm": 0.11009194701910019, | |
| "learning_rate": 0.00018029697332052277, | |
| "loss": 0.5779, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.9194366197183098, | |
| "grad_norm": 0.1268339455127716, | |
| "learning_rate": 0.0001800789652505068, | |
| "loss": 0.5761, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.923943661971831, | |
| "grad_norm": 0.13632765412330627, | |
| "learning_rate": 0.00017985989104742434, | |
| "loss": 0.6021, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.9284507042253521, | |
| "grad_norm": 0.11911677569150925, | |
| "learning_rate": 0.00017963975362792454, | |
| "loss": 0.5727, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.9329577464788732, | |
| "grad_norm": 0.143024280667305, | |
| "learning_rate": 0.00017941855592281184, | |
| "loss": 0.5952, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.9374647887323944, | |
| "grad_norm": 0.12256220728158951, | |
| "learning_rate": 0.00017919630087700672, | |
| "loss": 0.5981, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.9419718309859155, | |
| "grad_norm": 0.12445315718650818, | |
| "learning_rate": 0.00017897299144950662, | |
| "loss": 0.5765, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.9464788732394366, | |
| "grad_norm": 0.11824553459882736, | |
| "learning_rate": 0.00017874863061334657, | |
| "loss": 0.5752, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9509859154929577, | |
| "grad_norm": 0.10992954671382904, | |
| "learning_rate": 0.00017852322135555946, | |
| "loss": 0.5859, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.9554929577464789, | |
| "grad_norm": 0.1199469268321991, | |
| "learning_rate": 0.00017829676667713642, | |
| "loss": 0.5991, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.11440328508615494, | |
| "learning_rate": 0.0001780692695929868, | |
| "loss": 0.6178, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.9645070422535211, | |
| "grad_norm": 0.1150740534067154, | |
| "learning_rate": 0.00017784073313189795, | |
| "loss": 0.5874, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.9690140845070423, | |
| "grad_norm": 0.1373901069164276, | |
| "learning_rate": 0.0001776111603364952, | |
| "loss": 0.5924, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.9735211267605633, | |
| "grad_norm": 0.11277955770492554, | |
| "learning_rate": 0.000177380554263201, | |
| "loss": 0.5903, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.9780281690140845, | |
| "grad_norm": 0.1162528321146965, | |
| "learning_rate": 0.0001771489179821943, | |
| "loss": 0.5654, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.9825352112676057, | |
| "grad_norm": 0.1154017448425293, | |
| "learning_rate": 0.0001769162545773699, | |
| "loss": 0.5799, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.9870422535211267, | |
| "grad_norm": 0.12194578349590302, | |
| "learning_rate": 0.00017668256714629713, | |
| "loss": 0.5735, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.9915492957746479, | |
| "grad_norm": 0.1068485751748085, | |
| "learning_rate": 0.00017644785880017874, | |
| "loss": 0.5548, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9960563380281691, | |
| "grad_norm": 0.12018559128046036, | |
| "learning_rate": 0.0001762121326638095, | |
| "loss": 0.6097, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.11836925894021988, | |
| "learning_rate": 0.00017597539187553447, | |
| "loss": 0.5916, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 1.0045070422535212, | |
| "grad_norm": 0.10781855881214142, | |
| "learning_rate": 0.00017573763958720736, | |
| "loss": 0.5735, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 1.0090140845070423, | |
| "grad_norm": 0.11357908695936203, | |
| "learning_rate": 0.00017549887896414851, | |
| "loss": 0.5899, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.0135211267605633, | |
| "grad_norm": 0.10758072882890701, | |
| "learning_rate": 0.00017525911318510274, | |
| "loss": 0.5952, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.0180281690140844, | |
| "grad_norm": 0.10980618000030518, | |
| "learning_rate": 0.00017501834544219697, | |
| "loss": 0.5673, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 1.0225352112676056, | |
| "grad_norm": 0.10185301303863525, | |
| "learning_rate": 0.0001747765789408979, | |
| "loss": 0.5709, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 1.0270422535211268, | |
| "grad_norm": 0.10787362605333328, | |
| "learning_rate": 0.00017453381689996916, | |
| "loss": 0.5742, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 1.031549295774648, | |
| "grad_norm": 0.10553862154483795, | |
| "learning_rate": 0.00017429006255142851, | |
| "loss": 0.5666, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 1.036056338028169, | |
| "grad_norm": 0.11908821016550064, | |
| "learning_rate": 0.00017404531914050483, | |
| "loss": 0.6023, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.04056338028169, | |
| "grad_norm": 0.11501052975654602, | |
| "learning_rate": 0.00017379958992559493, | |
| "loss": 0.6038, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 1.0450704225352112, | |
| "grad_norm": 0.11365503072738647, | |
| "learning_rate": 0.00017355287817822013, | |
| "loss": 0.5774, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 1.0495774647887324, | |
| "grad_norm": 0.1214151382446289, | |
| "learning_rate": 0.00017330518718298264, | |
| "loss": 0.5707, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 1.0540845070422535, | |
| "grad_norm": 0.12372933328151703, | |
| "learning_rate": 0.00017305652023752205, | |
| "loss": 0.5665, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 1.0585915492957747, | |
| "grad_norm": 0.1101953536272049, | |
| "learning_rate": 0.00017280688065247118, | |
| "loss": 0.5547, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.0630985915492959, | |
| "grad_norm": 0.12429898232221603, | |
| "learning_rate": 0.00017255627175141215, | |
| "loss": 0.5855, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 1.0676056338028168, | |
| "grad_norm": 0.12096191197633743, | |
| "learning_rate": 0.0001723046968708321, | |
| "loss": 0.5754, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 1.072112676056338, | |
| "grad_norm": 0.11296476423740387, | |
| "learning_rate": 0.0001720521593600787, | |
| "loss": 0.6131, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 1.0766197183098591, | |
| "grad_norm": 0.16034449636936188, | |
| "learning_rate": 0.00017179866258131568, | |
| "loss": 0.583, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 1.0811267605633803, | |
| "grad_norm": 0.1200270801782608, | |
| "learning_rate": 0.000171544209909478, | |
| "loss": 0.5689, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0856338028169015, | |
| "grad_norm": 0.11855066567659378, | |
| "learning_rate": 0.0001712888047322269, | |
| "loss": 0.6263, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 1.0901408450704226, | |
| "grad_norm": 0.11620208621025085, | |
| "learning_rate": 0.00017103245044990475, | |
| "loss": 0.55, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 1.0946478873239436, | |
| "grad_norm": 0.11482568085193634, | |
| "learning_rate": 0.00017077515047549008, | |
| "loss": 0.5802, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 1.0991549295774647, | |
| "grad_norm": 0.12208764255046844, | |
| "learning_rate": 0.00017051690823455162, | |
| "loss": 0.5672, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 1.103661971830986, | |
| "grad_norm": 0.14577889442443848, | |
| "learning_rate": 0.00017025772716520323, | |
| "loss": 0.5889, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.108169014084507, | |
| "grad_norm": 0.13474218547344208, | |
| "learning_rate": 0.00016999761071805771, | |
| "loss": 0.5709, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 1.1126760563380282, | |
| "grad_norm": 0.15604770183563232, | |
| "learning_rate": 0.00016973656235618113, | |
| "loss": 0.5923, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 1.1171830985915494, | |
| "grad_norm": 0.09855290502309799, | |
| "learning_rate": 0.00016947458555504664, | |
| "loss": 0.551, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 1.1216901408450703, | |
| "grad_norm": 0.14074093103408813, | |
| "learning_rate": 0.0001692116838024881, | |
| "loss": 0.5418, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 1.1261971830985915, | |
| "grad_norm": 0.13044053316116333, | |
| "learning_rate": 0.00016894786059865383, | |
| "loss": 0.5672, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.1307042253521127, | |
| "grad_norm": 0.11453069746494293, | |
| "learning_rate": 0.00016868311945595978, | |
| "loss": 0.5794, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 1.1352112676056338, | |
| "grad_norm": 0.13302022218704224, | |
| "learning_rate": 0.00016841746389904304, | |
| "loss": 0.5389, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.139718309859155, | |
| "grad_norm": 0.11696815490722656, | |
| "learning_rate": 0.0001681508974647147, | |
| "loss": 0.5419, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 1.144225352112676, | |
| "grad_norm": 0.13234978914260864, | |
| "learning_rate": 0.0001678834237019129, | |
| "loss": 0.5247, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 1.1487323943661971, | |
| "grad_norm": 0.12429715692996979, | |
| "learning_rate": 0.00016761504617165537, | |
| "loss": 0.5477, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.1532394366197183, | |
| "grad_norm": 0.145405575633049, | |
| "learning_rate": 0.00016734576844699235, | |
| "loss": 0.5931, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 1.1577464788732394, | |
| "grad_norm": 0.12818464636802673, | |
| "learning_rate": 0.00016707559411295874, | |
| "loss": 0.5467, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 1.1622535211267606, | |
| "grad_norm": 0.1135251522064209, | |
| "learning_rate": 0.00016680452676652642, | |
| "loss": 0.5456, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 1.1667605633802818, | |
| "grad_norm": 0.12029904127120972, | |
| "learning_rate": 0.00016653257001655652, | |
| "loss": 0.5854, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 1.1712676056338027, | |
| "grad_norm": 0.17769469320774078, | |
| "learning_rate": 0.00016625972748375128, | |
| "loss": 0.5633, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.1757746478873239, | |
| "grad_norm": 0.09973835945129395, | |
| "learning_rate": 0.00016598600280060566, | |
| "loss": 0.5254, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 1.180281690140845, | |
| "grad_norm": 0.11614567786455154, | |
| "learning_rate": 0.00016571139961135927, | |
| "loss": 0.5781, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 1.1847887323943662, | |
| "grad_norm": 0.12455403804779053, | |
| "learning_rate": 0.0001654359215719478, | |
| "loss": 0.5932, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 1.1892957746478874, | |
| "grad_norm": 0.10969316214323044, | |
| "learning_rate": 0.0001651595723499541, | |
| "loss": 0.5989, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 1.1938028169014085, | |
| "grad_norm": 0.23572060465812683, | |
| "learning_rate": 0.00016488235562455965, | |
| "loss": 0.5748, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.1983098591549295, | |
| "grad_norm": 0.1086173951625824, | |
| "learning_rate": 0.00016460427508649546, | |
| "loss": 0.5773, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 1.2028169014084507, | |
| "grad_norm": 0.1331978142261505, | |
| "learning_rate": 0.00016432533443799284, | |
| "loss": 0.5821, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 1.2073239436619718, | |
| "grad_norm": 0.1528872549533844, | |
| "learning_rate": 0.00016404553739273427, | |
| "loss": 0.5652, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 1.211830985915493, | |
| "grad_norm": 0.11898130923509598, | |
| "learning_rate": 0.0001637648876758039, | |
| "loss": 0.5689, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 1.2163380281690142, | |
| "grad_norm": 0.1391112506389618, | |
| "learning_rate": 0.00016348338902363787, | |
| "loss": 0.6048, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.220845070422535, | |
| "grad_norm": 0.11310067027807236, | |
| "learning_rate": 0.00016320104518397472, | |
| "loss": 0.5668, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 1.2253521126760563, | |
| "grad_norm": 0.12252317368984222, | |
| "learning_rate": 0.00016291785991580534, | |
| "loss": 0.5977, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 1.2298591549295774, | |
| "grad_norm": 0.13545405864715576, | |
| "learning_rate": 0.00016263383698932306, | |
| "loss": 0.5651, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 1.2343661971830986, | |
| "grad_norm": 0.14084038138389587, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 0.5767, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 1.2388732394366198, | |
| "grad_norm": 0.13004128634929657, | |
| "learning_rate": 0.00016206329329790354, | |
| "loss": 0.5675, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.243380281690141, | |
| "grad_norm": 0.15050950646400452, | |
| "learning_rate": 0.00016177678012891232, | |
| "loss": 0.5874, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 1.247887323943662, | |
| "grad_norm": 0.12289810925722122, | |
| "learning_rate": 0.00016148944449339902, | |
| "loss": 0.5644, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 1.252394366197183, | |
| "grad_norm": 0.13767307996749878, | |
| "learning_rate": 0.00016120129021681296, | |
| "loss": 0.5602, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 1.2569014084507042, | |
| "grad_norm": 0.14790986478328705, | |
| "learning_rate": 0.0001609123211355025, | |
| "loss": 0.5526, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 1.2614084507042254, | |
| "grad_norm": 0.12315787374973297, | |
| "learning_rate": 0.0001606225410966638, | |
| "loss": 0.5788, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.2659154929577465, | |
| "grad_norm": 0.12627176940441132, | |
| "learning_rate": 0.00016033195395828985, | |
| "loss": 0.5431, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 1.2704225352112677, | |
| "grad_norm": 0.12655603885650635, | |
| "learning_rate": 0.00016004056358911883, | |
| "loss": 0.5849, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 1.2749295774647886, | |
| "grad_norm": 0.11540428549051285, | |
| "learning_rate": 0.0001597483738685829, | |
| "loss": 0.5538, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 1.2794366197183098, | |
| "grad_norm": 0.14923222362995148, | |
| "learning_rate": 0.00015945538868675628, | |
| "loss": 0.598, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 1.283943661971831, | |
| "grad_norm": 0.1102415919303894, | |
| "learning_rate": 0.00015916161194430372, | |
| "loss": 0.5503, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.2884507042253521, | |
| "grad_norm": 0.1324516087770462, | |
| "learning_rate": 0.00015886704755242829, | |
| "loss": 0.5817, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 1.2929577464788733, | |
| "grad_norm": 0.11458254605531693, | |
| "learning_rate": 0.00015857169943281948, | |
| "loss": 0.5566, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 1.2974647887323942, | |
| "grad_norm": 0.11885883659124374, | |
| "learning_rate": 0.00015827557151760105, | |
| "loss": 0.5518, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 1.3019718309859156, | |
