Text Generation
Transformers
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use laion/coderforge-31600-opt100k__Qwen3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use laion/coderforge-31600-opt100k__Qwen3-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="laion/coderforge-31600-opt100k__Qwen3-8B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("laion/coderforge-31600-opt100k__Qwen3-8B") model = AutoModelForCausalLM.from_pretrained("laion/coderforge-31600-opt100k__Qwen3-8B") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use laion/coderforge-31600-opt100k__Qwen3-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "laion/coderforge-31600-opt100k__Qwen3-8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "laion/coderforge-31600-opt100k__Qwen3-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/laion/coderforge-31600-opt100k__Qwen3-8B
- SGLang
How to use laion/coderforge-31600-opt100k__Qwen3-8B 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 "laion/coderforge-31600-opt100k__Qwen3-8B" \ --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": "laion/coderforge-31600-opt100k__Qwen3-8B", "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 "laion/coderforge-31600-opt100k__Qwen3-8B" \ --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": "laion/coderforge-31600-opt100k__Qwen3-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use laion/coderforge-31600-opt100k__Qwen3-8B with Docker Model Runner:
docker model run hf.co/laion/coderforge-31600-opt100k__Qwen3-8B
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 1650, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015182186234817813, | |
| "grad_norm": 9.680750416793106, | |
| "learning_rate": 9.696969696969698e-07, | |
| "loss": 0.4981, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.16301292181015015, | |
| "step": 5, | |
| "valid_targets_mean": 8828.2, | |
| "valid_targets_min": 1325 | |
| }, | |
| { | |
| "epoch": 0.030364372469635626, | |
| "grad_norm": 5.384175841106515, | |
| "learning_rate": 2.181818181818182e-06, | |
| "loss": 0.4664, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.14661766588687897, | |
| "step": 10, | |
| "valid_targets_mean": 8116.5, | |
| "valid_targets_min": 1739 | |
| }, | |
| { | |
| "epoch": 0.04554655870445344, | |
| "grad_norm": 1.795228304663614, | |
| "learning_rate": 3.3939393939393946e-06, | |
| "loss": 0.411, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.1312033087015152, | |
| "step": 15, | |
| "valid_targets_mean": 8655.5, | |
| "valid_targets_min": 2121 | |
| }, | |
| { | |
| "epoch": 0.06072874493927125, | |
| "grad_norm": 0.8797536152238489, | |
| "learning_rate": 4.606060606060606e-06, | |
| "loss": 0.3689, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11456456035375595, | |
| "step": 20, | |
| "valid_targets_mean": 8205.9, | |
| "valid_targets_min": 1946 | |
| }, | |
| { | |
| "epoch": 0.07591093117408906, | |
| "grad_norm": 0.5376812432690758, | |
| "learning_rate": 5.8181818181818185e-06, | |
| "loss": 0.329, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11359838396310806, | |
| "step": 25, | |
| "valid_targets_mean": 9102.8, | |
| "valid_targets_min": 2247 | |
| }, | |
| { | |
| "epoch": 0.09109311740890688, | |
| "grad_norm": 0.4616655086429676, | |
| "learning_rate": 7.030303030303031e-06, | |
| "loss": 0.3004, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09466002881526947, | |
| "step": 30, | |
| "valid_targets_mean": 8613.6, | |
| "valid_targets_min": 2329 | |
| }, | |
| { | |
| "epoch": 0.1062753036437247, | |
| "grad_norm": 0.3132464945496789, | |
| "learning_rate": 8.242424242424243e-06, | |
| "loss": 0.2652, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.07809363305568695, | |
| "step": 35, | |
| "valid_targets_mean": 8026.8, | |
| "valid_targets_min": 3644 | |
| }, | |
| { | |
| "epoch": 0.1214574898785425, | |
| "grad_norm": 0.2346336524366432, | |
| "learning_rate": 9.454545454545456e-06, | |
| "loss": 0.2338, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.07364151626825333, | |
| "step": 40, | |
| "valid_targets_mean": 8478.8, | |
| "valid_targets_min": 2543 | |
| }, | |
| { | |
| "epoch": 0.13663967611336034, | |
| "grad_norm": 0.20366673828792597, | |
| "learning_rate": 1.0666666666666667e-05, | |
| "loss": 0.2244, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.07662152498960495, | |
| "step": 45, | |
| "valid_targets_mean": 8863.4, | |
| "valid_targets_min": 3657 | |
| }, | |
| { | |
| "epoch": 0.15182186234817813, | |
| "grad_norm": 0.18614199019486613, | |
| "learning_rate": 1.187878787878788e-05, | |
| "loss": 0.2095, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.06064519286155701, | |
| "step": 50, | |
| "valid_targets_mean": 8296.4, | |
| "valid_targets_min": 3093 | |
| }, | |
| { | |
| "epoch": 0.16700404858299595, | |
| "grad_norm": 0.17240009626311575, | |
| "learning_rate": 1.3090909090909092e-05, | |
| "loss": 0.1997, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.06190265715122223, | |
| "step": 55, | |
| "valid_targets_mean": 9049.6, | |
| "valid_targets_min": 2847 | |
| }, | |
| { | |
| "epoch": 0.18218623481781376, | |
| "grad_norm": 0.1702479807181084, | |
| "learning_rate": 1.4303030303030305e-05, | |
| "loss": 0.1892, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.058364734053611755, | |
| "step": 60, | |
| "valid_targets_mean": 7953.8, | |
| "valid_targets_min": 1555 | |
| }, | |
| { | |
| "epoch": 0.19736842105263158, | |
| "grad_norm": 0.15654488086952745, | |
| "learning_rate": 1.5515151515151516e-05, | |
| "loss": 0.1831, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.056126583367586136, | |
| "step": 65, | |
| "valid_targets_mean": 8447.6, | |
| "valid_targets_min": 2404 | |
| }, | |
| { | |
| "epoch": 0.2125506072874494, | |
| "grad_norm": 0.15451761067766834, | |
| "learning_rate": 1.672727272727273e-05, | |
| "loss": 0.177, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.055357493460178375, | |
| "step": 70, | |
| "valid_targets_mean": 7695.7, | |
| "valid_targets_min": 2372 | |
| }, | |
| { | |
| "epoch": 0.22773279352226722, | |
| "grad_norm": 0.1619018754546456, | |
| "learning_rate": 1.7939393939393942e-05, | |
| "loss": 0.1741, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.057761505246162415, | |
| "step": 75, | |
| "valid_targets_mean": 8764.5, | |
| "valid_targets_min": 3045 | |
| }, | |
| { | |
| "epoch": 0.242914979757085, | |
| "grad_norm": 0.1766027380968946, | |
| "learning_rate": 1.9151515151515152e-05, | |
| "loss": 0.1703, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.05490858107805252, | |
| "step": 80, | |
| "valid_targets_mean": 8550.6, | |
| "valid_targets_min": 3183 | |
| }, | |
| { | |
| "epoch": 0.25809716599190285, | |
| "grad_norm": 0.15651695646208139, | |
| "learning_rate": 2.0363636363636365e-05, | |
| "loss": 0.1673, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.05388278886675835, | |
| "step": 85, | |
| "valid_targets_mean": 9359.7, | |
| "valid_targets_min": 2372 | |
| }, | |
| { | |
| "epoch": 0.2732793522267207, | |
| "grad_norm": 0.15769538505076752, | |
| "learning_rate": 2.1575757575757578e-05, | |
| "loss": 0.1679, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.056751832365989685, | |
| "step": 90, | |
| "valid_targets_mean": 9334.6, | |
| "valid_targets_min": 4322 | |
| }, | |
| { | |
| "epoch": 0.28846153846153844, | |
| "grad_norm": 0.148149301248057, | |
| "learning_rate": 2.278787878787879e-05, | |
| "loss": 0.1642, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.054115891456604004, | |
| "step": 95, | |
| "valid_targets_mean": 8474.4, | |
| "valid_targets_min": 2161 | |
| }, | |
| { | |
| "epoch": 0.30364372469635625, | |
| "grad_norm": 0.1692378731737842, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.1584, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.057165682315826416, | |
| "step": 100, | |
| "valid_targets_mean": 8987.0, | |
| "valid_targets_min": 3077 | |
| }, | |
| { | |
| "epoch": 0.3188259109311741, | |
| "grad_norm": 0.17810214096516594, | |
| "learning_rate": 2.5212121212121214e-05, | |
| "loss": 0.1627, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04772390425205231, | |
| "step": 105, | |
| "valid_targets_mean": 8825.8, | |
| "valid_targets_min": 2628 | |
| }, | |
| { | |
| "epoch": 0.3340080971659919, | |
| "grad_norm": 0.16153957596328428, | |
| "learning_rate": 2.6424242424242427e-05, | |
| "loss": 0.1589, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.056263308972120285, | |
| "step": 110, | |
| "valid_targets_mean": 9457.8, | |
| "valid_targets_min": 2369 | |
| }, | |
| { | |
| "epoch": 0.3491902834008097, | |
| "grad_norm": 0.18858682797573695, | |
| "learning_rate": 2.763636363636364e-05, | |
| "loss": 0.1562, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.05262404680252075, | |
| "step": 115, | |
| "valid_targets_mean": 8780.1, | |
| "valid_targets_min": 1732 | |
| }, | |
| { | |
| "epoch": 0.3643724696356275, | |
| "grad_norm": 0.18730347764861258, | |
| "learning_rate": 2.884848484848485e-05, | |
| "loss": 0.1549, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.052941761910915375, | |
| "step": 120, | |
| "valid_targets_mean": 8754.1, | |
| "valid_targets_min": 2052 | |
| }, | |
| { | |
| "epoch": 0.37955465587044535, | |
| "grad_norm": 0.1680433739318899, | |
| "learning_rate": 3.0060606060606062e-05, | |
| "loss": 0.1544, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0610114187002182, | |
| "step": 125, | |
| "valid_targets_mean": 9624.0, | |
| "valid_targets_min": 5281 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "grad_norm": 0.16016568684388943, | |
| "learning_rate": 3.127272727272728e-05, | |
| "loss": 0.1531, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04802710935473442, | |
| "step": 130, | |
| "valid_targets_mean": 8650.3, | |
| "valid_targets_min": 2707 | |
| }, | |
| { | |
| "epoch": 0.409919028340081, | |
| "grad_norm": 0.15365407866487032, | |
| "learning_rate": 3.2484848484848485e-05, | |
| "loss": 0.151, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.048533085733652115, | |
| "step": 135, | |
| "valid_targets_mean": 8942.3, | |
| "valid_targets_min": 4505 | |
| }, | |
| { | |
| "epoch": 0.4251012145748988, | |
| "grad_norm": 0.15868357285929927, | |
| "learning_rate": 3.36969696969697e-05, | |
| "loss": 0.1488, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04487761855125427, | |
| "step": 140, | |
| "valid_targets_mean": 8703.2, | |
| "valid_targets_min": 2783 | |
| }, | |
| { | |
| "epoch": 0.4402834008097166, | |
| "grad_norm": 0.1702194685895695, | |
| "learning_rate": 3.490909090909091e-05, | |
| "loss": 0.1517, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0522955060005188, | |
| "step": 145, | |
| "valid_targets_mean": 8819.5, | |
| "valid_targets_min": 3279 | |
| }, | |
| { | |
| "epoch": 0.45546558704453444, | |
| "grad_norm": 0.16507412340776675, | |
| "learning_rate": 3.6121212121212124e-05, | |
| "loss": 0.1493, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0495118647813797, | |
| "step": 150, | |
| "valid_targets_mean": 8359.1, | |
| "valid_targets_min": 2624 | |
| }, | |
| { | |
| "epoch": 0.4706477732793522, | |
| "grad_norm": 0.18186699402097176, | |
| "learning_rate": 3.733333333333334e-05, | |
| "loss": 0.1489, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04887845367193222, | |
| "step": 155, | |
| "valid_targets_mean": 8089.2, | |
| "valid_targets_min": 2462 | |
| }, | |
| { | |
| "epoch": 0.48582995951417, | |
| "grad_norm": 0.1706066739805533, | |
| "learning_rate": 3.854545454545455e-05, | |
| "loss": 0.1476, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04758952558040619, | |
| "step": 160, | |
| "valid_targets_mean": 8475.0, | |
| "valid_targets_min": 2841 | |
| }, | |
| { | |
| "epoch": 0.5010121457489879, | |
| "grad_norm": 0.184567878659678, | |
| "learning_rate": 3.9757575757575757e-05, | |
| "loss": 0.1458, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04584205150604248, | |
| "step": 165, | |
| "valid_targets_mean": 8380.9, | |
| "valid_targets_min": 3546 | |
| }, | |
| { | |
| "epoch": 0.5161943319838057, | |
| "grad_norm": 0.17606415371690057, | |
| "learning_rate": 3.999928391557286e-05, | |
| "loss": 0.1448, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04435788840055466, | |
| "step": 170, | |
| "valid_targets_mean": 8671.6, | |
| "valid_targets_min": 2770 | |
| }, | |
| { | |
| "epoch": 0.5313765182186235, | |
| "grad_norm": 0.19023662888867493, | |
| "learning_rate": 3.999637491047052e-05, | |
| "loss": 0.1417, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.047455839812755585, | |
| "step": 175, | |
| "valid_targets_mean": 8028.8, | |
| "valid_targets_min": 3903 | |
| }, | |
| { | |
| "epoch": 0.5465587044534413, | |
| "grad_norm": 0.16854697838570404, | |
| "learning_rate": 3.999122855464813e-05, | |
| "loss": 0.1451, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.05596259981393814, | |
| "step": 180, | |
| "valid_targets_mean": 8567.8, | |
| "valid_targets_min": 3896 | |
| }, | |
| { | |
| "epoch": 0.5617408906882592, | |
| "grad_norm": 0.17265862396124912, | |
| "learning_rate": 3.998384542392021e-05, | |
| "loss": 0.1443, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.048528943210840225, | |
| "step": 185, | |
| "valid_targets_mean": 8706.2, | |
| "valid_targets_min": 4483 | |
| }, | |
| { | |
| "epoch": 0.5769230769230769, | |
| "grad_norm": 0.1762979298095639, | |
| "learning_rate": 3.9974226344369124e-05, | |
| "loss": 0.1443, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04988047853112221, | |
| "step": 190, | |
| "valid_targets_mean": 9589.9, | |
| "valid_targets_min": 3039 | |
| }, | |
| { | |
| "epoch": 0.5921052631578947, | |
| "grad_norm": 0.14429322749019874, | |
| "learning_rate": 3.996237239225268e-05, | |
| "loss": 0.1429, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.044703707098960876, | |
| "step": 195, | |
| "valid_targets_mean": 8595.4, | |
| "valid_targets_min": 3420 | |
| }, | |
| { | |
| "epoch": 0.6072874493927125, | |
| "grad_norm": 0.17087895601654476, | |
| "learning_rate": 3.994828489388371e-05, | |
| "loss": 0.1447, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04976490139961243, | |
| "step": 200, | |
| "valid_targets_mean": 8717.7, | |
| "valid_targets_min": 2668 | |
| }, | |
| { | |
| "epoch": 0.6224696356275303, | |
| "grad_norm": 0.1706839519419773, | |
| "learning_rate": 3.993196542548162e-05, | |
| "loss": 0.1433, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04873702675104141, | |
| "step": 205, | |
| "valid_targets_mean": 8518.2, | |
| "valid_targets_min": 2136 | |
| }, | |
| { | |
| "epoch": 0.6376518218623481, | |
| "grad_norm": 0.1587393394181682, | |
| "learning_rate": 3.991341581299609e-05, | |
| "loss": 0.1391, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.043740272521972656, | |
| "step": 210, | |
| "valid_targets_mean": 8564.2, | |
| "valid_targets_min": 4150 | |
| }, | |
| { | |
| "epoch": 0.652834008097166, | |
| "grad_norm": 0.15303173273201542, | |
| "learning_rate": 3.9892638131902765e-05, | |
| "loss": 0.1383, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.051525503396987915, | |
| "step": 215, | |
| "valid_targets_mean": 9460.3, | |
| "valid_targets_min": 3977 | |
| }, | |
| { | |
| "epoch": 0.6680161943319838, | |
| "grad_norm": 0.16653745659079902, | |
| "learning_rate": 3.9869634706971e-05, | |
| "loss": 0.1424, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.05185450613498688, | |
| "step": 220, | |
| "valid_targets_mean": 8020.6, | |
| "valid_targets_min": 1960 | |
| }, | |
| { | |
| "epoch": 0.6831983805668016, | |
| "grad_norm": 0.16497156873482458, | |
| "learning_rate": 3.984440811200379e-05, | |
| "loss": 0.1381, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.047338757663965225, | |
| "step": 225, | |
| "valid_targets_mean": 9014.6, | |
| "valid_targets_min": 2130 | |
| }, | |
| { | |
| "epoch": 0.6983805668016194, | |
| "grad_norm": 0.15264181337502675, | |
| "learning_rate": 3.981696116954973e-05, | |
| "loss": 0.1391, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.040149230509996414, | |
| "step": 230, | |
| "valid_targets_mean": 7745.8, | |
| "valid_targets_min": 2111 | |
| }, | |
| { | |
| "epoch": 0.7135627530364372, | |
| "grad_norm": 0.14924795485166983, | |
| "learning_rate": 3.978729695058729e-05, | |
| "loss": 0.137, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04717732220888138, | |
| "step": 235, | |
| "valid_targets_mean": 8852.4, | |
| "valid_targets_min": 1383 | |
| }, | |
| { | |
| "epoch": 0.728744939271255, | |
| "grad_norm": 0.15564976927696877, | |
| "learning_rate": 3.9755418774181146e-05, | |
| "loss": 0.1407, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.053252290934324265, | |
| "step": 240, | |
| "valid_targets_mean": 9674.4, | |
| "valid_targets_min": 2998 | |
| }, | |
| { | |
| "epoch": 0.7439271255060729, | |
| "grad_norm": 0.1613910331589448, | |
| "learning_rate": 3.9721330207110835e-05, | |
| "loss": 0.1377, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04503578320145607, | |
| "step": 245, | |
| "valid_targets_mean": 8254.4, | |
| "valid_targets_min": 1946 | |
| }, | |
| { | |
| "epoch": 0.7591093117408907, | |
| "grad_norm": 0.1577040829725991, | |
| "learning_rate": 3.9685035063471675e-05, | |
| "loss": 0.1377, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0437023788690567, | |
| "step": 250, | |
| "valid_targets_mean": 8235.9, | |
| "valid_targets_min": 2508 | |
| }, | |
| { | |
| "epoch": 0.7742914979757085, | |
| "grad_norm": 0.15477862879114376, | |
| "learning_rate": 3.964653740424804e-05, | |
| "loss": 0.1379, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.045161373913288116, | |
| "step": 255, | |
| "valid_targets_mean": 8814.3, | |
| "valid_targets_min": 1743 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 0.15360128690173375, | |
| "learning_rate": 3.960584153685895e-05, | |
| "loss": 0.1379, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04476224631071091, | |
| "step": 260, | |
| "valid_targets_mean": 8595.0, | |
| "valid_targets_min": 3204 | |
| }, | |
| { | |
| "epoch": 0.8046558704453441, | |
| "grad_norm": 0.14790201962384034, | |
| "learning_rate": 3.9562952014676116e-05, | |
| "loss": 0.137, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04971081763505936, | |
| "step": 265, | |
| "valid_targets_mean": 9996.3, | |
| "valid_targets_min": 2078 | |
| }, | |
| { | |
| "epoch": 0.819838056680162, | |
| "grad_norm": 0.14082892812860626, | |
| "learning_rate": 3.9517873636514525e-05, | |
| "loss": 0.141, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.05578511953353882, | |
| "step": 270, | |
| "valid_targets_mean": 8771.0, | |
| "valid_targets_min": 952 | |
| }, | |
| { | |
| "epoch": 0.8350202429149798, | |
| "grad_norm": 0.1508735440957467, | |
| "learning_rate": 3.947061144609546e-05, | |
| "loss": 0.1341, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.051772911101579666, | |
| "step": 275, | |
| "valid_targets_mean": 9703.9, | |
| "valid_targets_min": 5437 | |
| }, | |
| { | |
| "epoch": 0.8502024291497976, | |
| "grad_norm": 0.14309355810426586, | |
| "learning_rate": 3.942117073148221e-05, | |
| "loss": 0.1367, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04774951934814453, | |
| "step": 280, | |
| "valid_targets_mean": 8803.2, | |
| "valid_targets_min": 3976 | |
| }, | |
| { | |
| "epoch": 0.8653846153846154, | |
| "grad_norm": 0.14481089279560608, | |
| "learning_rate": 3.9369557024488345e-05, | |
| "loss": 0.1367, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.038745008409023285, | |
| "step": 285, | |
| "valid_targets_mean": 7695.8, | |
| "valid_targets_min": 1998 | |
| }, | |
| { | |
| "epoch": 0.8805668016194332, | |
| "grad_norm": 0.15327710917078846, | |
| "learning_rate": 3.931577610005883e-05, | |
| "loss": 0.1363, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04735741764307022, | |
| "step": 290, | |
| "valid_targets_mean": 8560.0, | |
| "valid_targets_min": 3349 | |
| }, | |
| { | |
| "epoch": 0.895748987854251, | |
| "grad_norm": 0.1489896412053705, | |
| "learning_rate": 3.925983397562385e-05, | |
| "loss": 0.1353, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04699864983558655, | |
| "step": 295, | |
| "valid_targets_mean": 8933.8, | |
| "valid_targets_min": 4202 | |
| }, | |
| { | |
| "epoch": 0.9109311740890689, | |
| "grad_norm": 0.13555073407083684, | |
| "learning_rate": 3.920173691042554e-05, | |
| "loss": 0.1359, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.046111904084682465, | |
| "step": 300, | |
| "valid_targets_mean": 9392.7, | |
| "valid_targets_min": 4608 | |
| }, | |
| { | |
| "epoch": 0.9261133603238867, | |
| "grad_norm": 0.14357742826075878, | |
| "learning_rate": 3.914149140481766e-05, | |
| "loss": 0.135, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.046564266085624695, | |
| "step": 305, | |
| "valid_targets_mean": 9501.2, | |
| "valid_targets_min": 3889 | |
| }, | |
| { | |
| "epoch": 0.9412955465587044, | |
| "grad_norm": 0.13521839079517559, | |
| "learning_rate": 3.9079104199538256e-05, | |
| "loss": 0.1356, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04585843160748482, | |
| "step": 310, | |
| "valid_targets_mean": 8548.6, | |
| "valid_targets_min": 2683 | |
| }, | |
| { | |
| "epoch": 0.9564777327935222, | |
| "grad_norm": 0.1509979487584022, | |
| "learning_rate": 3.901458227495549e-05, | |
| "loss": 0.1355, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.044473253190517426, | |
| "step": 315, | |
| "valid_targets_mean": 8206.3, | |
| "valid_targets_min": 3121 | |
| }, | |
| { | |
| "epoch": 0.97165991902834, | |
| "grad_norm": 0.14367835173970656, | |
| "learning_rate": 3.8947932850286585e-05, | |
| "loss": 0.1316, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.05093437805771828, | |
| "step": 320, | |
| "valid_targets_mean": 9368.8, | |
| "valid_targets_min": 2512 | |
| }, | |
| { | |
| "epoch": 0.9868421052631579, | |
| "grad_norm": 0.15094139534937875, | |
| "learning_rate": 3.887916338279014e-05, | |
| "loss": 0.1371, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.044892799109220505, | |
| "step": 325, | |
| "valid_targets_mean": 8683.1, | |
| "valid_targets_min": 2766 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.19808293241580446, | |
| "learning_rate": 3.8808281566931675e-05, | |
| "loss": 0.1339, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.13325560092926025, | |
| "step": 330, | |
| "valid_targets_mean": 8881.3, | |
| "valid_targets_min": 4218 | |
| }, | |
| { | |
| "epoch": 1.0151821862348178, | |
| "grad_norm": 0.15965514008947806, | |
| "learning_rate": 3.873529533352277e-05, | |
| "loss": 0.1225, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0422063022851944, | |
| "step": 335, | |