| "grad_norm": 0.12516717612743378, | |
| "learning_rate": 0.00015797866774927848, | |
| "loss": 0.5898, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 1.3064788732394366, | |
| "grad_norm": 0.14177542924880981, | |
| "learning_rate": 0.00015768099208068664, | |
| "loss": 0.6099, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.3109859154929577, | |
| "grad_norm": 0.1278507560491562, | |
| "learning_rate": 0.00015738254847493704, | |
| "loss": 0.5552, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 1.315492957746479, | |
| "grad_norm": 0.12453269958496094, | |
| "learning_rate": 0.00015708334090536527, | |
| "loss": 0.5922, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.1163586899638176, | |
| "learning_rate": 0.00015678337335547782, | |
| "loss": 0.5345, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 1.3245070422535212, | |
| "grad_norm": 0.11830248683691025, | |
| "learning_rate": 0.00015648264981889934, | |
| "loss": 0.5801, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 1.3290140845070422, | |
| "grad_norm": 0.17942926287651062, | |
| "learning_rate": 0.00015618117429931926, | |
| "loss": 0.5367, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.3335211267605633, | |
| "grad_norm": 0.13405169546604156, | |
| "learning_rate": 0.00015587895081043844, | |
| "loss": 0.564, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 1.3380281690140845, | |
| "grad_norm": 0.11632625758647919, | |
| "learning_rate": 0.00015557598337591607, | |
| "loss": 0.5629, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 1.3425352112676057, | |
| "grad_norm": 0.15242446959018707, | |
| "learning_rate": 0.00015527227602931572, | |
| "loss": 0.6318, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 1.3470422535211268, | |
| "grad_norm": 0.13854624330997467, | |
| "learning_rate": 0.00015496783281405177, | |
| "loss": 0.5683, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 1.3515492957746478, | |
| "grad_norm": 0.1268724948167801, | |
| "learning_rate": 0.00015466265778333574, | |
| "loss": 0.5661, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.356056338028169, | |
| "grad_norm": 0.1456933319568634, | |
| "learning_rate": 0.00015435675500012212, | |
| "loss": 0.5801, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 1.36056338028169, | |
| "grad_norm": 0.1346408724784851, | |
| "learning_rate": 0.00015405012853705432, | |
| "loss": 0.5811, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 1.3650704225352113, | |
| "grad_norm": 0.1391272395849228, | |
| "learning_rate": 0.00015374278247641052, | |
| "loss": 0.5864, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 1.3695774647887324, | |
| "grad_norm": 0.11695600301027298, | |
| "learning_rate": 0.00015343472091004925, | |
| "loss": 0.5919, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 1.3740845070422536, | |
| "grad_norm": 0.13721643388271332, | |
| "learning_rate": 0.00015312594793935494, | |
| "loss": 0.5863, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 1.3785915492957748, | |
| "grad_norm": 0.1210237517952919, | |
| "learning_rate": 0.00015281646767518337, | |
| "loss": 0.5549, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 1.3830985915492957, | |
| "grad_norm": 0.14290763437747955, | |
| "learning_rate": 0.00015250628423780683, | |
| "loss": 0.5884, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 1.3876056338028169, | |
| "grad_norm": 0.14939945936203003, | |
| "learning_rate": 0.00015219540175685938, | |
| "loss": 0.5369, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 1.392112676056338, | |
| "grad_norm": 0.12331175804138184, | |
| "learning_rate": 0.00015188382437128167, | |
| "loss": 0.5702, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 1.3966197183098592, | |
| "grad_norm": 0.11888106167316437, | |
| "learning_rate": 0.0001515715562292662, | |
| "loss": 0.5274, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.4011267605633804, | |
| "grad_norm": 0.13149474561214447, | |
| "learning_rate": 0.00015125860148820167, | |
| "loss": 0.5785, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 1.4056338028169013, | |
| "grad_norm": 0.12267362326383591, | |
| "learning_rate": 0.00015094496431461795, | |
| "loss": 0.5455, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.4101408450704225, | |
| "grad_norm": 0.1183052584528923, | |
| "learning_rate": 0.00015063064888413047, | |
| "loss": 0.5453, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 1.4146478873239436, | |
| "grad_norm": 0.14539587497711182, | |
| "learning_rate": 0.00015031565938138458, | |
| "loss": 0.5424, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 1.4191549295774648, | |
| "grad_norm": 0.12015419453382492, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.555, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.423661971830986, | |
| "grad_norm": 0.11795421689748764, | |
| "learning_rate": 0.00014968367494251484, | |
| "loss": 0.5337, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 1.428169014084507, | |
| "grad_norm": 0.2184419184923172, | |
| "learning_rate": 0.00014936668842032973, | |
| "loss": 0.5802, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 1.4326760563380283, | |
| "grad_norm": 0.12965649366378784, | |
| "learning_rate": 0.00014904904465365168, | |
| "loss": 0.5455, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.4371830985915492, | |
| "grad_norm": 0.13248752057552338, | |
| "learning_rate": 0.000148730747871438, | |
| "loss": 0.5809, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 1.4416901408450704, | |
| "grad_norm": 0.12989097833633423, | |
| "learning_rate": 0.00014841180231133988, | |
| "loss": 0.5702, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.4461971830985916, | |
| "grad_norm": 0.11466707289218903, | |
| "learning_rate": 0.00014809221221964608, | |
| "loss": 0.5853, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 1.4507042253521127, | |
| "grad_norm": 0.13086023926734924, | |
| "learning_rate": 0.0001477719818512263, | |
| "loss": 0.5637, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 1.455211267605634, | |
| "grad_norm": 0.12968841195106506, | |
| "learning_rate": 0.0001474511154694746, | |
| "loss": 0.528, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 1.4597183098591549, | |
| "grad_norm": 0.10484195500612259, | |
| "learning_rate": 0.00014712961734625264, | |
| "loss": 0.5357, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.464225352112676, | |
| "grad_norm": 0.12601444125175476, | |
| "learning_rate": 0.00014680749176183274, | |
| "loss": 0.5336, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.4687323943661972, | |
| "grad_norm": 0.1338932365179062, | |
| "learning_rate": 0.00014648474300484095, | |
| "loss": 0.5427, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 1.4732394366197183, | |
| "grad_norm": 0.11979039758443832, | |
| "learning_rate": 0.00014616137537219997, | |
| "loss": 0.5655, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 1.4777464788732395, | |
| "grad_norm": 0.1427401751279831, | |
| "learning_rate": 0.00014583739316907188, | |
| "loss": 0.5734, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 1.4822535211267605, | |
| "grad_norm": 0.13836687803268433, | |
| "learning_rate": 0.0001455128007088009, | |
| "loss": 0.5407, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 1.4867605633802816, | |
| "grad_norm": 0.10016699135303497, | |
| "learning_rate": 0.00014518760231285583, | |
| "loss": 0.5709, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.4912676056338028, | |
| "grad_norm": 0.13350802659988403, | |
| "learning_rate": 0.00014486180231077278, | |
| "loss": 0.5508, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 1.495774647887324, | |
| "grad_norm": 0.11883152276277542, | |
| "learning_rate": 0.00014453540504009714, | |
| "loss": 0.5258, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 1.5002816901408451, | |
| "grad_norm": 0.11694121360778809, | |
| "learning_rate": 0.0001442084148463262, | |
| "loss": 0.567, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.504788732394366, | |
| "grad_norm": 0.13168871402740479, | |
| "learning_rate": 0.00014388083608285113, | |
| "loss": 0.5504, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 1.5092957746478874, | |
| "grad_norm": 0.11850599944591522, | |
| "learning_rate": 0.00014355267311089897, | |
| "loss": 0.5587, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.5138028169014084, | |
| "grad_norm": 0.11114364862442017, | |
| "learning_rate": 0.00014322393029947468, | |
| "loss": 0.5398, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 1.5183098591549296, | |
| "grad_norm": 0.1272014081478119, | |
| "learning_rate": 0.00014289461202530296, | |
| "loss": 0.5487, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 1.5228169014084507, | |
| "grad_norm": 0.11661308258771896, | |
| "learning_rate": 0.00014256472267276982, | |
| "loss": 0.5422, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 1.5273239436619719, | |
| "grad_norm": 0.11852391809225082, | |
| "learning_rate": 0.0001422342666338645, | |
| "loss": 0.5594, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 1.531830985915493, | |
| "grad_norm": 0.15416082739830017, | |
| "learning_rate": 0.00014190324830812067, | |
| "loss": 0.5379, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.536338028169014, | |
| "grad_norm": 0.11813542246818542, | |
| "learning_rate": 0.00014157167210255815, | |
| "loss": 0.5642, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 1.5408450704225352, | |
| "grad_norm": 0.11259282380342484, | |
| "learning_rate": 0.00014123954243162404, | |
| "loss": 0.5681, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 1.5453521126760563, | |
| "grad_norm": 0.12045090645551682, | |
| "learning_rate": 0.00014090686371713402, | |
| "loss": 0.5393, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 1.5498591549295775, | |
| "grad_norm": 0.11575852334499359, | |
| "learning_rate": 0.00014057364038821347, | |
| "loss": 0.5578, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 1.5543661971830987, | |
| "grad_norm": 0.1217094361782074, | |
| "learning_rate": 0.0001402398768812385, | |
| "loss": 0.5191, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 1.5588732394366196, | |
| "grad_norm": 0.12148681282997131, | |
| "learning_rate": 0.00013990557763977695, | |
| "loss": 0.5386, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 1.563380281690141, | |
| "grad_norm": 0.120498426258564, | |
| "learning_rate": 0.0001395707471145291, | |
| "loss": 0.5481, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 1.567887323943662, | |
| "grad_norm": 0.12890687584877014, | |
| "learning_rate": 0.0001392353897632685, | |
| "loss": 0.5487, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 1.572394366197183, | |
| "grad_norm": 0.19078081846237183, | |
| "learning_rate": 0.0001388995100507827, | |
| "loss": 0.5396, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 1.5769014084507043, | |
| "grad_norm": 0.1250527799129486, | |
| "learning_rate": 0.0001385631124488136, | |
| "loss": 0.5489, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.5814084507042252, | |
| "grad_norm": 0.14552123844623566, | |
| "learning_rate": 0.00013822620143599804, | |
| "loss": 0.5672, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 1.5859154929577466, | |
| "grad_norm": 0.10857994854450226, | |
| "learning_rate": 0.00013788878149780827, | |
| "loss": 0.5457, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 1.5904225352112675, | |
| "grad_norm": 0.1588989943265915, | |
| "learning_rate": 0.00013755085712649202, | |
| "loss": 0.5691, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 1.5949295774647887, | |
| "grad_norm": 0.1268385797739029, | |
| "learning_rate": 0.0001372124328210129, | |
| "loss": 0.5691, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 1.5994366197183099, | |
| "grad_norm": 0.12925177812576294, | |
| "learning_rate": 0.00013687351308699027, | |
| "loss": 0.5465, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 1.603943661971831, | |
| "grad_norm": 0.118260458111763, | |
| "learning_rate": 0.00013653410243663952, | |
| "loss": 0.5307, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 1.6084507042253522, | |
| "grad_norm": 0.12612397968769073, | |
| "learning_rate": 0.00013619420538871178, | |
| "loss": 0.5586, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 1.6129577464788731, | |
| "grad_norm": 0.11145804077386856, | |
| "learning_rate": 0.00013585382646843396, | |
| "loss": 0.5785, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 1.6174647887323945, | |
| "grad_norm": 0.12373437732458115, | |
| "learning_rate": 0.00013551297020744825, | |
| "loss": 0.5458, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 1.6219718309859155, | |
| "grad_norm": 0.11881903558969498, | |
| "learning_rate": 0.00013517164114375195, | |
| "loss": 0.5599, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.6264788732394366, | |
| "grad_norm": 0.11561185866594315, | |
| "learning_rate": 0.00013482984382163712, | |
| "loss": 0.5342, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 1.6309859154929578, | |
| "grad_norm": 0.11933106929063797, | |
| "learning_rate": 0.00013448758279162993, | |
| "loss": 0.5126, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 1.6354929577464787, | |
| "grad_norm": 0.1258057802915573, | |
| "learning_rate": 0.00013414486261043008, | |
| "loss": 0.5531, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 1.6400000000000001, | |
| "grad_norm": 0.12655043601989746, | |
| "learning_rate": 0.00013380168784085027, | |
| "loss": 0.5629, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 1.644507042253521, | |
| "grad_norm": 0.12148042023181915, | |
| "learning_rate": 0.00013345806305175542, | |
| "loss": 0.5339, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 1.6490140845070422, | |
| "grad_norm": 0.17970451712608337, | |
| "learning_rate": 0.0001331139928180016, | |
| "loss": 0.5586, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 1.6535211267605634, | |
| "grad_norm": 0.13397206366062164, | |
| "learning_rate": 0.00013276948172037556, | |
| "loss": 0.5451, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 1.6580281690140843, | |
| "grad_norm": 0.12288239598274231, | |
| "learning_rate": 0.0001324245343455333, | |
| "loss": 0.5378, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 1.6625352112676057, | |
| "grad_norm": 0.1233164519071579, | |
| "learning_rate": 0.00013207915528593933, | |
| "loss": 0.5355, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 1.6670422535211267, | |
| "grad_norm": 0.12358216941356659, | |
| "learning_rate": 0.00013173334913980534, | |
| "loss": 0.5578, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.6715492957746478, | |
| "grad_norm": 0.12331364303827286, | |
| "learning_rate": 0.0001313871205110291, | |
| "loss": 0.544, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 1.676056338028169, | |
| "grad_norm": 0.12452603131532669, | |
| "learning_rate": 0.00013104047400913302, | |
| "loss": 0.5519, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 1.6805633802816902, | |
| "grad_norm": 0.11694569885730743, | |
| "learning_rate": 0.000130693414249203, | |
| "loss": 0.5513, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 1.6850704225352113, | |
| "grad_norm": 0.12917865812778473, | |
| "learning_rate": 0.00013034594585182677, | |