| "valid_targets_mean": 8870.9, | |
| "valid_targets_min": 3617 | |
| }, | |
| { | |
| "epoch": 1.0303643724696356, | |
| "grad_norm": 0.13490802741845673, | |
| "learning_rate": 3.8660212848833705e-05, | |
| "loss": 0.1193, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03918652608990669, | |
| "step": 340, | |
| "valid_targets_mean": 8422.7, | |
| "valid_targets_min": 3024 | |
| }, | |
| { | |
| "epoch": 1.0455465587044535, | |
| "grad_norm": 0.1431855228231231, | |
| "learning_rate": 3.858304251367972e-05, | |
| "loss": 0.1211, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.040075261145830154, | |
| "step": 345, | |
| "valid_targets_mean": 9017.8, | |
| "valid_targets_min": 1851 | |
| }, | |
| { | |
| "epoch": 1.0607287449392713, | |
| "grad_norm": 0.14317028974999854, | |
| "learning_rate": 3.850379296248107e-05, | |
| "loss": 0.1204, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0401369147002697, | |
| "step": 350, | |
| "valid_targets_mean": 8512.6, | |
| "valid_targets_min": 2878 | |
| }, | |
| { | |
| "epoch": 1.075910931174089, | |
| "grad_norm": 0.14786725340502474, | |
| "learning_rate": 3.8422473062297e-05, | |
| "loss": 0.1223, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.039123423397541046, | |
| "step": 355, | |
| "valid_targets_mean": 8480.0, | |
| "valid_targets_min": 1383 | |
| }, | |
| { | |
| "epoch": 1.091093117408907, | |
| "grad_norm": 0.14683819951668464, | |
| "learning_rate": 3.8339091911833545e-05, | |
| "loss": 0.1208, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03423229232430458, | |
| "step": 360, | |
| "valid_targets_mean": 7983.2, | |
| "valid_targets_min": 2485 | |
| }, | |
| { | |
| "epoch": 1.1062753036437247, | |
| "grad_norm": 0.13837626290735588, | |
| "learning_rate": 3.825365884042553e-05, | |
| "loss": 0.1202, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.040624041110277176, | |
| "step": 365, | |
| "valid_targets_mean": 8933.7, | |
| "valid_targets_min": 2306 | |
| }, | |
| { | |
| "epoch": 1.1214574898785425, | |
| "grad_norm": 0.1331553888335518, | |
| "learning_rate": 3.8166183406992745e-05, | |
| "loss": 0.1218, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04125307500362396, | |
| "step": 370, | |
| "valid_targets_mean": 9297.2, | |
| "valid_targets_min": 1743 | |
| }, | |
| { | |
| "epoch": 1.1366396761133604, | |
| "grad_norm": 0.1378377264881279, | |
| "learning_rate": 3.807667539897041e-05, | |
| "loss": 0.1179, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04190453514456749, | |
| "step": 375, | |
| "valid_targets_mean": 9175.1, | |
| "valid_targets_min": 2563 | |
| }, | |
| { | |
| "epoch": 1.1518218623481782, | |
| "grad_norm": 0.14763349659362032, | |
| "learning_rate": 3.798514483121408e-05, | |
| "loss": 0.1232, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.043424300849437714, | |
| "step": 380, | |
| "valid_targets_mean": 9650.2, | |
| "valid_targets_min": 1695 | |
| }, | |
| { | |
| "epoch": 1.167004048582996, | |
| "grad_norm": 0.1519063682496478, | |
| "learning_rate": 3.789160194487908e-05, | |
| "loss": 0.1229, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0388462096452713, | |
| "step": 385, | |
| "valid_targets_mean": 8738.1, | |
| "valid_targets_min": 4652 | |
| }, | |
| { | |
| "epoch": 1.1821862348178138, | |
| "grad_norm": 0.14918293420523987, | |
| "learning_rate": 3.7796057206274686e-05, | |
| "loss": 0.1218, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04523391276597977, | |
| "step": 390, | |
| "valid_targets_mean": 8981.8, | |
| "valid_targets_min": 3303 | |
| }, | |
| { | |
| "epoch": 1.1973684210526316, | |
| "grad_norm": 0.14743398446357003, | |
| "learning_rate": 3.769852130569304e-05, | |
| "loss": 0.12, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.042628586292266846, | |
| "step": 395, | |
| "valid_targets_mean": 8501.0, | |
| "valid_targets_min": 1694 | |
| }, | |
| { | |
| "epoch": 1.2125506072874495, | |
| "grad_norm": 0.14404088467168605, | |
| "learning_rate": 3.7599005156213066e-05, | |
| "loss": 0.1202, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04287807270884514, | |
| "step": 400, | |
| "valid_targets_mean": 8704.5, | |
| "valid_targets_min": 2069 | |
| }, | |
| { | |
| "epoch": 1.2277327935222673, | |
| "grad_norm": 0.13179680215020095, | |
| "learning_rate": 3.74975198924794e-05, | |
| "loss": 0.1197, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04075103998184204, | |
| "step": 405, | |
| "valid_targets_mean": 8705.5, | |
| "valid_targets_min": 3010 | |
| }, | |
| { | |
| "epoch": 1.242914979757085, | |
| "grad_norm": 0.13185060093993278, | |
| "learning_rate": 3.739407686945658e-05, | |
| "loss": 0.1202, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03605141490697861, | |
| "step": 410, | |
| "valid_targets_mean": 7899.5, | |
| "valid_targets_min": 2349 | |
| }, | |
| { | |
| "epoch": 1.258097165991903, | |
| "grad_norm": 0.15477508884351784, | |
| "learning_rate": 3.728868766115854e-05, | |
| "loss": 0.1209, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04045581817626953, | |
| "step": 415, | |
| "valid_targets_mean": 8937.2, | |
| "valid_targets_min": 2877 | |
| }, | |
| { | |
| "epoch": 1.2732793522267207, | |
| "grad_norm": 0.1423658323336795, | |
| "learning_rate": 3.718136405935365e-05, | |
| "loss": 0.118, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04214191064238548, | |
| "step": 420, | |
| "valid_targets_mean": 9205.8, | |
| "valid_targets_min": 4899 | |
| }, | |
| { | |
| "epoch": 1.2884615384615383, | |
| "grad_norm": 0.13299434343518607, | |
| "learning_rate": 3.707211807224534e-05, | |
| "loss": 0.1227, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03906003758311272, | |
| "step": 425, | |
| "valid_targets_mean": 8680.7, | |
| "valid_targets_min": 1442 | |
| }, | |
| { | |
| "epoch": 1.3036437246963564, | |
| "grad_norm": 0.14193349094515145, | |
| "learning_rate": 3.696096192312852e-05, | |
| "loss": 0.1217, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04030559957027435, | |
| "step": 430, | |
| "valid_targets_mean": 8542.9, | |
| "valid_targets_min": 3624 | |
| }, | |
| { | |
| "epoch": 1.318825910931174, | |
| "grad_norm": 0.14525254788310676, | |
| "learning_rate": 3.684790804902199e-05, | |
| "loss": 0.1203, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03852429986000061, | |
| "step": 435, | |
| "valid_targets_mean": 9228.2, | |
| "valid_targets_min": 4201 | |
| }, | |
| { | |
| "epoch": 1.334008097165992, | |
| "grad_norm": 0.13424883273699872, | |
| "learning_rate": 3.673296909927682e-05, | |
| "loss": 0.1183, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03693283721804619, | |
| "step": 440, | |
| "valid_targets_mean": 8962.3, | |
| "valid_targets_min": 2116 | |
| }, | |
| { | |
| "epoch": 1.3491902834008096, | |
| "grad_norm": 0.13582092890740538, | |
| "learning_rate": 3.661615793416109e-05, | |
| "loss": 0.1176, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.037568140774965286, | |
| "step": 445, | |
| "valid_targets_mean": 8539.6, | |
| "valid_targets_min": 1088 | |
| }, | |
| { | |
| "epoch": 1.3643724696356276, | |
| "grad_norm": 0.1426561833624166, | |
| "learning_rate": 3.649748762342098e-05, | |
| "loss": 0.1197, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04003506898880005, | |
| "step": 450, | |
| "valid_targets_mean": 8882.3, | |
| "valid_targets_min": 5064 | |
| }, | |
| { | |
| "epoch": 1.3795546558704452, | |
| "grad_norm": 0.14205167937449403, | |
| "learning_rate": 3.637697144481839e-05, | |
| "loss": 0.1174, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04064129665493965, | |
| "step": 455, | |
| "valid_targets_mean": 9428.7, | |
| "valid_targets_min": 5854 | |
| }, | |
| { | |
| "epoch": 1.3947368421052633, | |
| "grad_norm": 0.1346883217605652, | |
| "learning_rate": 3.625462288264536e-05, | |
| "loss": 0.1188, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04384438693523407, | |
| "step": 460, | |
| "valid_targets_mean": 8659.9, | |
| "valid_targets_min": 3170 | |
| }, | |
| { | |
| "epoch": 1.4099190283400809, | |
| "grad_norm": 0.13647461582268927, | |
| "learning_rate": 3.613045562621533e-05, | |
| "loss": 0.1177, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.036319226026535034, | |
| "step": 465, | |
| "valid_targets_mean": 9370.1, | |
| "valid_targets_min": 3050 | |
| }, | |
| { | |
| "epoch": 1.425101214574899, | |
| "grad_norm": 0.1333080513085188, | |
| "learning_rate": 3.600448356833146e-05, | |
| "loss": 0.1161, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.036676615476608276, | |
| "step": 470, | |
| "valid_targets_mean": 8776.6, | |
| "valid_targets_min": 1761 | |
| }, | |
| { | |
| "epoch": 1.4402834008097165, | |
| "grad_norm": 0.13799900506494325, | |
| "learning_rate": 3.587672080373219e-05, | |
| "loss": 0.118, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03807856887578964, | |
| "step": 475, | |
| "valid_targets_mean": 9003.5, | |
| "valid_targets_min": 2337 | |
| }, | |
| { | |
| "epoch": 1.4554655870445345, | |
| "grad_norm": 0.1441999573113224, | |
| "learning_rate": 3.574718162751426e-05, | |
| "loss": 0.1211, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.037710558623075485, | |
| "step": 480, | |
| "valid_targets_mean": 8930.4, | |
| "valid_targets_min": 2960 | |
| }, | |
| { | |
| "epoch": 1.4706477732793521, | |
| "grad_norm": 0.13542691460656633, | |
| "learning_rate": 3.561588053353319e-05, | |
| "loss": 0.1183, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.039702557027339935, | |
| "step": 485, | |
| "valid_targets_mean": 8979.6, | |
| "valid_targets_min": 3143 | |
| }, | |
| { | |
| "epoch": 1.48582995951417, | |
| "grad_norm": 0.13667440514511725, | |
| "learning_rate": 3.5482832212781655e-05, | |
| "loss": 0.119, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.041578102856874466, | |
| "step": 490, | |
| "valid_targets_mean": 9393.0, | |
| "valid_targets_min": 4461 | |
| }, | |
| { | |
| "epoch": 1.5010121457489878, | |
| "grad_norm": 0.14758499373688547, | |
| "learning_rate": 3.53480515517457e-05, | |
| "loss": 0.1195, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.041897259652614594, | |
| "step": 495, | |
| "valid_targets_mean": 8865.5, | |
| "valid_targets_min": 4513 | |
| }, | |
| { | |
| "epoch": 1.5161943319838058, | |
| "grad_norm": 0.1393660306700683, | |
| "learning_rate": 3.5211553630739166e-05, | |
| "loss": 0.1172, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.038587454706430435, | |
| "step": 500, | |
| "valid_targets_mean": 8912.3, | |
| "valid_targets_min": 2193 | |
| }, | |
| { | |
| "epoch": 1.5313765182186234, | |
| "grad_norm": 0.1321451791186284, | |
| "learning_rate": 3.5073353722216334e-05, | |
| "loss": 0.1167, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04267330467700958, | |
| "step": 505, | |
| "valid_targets_mean": 9450.8, | |
| "valid_targets_min": 5214 | |
| }, | |
| { | |
| "epoch": 1.5465587044534415, | |
| "grad_norm": 0.1373867196940578, | |
| "learning_rate": 3.4933467289063156e-05, | |
| "loss": 0.1182, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.037735819816589355, | |
| "step": 510, | |
| "valid_targets_mean": 8891.8, | |
| "valid_targets_min": 2906 | |
| }, | |
| { | |
| "epoch": 1.561740890688259, | |
| "grad_norm": 0.14010908150846232, | |
| "learning_rate": 3.4791909982867175e-05, | |
| "loss": 0.1169, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03755822777748108, | |
| "step": 515, | |
| "valid_targets_mean": 8452.1, | |
| "valid_targets_min": 2078 | |
| }, | |
| { | |
| "epoch": 1.5769230769230769, | |
| "grad_norm": 0.13625234613813128, | |
| "learning_rate": 3.464869764216622e-05, | |
| "loss": 0.1201, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03687182441353798, | |
| "step": 520, | |
| "valid_targets_mean": 8567.8, | |
| "valid_targets_min": 3361 | |
| }, | |
| { | |
| "epoch": 1.5921052631578947, | |
| "grad_norm": 0.12476852741398382, | |
| "learning_rate": 3.450384629067635e-05, | |
| "loss": 0.1159, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0386493057012558, | |
| "step": 525, | |
| "valid_targets_mean": 8937.7, | |
| "valid_targets_min": 2136 | |
| }, | |
| { | |
| "epoch": 1.6072874493927125, | |
| "grad_norm": 0.13653312440046914, | |
| "learning_rate": 3.435737213549896e-05, | |
| "loss": 0.1198, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.043314091861248016, | |
| "step": 530, | |
| "valid_targets_mean": 9161.1, | |
| "valid_targets_min": 3081 | |
| }, | |
| { | |
| "epoch": 1.6224696356275303, | |
| "grad_norm": 0.1306266517072205, | |
| "learning_rate": 3.420929156530738e-05, | |
| "loss": 0.12, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04418621584773064, | |
| "step": 535, | |
| "valid_targets_mean": 9512.2, | |
| "valid_targets_min": 4618 | |
| }, | |
| { | |
| "epoch": 1.6376518218623481, | |
| "grad_norm": 0.13824516516340166, | |
| "learning_rate": 3.405962114851324e-05, | |
| "loss": 0.1192, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03845050930976868, | |
| "step": 540, | |
| "valid_targets_mean": 9317.7, | |
| "valid_targets_min": 1504 | |
| }, | |
| { | |
| "epoch": 1.652834008097166, | |
| "grad_norm": 0.13248912774943605, | |
| "learning_rate": 3.390837763141261e-05, | |
| "loss": 0.1149, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03524269908666611, | |
| "step": 545, | |
| "valid_targets_mean": 8158.3, | |
| "valid_targets_min": 5338 | |
| }, | |
| { | |
| "epoch": 1.6680161943319838, | |
| "grad_norm": 0.13124362754573704, | |
| "learning_rate": 3.3755577936312344e-05, | |
| "loss": 0.1159, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03851894289255142, | |
| "step": 550, | |
| "valid_targets_mean": 8900.9, | |
| "valid_targets_min": 1420 | |
| }, | |
| { | |
| "epoch": 1.6831983805668016, | |
| "grad_norm": 0.13309098907855046, | |
| "learning_rate": 3.360123915963662e-05, | |
| "loss": 0.117, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04058458283543587, | |
| "step": 555, | |
| "valid_targets_mean": 8476.7, | |
| "valid_targets_min": 2404 | |
| }, | |
| { | |
| "epoch": 1.6983805668016194, | |
| "grad_norm": 0.12167500700332151, | |
| "learning_rate": 3.3445378570014125e-05, | |
| "loss": 0.117, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.037073682993650436, | |
| "step": 560, | |
| "valid_targets_mean": 9046.7, | |
| "valid_targets_min": 3708 | |
| }, | |
| { | |
| "epoch": 1.7135627530364372, | |
| "grad_norm": 0.12722819484615613, | |
| "learning_rate": 3.328801360634585e-05, | |
| "loss": 0.117, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.042664721608161926, | |
| "step": 565, | |
| "valid_targets_mean": 8931.7, | |
| "valid_targets_min": 2676 | |
| }, | |
| { | |
| "epoch": 1.728744939271255, | |
| "grad_norm": 0.1350300692639102, | |
| "learning_rate": 3.312916187585392e-05, | |
| "loss": 0.1202, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.043970100581645966, | |
| "step": 570, | |
| "valid_targets_mean": 9082.5, | |
| "valid_targets_min": 3889 | |
| }, | |
| { | |
| "epoch": 1.7439271255060729, | |
| "grad_norm": 0.13784070061482687, | |
| "learning_rate": 3.296884115211157e-05, | |
| "loss": 0.1183, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03849092125892639, | |
| "step": 575, | |
| "valid_targets_mean": 8367.6, | |
| "valid_targets_min": 4370 | |
| }, | |
| { | |
| "epoch": 1.7591093117408907, | |
| "grad_norm": 0.12990841009377552, | |
| "learning_rate": 3.280706937305445e-05, | |
| "loss": 0.1153, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04104745760560036, | |
| "step": 580, | |
| "valid_targets_mean": 8765.1, | |
| "valid_targets_min": 3202 | |
| }, | |
| { | |
| "epoch": 1.7742914979757085, | |
| "grad_norm": 0.12658647192711886, | |
| "learning_rate": 3.2643864638973645e-05, | |
| "loss": 0.1165, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0371856614947319, | |
| "step": 585, | |
| "valid_targets_mean": 8582.4, | |
| "valid_targets_min": 3706 | |
| }, | |
| { | |
| "epoch": 1.7894736842105263, | |
| "grad_norm": 0.1420527888443784, | |
| "learning_rate": 3.2479245210490434e-05, | |
| "loss": 0.1199, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04411791265010834, | |
| "step": 590, | |
| "valid_targets_mean": 8860.8, | |
| "valid_targets_min": 3828 | |
| }, | |
| { | |
| "epoch": 1.8046558704453441, | |
| "grad_norm": 0.13479603583252717, | |
| "learning_rate": 3.2313229506513167e-05, | |
| "loss": 0.1163, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.036885298788547516, | |
| "step": 595, | |
| "valid_targets_mean": 8531.2, | |
| "valid_targets_min": 3881 | |
| }, | |
| { | |
| "epoch": 1.819838056680162, | |
| "grad_norm": 0.13357000689361798, | |
| "learning_rate": 3.2145836102176424e-05, | |
| "loss": 0.1167, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.040830910205841064, | |
| "step": 600, | |
| "valid_targets_mean": 8512.3, | |
| "valid_targets_min": 2760 | |
| }, | |
| { | |
| "epoch": 1.8350202429149798, | |
| "grad_norm": 0.13342098396862487, | |
| "learning_rate": 3.197708372676265e-05, | |
| "loss": 0.1178, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.04097800329327583, | |
| "step": 605, | |
| "valid_targets_mean": 8799.1, | |
| "valid_targets_min": 3515 | |
| }, | |
| { | |
| "epoch": 1.8502024291497976, | |
| "grad_norm": 0.12260817127337884, | |
| "learning_rate": 3.1806991261606604e-05, | |
| "loss": 0.1146, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03742881119251251, | |
| "step": 610, | |
| "valid_targets_mean": 9052.3, | |
| "valid_targets_min": 2167 | |
| }, | |
| { | |
| "epoch": 1.8653846153846154, | |
| "grad_norm": 0.12824819852397937, | |
| "learning_rate": 3.163557773798276e-05, | |
| "loss": 0.1229, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.039812471717596054, | |
| "step": 615, | |
| "valid_targets_mean": 9325.1, | |
| "valid_targets_min": 4081 | |
| }, | |
| { | |
| "epoch": 1.8805668016194332, | |
| "grad_norm": 0.13513869017413108, | |
| "learning_rate": 3.146286233497593e-05, | |
| "loss": 0.1161, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.044601816684007645, | |
| "step": 620, | |
| "valid_targets_mean": 9947.7, | |
| "valid_targets_min": 4796 | |
| }, | |
| { | |
| "epoch": 1.895748987854251, | |
| "grad_norm": 0.12789426195152298, | |
| "learning_rate": 3.128886437733539e-05, | |
| "loss": 0.1146, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03474682569503784, | |
| "step": 625, | |
| "valid_targets_mean": 8547.9, | |
| "valid_targets_min": 2143 | |
| }, | |
| { | |
| "epoch": 1.9109311740890689, | |
| "grad_norm": 0.13217720629344965, | |
| "learning_rate": 3.111360333331263e-05, | |
| "loss": 0.1174, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03625170513987541, | |
| "step": 630, | |
| "valid_targets_mean": 8220.0, | |
| "valid_targets_min": 2195 | |
| }, | |
| { | |
| "epoch": 1.9261133603238867, | |
| "grad_norm": 0.13115204968801353, | |
| "learning_rate": 3.093709881248312e-05, | |
| "loss": 0.1142, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03680944815278053, | |
| "step": 635, | |
| "valid_targets_mean": 8190.2, | |
| "valid_targets_min": 2111 | |
| }, | |
| { | |
| "epoch": 1.9412955465587043, | |
| "grad_norm": 0.12666792237363333, | |
| "learning_rate": 3.075937056355225e-05, | |
| "loss": 0.116, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03545242175459862, | |
| "step": 640, | |
| "valid_targets_mean": 8163.5, | |
| "valid_targets_min": 3034 | |
| }, | |
| { | |
| "epoch": 1.9564777327935223, | |
| "grad_norm": 0.13273688917833829, | |
| "learning_rate": 3.0580438472145665e-05, | |
| "loss": 0.1174, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03758101910352707, | |
| "step": 645, | |
| "valid_targets_mean": 8741.6, | |
| "valid_targets_min": 2680 | |
| }, | |
| { | |
| "epoch": 1.97165991902834, | |
| "grad_norm": 0.12923137137706422, | |
| "learning_rate": 3.0400322558584308e-05, | |
| "loss": 0.1139, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.039797790348529816, | |
| "step": 650, | |
| "valid_targets_mean": 9020.0, | |
| "valid_targets_min": 3504 | |
| }, | |
| { | |
| "epoch": 1.986842105263158, | |
| "grad_norm": 0.11987183056887181, | |
| "learning_rate": 3.0219042975644415e-05, | |
| "loss": 0.1168, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03768943250179291, | |
| "step": 655, | |
| "valid_targets_mean": 8646.0, | |
| "valid_targets_min": 2358 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.19522580085540725, | |
| "learning_rate": 3.0036620006302624e-05, | |
| "loss": 0.1147, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.1115252897143364, | |
| "step": 660, | |
| "valid_targets_mean": 9397.5, | |
| "valid_targets_min": 2582 | |
| }, | |
| { | |
| "epoch": 2.0151821862348176, | |
| "grad_norm": 0.15092624871636195, | |
| "learning_rate": 2.9853074061466602e-05, | |
| "loss": 0.0987, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03304405137896538, | |
| "step": 665, | |
| "valid_targets_mean": 8997.2, | |
| "valid_targets_min": 2213 | |
| }, | |
| { | |
| "epoch": 2.0303643724696356, | |
| "grad_norm": 0.14085296995450658, | |
| "learning_rate": 2.9668425677691278e-05, | |
| "loss": 0.0969, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03202366083860397, | |
| "step": 670, | |
| "valid_targets_mean": 8815.9, | |
| "valid_targets_min": 4417 | |
| }, | |
| { | |
| "epoch": 2.0455465587044532, | |
| "grad_norm": 0.12689925480612596, | |
| "learning_rate": 2.948269551488108e-05, | |
| "loss": 0.1002, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.030134135857224464, | |
| "step": 675, | |
| "valid_targets_mean": 8330.5, | |
| "valid_targets_min": 2034 | |
| }, | |
| { | |
| "epoch": 2.0607287449392713, | |
| "grad_norm": 0.1367619328122673, | |
| "learning_rate": 2.929590435397832e-05, | |
| "loss": 0.0998, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03334369510412216, | |
| "step": 680, | |
| "valid_targets_mean": 8493.7, | |
| "valid_targets_min": 3337 | |
| }, | |
| { | |
| "epoch": 2.075910931174089, | |
| "grad_norm": 0.1386374272500319, | |
| "learning_rate": 2.9108073094638066e-05, | |
| "loss": 0.0976, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03655136376619339, | |
| "step": 685, | |
| "valid_targets_mean": 9160.6, | |
| "valid_targets_min": 3120 | |
| }, | |
| { | |
| "epoch": 2.091093117408907, | |
| "grad_norm": 0.12902508736070778, | |
| "learning_rate": 2.8919222752889727e-05, | |
| "loss": 0.0994, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.030925486236810684, | |
| "step": 690, | |
| "valid_targets_mean": 8539.5, | |
| "valid_targets_min": 3485 | |
| }, | |
| { | |
| "epoch": 2.1062753036437245, | |
| "grad_norm": 0.12092057912223488, | |
| "learning_rate": 2.8729374458785647e-05, | |