| "loss": 0.5513, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 1.6895774647887323, | |
| "grad_norm": 0.12343605607748032, | |
| "learning_rate": 0.0001299980734430324, | |
| "loss": 0.5366, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.6940845070422537, | |
| "grad_norm": 0.11165818572044373, | |
| "learning_rate": 0.000129649801654227, | |
| "loss": 0.5371, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 1.6985915492957746, | |
| "grad_norm": 0.1372881680727005, | |
| "learning_rate": 0.00012930113512213463, | |
| "loss": 0.5446, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 1.7030985915492958, | |
| "grad_norm": 0.13788315653800964, | |
| "learning_rate": 0.00012895207848873487, | |
| "loss": 0.5343, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.707605633802817, | |
| "grad_norm": 0.11924686282873154, | |
| "learning_rate": 0.00012860263640120085, | |
| "loss": 0.5255, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 1.7121126760563379, | |
| "grad_norm": 0.11935974657535553, | |
| "learning_rate": 0.0001282528135118375, | |
| "loss": 0.5962, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.7166197183098593, | |
| "grad_norm": 0.1333233267068863, | |
| "learning_rate": 0.0001279026144780196, | |
| "loss": 0.5603, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 1.7211267605633802, | |
| "grad_norm": 0.1334204375743866, | |
| "learning_rate": 0.00012755204396212966, | |
| "loss": 0.5505, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 1.7256338028169014, | |
| "grad_norm": 0.131240114569664, | |
| "learning_rate": 0.00012720110663149594, | |
| "loss": 0.5538, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 1.7301408450704225, | |
| "grad_norm": 0.13378827273845673, | |
| "learning_rate": 0.00012684980715833039, | |
| "loss": 0.5555, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 1.7346478873239437, | |
| "grad_norm": 0.12199459224939346, | |
| "learning_rate": 0.0001264981502196662, | |
| "loss": 0.5642, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.7391549295774649, | |
| "grad_norm": 0.14442510902881622, | |
| "learning_rate": 0.00012614614049729576, | |
| "loss": 0.5405, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 1.7436619718309858, | |
| "grad_norm": 0.12474284321069717, | |
| "learning_rate": 0.00012579378267770834, | |
| "loss": 0.5849, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 1.7481690140845072, | |
| "grad_norm": 0.11631778627634048, | |
| "learning_rate": 0.00012544108145202748, | |
| "loss": 0.5273, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 1.7526760563380281, | |
| "grad_norm": 0.11749529093503952, | |
| "learning_rate": 0.00012508804151594867, | |
| "loss": 0.5916, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 1.7571830985915493, | |
| "grad_norm": 0.13148164749145508, | |
| "learning_rate": 0.00012473466756967696, | |
| "loss": 0.539, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.7616901408450705, | |
| "grad_norm": 0.12642063200473785, | |
| "learning_rate": 0.00012438096431786408, | |
| "loss": 0.5421, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 1.7661971830985914, | |
| "grad_norm": 0.12551520764827728, | |
| "learning_rate": 0.00012402693646954607, | |
| "loss": 0.5356, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 1.7707042253521128, | |
| "grad_norm": 0.12111272662878036, | |
| "learning_rate": 0.00012367258873808052, | |
| "loss": 0.5356, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 1.7752112676056337, | |
| "grad_norm": 0.12639492750167847, | |
| "learning_rate": 0.00012331792584108374, | |
| "loss": 0.5582, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 1.779718309859155, | |
| "grad_norm": 0.21740061044692993, | |
| "learning_rate": 0.00012296295250036803, | |
| "loss": 0.5388, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.784225352112676, | |
| "grad_norm": 0.12856127321720123, | |
| "learning_rate": 0.00012260767344187873, | |
| "loss": 0.5457, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 1.788732394366197, | |
| "grad_norm": 0.11823161691427231, | |
| "learning_rate": 0.00012225209339563145, | |
| "loss": 0.5385, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 1.7932394366197184, | |
| "grad_norm": 0.11629433184862137, | |
| "learning_rate": 0.00012189621709564894, | |
| "loss": 0.5495, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 1.7977464788732394, | |
| "grad_norm": 0.13767673075199127, | |
| "learning_rate": 0.00012154004927989815, | |
| "loss": 0.5202, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 1.8022535211267605, | |
| "grad_norm": 0.11361772567033768, | |
| "learning_rate": 0.00012118359469022712, | |
| "loss": 0.5414, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.8067605633802817, | |
| "grad_norm": 0.1155274510383606, | |
| "learning_rate": 0.00012082685807230194, | |
| "loss": 0.5372, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 1.8112676056338028, | |
| "grad_norm": 0.13188374042510986, | |
| "learning_rate": 0.00012046984417554337, | |
| "loss": 0.557, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 1.815774647887324, | |
| "grad_norm": 0.11928690969944, | |
| "learning_rate": 0.00012011255775306378, | |
| "loss": 0.5272, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 1.820281690140845, | |
| "grad_norm": 0.11563651263713837, | |
| "learning_rate": 0.00011975500356160383, | |
| "loss": 0.5154, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 1.8247887323943663, | |
| "grad_norm": 0.12366284430027008, | |
| "learning_rate": 0.00011939718636146913, | |
| "loss": 0.557, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.8292957746478873, | |
| "grad_norm": 0.11570242792367935, | |
| "learning_rate": 0.00011903911091646684, | |
| "loss": 0.5297, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 1.8338028169014085, | |
| "grad_norm": 0.12199252098798752, | |
| "learning_rate": 0.00011868078199384229, | |
| "loss": 0.533, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 1.8383098591549296, | |
| "grad_norm": 0.13045908510684967, | |
| "learning_rate": 0.00011832220436421549, | |
| "loss": 0.548, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 1.8428169014084506, | |
| "grad_norm": 0.20884227752685547, | |
| "learning_rate": 0.00011796338280151756, | |
| "loss": 0.5449, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 1.847323943661972, | |
| "grad_norm": 0.11599334329366684, | |
| "learning_rate": 0.00011760432208292729, | |
| "loss": 0.5355, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.8518309859154929, | |
| "grad_norm": 0.11243471503257751, | |
| "learning_rate": 0.0001172450269888075, | |
| "loss": 0.5569, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 1.856338028169014, | |
| "grad_norm": 0.1418810337781906, | |
| "learning_rate": 0.00011688550230264128, | |
| "loss": 0.5416, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 1.8608450704225352, | |
| "grad_norm": 0.12925301492214203, | |
| "learning_rate": 0.0001165257528109685, | |
| "loss": 0.5654, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 1.8653521126760564, | |
| "grad_norm": 0.1256323903799057, | |
| "learning_rate": 0.0001161657833033219, | |
| "loss": 0.5732, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 1.8698591549295775, | |
| "grad_norm": 0.12409226596355438, | |
| "learning_rate": 0.00011580559857216347, | |
| "loss": 0.5258, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.8743661971830985, | |
| "grad_norm": 0.12138303369283676, | |
| "learning_rate": 0.00011544520341282053, | |
| "loss": 0.5309, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 1.8788732394366199, | |
| "grad_norm": 0.12081386148929596, | |
| "learning_rate": 0.00011508460262342197, | |
| "loss": 0.531, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 1.8833802816901408, | |
| "grad_norm": 0.10810014605522156, | |
| "learning_rate": 0.00011472380100483438, | |
| "loss": 0.532, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 1.887887323943662, | |
| "grad_norm": 0.1251344531774521, | |
| "learning_rate": 0.00011436280336059799, | |
| "loss": 0.5214, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 1.8923943661971832, | |
| "grad_norm": 0.12114979326725006, | |
| "learning_rate": 0.00011400161449686293, | |
| "loss": 0.5596, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.896901408450704, | |
| "grad_norm": 0.11715710908174515, | |
| "learning_rate": 0.00011364023922232503, | |
| "loss": 0.5259, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 1.9014084507042255, | |
| "grad_norm": 0.12593631446361542, | |
| "learning_rate": 0.00011327868234816203, | |
| "loss": 0.5336, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 1.9059154929577464, | |
| "grad_norm": 0.1148916706442833, | |
| "learning_rate": 0.00011291694868796929, | |
| "loss": 0.5693, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 1.9104225352112676, | |
| "grad_norm": 0.10621920973062515, | |
| "learning_rate": 0.00011255504305769589, | |
| "loss": 0.5326, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 1.9149295774647888, | |
| "grad_norm": 0.12841050326824188, | |
| "learning_rate": 0.00011219297027558038, | |
| "loss": 0.6288, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.9194366197183097, | |
| "grad_norm": 0.12406205385923386, | |
| "learning_rate": 0.0001118307351620867, | |
| "loss": 0.5467, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 1.923943661971831, | |
| "grad_norm": 0.12403929233551025, | |
| "learning_rate": 0.00011146834253984006, | |
| "loss": 0.542, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 1.928450704225352, | |
| "grad_norm": 0.128191277384758, | |
| "learning_rate": 0.00011110579723356256, | |
| "loss": 0.568, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 1.9329577464788732, | |
| "grad_norm": 0.11979478597640991, | |
| "learning_rate": 0.00011074310407000914, | |
| "loss": 0.5645, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 1.9374647887323944, | |
| "grad_norm": 0.12257257848978043, | |
| "learning_rate": 0.0001103802678779032, | |
| "loss": 0.5444, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.9419718309859155, | |
| "grad_norm": 0.11612683534622192, | |
| "learning_rate": 0.00011001729348787239, | |
| "loss": 0.5313, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 1.9464788732394367, | |
| "grad_norm": 0.11943483352661133, | |
| "learning_rate": 0.00010965418573238424, | |
| "loss": 0.5698, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 1.9509859154929576, | |
| "grad_norm": 0.11692250519990921, | |
| "learning_rate": 0.00010929094944568182, | |
| "loss": 0.5395, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 1.955492957746479, | |
| "grad_norm": 0.12217355519533157, | |
| "learning_rate": 0.00010892758946371944, | |
| "loss": 0.5332, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.13013868033885956, | |
| "learning_rate": 0.00010856411062409823, | |
| "loss": 0.5402, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.9645070422535211, | |
| "grad_norm": 0.11624142527580261, | |
| "learning_rate": 0.00010820051776600175, | |
| "loss": 0.5619, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 1.9690140845070423, | |
| "grad_norm": 0.1206846535205841, | |
| "learning_rate": 0.00010783681573013145, | |
| "loss": 0.5469, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 1.9735211267605632, | |
| "grad_norm": 0.11562936753034592, | |
| "learning_rate": 0.00010747300935864243, | |
| "loss": 0.5434, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.9780281690140846, | |
| "grad_norm": 0.10758832097053528, | |
| "learning_rate": 0.0001071091034950788, | |
| "loss": 0.5295, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 1.9825352112676056, | |
| "grad_norm": 0.11116923391819, | |
| "learning_rate": 0.00010674510298430935, | |
| "loss": 0.5516, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.9870422535211267, | |
| "grad_norm": 0.10766938328742981, | |
| "learning_rate": 0.00010638101267246283, | |
| "loss": 0.5319, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 1.991549295774648, | |
| "grad_norm": 0.13807927072048187, | |
| "learning_rate": 0.00010601683740686366, | |
| "loss": 0.5482, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 1.996056338028169, | |
| "grad_norm": 0.11675193160772324, | |
| "learning_rate": 0.00010565258203596722, | |
| "loss": 0.5371, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.12133872509002686, | |
| "learning_rate": 0.00010528825140929541, | |
| "loss": 0.5284, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 2.004507042253521, | |
| "grad_norm": 0.12044970691204071, | |
| "learning_rate": 0.00010492385037737207, | |
| "loss": 0.5278, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 2.0090140845070423, | |
| "grad_norm": 0.12002495676279068, | |
| "learning_rate": 0.00010455938379165835, | |
| "loss": 0.5774, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 2.0135211267605633, | |
| "grad_norm": 0.11336331069469452, | |
| "learning_rate": 0.00010419485650448814, | |
| "loss": 0.5003, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 2.0180281690140847, | |
| "grad_norm": 0.1343923956155777, | |
| "learning_rate": 0.00010383027336900355, | |
| "loss": 0.5172, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 2.0225352112676056, | |
| "grad_norm": 0.12244565784931183, | |
| "learning_rate": 0.00010346563923909014, | |
| "loss": 0.5267, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 2.0270422535211265, | |
| "grad_norm": 0.11235007643699646, | |
| "learning_rate": 0.00010310095896931242, | |
| "loss": 0.5211, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.031549295774648, | |
| "grad_norm": 0.18670588731765747, | |
| "learning_rate": 0.00010273623741484923, | |
| "loss": 0.5181, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 2.036056338028169, | |
| "grad_norm": 0.12979289889335632, | |
| "learning_rate": 0.00010237147943142898, | |
| "loss": 0.5333, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 2.0405633802816903, | |
| "grad_norm": 0.11047399044036865, | |
| "learning_rate": 0.00010200668987526512, | |
| "loss": 0.5264, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 2.045070422535211, | |
| "grad_norm": 0.1219114437699318, | |
| "learning_rate": 0.00010164187360299142, | |
| "loss": 0.518, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 2.0495774647887326, | |
| "grad_norm": 0.12627394497394562, | |
| "learning_rate": 0.00010127703547159739, | |
| "loss": 0.5094, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 2.0540845070422535, | |
| "grad_norm": 0.11944904178380966, | |
| "learning_rate": 0.00010091218033836348, | |
| "loss": 0.5272, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 2.0585915492957745, | |
| "grad_norm": 0.13259534537792206, | |
| "learning_rate": 0.00010054731306079656, | |
| "loss": 0.5347, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 2.063098591549296, | |
| "grad_norm": 0.1272563338279724, | |
| "learning_rate": 0.00010018243849656517, | |
| "loss": 0.5144, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 2.067605633802817, | |
| "grad_norm": 0.10852837562561035, | |
| "learning_rate": 9.981756150343485e-05, | |
| "loss": 0.5384, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 2.072112676056338, | |
| "grad_norm": 0.12837117910385132, | |
| "learning_rate": 9.945268693920346e-05, | |
| "loss": 0.5534, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.076619718309859, | |
| "grad_norm": 0.1136341392993927, | |
| "learning_rate": 9.908781966163655e-05, | |
| "loss": 0.5318, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 2.08112676056338, | |
| "grad_norm": 0.11348137259483337, | |
| "learning_rate": 9.872296452840264e-05, | |
| "loss": 0.5138, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 2.0856338028169015, | |
| "grad_norm": 0.12767234444618225, | |
| "learning_rate": 9.83581263970086e-05, | |
| "loss": 0.516, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 2.0901408450704224, | |
| "grad_norm": 0.12416424602270126, | |
| "learning_rate": 9.799331012473493e-05, | |
| "loss": 0.5428, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 2.094647887323944, | |
| "grad_norm": 0.12291053682565689, | |
| "learning_rate": 9.762852056857102e-05, | |
| "loss": 0.5209, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 2.0991549295774647, | |
| "grad_norm": 0.14804038405418396, | |
| "learning_rate": 9.726376258515078e-05, | |
| "loss": 0.5522, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 2.103661971830986, | |
| "grad_norm": 0.12152467668056488, | |
| "learning_rate": 9.689904103068758e-05, | |
| "loss": 0.5358, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 2.108169014084507, | |
| "grad_norm": 0.11182091385126114, | |
| "learning_rate": 9.653436076090988e-05, | |
| "loss": 0.5497, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 2.112676056338028, | |
| "grad_norm": 0.107152059674263, | |
| "learning_rate": 9.616972663099647e-05, | |
| "loss": 0.5153, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 2.1171830985915494, | |
| "grad_norm": 0.12143649160861969, | |
| "learning_rate": 9.580514349551187e-05, | |
| "loss": 0.5852, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.1216901408450703, | |
| "grad_norm": 0.11740640550851822, | |
| "learning_rate": 9.544061620834167e-05, | |
| "loss": 0.5597, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 2.1261971830985917, | |
| "grad_norm": 0.10704807937145233, | |
| "learning_rate": 9.507614962262795e-05, | |
| "loss": 0.5306, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 2.1307042253521127, | |
| "grad_norm": 0.11234696209430695, | |
| "learning_rate": 9.471174859070461e-05, | |
| "loss": 0.5185, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 2.1352112676056336, | |
| "grad_norm": 0.12021481990814209, | |
| "learning_rate": 9.434741796403282e-05, | |
| "loss": 0.5727, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 2.139718309859155, | |
| "grad_norm": 0.11688639968633652, | |
| "learning_rate": 9.398316259313637e-05, | |
| "loss": 0.5302, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.144225352112676, | |
| "grad_norm": 0.1164378821849823, | |
| "learning_rate": 9.361898732753716e-05, | |
| "loss": 0.5156, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 2.1487323943661973, | |
| "grad_norm": 0.11934376507997513, | |
| "learning_rate": 9.325489701569065e-05, | |
| "loss": 0.5397, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 2.1532394366197183, | |
| "grad_norm": 0.1212429478764534, | |
| "learning_rate": 9.289089650492118e-05, | |
| "loss": 0.5451, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 2.1577464788732392, | |
| "grad_norm": 0.1096879169344902, | |
| "learning_rate": 9.252699064135758e-05, | |
| "loss": 0.545, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 2.1622535211267606, | |
| "grad_norm": 0.11909584701061249, | |
| "learning_rate": 9.216318426986856e-05, | |
| "loss": 0.5305, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.1667605633802816, | |
| "grad_norm": 0.12082231044769287, | |
| "learning_rate": 9.179948223399828e-05, | |
| "loss": 0.5121, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 2.171267605633803, | |
| "grad_norm": 0.11738288402557373, | |
| "learning_rate": 9.143588937590178e-05, | |
| "loss": 0.5111, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 2.175774647887324, | |
| "grad_norm": 0.1155785471200943, | |
| "learning_rate": 9.107241053628059e-05, | |
| "loss": 0.5558, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 2.1802816901408453, | |
| "grad_norm": 0.11050604283809662, | |
| "learning_rate": 9.070905055431822e-05, | |
| "loss": 0.505, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 2.184788732394366, | |
| "grad_norm": 0.11163124442100525, | |
| "learning_rate": 9.034581426761581e-05, | |
| "loss": 0.5204, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 2.189295774647887, | |
| "grad_norm": 0.11405828595161438, | |
| "learning_rate": 8.998270651212764e-05, | |
| "loss": 0.5267, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 2.1938028169014085, | |
| "grad_norm": 0.10824751108884811, | |
| "learning_rate": 8.961973212209684e-05, | |
| "loss": 0.5363, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 2.1983098591549295, | |
| "grad_norm": 0.120577372610569, | |
| "learning_rate": 8.925689592999088e-05, | |
| "loss": 0.5438, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 2.202816901408451, | |
| "grad_norm": 0.12007007002830505, | |
| "learning_rate": 8.889420276643746e-05, | |
| "loss": 0.5179, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 2.207323943661972, | |
| "grad_norm": 0.115611732006073, | |
| "learning_rate": 8.853165746015997e-05, | |
| "loss": 0.544, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.2118309859154928, | |
| "grad_norm": 0.1210789903998375, | |
| "learning_rate": 8.816926483791331e-05, | |
| "loss": 0.528, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 2.216338028169014, | |
| "grad_norm": 0.13798987865447998, | |
| "learning_rate": 8.780702972441964e-05, | |
| "loss": 0.5168, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 2.220845070422535, | |
| "grad_norm": 0.11814180761575699, | |
| "learning_rate": 8.744495694230412e-05, | |
| "loss": 0.5351, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 2.2253521126760565, | |
| "grad_norm": 0.10845314711332321, | |
| "learning_rate": 8.708305131203072e-05, | |
| "loss": 0.5411, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 2.2298591549295774, | |
| "grad_norm": 0.1123770996928215, | |
| "learning_rate": 8.672131765183799e-05, | |
| "loss": 0.5128, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 2.234366197183099, | |
| "grad_norm": 0.1154399961233139, | |
| "learning_rate": 8.635976077767499e-05, | |
| "loss": 0.5264, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 2.2388732394366198, | |
| "grad_norm": 0.1050579845905304, | |
| "learning_rate": 8.599838550313713e-05, | |
| "loss": 0.5429, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 2.2433802816901407, | |
| "grad_norm": 0.11692402511835098, | |
| "learning_rate": 8.563719663940205e-05, | |
| "loss": 0.5044, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 2.247887323943662, | |
| "grad_norm": 0.11380699276924133, | |
| "learning_rate": 8.527619899516567e-05, | |
| "loss": 0.5159, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 2.252394366197183, | |
| "grad_norm": 0.1111583560705185, | |
| "learning_rate": 8.491539737657802e-05, | |
| "loss": 0.5434, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.2569014084507044, | |
| "grad_norm": 0.14941135048866272, | |
| "learning_rate": 8.455479658717947e-05, | |
| "loss": 0.5846, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 2.2614084507042254, | |
| "grad_norm": 0.11948571354150772, | |
| "learning_rate": 8.419440142783653e-05, | |
| "loss": 0.5286, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 2.2659154929577463, | |
| "grad_norm": 0.12659218907356262, | |
| "learning_rate": 8.383421669667812e-05, | |
| "loss": 0.509, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 2.2704225352112677, | |
| "grad_norm": 0.11504048109054565, | |
| "learning_rate": 8.347424718903151e-05, | |
| "loss": 0.5394, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 2.2749295774647886, | |
| "grad_norm": 0.11881807446479797, | |
| "learning_rate": 8.311449769735873e-05, | |
| "loss": 0.5307, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 2.27943661971831, | |
| "grad_norm": 0.13386914134025574, | |
| "learning_rate": 8.275497301119253e-05, | |
| "loss": 0.5274, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 2.283943661971831, | |
| "grad_norm": 0.15793730318546295, | |
| "learning_rate": 8.239567791707272e-05, | |
| "loss": 0.5575, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 2.288450704225352, | |
| "grad_norm": 0.11447100341320038, | |
| "learning_rate": 8.203661719848248e-05, | |
| "loss": 0.5266, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 2.2929577464788733, | |
| "grad_norm": 0.1401495337486267, | |
| "learning_rate": 8.167779563578456e-05, | |
| "loss": 0.5321, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 2.2974647887323942, | |
| "grad_norm": 0.11609887331724167, | |
| "learning_rate": 8.131921800615773e-05, | |
| "loss": 0.5176, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.3019718309859156, | |
| "grad_norm": 0.11702638119459152, | |
| "learning_rate": 8.096088908353315e-05, | |
| "loss": 0.5196, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 2.3064788732394366, | |
| "grad_norm": 0.1231730580329895, | |
| "learning_rate": 8.060281363853087e-05, | |
| "loss": 0.5367, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 2.3109859154929575, | |
| "grad_norm": 0.12909771502017975, | |
| "learning_rate": 8.024499643839618e-05, | |
| "loss": 0.543, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 2.315492957746479, | |
| "grad_norm": 0.12570002675056458, | |
| "learning_rate": 7.988744224693625e-05, | |
| "loss": 0.5349, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 0.11345330625772476, | |
| "learning_rate": 7.953015582445667e-05, | |
| "loss": 0.5566, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 2.3245070422535212, | |
| "grad_norm": 0.1203540787100792, | |
| "learning_rate": 7.917314192769808e-05, | |
| "loss": 0.5455, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 2.329014084507042, | |
| "grad_norm": 0.12087874859571457, | |
| "learning_rate": 7.881640530977288e-05, | |
| "loss": 0.5499, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 2.3335211267605636, | |
| "grad_norm": 0.11830297857522964, | |
| "learning_rate": 7.845995072010188e-05, | |
| "loss": 0.5653, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 2.3380281690140845, | |
| "grad_norm": 0.11518878489732742, | |
| "learning_rate": 7.810378290435108e-05, | |
| "loss": 0.5202, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 2.3425352112676054, | |
| "grad_norm": 0.1460411250591278, | |
| "learning_rate": 7.774790660436858e-05, | |
| "loss": 0.5443, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.347042253521127, | |
| "grad_norm": 0.13443294167518616, | |
| "learning_rate": 7.739232655812128e-05, | |
| "loss": 0.5673, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 2.3515492957746478, | |
| "grad_norm": 0.10706333070993423, | |
| "learning_rate": 7.703704749963201e-05, | |
| "loss": 0.5351, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 2.356056338028169, | |
| "grad_norm": 0.1250416338443756, | |
| "learning_rate": 7.668207415891624e-05, | |
| "loss": 0.5491, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 2.36056338028169, | |
| "grad_norm": 0.24670056998729706, | |
| "learning_rate": 7.632741126191947e-05, | |
| "loss": 0.5248, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 2.3650704225352115, | |
| "grad_norm": 0.1117803156375885, | |
| "learning_rate": 7.597306353045393e-05, | |
| "loss": 0.5701, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.3695774647887324, | |
| "grad_norm": 0.10440925508737564, | |
| "learning_rate": 7.561903568213595e-05, | |
| "loss": 0.5028, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 2.3740845070422534, | |
| "grad_norm": 0.11765775829553604, | |
| "learning_rate": 7.526533243032307e-05, | |
| "loss": 0.5229, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 2.3785915492957748, | |
| "grad_norm": 0.11378080397844315, | |
| "learning_rate": 7.491195848405135e-05, | |
| "loss": 0.528, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 2.3830985915492957, | |
| "grad_norm": 0.12597879767417908, | |
| "learning_rate": 7.455891854797256e-05, | |
| "loss": 0.5027, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 2.387605633802817, | |
| "grad_norm": 0.13118213415145874, | |
| "learning_rate": 7.420621732229169e-05, | |
| "loss": 0.5186, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.392112676056338, | |
| "grad_norm": 0.11117777973413467, | |
| "learning_rate": 7.385385950270425e-05, | |
| "loss": 0.5207, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 2.396619718309859, | |
| "grad_norm": 0.1138320192694664, | |
| "learning_rate": 7.350184978033386e-05, | |
| "loss": 0.5089, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 2.4011267605633804, | |
| "grad_norm": 0.11337253451347351, | |
| "learning_rate": 7.315019284166966e-05, | |
| "loss": 0.5165, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 2.4056338028169013, | |
| "grad_norm": 0.10323511809110641, | |
| "learning_rate": 7.279889336850408e-05, | |
| "loss": 0.5154, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 2.4101408450704227, | |
| "grad_norm": 0.11857807636260986, | |
| "learning_rate": 7.244795603787036e-05, | |
| "loss": 0.509, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 2.4146478873239436, | |
| "grad_norm": 0.1258813738822937, | |
| "learning_rate": 7.209738552198043e-05, | |
| "loss": 0.5246, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 2.4191549295774646, | |
| "grad_norm": 0.11479494720697403, | |
| "learning_rate": 7.17471864881625e-05, | |
| "loss": 0.5376, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 2.423661971830986, | |
| "grad_norm": 0.10941333323717117, | |
| "learning_rate": 7.139736359879916e-05, | |
| "loss": 0.5198, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 2.428169014084507, | |
| "grad_norm": 0.1188211664557457, | |
| "learning_rate": 7.104792151126515e-05, | |
| "loss": 0.5174, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 2.4326760563380283, | |
| "grad_norm": 0.12148640304803848, | |
| "learning_rate": 7.069886487786536e-05, | |
| "loss": 0.5372, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.4371830985915492, | |
| "grad_norm": 0.10996753722429276, | |
| "learning_rate": 7.035019834577301e-05, | |
| "loss": 0.5211, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 2.44169014084507, | |
| "grad_norm": 0.1371939480304718, | |
| "learning_rate": 7.00019265569676e-05, | |
| "loss": 0.5551, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 2.4461971830985916, | |
| "grad_norm": 0.1196320503950119, | |
| "learning_rate": 6.96540541481733e-05, | |
| "loss": 0.5357, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 2.4507042253521125, | |
| "grad_norm": 0.10747256129980087, | |
| "learning_rate": 6.930658575079705e-05, | |
| "loss": 0.5368, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 2.455211267605634, | |
| "grad_norm": 0.11347094923257828, | |
| "learning_rate": 6.8959525990867e-05, | |
| "loss": 0.5174, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 2.459718309859155, | |