| "loss": 0.097, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03300788998603821, | |
| "step": 695, | |
| "valid_targets_mean": 9422.6, | |
| "valid_targets_min": 2913 | |
| }, | |
| { | |
| "epoch": 2.1214574898785425, | |
| "grad_norm": 0.1325018165528914, | |
| "learning_rate": 2.8538549454036838e-05, | |
| "loss": 0.0994, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.035598378628492355, | |
| "step": 700, | |
| "valid_targets_mean": 8580.9, | |
| "valid_targets_min": 1761 | |
| }, | |
| { | |
| "epoch": 2.13663967611336, | |
| "grad_norm": 0.12247763965717091, | |
| "learning_rate": 2.834676908963636e-05, | |
| "loss": 0.0971, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.029358722269535065, | |
| "step": 705, | |
| "valid_targets_mean": 8849.5, | |
| "valid_targets_min": 1475 | |
| }, | |
| { | |
| "epoch": 2.151821862348178, | |
| "grad_norm": 0.14022927867235768, | |
| "learning_rate": 2.815405482347037e-05, | |
| "loss": 0.0995, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03130686655640602, | |
| "step": 710, | |
| "valid_targets_mean": 8192.2, | |
| "valid_targets_min": 1695 | |
| }, | |
| { | |
| "epoch": 2.167004048582996, | |
| "grad_norm": 0.12911142981333992, | |
| "learning_rate": 2.796042821791725e-05, | |
| "loss": 0.1014, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.033592142164707184, | |
| "step": 715, | |
| "valid_targets_mean": 8755.0, | |
| "valid_targets_min": 4146 | |
| }, | |
| { | |
| "epoch": 2.182186234817814, | |
| "grad_norm": 0.13365694219388094, | |
| "learning_rate": 2.776591093743505e-05, | |
| "loss": 0.0971, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03200051188468933, | |
| "step": 720, | |
| "valid_targets_mean": 8630.2, | |
| "valid_targets_min": 2440 | |
| }, | |
| { | |
| "epoch": 2.1973684210526314, | |
| "grad_norm": 0.13886896480725291, | |
| "learning_rate": 2.7570524746137485e-05, | |
| "loss": 0.1009, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03102896362543106, | |
| "step": 725, | |
| "valid_targets_mean": 8521.6, | |
| "valid_targets_min": 2182 | |
| }, | |
| { | |
| "epoch": 2.2125506072874495, | |
| "grad_norm": 0.13626921427735725, | |
| "learning_rate": 2.7374291505358818e-05, | |
| "loss": 0.0971, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.028175748884677887, | |
| "step": 730, | |
| "valid_targets_mean": 8313.0, | |
| "valid_targets_min": 2471 | |
| }, | |
| { | |
| "epoch": 2.227732793522267, | |
| "grad_norm": 0.12639769434698722, | |
| "learning_rate": 2.7177233171207817e-05, | |
| "loss": 0.0967, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.030831187963485718, | |
| "step": 735, | |
| "valid_targets_mean": 8293.0, | |
| "valid_targets_min": 169 | |
| }, | |
| { | |
| "epoch": 2.242914979757085, | |
| "grad_norm": 0.1269160689722301, | |
| "learning_rate": 2.6979371792111147e-05, | |
| "loss": 0.0997, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.036900125443935394, | |
| "step": 740, | |
| "valid_targets_mean": 9331.3, | |
| "valid_targets_min": 3646 | |
| }, | |
| { | |
| "epoch": 2.2580971659919027, | |
| "grad_norm": 0.12465789689604725, | |
| "learning_rate": 2.678072950634641e-05, | |
| "loss": 0.0981, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.029040224850177765, | |
| "step": 745, | |
| "valid_targets_mean": 8606.2, | |
| "valid_targets_min": 1819 | |
| }, | |
| { | |
| "epoch": 2.2732793522267207, | |
| "grad_norm": 0.13977622405735166, | |
| "learning_rate": 2.6581328539565184e-05, | |
| "loss": 0.0969, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.029864827170968056, | |
| "step": 750, | |
| "valid_targets_mean": 8254.0, | |
| "valid_targets_min": 1867 | |
| }, | |
| { | |
| "epoch": 2.2884615384615383, | |
| "grad_norm": 0.13266887088577622, | |
| "learning_rate": 2.638119120230616e-05, | |
| "loss": 0.0999, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03668136149644852, | |
| "step": 755, | |
| "valid_targets_mean": 8458.7, | |
| "valid_targets_min": 1946 | |
| }, | |
| { | |
| "epoch": 2.3036437246963564, | |
| "grad_norm": 0.14158216971702048, | |
| "learning_rate": 2.618033988749895e-05, | |
| "loss": 0.1013, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03187715262174606, | |
| "step": 760, | |
| "valid_targets_mean": 8106.2, | |
| "valid_targets_min": 1804 | |
| }, | |
| { | |
| "epoch": 2.318825910931174, | |
| "grad_norm": 0.12995234758461993, | |
| "learning_rate": 2.5978797067958542e-05, | |
| "loss": 0.098, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.028093889355659485, | |
| "step": 765, | |
| "valid_targets_mean": 8321.8, | |
| "valid_targets_min": 3086 | |
| }, | |
| { | |
| "epoch": 2.334008097165992, | |
| "grad_norm": 0.12167921261274191, | |
| "learning_rate": 2.5776585293870877e-05, | |
| "loss": 0.0967, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.031541623175144196, | |
| "step": 770, | |
| "valid_targets_mean": 8667.0, | |
| "valid_targets_min": 2675 | |
| }, | |
| { | |
| "epoch": 2.3491902834008096, | |
| "grad_norm": 0.13828425659159516, | |
| "learning_rate": 2.557372719026976e-05, | |
| "loss": 0.0997, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03466714173555374, | |
| "step": 775, | |
| "valid_targets_mean": 8686.8, | |
| "valid_targets_min": 3903 | |
| }, | |
| { | |
| "epoch": 2.3643724696356276, | |
| "grad_norm": 0.13539371782730703, | |
| "learning_rate": 2.537024545450539e-05, | |
| "loss": 0.0992, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.034908317029476166, | |
| "step": 780, | |
| "valid_targets_mean": 9167.0, | |
| "valid_targets_min": 3838 | |
| }, | |
| { | |
| "epoch": 2.3795546558704452, | |
| "grad_norm": 0.13066885243668733, | |
| "learning_rate": 2.5166162853704825e-05, | |
| "loss": 0.0981, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03469014912843704, | |
| "step": 785, | |
| "valid_targets_mean": 8483.3, | |
| "valid_targets_min": 3143 | |
| }, | |
| { | |
| "epoch": 2.3947368421052633, | |
| "grad_norm": 0.13106558352402994, | |
| "learning_rate": 2.496150222222458e-05, | |
| "loss": 0.0982, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.034638337790966034, | |
| "step": 790, | |
| "valid_targets_mean": 9069.6, | |
| "valid_targets_min": 3841 | |
| }, | |
| { | |
| "epoch": 2.409919028340081, | |
| "grad_norm": 0.13409122600658832, | |
| "learning_rate": 2.475628645909576e-05, | |
| "loss": 0.0995, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03560870885848999, | |
| "step": 795, | |
| "valid_targets_mean": 8651.1, | |
| "valid_targets_min": 2365 | |
| }, | |
| { | |
| "epoch": 2.425101214574899, | |
| "grad_norm": 0.13204393054443267, | |
| "learning_rate": 2.4550538525461963e-05, | |
| "loss": 0.1006, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.030237320810556412, | |
| "step": 800, | |
| "valid_targets_mean": 9126.9, | |
| "valid_targets_min": 5194 | |
| }, | |
| { | |
| "epoch": 2.4402834008097165, | |
| "grad_norm": 0.1363390436934973, | |
| "learning_rate": 2.434428144201016e-05, | |
| "loss": 0.0997, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03139049559831619, | |
| "step": 805, | |
| "valid_targets_mean": 8714.0, | |
| "valid_targets_min": 2083 | |
| }, | |
| { | |
| "epoch": 2.4554655870445345, | |
| "grad_norm": 0.1352605476978129, | |
| "learning_rate": 2.4137538286394976e-05, | |
| "loss": 0.0993, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.030325546860694885, | |
| "step": 810, | |
| "valid_targets_mean": 8818.2, | |
| "valid_targets_min": 2843 | |
| }, | |
| { | |
| "epoch": 2.470647773279352, | |
| "grad_norm": 0.13238076939675822, | |
| "learning_rate": 2.3930332190656604e-05, | |
| "loss": 0.098, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0321936309337616, | |
| "step": 815, | |
| "valid_targets_mean": 8838.6, | |
| "valid_targets_min": 2433 | |
| }, | |
| { | |
| "epoch": 2.48582995951417, | |
| "grad_norm": 0.12611749014978751, | |
| "learning_rate": 2.3722686338632602e-05, | |
| "loss": 0.0987, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0339176282286644, | |
| "step": 820, | |
| "valid_targets_mean": 9581.3, | |
| "valid_targets_min": 4055 | |
| }, | |
| { | |
| "epoch": 2.501012145748988, | |
| "grad_norm": 0.12396226475998423, | |
| "learning_rate": 2.3514623963363886e-05, | |
| "loss": 0.0966, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.032344065606594086, | |
| "step": 825, | |
| "valid_targets_mean": 8986.5, | |
| "valid_targets_min": 1530 | |
| }, | |
| { | |
| "epoch": 2.516194331983806, | |
| "grad_norm": 0.13883230836409782, | |
| "learning_rate": 2.330616834449525e-05, | |
| "loss": 0.1008, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03282139077782631, | |
| "step": 830, | |
| "valid_targets_mean": 8606.3, | |
| "valid_targets_min": 4732 | |
| }, | |
| { | |
| "epoch": 2.5313765182186234, | |
| "grad_norm": 0.12842839590550523, | |
| "learning_rate": 2.309734280567065e-05, | |
| "loss": 0.1011, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.031715936958789825, | |
| "step": 835, | |
| "valid_targets_mean": 9411.6, | |
| "valid_targets_min": 2365 | |
| }, | |
| { | |
| "epoch": 2.5465587044534415, | |
| "grad_norm": 0.1361943791218576, | |
| "learning_rate": 2.28881707119236e-05, | |
| "loss": 0.0973, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.032900143414735794, | |
| "step": 840, | |
| "valid_targets_mean": 9131.6, | |
| "valid_targets_min": 5686 | |
| }, | |
| { | |
| "epoch": 2.561740890688259, | |
| "grad_norm": 0.13205912540081857, | |
| "learning_rate": 2.267867546706287e-05, | |
| "loss": 0.0958, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03186526894569397, | |
| "step": 845, | |
| "valid_targets_mean": 9056.0, | |
| "valid_targets_min": 3465 | |
| }, | |
| { | |
| "epoch": 2.5769230769230766, | |
| "grad_norm": 0.13183033650573428, | |
| "learning_rate": 2.2468880511053896e-05, | |
| "loss": 0.1004, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.035993125289678574, | |
| "step": 850, | |
| "valid_targets_mean": 8029.7, | |
| "valid_targets_min": 922 | |
| }, | |
| { | |
| "epoch": 2.5921052631578947, | |
| "grad_norm": 0.12337688518620997, | |
| "learning_rate": 2.2258809317396163e-05, | |
| "loss": 0.0964, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03249669820070267, | |
| "step": 855, | |
| "valid_targets_mean": 8941.4, | |
| "valid_targets_min": 3512 | |
| }, | |
| { | |
| "epoch": 2.6072874493927127, | |
| "grad_norm": 0.1347108450640613, | |
| "learning_rate": 2.2048485390496757e-05, | |
| "loss": 0.0959, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03107546642422676, | |
| "step": 860, | |
| "valid_targets_mean": 8734.8, | |
| "valid_targets_min": 2738 | |
| }, | |
| { | |
| "epoch": 2.6224696356275303, | |
| "grad_norm": 0.12873112162059336, | |
| "learning_rate": 2.1837932263040553e-05, | |
| "loss": 0.1011, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03735276684165001, | |
| "step": 865, | |
| "valid_targets_mean": 9120.7, | |
| "valid_targets_min": 3841 | |
| }, | |
| { | |
| "epoch": 2.637651821862348, | |
| "grad_norm": 0.1342383752515572, | |
| "learning_rate": 2.1627173493357167e-05, | |
| "loss": 0.0972, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03402619808912277, | |
| "step": 870, | |
| "valid_targets_mean": 9345.4, | |
| "valid_targets_min": 3724 | |
| }, | |
| { | |
| "epoch": 2.652834008097166, | |
| "grad_norm": 0.12351589431152983, | |
| "learning_rate": 2.1416232662785084e-05, | |
| "loss": 0.0987, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03457936644554138, | |
| "step": 875, | |
| "valid_targets_mean": 9191.9, | |
| "valid_targets_min": 2454 | |
| }, | |
| { | |
| "epoch": 2.668016194331984, | |
| "grad_norm": 0.12880276663598475, | |
| "learning_rate": 2.1205133373033173e-05, | |
| "loss": 0.0957, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03351035714149475, | |
| "step": 880, | |
| "valid_targets_mean": 8895.0, | |
| "valid_targets_min": 1864 | |
| }, | |
| { | |
| "epoch": 2.6831983805668016, | |
| "grad_norm": 0.149520004397409, | |
| "learning_rate": 2.0993899243539953e-05, | |
| "loss": 0.0995, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.034513555467128754, | |
| "step": 885, | |
| "valid_targets_mean": 8898.2, | |
| "valid_targets_min": 1694 | |
| }, | |
| { | |
| "epoch": 2.698380566801619, | |
| "grad_norm": 0.13316504062399304, | |
| "learning_rate": 2.0782553908830887e-05, | |
| "loss": 0.0949, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.032010383903980255, | |
| "step": 890, | |
| "valid_targets_mean": 8021.3, | |
| "valid_targets_min": 1902 | |
| }, | |
| { | |
| "epoch": 2.7135627530364372, | |
| "grad_norm": 0.12712523699929512, | |
| "learning_rate": 2.0571121015873924e-05, | |
| "loss": 0.0957, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03334994614124298, | |
| "step": 895, | |
| "valid_targets_mean": 9190.2, | |
| "valid_targets_min": 2618 | |
| }, | |
| { | |
| "epoch": 2.7287449392712553, | |
| "grad_norm": 0.1443716570889358, | |
| "learning_rate": 2.0359624221433728e-05, | |
| "loss": 0.097, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03155478090047836, | |
| "step": 900, | |
| "valid_targets_mean": 8620.0, | |
| "valid_targets_min": 3497 | |
| }, | |
| { | |
| "epoch": 2.743927125506073, | |
| "grad_norm": 0.12173390516856115, | |
| "learning_rate": 2.014808718942476e-05, | |
| "loss": 0.0992, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.030620016157627106, | |
| "step": 905, | |
| "valid_targets_mean": 8797.9, | |
| "valid_targets_min": 3961 | |
| }, | |
| { | |
| "epoch": 2.7591093117408905, | |
| "grad_norm": 0.13642352732887367, | |
| "learning_rate": 1.9936533588263557e-05, | |
| "loss": 0.0949, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02945447713136673, | |
| "step": 910, | |
| "valid_targets_mean": 8671.8, | |
| "valid_targets_min": 2552 | |
| }, | |
| { | |
| "epoch": 2.7742914979757085, | |
| "grad_norm": 0.12881653709766408, | |
| "learning_rate": 1.9724987088220565e-05, | |
| "loss": 0.0989, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0348372682929039, | |
| "step": 915, | |
| "valid_targets_mean": 8983.8, | |
| "valid_targets_min": 3997 | |
| }, | |
| { | |
| "epoch": 2.7894736842105265, | |
| "grad_norm": 0.12743160260279732, | |
| "learning_rate": 1.951347135877169e-05, | |
| "loss": 0.0958, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.032750196754932404, | |
| "step": 920, | |
| "valid_targets_mean": 8917.7, | |
| "valid_targets_min": 2760 | |
| }, | |
| { | |
| "epoch": 2.804655870445344, | |
| "grad_norm": 0.13731164608336624, | |
| "learning_rate": 1.930201006594999e-05, | |
| "loss": 0.0984, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.034120626747608185, | |
| "step": 925, | |
| "valid_targets_mean": 8190.1, | |
| "valid_targets_min": 2542 | |
| }, | |
| { | |
| "epoch": 2.8198380566801617, | |
| "grad_norm": 0.12204247767524522, | |
| "learning_rate": 1.9090626869697714e-05, | |
| "loss": 0.0977, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.031239423900842667, | |
| "step": 930, | |
| "valid_targets_mean": 8339.9, | |
| "valid_targets_min": 2165 | |
| }, | |
| { | |
| "epoch": 2.83502024291498, | |
| "grad_norm": 0.12217950202148058, | |
| "learning_rate": 1.8879345421219063e-05, | |
| "loss": 0.0999, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.029417358338832855, | |
| "step": 935, | |
| "valid_targets_mean": 8681.9, | |
| "valid_targets_min": 2248 | |
| }, | |
| { | |
| "epoch": 2.850202429149798, | |
| "grad_norm": 0.12631981727449754, | |
| "learning_rate": 1.8668189360333923e-05, | |
| "loss": 0.0995, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.033066682517528534, | |
| "step": 940, | |
| "valid_targets_mean": 8277.4, | |
| "valid_targets_min": 2753 | |
| }, | |
| { | |
| "epoch": 2.8653846153846154, | |
| "grad_norm": 0.14015689620247335, | |
| "learning_rate": 1.845718231283281e-05, | |
| "loss": 0.0961, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03217507153749466, | |
| "step": 945, | |
| "valid_targets_mean": 8615.8, | |
| "valid_targets_min": 2228 | |
| }, | |
| { | |
| "epoch": 2.880566801619433, | |
| "grad_norm": 0.12285786855838084, | |
| "learning_rate": 1.8246347887833457e-05, | |
| "loss": 0.0977, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03462362661957741, | |
| "step": 950, | |
| "valid_targets_mean": 8879.0, | |
| "valid_targets_min": 2933 | |
| }, | |
| { | |
| "epoch": 2.895748987854251, | |
| "grad_norm": 0.13301121318388298, | |
| "learning_rate": 1.8035709675139258e-05, | |
| "loss": 0.0976, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03281358629465103, | |
| "step": 955, | |
| "valid_targets_mean": 7664.7, | |
| "valid_targets_min": 2321 | |
| }, | |
| { | |
| "epoch": 2.910931174089069, | |
| "grad_norm": 0.12038376473883386, | |
| "learning_rate": 1.7825291242599837e-05, | |
| "loss": 0.0956, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03123294934630394, | |
| "step": 960, | |
| "valid_targets_mean": 8834.1, | |
| "valid_targets_min": 3211 | |
| }, | |
| { | |
| "epoch": 2.9261133603238867, | |
| "grad_norm": 0.12952163890461427, | |
| "learning_rate": 1.7615116133474084e-05, | |
| "loss": 0.0994, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.037808723747730255, | |
| "step": 965, | |
| "valid_targets_mean": 9780.4, | |
| "valid_targets_min": 5182 | |
| }, | |
| { | |
| "epoch": 2.9412955465587043, | |
| "grad_norm": 0.12428619863573033, | |
| "learning_rate": 1.7405207863795966e-05, | |
| "loss": 0.0961, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.030495252460241318, | |
| "step": 970, | |
| "valid_targets_mean": 8197.4, | |
| "valid_targets_min": 2872 | |
| }, | |
| { | |
| "epoch": 2.9564777327935223, | |
| "grad_norm": 0.11976194308976043, | |
| "learning_rate": 1.719558991974339e-05, | |
| "loss": 0.0954, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.030241120606660843, | |
| "step": 975, | |
| "valid_targets_mean": 8498.5, | |
| "valid_targets_min": 4977 | |
| }, | |
| { | |
| "epoch": 2.97165991902834, | |
| "grad_norm": 0.12482486618035292, | |
| "learning_rate": 1.698628575501034e-05, | |
| "loss": 0.0961, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03207958862185478, | |
| "step": 980, | |
| "valid_targets_mean": 8163.7, | |
| "valid_targets_min": 1612 | |
| }, | |
| { | |
| "epoch": 2.986842105263158, | |
| "grad_norm": 0.12975444599367592, | |
| "learning_rate": 1.6777318788182723e-05, | |
| "loss": 0.0991, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03369869291782379, | |
| "step": 985, | |
| "valid_targets_mean": 8489.5, | |
| "valid_targets_min": 4762 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.20133111246333635, | |
| "learning_rate": 1.6568712400118102e-05, | |
| "loss": 0.0941, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09041516482830048, | |
| "step": 990, | |
| "valid_targets_mean": 7403.2, | |
| "valid_targets_min": 2167 | |
| }, | |
| { | |
| "epoch": 3.0151821862348176, | |
| "grad_norm": 0.1300244124239613, | |
| "learning_rate": 1.636048993132969e-05, | |
| "loss": 0.081, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.028862426057457924, | |
| "step": 995, | |
| "valid_targets_mean": 9343.4, | |
| "valid_targets_min": 2880 | |
| }, | |
| { | |
| "epoch": 3.0303643724696356, | |
| "grad_norm": 0.1538310889509633, | |
| "learning_rate": 1.615267467937479e-05, | |
| "loss": 0.0842, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.023721909150481224, | |
| "step": 1000, | |
| "valid_targets_mean": 7559.3, | |
| "valid_targets_min": 1977 | |
| }, | |
| { | |
| "epoch": 3.0455465587044532, | |
| "grad_norm": 0.13906081901353665, | |
| "learning_rate": 1.59452898962481e-05, | |
| "loss": 0.0809, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02819231152534485, | |
| "step": 1005, | |
| "valid_targets_mean": 8851.3, | |
| "valid_targets_min": 3774 | |
| }, | |
| { | |
| "epoch": 3.0607287449392713, | |
| "grad_norm": 0.12942897167400005, | |
| "learning_rate": 1.573835878578013e-05, | |
| "loss": 0.0813, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.023790959268808365, | |
| "step": 1010, | |
| "valid_targets_mean": 8412.5, | |
| "valid_targets_min": 2458 | |
| }, | |
| { | |
| "epoch": 3.075910931174089, | |
| "grad_norm": 0.13475137131117412, | |
| "learning_rate": 1.5531904501040917e-05, | |
| "loss": 0.0839, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.023328719660639763, | |
| "step": 1015, | |
| "valid_targets_mean": 7928.6, | |
| "valid_targets_min": 3499 | |
| }, | |
| { | |
| "epoch": 3.091093117408907, | |
| "grad_norm": 0.13321912783313525, | |
| "learning_rate": 1.5325950141749522e-05, | |
| "loss": 0.0811, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.029503388330340385, | |
| "step": 1020, | |
| "valid_targets_mean": 8502.7, | |
| "valid_targets_min": 2539 | |
| }, | |
| { | |
| "epoch": 3.1062753036437245, | |
| "grad_norm": 0.146585656738337, | |
| "learning_rate": 1.5120518751689438e-05, | |
| "loss": 0.081, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0265448410063982, | |
| "step": 1025, | |
| "valid_targets_mean": 8719.2, | |
| "valid_targets_min": 2494 | |
| }, | |
| { | |
| "epoch": 3.1214574898785425, | |
| "grad_norm": 0.12998183812048772, | |
| "learning_rate": 1.4915633316130267e-05, | |
| "loss": 0.0817, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.027232753112912178, | |
| "step": 1030, | |
| "valid_targets_mean": 8657.9, | |
| "valid_targets_min": 2668 | |
| }, | |
| { | |
| "epoch": 3.13663967611336, | |
| "grad_norm": 0.13335184812061046, | |
| "learning_rate": 1.4711316759255963e-05, | |
| "loss": 0.0815, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02671901136636734, | |
| "step": 1035, | |
| "valid_targets_mean": 9244.4, | |
| "valid_targets_min": 2863 | |
| }, | |
| { | |
| "epoch": 3.151821862348178, | |
| "grad_norm": 0.12839796075910578, | |
| "learning_rate": 1.450759194159987e-05, | |
| "loss": 0.0834, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03188029304146767, | |
| "step": 1040, | |
| "valid_targets_mean": 9055.3, | |
| "valid_targets_min": 3790 | |
| }, | |
| { | |
| "epoch": 3.167004048582996, | |
| "grad_norm": 0.1390207194630811, | |
| "learning_rate": 1.4304481657486955e-05, | |
| "loss": 0.0807, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02572905644774437, | |
| "step": 1045, | |
| "valid_targets_mean": 7839.9, | |
| "valid_targets_min": 1768 | |
| }, | |
| { | |
| "epoch": 3.182186234817814, | |
| "grad_norm": 0.12862762781860484, | |
| "learning_rate": 1.4102008632483344e-05, | |
| "loss": 0.0798, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02668273262679577, | |
| "step": 1050, | |
| "valid_targets_mean": 8372.1, | |
| "valid_targets_min": 2661 | |
| }, | |
| { | |
| "epoch": 3.1973684210526314, | |