| "grad_norm": 0.12358327209949493, | |
| "learning_rate": 6.861287948897091e-05, | |
| "loss": 0.5529, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 2.4642253521126762, | |
| "grad_norm": 0.12316222488880157, | |
| "learning_rate": 6.826665086019466e-05, | |
| "loss": 0.5625, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 2.468732394366197, | |
| "grad_norm": 0.11993323266506195, | |
| "learning_rate": 6.792084471406069e-05, | |
| "loss": 0.5229, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 2.473239436619718, | |
| "grad_norm": 0.11845649033784866, | |
| "learning_rate": 6.75754656544667e-05, | |
| "loss": 0.5136, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 2.4777464788732395, | |
| "grad_norm": 0.11402633786201477, | |
| "learning_rate": 6.723051827962445e-05, | |
| "loss": 0.5516, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.4822535211267605, | |
| "grad_norm": 0.10994803160429001, | |
| "learning_rate": 6.68860071819984e-05, | |
| "loss": 0.5077, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 2.486760563380282, | |
| "grad_norm": 0.12263881415128708, | |
| "learning_rate": 6.654193694824462e-05, | |
| "loss": 0.548, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 2.491267605633803, | |
| "grad_norm": 0.12687471508979797, | |
| "learning_rate": 6.619831215914974e-05, | |
| "loss": 0.5835, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 2.495774647887324, | |
| "grad_norm": 0.11021614074707031, | |
| "learning_rate": 6.585513738956996e-05, | |
| "loss": 0.5442, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 2.500281690140845, | |
| "grad_norm": 0.12376144528388977, | |
| "learning_rate": 6.551241720837014e-05, | |
| "loss": 0.5038, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 2.504788732394366, | |
| "grad_norm": 0.12698741257190704, | |
| "learning_rate": 6.517015617836291e-05, | |
| "loss": 0.5143, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 2.5092957746478874, | |
| "grad_norm": 0.1203697919845581, | |
| "learning_rate": 6.48283588562481e-05, | |
| "loss": 0.5443, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 2.5138028169014084, | |
| "grad_norm": 0.10425330698490143, | |
| "learning_rate": 6.448702979255176e-05, | |
| "loss": 0.4859, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 2.5183098591549298, | |
| "grad_norm": 0.11607982218265533, | |
| "learning_rate": 6.414617353156605e-05, | |
| "loss": 0.5198, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 2.5228169014084507, | |
| "grad_norm": 0.1305762082338333, | |
| "learning_rate": 6.380579461128819e-05, | |
| "loss": 0.5886, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.5273239436619717, | |
| "grad_norm": 0.11528196185827255, | |
| "learning_rate": 6.34658975633605e-05, | |
| "loss": 0.5168, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 2.531830985915493, | |
| "grad_norm": 0.12088954448699951, | |
| "learning_rate": 6.312648691300975e-05, | |
| "loss": 0.5301, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 2.536338028169014, | |
| "grad_norm": 0.11259355396032333, | |
| "learning_rate": 6.278756717898713e-05, | |
| "loss": 0.5079, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 2.5408450704225354, | |
| "grad_norm": 0.10837467759847641, | |
| "learning_rate": 6.2449142873508e-05, | |
| "loss": 0.5081, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 2.5453521126760563, | |
| "grad_norm": 0.11548671871423721, | |
| "learning_rate": 6.211121850219175e-05, | |
| "loss": 0.5236, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 2.5498591549295773, | |
| "grad_norm": 0.11041808128356934, | |
| "learning_rate": 6.1773798564002e-05, | |
| "loss": 0.5309, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 2.5543661971830987, | |
| "grad_norm": 0.13341392576694489, | |
| "learning_rate": 6.143688755118646e-05, | |
| "loss": 0.5239, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 2.5588732394366196, | |
| "grad_norm": 0.11479108780622482, | |
| "learning_rate": 6.110048994921734e-05, | |
| "loss": 0.5088, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 2.563380281690141, | |
| "grad_norm": 0.10170383006334305, | |
| "learning_rate": 6.0764610236731524e-05, | |
| "loss": 0.5027, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 2.567887323943662, | |
| "grad_norm": 0.1148676872253418, | |
| "learning_rate": 6.042925288547092e-05, | |
| "loss": 0.5454, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.572394366197183, | |
| "grad_norm": 0.11497487127780914, | |
| "learning_rate": 6.009442236022307e-05, | |
| "loss": 0.5149, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 2.5769014084507043, | |
| "grad_norm": 0.11571796983480453, | |
| "learning_rate": 5.9760123118761514e-05, | |
| "loss": 0.5188, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 2.581408450704225, | |
| "grad_norm": 0.10864008218050003, | |
| "learning_rate": 5.9426359611786573e-05, | |
| "loss": 0.5249, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 2.5859154929577466, | |
| "grad_norm": 0.11008573323488235, | |
| "learning_rate": 5.909313628286601e-05, | |
| "loss": 0.5418, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 2.5904225352112675, | |
| "grad_norm": 0.11387594044208527, | |
| "learning_rate": 5.8760457568375984e-05, | |
| "loss": 0.5342, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 2.5949295774647885, | |
| "grad_norm": 0.12866191565990448, | |
| "learning_rate": 5.842832789744186e-05, | |
| "loss": 0.5747, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 2.59943661971831, | |
| "grad_norm": 0.11581499129533768, | |
| "learning_rate": 5.8096751691879356e-05, | |
| "loss": 0.5323, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 2.6039436619718312, | |
| "grad_norm": 0.13145901262760162, | |
| "learning_rate": 5.776573336613553e-05, | |
| "loss": 0.5125, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 2.608450704225352, | |
| "grad_norm": 0.11746399849653244, | |
| "learning_rate": 5.7435277327230206e-05, | |
| "loss": 0.54, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 2.612957746478873, | |
| "grad_norm": 0.10810490697622299, | |
| "learning_rate": 5.7105387974697063e-05, | |
| "loss": 0.5299, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.6174647887323945, | |
| "grad_norm": 0.11249610036611557, | |
| "learning_rate": 5.677606970052529e-05, | |
| "loss": 0.5365, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 2.6219718309859155, | |
| "grad_norm": 0.10808350145816803, | |
| "learning_rate": 5.6447326889101e-05, | |
| "loss": 0.4997, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 2.626478873239437, | |
| "grad_norm": 0.11670640110969543, | |
| "learning_rate": 5.6119163917148866e-05, | |
| "loss": 0.5127, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 2.630985915492958, | |
| "grad_norm": 0.10403117537498474, | |
| "learning_rate": 5.5791585153673774e-05, | |
| "loss": 0.4984, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 2.6354929577464787, | |
| "grad_norm": 0.11643310636281967, | |
| "learning_rate": 5.546459495990288e-05, | |
| "loss": 0.5363, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 0.11666381359100342, | |
| "learning_rate": 5.513819768922723e-05, | |
| "loss": 0.5462, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 2.644507042253521, | |
| "grad_norm": 0.1106523647904396, | |
| "learning_rate": 5.481239768714417e-05, | |
| "loss": 0.5234, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 2.6490140845070425, | |
| "grad_norm": 0.11416450887918472, | |
| "learning_rate": 5.448719929119915e-05, | |
| "loss": 0.5158, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 2.6535211267605634, | |
| "grad_norm": 0.11326763778924942, | |
| "learning_rate": 5.416260683092814e-05, | |
| "loss": 0.5457, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 2.6580281690140843, | |
| "grad_norm": 0.10651212185621262, | |
| "learning_rate": 5.3838624627800074e-05, | |
| "loss": 0.5281, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.6625352112676057, | |
| "grad_norm": 0.11655013263225555, | |
| "learning_rate": 5.351525699515908e-05, | |
| "loss": 0.5355, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 2.6670422535211267, | |
| "grad_norm": 0.10108935087919235, | |
| "learning_rate": 5.319250823816731e-05, | |
| "loss": 0.509, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 2.671549295774648, | |
| "grad_norm": 0.10345329344272614, | |
| "learning_rate": 5.287038265374735e-05, | |
| "loss": 0.5093, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 2.676056338028169, | |
| "grad_norm": 0.11032966524362564, | |
| "learning_rate": 5.25488845305254e-05, | |
| "loss": 0.5083, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 2.68056338028169, | |
| "grad_norm": 0.11705298721790314, | |
| "learning_rate": 5.222801814877369e-05, | |
| "loss": 0.5108, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 2.6850704225352113, | |
| "grad_norm": 0.11696744710206985, | |
| "learning_rate": 5.190778778035395e-05, | |
| "loss": 0.5118, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 2.6895774647887323, | |
| "grad_norm": 0.10620059072971344, | |
| "learning_rate": 5.158819768866012e-05, | |
| "loss": 0.5279, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 2.6940845070422537, | |
| "grad_norm": 0.11230248957872391, | |
| "learning_rate": 5.126925212856202e-05, | |
| "loss": 0.5038, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 2.6985915492957746, | |
| "grad_norm": 0.11875911056995392, | |
| "learning_rate": 5.0950955346348314e-05, | |
| "loss": 0.5513, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 2.7030985915492955, | |
| "grad_norm": 0.11459613591432571, | |
| "learning_rate": 5.0633311579670296e-05, | |
| "loss": 0.5606, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.707605633802817, | |
| "grad_norm": 0.12176425009965897, | |
| "learning_rate": 5.031632505748516e-05, | |
| "loss": 0.5262, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 2.712112676056338, | |
| "grad_norm": 0.12691204249858856, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.5246, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 2.7166197183098593, | |
| "grad_norm": 0.09963858127593994, | |
| "learning_rate": 4.968434061861543e-05, | |
| "loss": 0.4977, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 2.72112676056338, | |
| "grad_norm": 0.10625036060810089, | |
| "learning_rate": 4.9369351115869535e-05, | |
| "loss": 0.512, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 2.725633802816901, | |
| "grad_norm": 0.11431818455457687, | |
| "learning_rate": 4.9055035685382055e-05, | |
| "loss": 0.5308, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 2.7301408450704225, | |
| "grad_norm": 0.10542725026607513, | |
| "learning_rate": 4.874139851179833e-05, | |
| "loss": 0.5301, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 2.734647887323944, | |
| "grad_norm": 0.10275546461343765, | |
| "learning_rate": 4.8428443770733835e-05, | |
| "loss": 0.5209, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 2.739154929577465, | |
| "grad_norm": 0.38522496819496155, | |
| "learning_rate": 4.811617562871832e-05, | |
| "loss": 0.5319, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 2.743661971830986, | |
| "grad_norm": 0.10014399141073227, | |
| "learning_rate": 4.7804598243140666e-05, | |
| "loss": 0.5151, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 2.748169014084507, | |
| "grad_norm": 0.11353477835655212, | |
| "learning_rate": 4.749371576219317e-05, | |
| "loss": 0.5246, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.752676056338028, | |
| "grad_norm": 0.10583645105361938, | |
| "learning_rate": 4.718353232481665e-05, | |
| "loss": 0.5132, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 2.7571830985915495, | |
| "grad_norm": 0.12215419858694077, | |
| "learning_rate": 4.6874052060645066e-05, | |
| "loss": 0.5331, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 2.7616901408450705, | |
| "grad_norm": 0.11868246644735336, | |
| "learning_rate": 4.6565279089950795e-05, | |
| "loss": 0.5023, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 2.7661971830985914, | |
| "grad_norm": 0.12116070836782455, | |
| "learning_rate": 4.62572175235895e-05, | |
| "loss": 0.5461, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 2.770704225352113, | |
| "grad_norm": 0.11347726732492447, | |
| "learning_rate": 4.5949871462945714e-05, | |
| "loss": 0.5095, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 2.7752112676056337, | |
| "grad_norm": 0.10805897414684296, | |
| "learning_rate": 4.56432449998779e-05, | |
| "loss": 0.5069, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 2.779718309859155, | |
| "grad_norm": 0.12143836170434952, | |
| "learning_rate": 4.533734221666425e-05, | |
| "loss": 0.5361, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 2.784225352112676, | |
| "grad_norm": 0.12267526239156723, | |
| "learning_rate": 4.503216718594825e-05, | |
| "loss": 0.5325, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 2.788732394366197, | |
| "grad_norm": 0.1219489648938179, | |
| "learning_rate": 4.472772397068431e-05, | |
| "loss": 0.5408, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 2.7932394366197184, | |
| "grad_norm": 0.11085795611143112, | |
| "learning_rate": 4.442401662408395e-05, | |
| "loss": 0.5221, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.7977464788732394, | |
| "grad_norm": 0.11736064404249191, | |
| "learning_rate": 4.4121049189561556e-05, | |
| "loss": 0.5367, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 2.8022535211267607, | |
| "grad_norm": 0.10407859832048416, | |
| "learning_rate": 4.381882570068079e-05, | |
| "loss": 0.4977, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 2.8067605633802817, | |
| "grad_norm": 0.10226607322692871, | |
| "learning_rate": 4.351735018110066e-05, | |
| "loss": 0.4931, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 2.8112676056338026, | |
| "grad_norm": 0.10844944417476654, | |
| "learning_rate": 4.321662664452221e-05, | |
| "loss": 0.5228, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 2.815774647887324, | |
| "grad_norm": 0.1089576929807663, | |
| "learning_rate": 4.291665909463477e-05, | |
| "loss": 0.5316, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.820281690140845, | |
| "grad_norm": 0.11149588227272034, | |
| "learning_rate": 4.2617451525063014e-05, | |
| "loss": 0.5147, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 2.8247887323943663, | |
| "grad_norm": 0.12150777131319046, | |
| "learning_rate": 4.231900791931341e-05, | |
| "loss": 0.5386, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 2.8292957746478873, | |
| "grad_norm": 0.11250042915344238, | |
| "learning_rate": 4.202133225072153e-05, | |
| "loss": 0.5494, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 2.8338028169014082, | |
| "grad_norm": 0.11534137278795242, | |
| "learning_rate": 4.1724428482398945e-05, | |
| "loss": 0.5483, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 2.8383098591549296, | |
| "grad_norm": 0.10241974890232086, | |
| "learning_rate": 4.142830056718052e-05, | |
| "loss": 0.5052, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.8428169014084506, | |
| "grad_norm": 0.11854840815067291, | |
| "learning_rate": 4.113295244757172e-05, | |
| "loss": 0.5385, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 2.847323943661972, | |
| "grad_norm": 0.11492074280977249, | |
| "learning_rate": 4.08383880556963e-05, | |
| "loss": 0.4985, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 2.851830985915493, | |
| "grad_norm": 0.10175682604312897, | |
| "learning_rate": 4.054461131324373e-05, | |
| "loss": 0.5064, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 2.856338028169014, | |
| "grad_norm": 0.11565281450748444, | |
| "learning_rate": 4.025162613141713e-05, | |
| "loss": 0.5084, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 2.860845070422535, | |
| "grad_norm": 0.10842733085155487, | |
| "learning_rate": 3.995943641088121e-05, | |
| "loss": 0.5128, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 2.8653521126760566, | |
| "grad_norm": 0.11573941260576248, | |
| "learning_rate": 3.966804604171019e-05, | |
| "loss": 0.5279, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 2.8698591549295775, | |
| "grad_norm": 0.11557252705097198, | |
| "learning_rate": 3.937745890333623e-05, | |
| "loss": 0.5174, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 2.8743661971830985, | |
| "grad_norm": 0.1108415350317955, | |
| "learning_rate": 3.908767886449752e-05, | |
| "loss": 0.5161, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 2.87887323943662, | |
| "grad_norm": 0.1033615991473198, | |
| "learning_rate": 3.8798709783187036e-05, | |
| "loss": 0.529, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 2.883380281690141, | |
| "grad_norm": 0.14297285676002502, | |
| "learning_rate": 3.8510555506600974e-05, | |
| "loss": 0.5096, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.887887323943662, | |
| "grad_norm": 0.1152140274643898, | |
| "learning_rate": 3.82232198710877e-05, | |
| "loss": 0.5361, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 2.892394366197183, | |
| "grad_norm": 0.11221909523010254, | |
| "learning_rate": 3.793670670209645e-05, | |
| "loss": 0.542, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 2.896901408450704, | |
| "grad_norm": 0.11155454814434052, | |
| "learning_rate": 3.7651019814126654e-05, | |
| "loss": 0.5383, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 2.9014084507042255, | |
| "grad_norm": 0.11201007664203644, | |
| "learning_rate": 3.736616301067694e-05, | |
| "loss": 0.5295, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 2.9059154929577464, | |
| "grad_norm": 0.09936228394508362, | |
| "learning_rate": 3.708214008419467e-05, | |
| "loss": 0.5093, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 2.910422535211268, | |
| "grad_norm": 0.11197184026241302, | |
| "learning_rate": 3.6798954816025286e-05, | |
| "loss": 0.5387, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 2.9149295774647888, | |
| "grad_norm": 0.11715072393417358, | |
| "learning_rate": 3.6516610976362155e-05, | |
| "loss": 0.5487, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 2.9194366197183097, | |
| "grad_norm": 0.10473347455263138, | |
| "learning_rate": 3.623511232419612e-05, | |
| "loss": 0.5017, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 2.923943661971831, | |
| "grad_norm": 0.10394609719514847, | |
| "learning_rate": 3.595446260726576e-05, | |
| "loss": 0.5091, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 2.928450704225352, | |
| "grad_norm": 0.10504930466413498, | |
| "learning_rate": 3.5674665562007184e-05, | |
| "loss": 0.5299, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.9329577464788734, | |
| "grad_norm": 0.11549410969018936, | |
| "learning_rate": 3.5395724913504545e-05, | |
| "loss": 0.5435, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 2.9374647887323944, | |
| "grad_norm": 0.12606476247310638, | |
| "learning_rate": 3.511764437544036e-05, | |
| "loss": 0.5115, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 2.9419718309859153, | |
| "grad_norm": 0.10190090537071228, | |
| "learning_rate": 3.48404276500459e-05, | |
| "loss": 0.499, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 2.9464788732394367, | |
| "grad_norm": 0.11330178380012512, | |
| "learning_rate": 3.456407842805223e-05, | |
| "loss": 0.5286, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 2.9509859154929576, | |
| "grad_norm": 0.10447689890861511, | |
| "learning_rate": 3.4288600388640714e-05, | |
| "loss": 0.4856, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 2.955492957746479, | |
| "grad_norm": 0.11650539189577103, | |
| "learning_rate": 3.4013997199394376e-05, | |
| "loss": 0.5344, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 0.1107359305024147, | |
| "learning_rate": 3.3740272516248736e-05, | |
| "loss": 0.5121, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 2.964507042253521, | |
| "grad_norm": 0.11095371842384338, | |
| "learning_rate": 3.346742998344348e-05, | |
| "loss": 0.5136, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 2.9690140845070423, | |
| "grad_norm": 0.10957096517086029, | |
| "learning_rate": 3.3195473233473584e-05, | |
| "loss": 0.5263, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 2.9735211267605632, | |
| "grad_norm": 0.11277777701616287, | |
| "learning_rate": 3.292440588704131e-05, | |
| "loss": 0.5472, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.9780281690140846, | |
| "grad_norm": 0.10114355385303497, | |
| "learning_rate": 3.265423155300767e-05, | |
| "loss": 0.5272, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 2.9825352112676056, | |
| "grad_norm": 0.11590156704187393, | |
| "learning_rate": 3.238495382834464e-05, | |
| "loss": 0.521, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 2.9870422535211265, | |
| "grad_norm": 0.12712036073207855, | |
| "learning_rate": 3.211657629808712e-05, | |
| "loss": 0.5632, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 2.991549295774648, | |
| "grad_norm": 0.11136014014482498, | |
| "learning_rate": 3.184910253528528e-05, | |
| "loss": 0.5139, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 2.9960563380281693, | |
| "grad_norm": 0.10489501059055328, | |
| "learning_rate": 3.158253610095697e-05, | |
| "loss": 0.5046, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.1281147003173828, | |
| "learning_rate": 3.1316880544040226e-05, | |
| "loss": 0.5102, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.004507042253521, | |
| "grad_norm": 0.1174585297703743, | |
| "learning_rate": 3.105213940134621e-05, | |
| "loss": 0.5348, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 3.0090140845070423, | |
| "grad_norm": 0.11154928803443909, | |
| "learning_rate": 3.07883161975119e-05, | |
| "loss": 0.5283, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 3.0135211267605633, | |
| "grad_norm": 0.10453861951828003, | |
| "learning_rate": 3.0525414444953396e-05, | |
| "loss": 0.4933, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 3.0180281690140847, | |
| "grad_norm": 0.11380238831043243, | |
| "learning_rate": 3.026343764381887e-05, | |
| "loss": 0.5073, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.0225352112676056, | |
| "grad_norm": 0.0978739783167839, | |
| "learning_rate": 3.0002389281942332e-05, | |
| "loss": 0.5098, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 3.0270422535211265, | |
| "grad_norm": 0.11205834150314331, | |
| "learning_rate": 2.9742272834796813e-05, | |
| "loss": 0.55, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 3.031549295774648, | |
| "grad_norm": 0.11361253261566162, | |
| "learning_rate": 2.9483091765448422e-05, | |
| "loss": 0.5519, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 3.036056338028169, | |
| "grad_norm": 0.1036975234746933, | |
| "learning_rate": 2.9224849524509936e-05, | |
| "loss": 0.5319, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 3.0405633802816903, | |
| "grad_norm": 0.10117993503808975, | |
| "learning_rate": 2.896754955009524e-05, | |
| "loss": 0.5152, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 3.045070422535211, | |
| "grad_norm": 0.114353246986866, | |
| "learning_rate": 2.871119526777315e-05, | |
| "loss": 0.5187, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 3.0495774647887326, | |
| "grad_norm": 0.10379718244075775, | |
| "learning_rate": 2.8455790090522017e-05, | |
| "loss": 0.5105, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 3.0540845070422535, | |
| "grad_norm": 0.10687281936407089, | |
| "learning_rate": 2.820133741868434e-05, | |
| "loss": 0.502, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 3.0585915492957745, | |
| "grad_norm": 0.12042738497257233, | |
| "learning_rate": 2.794784063992131e-05, | |
| "loss": 0.5081, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 3.063098591549296, | |
| "grad_norm": 0.11131054908037186, | |
| "learning_rate": 2.7695303129167927e-05, | |
| "loss": 0.5123, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.067605633802817, | |
| "grad_norm": 0.10670991986989975, | |
| "learning_rate": 2.7443728248587852e-05, | |
| "loss": 0.5246, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 3.072112676056338, | |
| "grad_norm": 0.11702380329370499, | |
| "learning_rate": 2.719311934752884e-05, | |
| "loss": 0.5109, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 3.076619718309859, | |
| "grad_norm": 0.10768495500087738, | |
| "learning_rate": 2.6943479762477964e-05, | |
| "loss": 0.5195, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 3.08112676056338, | |
| "grad_norm": 0.1184210330247879, | |
| "learning_rate": 2.669481281701739e-05, | |
| "loss": 0.5585, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 3.0856338028169015, | |
| "grad_norm": 0.10743115097284317, | |
| "learning_rate": 2.6447121821779917e-05, | |
| "loss": 0.5134, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 3.0901408450704224, | |
| "grad_norm": 0.10095122456550598, | |
| "learning_rate": 2.620041007440508e-05, | |
| "loss": 0.5154, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 3.094647887323944, | |
| "grad_norm": 0.11585785448551178, | |
| "learning_rate": 2.5954680859495163e-05, | |
| "loss": 0.4975, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 3.0991549295774647, | |
| "grad_norm": 0.11215182393789291, | |
| "learning_rate": 2.570993744857151e-05, | |
| "loss": 0.5347, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 3.103661971830986, | |
| "grad_norm": 0.10896939039230347, | |
| "learning_rate": 2.5466183100030837e-05, | |
| "loss": 0.5013, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 3.108169014084507, | |
| "grad_norm": 0.11886619031429291, | |
| "learning_rate": 2.5223421059102104e-05, | |
| "loss": 0.5244, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.112676056338028, | |
| "grad_norm": 0.11181308329105377, | |
| "learning_rate": 2.4981654557803026e-05, | |
| "loss": 0.5391, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 3.1171830985915494, | |
| "grad_norm": 0.09808338433504105, | |
| "learning_rate": 2.474088681489729e-05, | |
| "loss": 0.525, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 3.1216901408450703, | |
| "grad_norm": 0.11004786193370819, | |
| "learning_rate": 2.4501121035851492e-05, | |
| "loss": 0.526, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 3.1261971830985917, | |
| "grad_norm": 0.10769461840391159, | |
| "learning_rate": 2.426236041279266e-05, | |
| "loss": 0.5611, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 3.1307042253521127, | |
| "grad_norm": 0.10455281287431717, | |
| "learning_rate": 2.4024608124465585e-05, | |
| "loss": 0.5384, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 3.1352112676056336, | |
| "grad_norm": 0.10149269551038742, | |
| "learning_rate": 2.378786733619054e-05, | |
| "loss": 0.5255, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 3.139718309859155, | |
| "grad_norm": 0.10262631624937057, | |
| "learning_rate": 2.35521411998213e-05, | |
| "loss": 0.5248, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 3.144225352112676, | |
| "grad_norm": 0.0997721254825592, | |
| "learning_rate": 2.331743285370288e-05, | |
| "loss": 0.5047, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 3.1487323943661973, | |
| "grad_norm": 0.09472807496786118, | |
| "learning_rate": 2.3083745422630122e-05, | |
| "loss": 0.5056, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 3.1532394366197183, | |
| "grad_norm": 0.10167699307203293, | |
| "learning_rate": 2.2851082017805703e-05, | |
| "loss": 0.5039, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.1577464788732392, | |
| "grad_norm": 0.11040908098220825, | |
| "learning_rate": 2.2619445736799028e-05, | |
| "loss": 0.5308, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 3.1622535211267606, | |
| "grad_norm": 0.1062508374452591, | |
| "learning_rate": 2.238883966350479e-05, | |
| "loss": 0.5251, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 3.1667605633802816, | |
| "grad_norm": 0.11194084584712982, | |
| "learning_rate": 2.215926686810206e-05, | |
| "loss": 0.5202, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 3.171267605633803, | |
| "grad_norm": 0.1002085953950882, | |
| "learning_rate": 2.1930730407013245e-05, | |
| "loss": 0.5095, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 3.175774647887324, | |
| "grad_norm": 0.09527210891246796, | |
| "learning_rate": 2.1703233322863616e-05, | |
| "loss": 0.5217, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 3.1802816901408453, | |
| "grad_norm": 0.10605484992265701, | |
| "learning_rate": 2.1476778644440553e-05, | |
| "loss": 0.5075, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 3.184788732394366, | |
| "grad_norm": 0.10591242462396622, | |
| "learning_rate": 2.1251369386653454e-05, | |
| "loss": 0.5129, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 3.189295774647887, | |
| "grad_norm": 0.11138251423835754, | |
| "learning_rate": 2.1027008550493376e-05, | |
| "loss": 0.5366, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 3.1938028169014085, | |
| "grad_norm": 0.10201424360275269, | |
| "learning_rate": 2.0803699122993293e-05, | |
| "loss": 0.5375, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 3.1983098591549295, | |
| "grad_norm": 0.10267283767461777, | |
| "learning_rate": 2.0581444077188194e-05, | |
| "loss": 0.5262, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 3.202816901408451, | |
| "grad_norm": 0.09566653519868851, | |
| "learning_rate": 2.0360246372075466e-05, | |
| "loss": 0.4986, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 3.207323943661972, | |
| "grad_norm": 0.09336459636688232, | |
| "learning_rate": 2.0140108952575698e-05, | |
| "loss": 0.4931, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 3.2118309859154928, | |
| "grad_norm": 0.10596734285354614, | |
| "learning_rate": 1.9921034749493205e-05, | |
| "loss": 0.5326, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 3.216338028169014, | |
| "grad_norm": 0.10336334258317947, | |
| "learning_rate": 1.9703026679477256e-05, | |
| "loss": 0.5073, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 3.220845070422535, | |
| "grad_norm": 0.0994623526930809, | |
| "learning_rate": 1.9486087644983054e-05, | |
| "loss": 0.5281, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 3.2253521126760565, | |
| "grad_norm": 0.09632834047079086, | |
| "learning_rate": 1.9270220534233263e-05, | |
| "loss": 0.5067, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 3.2298591549295774, | |
| "grad_norm": 0.10012217611074448, | |
| "learning_rate": 1.9055428221179338e-05, | |