| "grad_norm": 0.12823260099374925, | |
| "learning_rate": 1.3900195520853628e-05, | |
| "loss": 0.0832, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.030231501907110214, | |
| "step": 1055, | |
| "valid_targets_mean": 8906.9, | |
| "valid_targets_min": 3625 | |
| }, | |
| { | |
| "epoch": 3.2125506072874495, | |
| "grad_norm": 0.29000558843717655, | |
| "learning_rate": 1.3699064903026149e-05, | |
| "loss": 0.0824, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02641480602324009, | |
| "step": 1060, | |
| "valid_targets_mean": 8015.9, | |
| "valid_targets_min": 2045 | |
| }, | |
| { | |
| "epoch": 3.227732793522267, | |
| "grad_norm": 0.1370498256148732, | |
| "learning_rate": 1.34986392830665e-05, | |
| "loss": 0.0832, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.029746919870376587, | |
| "step": 1065, | |
| "valid_targets_mean": 9583.9, | |
| "valid_targets_min": 4463 | |
| }, | |
| { | |
| "epoch": 3.242914979757085, | |
| "grad_norm": 0.13136286499156907, | |
| "learning_rate": 1.3298941086159598e-05, | |
| "loss": 0.0804, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.028558827936649323, | |
| "step": 1070, | |
| "valid_targets_mean": 8967.4, | |
| "valid_targets_min": 2770 | |
| }, | |
| { | |
| "epoch": 3.2580971659919027, | |
| "grad_norm": 0.13544354991748672, | |
| "learning_rate": 1.3099992656100592e-05, | |
| "loss": 0.0833, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02712625078856945, | |
| "step": 1075, | |
| "valid_targets_mean": 9149.8, | |
| "valid_targets_min": 2736 | |
| }, | |
| { | |
| "epoch": 3.2732793522267207, | |
| "grad_norm": 0.1222558263782522, | |
| "learning_rate": 1.2901816252794848e-05, | |
| "loss": 0.0818, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.024769514799118042, | |
| "step": 1080, | |
| "valid_targets_mean": 9101.6, | |
| "valid_targets_min": 2473 | |
| }, | |
| { | |
| "epoch": 3.2884615384615383, | |
| "grad_norm": 0.13212043597814715, | |
| "learning_rate": 1.2704434049767356e-05, | |
| "loss": 0.0821, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.026221875101327896, | |
| "step": 1085, | |
| "valid_targets_mean": 7955.2, | |
| "valid_targets_min": 2192 | |
| }, | |
| { | |
| "epoch": 3.3036437246963564, | |
| "grad_norm": 0.1316474708961634, | |
| "learning_rate": 1.250786813168176e-05, | |
| "loss": 0.0833, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02585676684975624, | |
| "step": 1090, | |
| "valid_targets_mean": 8742.9, | |
| "valid_targets_min": 3075 | |
| }, | |
| { | |
| "epoch": 3.318825910931174, | |
| "grad_norm": 0.12810221668010108, | |
| "learning_rate": 1.2312140491869369e-05, | |
| "loss": 0.0848, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02804689295589924, | |
| "step": 1095, | |
| "valid_targets_mean": 9302.1, | |
| "valid_targets_min": 4611 | |
| }, | |
| { | |
| "epoch": 3.334008097165992, | |
| "grad_norm": 0.13098236805241345, | |
| "learning_rate": 1.2117273029868362e-05, | |
| "loss": 0.0805, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.025178449228405952, | |
| "step": 1100, | |
| "valid_targets_mean": 8410.0, | |
| "valid_targets_min": 2450 | |
| }, | |
| { | |
| "epoch": 3.3491902834008096, | |
| "grad_norm": 0.1326607067521302, | |
| "learning_rate": 1.1923287548973508e-05, | |
| "loss": 0.0823, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.025255359709262848, | |
| "step": 1105, | |
| "valid_targets_mean": 8941.5, | |
| "valid_targets_min": 6188 | |
| }, | |
| { | |
| "epoch": 3.3643724696356276, | |
| "grad_norm": 0.12805334419406478, | |
| "learning_rate": 1.1730205753796631e-05, | |
| "loss": 0.0833, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.027310512959957123, | |
| "step": 1110, | |
| "valid_targets_mean": 8349.2, | |
| "valid_targets_min": 2542 | |
| }, | |
| { | |
| "epoch": 3.3795546558704452, | |
| "grad_norm": 0.13306508321385133, | |
| "learning_rate": 1.1538049247838128e-05, | |
| "loss": 0.0813, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.028750218451023102, | |
| "step": 1115, | |
| "valid_targets_mean": 8993.6, | |
| "valid_targets_min": 2089 | |
| }, | |
| { | |
| "epoch": 3.3947368421052633, | |
| "grad_norm": 0.12348095383967343, | |
| "learning_rate": 1.134683953106983e-05, | |
| "loss": 0.0821, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02757805585861206, | |
| "step": 1120, | |
| "valid_targets_mean": 8663.5, | |
| "valid_targets_min": 2464 | |
| }, | |
| { | |
| "epoch": 3.409919028340081, | |
| "grad_norm": 0.12338003520827763, | |
| "learning_rate": 1.115659799752938e-05, | |
| "loss": 0.0809, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.024909667670726776, | |
| "step": 1125, | |
| "valid_targets_mean": 8722.2, | |
| "valid_targets_min": 1867 | |
| }, | |
| { | |
| "epoch": 3.425101214574899, | |
| "grad_norm": 0.12888592392390283, | |
| "learning_rate": 1.096734593292649e-05, | |
| "loss": 0.0817, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.027744624763727188, | |
| "step": 1130, | |
| "valid_targets_mean": 8955.2, | |
| "valid_targets_min": 4418 | |
| }, | |
| { | |
| "epoch": 3.4402834008097165, | |
| "grad_norm": 0.13401015211965453, | |
| "learning_rate": 1.077910451226138e-05, | |
| "loss": 0.0813, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.026715070009231567, | |
| "step": 1135, | |
| "valid_targets_mean": 8360.8, | |
| "valid_targets_min": 5281 | |
| }, | |
| { | |
| "epoch": 3.4554655870445345, | |
| "grad_norm": 0.1318082901846397, | |
| "learning_rate": 1.0591894797455526e-05, | |
| "loss": 0.0827, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.029033245518803596, | |
| "step": 1140, | |
| "valid_targets_mean": 8621.5, | |
| "valid_targets_min": 2575 | |
| }, | |
| { | |
| "epoch": 3.470647773279352, | |
| "grad_norm": 0.13213929885112138, | |
| "learning_rate": 1.0405737734995083e-05, | |
| "loss": 0.0828, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.031862929463386536, | |
| "step": 1145, | |
| "valid_targets_mean": 9804.8, | |
| "valid_targets_min": 2900 | |
| }, | |
| { | |
| "epoch": 3.48582995951417, | |
| "grad_norm": 0.12596722864815074, | |
| "learning_rate": 1.0220654153587225e-05, | |
| "loss": 0.082, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.026434356346726418, | |
| "step": 1150, | |
| "valid_targets_mean": 7724.9, | |
| "valid_targets_min": 1413 | |
| }, | |
| { | |
| "epoch": 3.501012145748988, | |
| "grad_norm": 0.1389136918376163, | |
| "learning_rate": 1.00366647618297e-05, | |
| "loss": 0.0832, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02750595659017563, | |
| "step": 1155, | |
| "valid_targets_mean": 8750.5, | |
| "valid_targets_min": 2994 | |
| }, | |
| { | |
| "epoch": 3.516194331983806, | |
| "grad_norm": 0.12959392476712628, | |
| "learning_rate": 9.853790145893742e-06, | |
| "loss": 0.0813, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02605414390563965, | |
| "step": 1160, | |
| "valid_targets_mean": 7632.8, | |
| "valid_targets_min": 1732 | |
| }, | |
| { | |
| "epoch": 3.5313765182186234, | |
| "grad_norm": 0.12341492655450281, | |
| "learning_rate": 9.672050767220765e-06, | |
| "loss": 0.0816, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.026276612654328346, | |
| "step": 1165, | |
| "valid_targets_mean": 8952.3, | |
| "valid_targets_min": 3359 | |
| }, | |
| { | |
| "epoch": 3.5465587044534415, | |
| "grad_norm": 0.12840346588638937, | |
| "learning_rate": 9.491466960232955e-06, | |
| "loss": 0.0817, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02403266541659832, | |
| "step": 1170, | |
| "valid_targets_mean": 8608.6, | |
| "valid_targets_min": 1811 | |
| }, | |
| { | |
| "epoch": 3.561740890688259, | |
| "grad_norm": 0.1401985965853516, | |
| "learning_rate": 9.312058930058114e-06, | |
| "loss": 0.0811, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02798900008201599, | |
| "step": 1175, | |
| "valid_targets_mean": 9429.9, | |
| "valid_targets_min": 3328 | |
| }, | |
| { | |
| "epoch": 3.5769230769230766, | |
| "grad_norm": 0.13280286908859026, | |
| "learning_rate": 9.133846750268945e-06, | |
| "loss": 0.0814, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02968199923634529, | |
| "step": 1180, | |
| "valid_targets_mean": 8732.2, | |
| "valid_targets_min": 2608 | |
| }, | |
| { | |
| "epoch": 3.5921052631578947, | |
| "grad_norm": 0.1266760167047694, | |
| "learning_rate": 8.956850360637046e-06, | |
| "loss": 0.083, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.03358772024512291, | |
| "step": 1185, | |
| "valid_targets_mean": 9538.2, | |
| "valid_targets_min": 2406 | |
| }, | |
| { | |
| "epoch": 3.6072874493927127, | |
| "grad_norm": 0.12687247552934675, | |
| "learning_rate": 8.78108956490194e-06, | |
| "loss": 0.081, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02509346976876259, | |
| "step": 1190, | |
| "valid_targets_mean": 8739.5, | |
| "valid_targets_min": 1539 | |
| }, | |
| { | |
| "epoch": 3.6224696356275303, | |
| "grad_norm": 0.12618888486441393, | |
| "learning_rate": 8.606584028555225e-06, | |
| "loss": 0.0821, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.028923707082867622, | |
| "step": 1195, | |
| "valid_targets_mean": 9431.6, | |
| "valid_targets_min": 1946 | |
| }, | |
| { | |
| "epoch": 3.637651821862348, | |
| "grad_norm": 0.13482723975285665, | |
| "learning_rate": 8.43335327664027e-06, | |
| "loss": 0.0822, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.025941604748368263, | |
| "step": 1200, | |
| "valid_targets_mean": 7870.4, | |
| "valid_targets_min": 797 | |
| }, | |
| { | |
| "epoch": 3.652834008097166, | |
| "grad_norm": 0.12698290001191898, | |
| "learning_rate": 8.261416691567601e-06, | |
| "loss": 0.0707, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.025689968839287758, | |
| "step": 1205, | |
| "valid_targets_mean": 9460.3, | |
| "valid_targets_min": 3977 | |
| }, | |
| { | |
| "epoch": 3.668016194331984, | |
| "grad_norm": 0.14171272362247936, | |
| "learning_rate": 8.090793510946242e-06, | |
| "loss": 0.073, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.027664491906762123, | |
| "step": 1210, | |
| "valid_targets_mean": 8020.6, | |
| "valid_targets_min": 1960 | |
| }, | |
| { | |
| "epoch": 3.6831983805668016, | |
| "grad_norm": 0.14283152121441356, | |
| "learning_rate": 7.921502825431258e-06, | |
| "loss": 0.0716, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02449328824877739, | |
| "step": 1215, | |
| "valid_targets_mean": 9014.6, | |
| "valid_targets_min": 2130 | |
| }, | |
| { | |
| "epoch": 3.698380566801619, | |
| "grad_norm": 0.13468840342691632, | |
| "learning_rate": 7.753563576587753e-06, | |
| "loss": 0.0716, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.021551329642534256, | |
| "step": 1220, | |
| "valid_targets_mean": 7745.8, | |
| "valid_targets_min": 2111 | |
| }, | |
| { | |
| "epoch": 3.7135627530364372, | |
| "grad_norm": 0.14091468195954504, | |
| "learning_rate": 7.5869945547715275e-06, | |
| "loss": 0.0685, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.023892266675829887, | |
| "step": 1225, | |
| "valid_targets_mean": 8852.4, | |
| "valid_targets_min": 1383 | |
| }, | |
| { | |
| "epoch": 3.7287449392712553, | |
| "grad_norm": 0.1336308106351021, | |
| "learning_rate": 7.421814397026674e-06, | |
| "loss": 0.072, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.027202630415558815, | |
| "step": 1230, | |
| "valid_targets_mean": 9674.4, | |