| "loss": 0.5009, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 3.234366197183099, | |
| "grad_norm": 0.11541806161403656, | |
| "learning_rate": 1.8841713565463548e-05, | |
| "loss": 0.5082, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 3.2388732394366198, | |
| "grad_norm": 0.11000224947929382, | |
| "learning_rate": 1.862907941238059e-05, | |
| "loss": 0.4974, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 3.2433802816901407, | |
| "grad_norm": 0.09478365629911423, | |
| "learning_rate": 1.8417528592840018e-05, | |
| "loss": 0.4858, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.247887323943662, | |
| "grad_norm": 0.11213672161102295, | |
| "learning_rate": 1.8207063923328237e-05, | |
| "loss": 0.5708, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 3.252394366197183, | |
| "grad_norm": 0.10433446615934372, | |
| "learning_rate": 1.799768820587132e-05, | |
| "loss": 0.507, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 3.2569014084507044, | |
| "grad_norm": 0.10733353346586227, | |
| "learning_rate": 1.77894042279975e-05, | |
| "loss": 0.5225, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 3.2614084507042254, | |
| "grad_norm": 0.10116215795278549, | |
| "learning_rate": 1.7582214762700054e-05, | |
| "loss": 0.5272, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 3.2659154929577463, | |
| "grad_norm": 0.1019587591290474, | |
| "learning_rate": 1.7376122568400532e-05, | |
| "loss": 0.5085, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 3.2704225352112677, | |
| "grad_norm": 0.0982939749956131, | |
| "learning_rate": 1.7171130388911848e-05, | |
| "loss": 0.5176, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 3.2749295774647886, | |
| "grad_norm": 0.10578010976314545, | |
| "learning_rate": 1.6967240953401954e-05, | |
| "loss": 0.4992, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 3.27943661971831, | |
| "grad_norm": 0.09891770035028458, | |
| "learning_rate": 1.676445697635728e-05, | |
| "loss": 0.483, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 3.283943661971831, | |
| "grad_norm": 0.10481581091880798, | |
| "learning_rate": 1.6562781157546835e-05, | |
| "loss": 0.518, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 3.288450704225352, | |
| "grad_norm": 0.09994784742593765, | |
| "learning_rate": 1.6362216181986002e-05, | |
| "loss": 0.4964, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 3.2929577464788733, | |
| "grad_norm": 0.10088899731636047, | |
| "learning_rate": 1.6162764719901046e-05, | |
| "loss": 0.5083, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 3.2974647887323942, | |
| "grad_norm": 0.103594109416008, | |
| "learning_rate": 1.596442942669335e-05, | |
| "loss": 0.5287, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 3.3019718309859156, | |
| "grad_norm": 0.1050785481929779, | |
| "learning_rate": 1.5767212942904276e-05, | |
| "loss": 0.5247, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 3.3064788732394366, | |
| "grad_norm": 0.10635862499475479, | |
| "learning_rate": 1.5571117894179754e-05, | |
| "loss": 0.5207, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 3.3109859154929575, | |
| "grad_norm": 0.10588835924863815, | |
| "learning_rate": 1.5376146891235598e-05, | |
| "loss": 0.501, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 3.315492957746479, | |
| "grad_norm": 0.11529035866260529, | |
| "learning_rate": 1.5182302529822479e-05, | |
| "loss": 0.5338, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "grad_norm": 0.11125069856643677, | |
| "learning_rate": 1.4989587390691628e-05, | |
| "loss": 0.5433, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 3.3245070422535212, | |
| "grad_norm": 0.10297177731990814, | |
| "learning_rate": 1.4798004039560242e-05, | |
| "loss": 0.5167, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 3.329014084507042, | |
| "grad_norm": 0.09564676135778427, | |
| "learning_rate": 1.4607555027077525e-05, | |
| "loss": 0.4976, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 3.3335211267605636, | |
| "grad_norm": 0.09943831712007523, | |
| "learning_rate": 1.4418242888790579e-05, | |
| "loss": 0.5223, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.3380281690140845, | |
| "grad_norm": 0.09775034338235855, | |
| "learning_rate": 1.4230070145110707e-05, | |
| "loss": 0.5125, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 3.3425352112676054, | |
| "grad_norm": 0.10720875859260559, | |
| "learning_rate": 1.4043039301279903e-05, | |
| "loss": 0.5541, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 3.347042253521127, | |
| "grad_norm": 0.10151630640029907, | |
| "learning_rate": 1.3857152847337395e-05, | |
| "loss": 0.516, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 3.3515492957746478, | |
| "grad_norm": 0.11832702904939651, | |
| "learning_rate": 1.3672413258086592e-05, | |
| "loss": 0.5162, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 3.356056338028169, | |
| "grad_norm": 0.09787547588348389, | |
| "learning_rate": 1.3488822993062089e-05, | |
| "loss": 0.4999, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 3.36056338028169, | |
| "grad_norm": 0.10296602547168732, | |
| "learning_rate": 1.3306384496496927e-05, | |
| "loss": 0.5479, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 3.3650704225352115, | |
| "grad_norm": 0.10161863267421722, | |
| "learning_rate": 1.3125100197290019e-05, | |
| "loss": 0.5444, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 3.3695774647887324, | |
| "grad_norm": 0.11383792757987976, | |
| "learning_rate": 1.2944972508973908e-05, | |
| "loss": 0.5736, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 3.3740845070422534, | |
| "grad_norm": 0.09610579162836075, | |
| "learning_rate": 1.2766003829682505e-05, | |
| "loss": 0.4991, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 3.3785915492957748, | |
| "grad_norm": 0.10732931643724442, | |
| "learning_rate": 1.258819654211929e-05, | |
| "loss": 0.5349, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.3830985915492957, | |
| "grad_norm": 0.10681644827127457, | |
| "learning_rate": 1.2411553013525457e-05, | |
| "loss": 0.5184, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 3.387605633802817, | |
| "grad_norm": 0.11193811148405075, | |
| "learning_rate": 1.2236075595648566e-05, | |
| "loss": 0.5576, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 3.392112676056338, | |
| "grad_norm": 0.11142749339342117, | |
| "learning_rate": 1.2061766624711035e-05, | |
| "loss": 0.5347, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 3.396619718309859, | |
| "grad_norm": 0.09409522265195847, | |
| "learning_rate": 1.1888628421379221e-05, | |
| "loss": 0.5002, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 3.4011267605633804, | |
| "grad_norm": 0.09690172225236893, | |
| "learning_rate": 1.1716663290732366e-05, | |
| "loss": 0.4881, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 3.4056338028169013, | |
| "grad_norm": 0.10559435188770294, | |
| "learning_rate": 1.1545873522232053e-05, | |
| "loss": 0.5071, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 3.4101408450704227, | |
| "grad_norm": 0.11353932321071625, | |
| "learning_rate": 1.1376261389691634e-05, | |
| "loss": 0.5303, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 3.4146478873239436, | |
| "grad_norm": 0.10134030133485794, | |
| "learning_rate": 1.1207829151245941e-05, | |
| "loss": 0.5171, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 3.4191549295774646, | |
| "grad_norm": 0.09742739796638489, | |
| "learning_rate": 1.1040579049321309e-05, | |
| "loss": 0.5122, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 3.423661971830986, | |
| "grad_norm": 0.09522052109241486, | |
| "learning_rate": 1.0874513310605628e-05, | |
| "loss": 0.5315, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 3.428169014084507, | |
| "grad_norm": 0.10180686414241791, | |
| "learning_rate": 1.0709634146018798e-05, | |
| "loss": 0.492, | |
| "step": 761 | |
| }, | |
| { | |
| "epoch": 3.4326760563380283, | |
| "grad_norm": 0.10120957344770432, | |
| "learning_rate": 1.0545943750683162e-05, | |
| "loss": 0.5219, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 3.4371830985915492, | |
| "grad_norm": 0.10289746522903442, | |
| "learning_rate": 1.0383444303894452e-05, | |
| "loss": 0.5022, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 3.44169014084507, | |
| "grad_norm": 0.10165810585021973, | |
| "learning_rate": 1.0222137969092581e-05, | |
| "loss": 0.5154, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 3.4461971830985916, | |
| "grad_norm": 0.10728448629379272, | |
| "learning_rate": 1.0062026893833033e-05, | |
| "loss": 0.5083, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 3.4507042253521125, | |
| "grad_norm": 0.11152730882167816, | |
| "learning_rate": 9.903113209758096e-06, | |
| "loss": 0.5656, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 3.455211267605634, | |
| "grad_norm": 0.11231085658073425, | |
| "learning_rate": 9.745399032568604e-06, | |
| "loss": 0.5132, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 3.459718309859155, | |
| "grad_norm": 0.09897750616073608, | |
| "learning_rate": 9.588886461995772e-06, | |
| "loss": 0.5097, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 3.4642253521126762, | |
| "grad_norm": 0.10121899843215942, | |
| "learning_rate": 9.43357758177309e-06, | |
| "loss": 0.4748, | |
| "step": 769 | |
| }, | |
| { | |
| "epoch": 3.468732394366197, | |
| "grad_norm": 0.11369026452302933, | |
| "learning_rate": 9.279474459608805e-06, | |
| "loss": 0.5531, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 3.473239436619718, | |
| "grad_norm": 0.09937481582164764, | |
| "learning_rate": 9.126579147158187e-06, | |
| "loss": 0.5213, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 3.4777464788732395, | |
| "grad_norm": 0.09812068939208984, | |
| "learning_rate": 8.974893679996388e-06, | |
| "loss": 0.5024, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 3.4822535211267605, | |
| "grad_norm": 0.11508133262395859, | |
| "learning_rate": 8.824420077591155e-06, | |
| "loss": 0.5378, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 3.486760563380282, | |
| "grad_norm": 0.11102595925331116, | |
| "learning_rate": 8.675160343276167e-06, | |
| "loss": 0.5344, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 3.491267605633803, | |
| "grad_norm": 0.09482184052467346, | |
| "learning_rate": 8.527116464224127e-06, | |
| "loss": 0.5032, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 3.495774647887324, | |
| "grad_norm": 0.09604179859161377, | |
| "learning_rate": 8.380290411420522e-06, | |
| "loss": 0.5006, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 3.500281690140845, | |
| "grad_norm": 0.10570445656776428, | |
| "learning_rate": 8.234684139637205e-06, | |
| "loss": 0.5378, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 3.504788732394366, | |
| "grad_norm": 0.09560370445251465, | |
| "learning_rate": 8.090299587406514e-06, | |
| "loss": 0.508, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 3.5092957746478874, | |
| "grad_norm": 0.09780082106590271, | |
| "learning_rate": 7.947138676995302e-06, | |
| "loss": 0.4905, | |
| "step": 779 | |
| }, | |
| { | |
| "epoch": 3.5138028169014084, | |
| "grad_norm": 0.10680654644966125, | |
| "learning_rate": 7.805203314379583e-06, | |
| "loss": 0.4999, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.5183098591549298, | |
| "grad_norm": 0.10805977880954742, | |
| "learning_rate": 7.664495389218884e-06, | |
| "loss": 0.5246, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 3.5228169014084507, | |
| "grad_norm": 0.1088169664144516, | |
| "learning_rate": 7.525016774831273e-06, | |
| "loss": 0.4862, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 3.5273239436619717, | |
| "grad_norm": 0.09178736060857773, | |
| "learning_rate": 7.386769328168353e-06, | |
| "loss": 0.5066, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 3.531830985915493, | |
| "grad_norm": 0.1102149561047554, | |
| "learning_rate": 7.249754889790539e-06, | |
| "loss": 0.5054, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 3.536338028169014, | |
| "grad_norm": 0.11161289364099503, | |
| "learning_rate": 7.113975283842589e-06, | |
| "loss": 0.534, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 3.5408450704225354, | |
| "grad_norm": 0.100556880235672, | |
| "learning_rate": 6.979432318029244e-06, | |
| "loss": 0.5078, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 3.5453521126760563, | |
| "grad_norm": 0.10358420014381409, | |
| "learning_rate": 6.846127783591294e-06, | |
| "loss": 0.5192, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 3.5498591549295773, | |
| "grad_norm": 0.10767854750156403, | |
| "learning_rate": 6.714063455281538e-06, | |
| "loss": 0.5081, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 3.5543661971830987, | |
| "grad_norm": 0.09717968106269836, | |
| "learning_rate": 6.583241091341353e-06, | |
| "loss": 0.4981, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 3.5588732394366196, | |
| "grad_norm": 0.0952880010008812, | |
| "learning_rate": 6.453662433477136e-06, | |
| "loss": 0.512, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 3.563380281690141, | |
| "grad_norm": 0.10167808830738068, | |
| "learning_rate": 6.325329206837216e-06, | |
| "loss": 0.5, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 3.567887323943662, | |
| "grad_norm": 0.09986628592014313, | |
| "learning_rate": 6.1982431199888225e-06, | |
| "loss": 0.5119, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 3.572394366197183, | |
| "grad_norm": 0.09896910190582275, | |
| "learning_rate": 6.072405864895403e-06, | |
| "loss": 0.4996, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 3.5769014084507043, | |
| "grad_norm": 0.0993683710694313, | |
| "learning_rate": 5.947819116893971e-06, | |
| "loss": 0.4988, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 3.581408450704225, | |
| "grad_norm": 0.10620611906051636, | |
| "learning_rate": 5.82448453467298e-06, | |
| "loss": 0.5162, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 3.5859154929577466, | |
| "grad_norm": 0.09343092143535614, | |
| "learning_rate": 5.7024037602500855e-06, | |
| "loss": 0.5073, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 3.5904225352112675, | |
| "grad_norm": 0.09894745796918869, | |
| "learning_rate": 5.581578418950373e-06, | |
| "loss": 0.5001, | |
| "step": 797 | |
| }, | |
| { | |
| "epoch": 3.5949295774647885, | |
| "grad_norm": 0.1150493249297142, | |
| "learning_rate": 5.462010119384664e-06, | |
| "loss": 0.5332, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 3.59943661971831, | |
| "grad_norm": 0.09008999168872833, | |
| "learning_rate": 5.343700453428168e-06, | |
| "loss": 0.5021, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 3.6039436619718312, | |
| "grad_norm": 0.09946510940790176, | |
| "learning_rate": 5.226650996199223e-06, | |
| "loss": 0.5182, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.608450704225352, | |
| "grad_norm": 0.09479941427707672, | |
| "learning_rate": 5.1108633060383606e-06, | |
| "loss": 0.5194, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 3.612957746478873, | |
| "grad_norm": 0.10796267539262772, | |
| "learning_rate": 4.996338924487509e-06, | |
| "loss": 0.5223, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 3.6174647887323945, | |
| "grad_norm": 0.09543827176094055, | |