| "valid_targets_min": 2998 | |
| }, | |
| { | |
| "epoch": 3.743927125506073, | |
| "grad_norm": 0.3419847246433934, | |
| "learning_rate": 7.258041585000317e-06, | |
| "loss": 0.0711, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.023032916709780693, | |
| "step": 1235, | |
| "valid_targets_mean": 8254.4, | |
| "valid_targets_min": 1946 | |
| }, | |
| { | |
| "epoch": 3.7591093117408905, | |
| "grad_norm": 0.1271858026184254, | |
| "learning_rate": 7.095694442874743e-06, | |
| "loss": 0.0717, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.022182870656251907, | |
| "step": 1240, | |
| "valid_targets_mean": 8235.9, | |
| "valid_targets_min": 2508 | |
| }, | |
| { | |
| "epoch": 3.7742914979757085, | |
| "grad_norm": 0.12838477659363734, | |
| "learning_rate": 6.934791135317147e-06, | |
| "loss": 0.0716, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.023270966485142708, | |
| "step": 1245, | |
| "valid_targets_mean": 8814.3, | |
| "valid_targets_min": 1743 | |
| }, | |
| { | |
| "epoch": 3.7894736842105265, | |
| "grad_norm": 0.13866652515206368, | |
| "learning_rate": 6.775349665447222e-06, | |
| "loss": 0.0709, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.022962071001529694, | |
| "step": 1250, | |
| "valid_targets_mean": 8595.0, | |
| "valid_targets_min": 3204 | |
| }, | |
| { | |
| "epoch": 3.804655870445344, | |
| "grad_norm": 0.1331118423089432, | |
| "learning_rate": 6.617387872822842e-06, | |
| "loss": 0.0708, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.025417642667889595, | |
| "step": 1255, | |
| "valid_targets_mean": 9996.3, | |
| "valid_targets_min": 2078 | |
| }, | |
| { | |
| "epoch": 3.8198380566801617, | |
| "grad_norm": 0.13411954457432299, | |
| "learning_rate": 6.460923431444015e-06, | |
| "loss": 0.0726, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.027501918375492096, | |
| "step": 1260, | |
| "valid_targets_mean": 8771.0, | |
| "valid_targets_min": 952 | |
| }, | |
| { | |
| "epoch": 3.83502024291498, | |
| "grad_norm": 0.13593796688612503, | |
| "learning_rate": 6.305973847775406e-06, | |
| "loss": 0.0701, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02605874091386795, | |
| "step": 1265, | |
| "valid_targets_mean": 9703.9, | |
| "valid_targets_min": 5437 | |
| }, | |
| { | |
| "epoch": 3.850202429149798, | |
| "grad_norm": 0.133099629748515, | |
| "learning_rate": 6.152556458787546e-06, | |
| "loss": 0.0721, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.024866309016942978, | |
| "step": 1270, | |
| "valid_targets_mean": 8803.2, | |
| "valid_targets_min": 3976 | |
| }, | |
| { | |
| "epoch": 3.8653846153846154, | |
| "grad_norm": 0.12707113727086652, | |
| "learning_rate": 6.000688430017048e-06, | |
| "loss": 0.0712, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.019301123917102814, | |
| "step": 1275, | |
| "valid_targets_mean": 7695.8, | |
| "valid_targets_min": 1998 | |
| }, | |
| { | |
| "epoch": 3.880566801619433, | |
| "grad_norm": 0.13012400460527512, | |
| "learning_rate": 5.850386753645998e-06, | |
| "loss": 0.0723, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.023172810673713684, | |
| "step": 1280, | |
| "valid_targets_mean": 8560.0, | |
| "valid_targets_min": 3349 | |
| }, | |
| { | |
| "epoch": 3.895748987854251, | |
| "grad_norm": 0.1363927958365897, | |
| "learning_rate": 5.701668246600731e-06, | |
| "loss": 0.07, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02273355983197689, | |
| "step": 1285, | |
| "valid_targets_mean": 8933.8, | |
| "valid_targets_min": 4202 | |
| }, | |
| { | |
| "epoch": 3.910931174089069, | |
| "grad_norm": 0.12311678132240385, | |
| "learning_rate": 5.554549548670227e-06, | |
| "loss": 0.072, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.024375557899475098, | |
| "step": 1290, | |
| "valid_targets_mean": 9392.7, | |
| "valid_targets_min": 4608 | |
| }, | |
| { | |
| "epoch": 3.9261133603238867, | |
| "grad_norm": 0.12687704957090615, | |
| "learning_rate": 5.409047120644307e-06, | |
| "loss": 0.0731, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.024769635871052742, | |
| "step": 1295, | |
| "valid_targets_mean": 9501.2, | |
| "valid_targets_min": 3889 | |
| }, | |
| { | |
| "epoch": 3.9412955465587043, | |
| "grad_norm": 0.13137510015605056, | |
| "learning_rate": 5.265177242471899e-06, | |
| "loss": 0.0716, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.023807276040315628, | |
| "step": 1300, | |
| "valid_targets_mean": 8548.6, | |
| "valid_targets_min": 2683 | |
| }, | |
| { | |
| "epoch": 3.9564777327935223, | |
| "grad_norm": 0.1352307145477781, | |
| "learning_rate": 5.122956011439486e-06, | |
| "loss": 0.0707, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.024619711562991142, | |
| "step": 1305, | |
| "valid_targets_mean": 8206.3, | |
| "valid_targets_min": 3121 | |
| }, | |
| { | |
| "epoch": 3.97165991902834, | |
| "grad_norm": 0.12849479293972313, | |
| "learning_rate": 4.982399340370017e-06, | |
| "loss": 0.0699, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02672148123383522, | |
| "step": 1310, | |
| "valid_targets_mean": 9368.8, | |
| "valid_targets_min": 2512 | |
| }, | |
| { | |
| "epoch": 3.986842105263158, | |
| "grad_norm": 0.12305779287697138, | |
| "learning_rate": 4.843522955842464e-06, | |
| "loss": 0.0725, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.022504793480038643, | |
| "step": 1315, | |
| "valid_targets_mean": 8683.1, | |
| "valid_targets_min": 2766 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.2100666782226991, | |
| "learning_rate": 4.706342396432213e-06, | |
| "loss": 0.0694, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.06145584210753441, | |
| "step": 1320, | |
| "valid_targets_mean": 8881.3, | |
| "valid_targets_min": 4218 | |
| }, | |
| { | |
| "epoch": 4.015182186234818, | |
| "grad_norm": 0.12856176805274305, | |
| "learning_rate": 4.570873010972477e-06, | |
| "loss": 0.0705, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0246361643075943, | |
| "step": 1325, | |
| "valid_targets_mean": 8659.3, | |
| "valid_targets_min": 4154 | |
| }, | |
| { | |
| "epoch": 4.030364372469635, | |
| "grad_norm": 0.13479861320087932, | |
| "learning_rate": 4.43712995683695e-06, | |
| "loss": 0.0725, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.027057047933340073, | |
| "step": 1330, | |
| "valid_targets_mean": 9499.3, | |
| "valid_targets_min": 4445 | |
| }, | |
| { | |
| "epoch": 4.045546558704453, | |
| "grad_norm": 0.12791517088829324, | |
| "learning_rate": 4.305128198243888e-06, | |
| "loss": 0.0714, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.022519756108522415, | |
| "step": 1335, | |
| "valid_targets_mean": 8525.4, | |
| "valid_targets_min": 3169 | |
| }, | |
| { | |
| "epoch": 4.060728744939271, | |
| "grad_norm": 0.13586667741133668, | |
| "learning_rate": 4.174882504581794e-06, | |
| "loss": 0.0715, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.022522293031215668, | |
| "step": 1340, | |
| "valid_targets_mean": 8128.8, | |
| "valid_targets_min": 1333 | |
| }, | |
| { | |
| "epoch": 4.075910931174089, | |
| "grad_norm": 0.13932759618587662, | |
| "learning_rate": 4.046407448756895e-06, | |
| "loss": 0.0733, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.030038908123970032, | |
| "step": 1345, | |
| "valid_targets_mean": 9147.9, | |
| "valid_targets_min": 2614 | |
| }, | |
| { | |
| "epoch": 4.0910931174089065, | |
| "grad_norm": 0.12873419394480645, | |
| "learning_rate": 3.91971740556262e-06, | |
| "loss": 0.072, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.025359926745295525, | |
| "step": 1350, | |
| "valid_targets_mean": 8476.8, | |
| "valid_targets_min": 2352 | |
| }, | |
| { | |
| "epoch": 4.1062753036437245, | |
| "grad_norm": 0.13545844466456364, | |
| "learning_rate": 3.7948265500712313e-06, | |
| "loss": 0.0729, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.024534335359930992, | |
| "step": 1355, | |
| "valid_targets_mean": 8737.6, | |
| "valid_targets_min": 2696 | |
| }, | |
| { | |
| "epoch": 4.1214574898785425, | |
| "grad_norm": 0.13069037608409761, | |
| "learning_rate": 3.6717488560478096e-06, | |
| "loss": 0.0739, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02294790744781494, | |
| "step": 1360, | |
| "valid_targets_mean": 8396.7, | |
| "valid_targets_min": 3006 | |
| }, | |
| { | |
| "epoch": 4.136639676113361, | |
| "grad_norm": 0.12579564556896974, | |
| "learning_rate": 3.5504980943867538e-06, | |
| "loss": 0.0701, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.020472146570682526, | |
| "step": 1365, | |
| "valid_targets_mean": 8974.2, | |
| "valid_targets_min": 3112 | |
| }, | |
| { | |
| "epoch": 4.151821862348178, | |
| "grad_norm": 0.13203124092382884, | |
| "learning_rate": 3.4310878315710074e-06, | |
| "loss": 0.0717, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02415456995368004, | |
| "step": 1370, | |
| "valid_targets_mean": 8521.4, | |
| "valid_targets_min": 1976 | |
| }, | |
| { | |
| "epoch": 4.167004048582996, | |
| "grad_norm": 0.12918264236234311, | |
| "learning_rate": 3.3135314281540954e-06, | |
| "loss": 0.07, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.024327686056494713, | |
| "step": 1375, | |
| "valid_targets_mean": 9189.1, | |
| "valid_targets_min": 5070 | |
| }, | |
| { | |
| "epoch": 4.182186234817814, | |
| "grad_norm": 0.13498726555461582, | |
| "learning_rate": 3.1978420372652776e-06, | |
| "loss": 0.0721, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02382536232471466, | |
| "step": 1380, | |
| "valid_targets_mean": 8467.6, | |
| "valid_targets_min": 1311 | |
| }, | |
| { | |
| "epoch": 4.197368421052632, | |
| "grad_norm": 0.13267822043050173, | |
| "learning_rate": 3.084032603137852e-06, | |
| "loss": 0.072, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0245407335460186, | |
| "step": 1385, | |
| "valid_targets_mean": 8739.2, | |
| "valid_targets_min": 4972 | |
| }, | |
| { | |
| "epoch": 4.212550607287449, | |
| "grad_norm": 0.13115184441298627, | |
| "learning_rate": 2.9721158596608622e-06, | |
| "loss": 0.0716, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02315356209874153, | |
| "step": 1390, | |
| "valid_targets_mean": 9052.2, | |
| "valid_targets_min": 1302 | |
| }, | |
| { | |
| "epoch": 4.227732793522267, | |
| "grad_norm": 0.13222968931245252, | |
| "learning_rate": 2.8621043289543314e-06, | |
| "loss": 0.073, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.026675129309296608, | |
| "step": 1395, | |
| "valid_targets_mean": 9368.6, | |
| "valid_targets_min": 1316 | |
| }, | |
| { | |
| "epoch": 4.242914979757085, | |
| "grad_norm": 0.13398665695635495, | |
| "learning_rate": 2.754010319968181e-06, | |
| "loss": 0.073, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02559933066368103, | |
| "step": 1400, | |
| "valid_targets_mean": 8597.0, | |
| "valid_targets_min": 1219 | |
| }, | |
| { | |
| "epoch": 4.258097165991903, | |
| "grad_norm": 0.12399177498556249, | |
| "learning_rate": 2.647845927105015e-06, | |
| "loss": 0.0717, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.026551511138677597, | |
| "step": 1405, | |
| "valid_targets_mean": 9392.8, | |
| "valid_targets_min": 3799 | |
| }, | |
| { | |
| "epoch": 4.27327935222672, | |
| "grad_norm": 0.12550426965554587, | |
| "learning_rate": 2.543623028866915e-06, | |
| "loss": 0.0718, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.023046307