| "learning_rate": 4.883079376269573e-06, | |
| "loss": 0.4974, | |
| "step": 803 | |
| }, | |
| { | |
| "epoch": 3.6219718309859155, | |
| "grad_norm": 0.09834381937980652, | |
| "learning_rate": 4.771086169268057e-06, | |
| "loss": 0.502, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 3.626478873239437, | |
| "grad_norm": 0.0954863652586937, | |
| "learning_rate": 4.660360794506946e-06, | |
| "loss": 0.5052, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 3.630985915492958, | |
| "grad_norm": 0.10441611707210541, | |
| "learning_rate": 4.550904726130989e-06, | |
| "loss": 0.5249, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 3.6354929577464787, | |
| "grad_norm": 0.1028057262301445, | |
| "learning_rate": 4.442719421385922e-06, | |
| "loss": 0.5309, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "grad_norm": 0.10420232266187668, | |
| "learning_rate": 4.3358063205992336e-06, | |
| "loss": 0.5092, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 3.644507042253521, | |
| "grad_norm": 0.09221101552248001, | |
| "learning_rate": 4.230166847160799e-06, | |
| "loss": 0.5059, | |
| "step": 809 | |
| }, | |
| { | |
| "epoch": 3.6490140845070425, | |
| "grad_norm": 0.10424289852380753, | |
| "learning_rate": 4.125802407504098e-06, | |
| "loss": 0.5007, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 3.6535211267605634, | |
| "grad_norm": 0.10054883360862732, | |
| "learning_rate": 4.022714391087379e-06, | |
| "loss": 0.5172, | |
| "step": 811 | |
| }, | |
| { | |
| "epoch": 3.6580281690140843, | |
| "grad_norm": 0.11087238043546677, | |
| "learning_rate": 3.9209041703752395e-06, | |
| "loss": 0.5811, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 3.6625352112676057, | |
| "grad_norm": 0.10872288048267365, | |
| "learning_rate": 3.820373100820263e-06, | |
| "loss": 0.5131, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 3.6670422535211267, | |
| "grad_norm": 0.1310155689716339, | |
| "learning_rate": 3.7211225208450774e-06, | |
| "loss": 0.4928, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 3.671549295774648, | |
| "grad_norm": 0.10429683327674866, | |
| "learning_rate": 3.623153751824482e-06, | |
| "loss": 0.5158, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 3.676056338028169, | |
| "grad_norm": 0.09816399961709976, | |
| "learning_rate": 3.5264680980677924e-06, | |
| "loss": 0.511, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 3.68056338028169, | |
| "grad_norm": 0.09635947644710541, | |
| "learning_rate": 3.431066846801634e-06, | |
| "loss": 0.5009, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 3.6850704225352113, | |
| "grad_norm": 0.1052606850862503, | |
| "learning_rate": 3.3369512681526326e-06, | |
| "loss": 0.5164, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 3.6895774647887323, | |
| "grad_norm": 0.09707427024841309, | |
| "learning_rate": 3.2441226151306404e-06, | |
| "loss": 0.5412, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 3.6940845070422537, | |
| "grad_norm": 0.09661922603845596, | |
| "learning_rate": 3.1525821236119577e-06, | |
| "loss": 0.4996, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 3.6985915492957746, | |
| "grad_norm": 0.1082405224442482, | |
| "learning_rate": 3.0623310123229387e-06, | |
| "loss": 0.5218, | |
| "step": 821 | |
| }, | |
| { | |
| "epoch": 3.7030985915492955, | |
| "grad_norm": 0.08868458867073059, | |
| "learning_rate": 2.973370482823734e-06, | |
| "loss": 0.4729, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 3.707605633802817, | |
| "grad_norm": 0.1018679216504097, | |
| "learning_rate": 2.8857017194923173e-06, | |
| "loss": 0.5318, | |
| "step": 823 | |
| }, | |
| { | |
| "epoch": 3.712112676056338, | |
| "grad_norm": 0.10018418729305267, | |
| "learning_rate": 2.7993258895086973e-06, | |
| "loss": 0.5007, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 3.7166197183098593, | |
| "grad_norm": 0.08692584931850433, | |
| "learning_rate": 2.714244142839395e-06, | |
| "loss": 0.5122, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 3.72112676056338, | |
| "grad_norm": 0.09924297034740448, | |
| "learning_rate": 2.6304576122221035e-06, | |
| "loss": 0.5165, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 3.725633802816901, | |
| "grad_norm": 0.09864252805709839, | |
| "learning_rate": 2.5479674131506425e-06, | |
| "loss": 0.5397, | |
| "step": 827 | |
| }, | |
| { | |
| "epoch": 3.7301408450704225, | |
| "grad_norm": 0.09954255074262619, | |
| "learning_rate": 2.466774643860115e-06, | |
| "loss": 0.5043, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 3.734647887323944, | |
| "grad_norm": 0.11289742588996887, | |
| "learning_rate": 2.386880385312218e-06, | |
| "loss": 0.528, | |
| "step": 829 | |
| }, | |
| { | |
| "epoch": 3.739154929577465, | |
| "grad_norm": 0.09993050992488861, | |
| "learning_rate": 2.3082857011809344e-06, | |
| "loss": 0.4994, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 3.743661971830986, | |
| "grad_norm": 0.09765881299972534, | |
| "learning_rate": 2.230991637838309e-06, | |
| "loss": 0.4916, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 3.748169014084507, | |
| "grad_norm": 0.10377711802721024, | |
| "learning_rate": 2.1549992243405816e-06, | |
| "loss": 0.5386, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 3.752676056338028, | |
| "grad_norm": 0.09763538837432861, | |
| "learning_rate": 2.080309472414388e-06, | |
| "loss": 0.5002, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 3.7571830985915495, | |
| "grad_norm": 0.09959236532449722, | |
| "learning_rate": 2.006923376443415e-06, | |
| "loss": 0.4978, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 3.7616901408450705, | |
| "grad_norm": 0.09664242714643478, | |
| "learning_rate": 1.934841913455032e-06, | |
| "loss": 0.5301, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 3.7661971830985914, | |
| "grad_norm": 0.10548033565282822, | |
| "learning_rate": 1.8640660431074265e-06, | |
| "loss": 0.5179, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 3.770704225352113, | |
| "grad_norm": 0.10041049867868423, | |
| "learning_rate": 1.7945967076766546e-06, | |
| "loss": 0.5119, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 3.7752112676056337, | |
| "grad_norm": 0.09538040310144424, | |
| "learning_rate": 1.7264348320442992e-06, | |
| "loss": 0.5145, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 3.779718309859155, | |
| "grad_norm": 0.1140114888548851, | |
| "learning_rate": 1.6595813236849556e-06, | |
| "loss": 0.5112, | |
| "step": 839 | |
| }, | |
| { | |
| "epoch": 3.784225352112676, | |
| "grad_norm": 0.09238018095493317, | |
| "learning_rate": 1.5940370726542863e-06, | |
| "loss": 0.496, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 3.788732394366197, | |
| "grad_norm": 0.10022945702075958, | |
| "learning_rate": 1.5298029515771195e-06, | |
| "loss": 0.5104, | |
| "step": 841 | |
| }, | |
| { | |
| "epoch": 3.7932394366197184, | |
| "grad_norm": 0.1022907942533493, | |
| "learning_rate": 1.4668798156358465e-06, | |
| "loss": 0.515, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 3.7977464788732394, | |
| "grad_norm": 0.09121408313512802, | |
| "learning_rate": 1.4052685025590096e-06, | |
| "loss": 0.4859, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 3.8022535211267607, | |
| "grad_norm": 0.09021437168121338, | |
| "learning_rate": 1.344969832610199e-06, | |
| "loss": 0.493, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 3.8067605633802817, | |
| "grad_norm": 0.09189501404762268, | |
| "learning_rate": 1.2859846085770733e-06, | |
| "loss": 0.4916, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 3.8112676056338026, | |
| "grad_norm": 0.09620609134435654, | |
| "learning_rate": 1.2283136157607121e-06, | |
| "loss": 0.5147, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 3.815774647887324, | |
| "grad_norm": 0.09854090213775635, | |
| "learning_rate": 1.1719576219651585e-06, | |
| "loss": 0.4978, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 3.820281690140845, | |
| "grad_norm": 0.0998944416642189, | |
| "learning_rate": 1.1169173774871478e-06, | |
| "loss": 0.5132, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 3.8247887323943663, | |
| "grad_norm": 0.09280737489461899, | |
| "learning_rate": 1.0631936151062172e-06, | |
| "loss": 0.5251, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 3.8292957746478873, | |
| "grad_norm": 0.10368622094392776, | |
| "learning_rate": 1.010787050074835e-06, | |
| "loss": 0.511, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.8338028169014082, | |
| "grad_norm": 0.09526852518320084, | |
| "learning_rate": 9.596983801089864e-07, | |
| "loss": 0.562, | |
| "step": 851 | |
| }, | |
| { | |
| "epoch": 3.8383098591549296, | |
| "grad_norm": 0.10724498331546783, | |
| "learning_rate": 9.099282853787805e-07, | |
| "loss": 0.5394, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 3.8428169014084506, | |
| "grad_norm": 0.08827169984579086, | |
| "learning_rate": 8.614774284994798e-07, | |
| "loss": 0.4826, | |
| "step": 853 | |
| }, | |
| { | |
| "epoch": 3.847323943661972, | |
| "grad_norm": 0.0911865234375, | |
| "learning_rate": 8.143464545226298e-07, | |
| "loss": 0.5189, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 3.851830985915493, | |
| "grad_norm": 0.08919581770896912, | |
| "learning_rate": 7.685359909274881e-07, | |
| "loss": 0.51, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 3.856338028169014, | |
| "grad_norm": 0.1076306402683258, | |
| "learning_rate": 7.24046647612675e-07, | |
| "loss": 0.5176, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 3.860845070422535, | |
| "grad_norm": 0.10025174915790558, | |
| "learning_rate": 6.808790168880364e-07, | |
| "loss": 0.5135, | |
| "step": 857 | |
| }, | |
| { | |
| "epoch": 3.8653521126760566, | |
| "grad_norm": 0.09523887187242508, | |
| "learning_rate": 6.390336734667823e-07, | |
| "loss": 0.4964, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 3.8698591549295775, | |
| "grad_norm": 0.09640923887491226, | |
| "learning_rate": 5.985111744578165e-07, | |
| "loss": 0.4899, | |
| "step": 859 | |
| }, | |
| { | |
| "epoch": 3.8743661971830985, | |
| "grad_norm": 0.0929466262459755, | |
| "learning_rate": 5.593120593582967e-07, | |
| "loss": 0.5196, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 3.87887323943662, | |
| "grad_norm": 0.10044664144515991, | |
| "learning_rate": 5.214368500465305e-07, | |
| "loss": 0.5162, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 3.883380281690141, | |
| "grad_norm": 0.1058187335729599, | |
| "learning_rate": 4.848860507749353e-07, | |
| "loss": 0.5232, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 3.887887323943662, | |
| "grad_norm": 0.10016901046037674, | |
| "learning_rate": 4.496601481634e-07, | |
| "loss": 0.5218, | |
| "step": 863 | |
| }, | |
| { | |
| "epoch": 3.892394366197183, | |
| "grad_norm": 0.10483549535274506, | |
| "learning_rate": 4.157596111927342e-07, | |
| "loss": 0.5097, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 3.896901408450704, | |
| "grad_norm": 0.10363733023405075, | |
| "learning_rate": 3.831848911984959e-07, | |
| "loss": 0.5297, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 3.9014084507042255, | |
| "grad_norm": 0.08613172918558121, | |
| "learning_rate": 3.51936421864929e-07, | |
| "loss": 0.4929, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 3.9059154929577464, | |
| "grad_norm": 0.09748660773038864, | |
| "learning_rate": 3.220146192192242e-07, | |
| "loss": 0.5301, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 3.910422535211268, | |
| "grad_norm": 0.09546560794115067, | |
| "learning_rate": 2.934198816259559e-07, | |
| "loss": 0.517, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 3.9149295774647888, | |
| "grad_norm": 0.10289441049098969, | |
| "learning_rate": 2.661525897817874e-07, | |
| "loss": 0.5074, | |
| "step": 869 | |
| }, | |
| { | |
| "epoch": 3.9194366197183097, | |
| "grad_norm": 0.0952000617980957, | |
| "learning_rate": 2.402131067104296e-07, | |
| "loss": 0.4901, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 3.923943661971831, | |
| "grad_norm": 0.10645543783903122, | |
| "learning_rate": 2.156017777577346e-07, | |
| "loss": 0.5192, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 3.928450704225352, | |
| "grad_norm": 0.10012649744749069, | |
| "learning_rate": 1.9231893058718754e-07, | |
| "loss": 0.512, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 3.9329577464788734, | |
| "grad_norm": 0.11233918368816376, | |
| "learning_rate": 1.7036487517547717e-07, | |
| "loss": 0.5288, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 3.9374647887323944, | |
| "grad_norm": 0.0949663370847702, | |
| "learning_rate": 1.4973990380841019e-07, | |
| "loss": 0.5148, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 3.9419718309859153, | |
| "grad_norm": 0.08848931640386581, | |
| "learning_rate": 1.3044429107700318e-07, | |
| "loss": 0.5156, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 3.9464788732394367, | |
| "grad_norm": 0.11036274582147598, | |
| "learning_rate": 1.1247829387381892e-07, | |
| "loss": 0.5136, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 3.9509859154929576, | |
| "grad_norm": 0.09624003618955612, | |
| "learning_rate": 9.584215138953579e-08, | |
| "loss": 0.5001, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 3.955492957746479, | |
| "grad_norm": 0.10382691025733948, | |
| "learning_rate": 8.053608510982802e-08, | |
| "loss": 0.5184, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "grad_norm": 0.18590374290943146, | |
| "learning_rate": 6.656029881233483e-08, | |
| "loss": 0.5439, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 3.964507042253521, | |
| "grad_norm": 0.09918248653411865, | |
| "learning_rate": 5.391497856399585e-08, | |
| "loss": 0.5139, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 3.9690140845070423, | |
| "grad_norm": 0.0977630540728569, | |
| "learning_rate": 4.260029271856425e-08, | |
| "loss": 0.5031, | |
| "step": 881 | |
| }, | |
| { | |
| "epoch": 3.9735211267605632, | |
| "grad_norm": 0.10441361367702484, | |
| "learning_rate": 3.2616391914364054e-08, | |
| "loss": 0.5304, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 3.9780281690140846, | |
| "grad_norm": 0.09436926990747452, | |
| "learning_rate": 2.396340907225847e-08, | |
| "loss": 0.4986, | |
| "step": 883 | |
| }, | |
| { | |
| "epoch": 3.9825352112676056, | |
| "grad_norm": 0.09458206593990326, | |
| "learning_rate": 1.664145939394013e-08, | |
| "loss": 0.5522, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 3.9870422535211265, | |
| "grad_norm": 0.10429766774177551, | |
| "learning_rate": 1.0650640360343468e-08, | |
| "loss": 0.5175, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 3.991549295774648, | |
| "grad_norm": 0.09607253223657608, | |
| "learning_rate": 5.991031730367969e-09, | |
| "loss": 0.5038, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 3.9960563380281693, | |
| "grad_norm": 0.13139435648918152, | |
| "learning_rate": 2.6626955398234564e-09, | |
| "loss": 0.5277, | |
| "step": 887 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.1130460873246193, | |
| "learning_rate": 6.656761005752188e-10, | |
| "loss": 0.51, | |
| "step": 888 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 888, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |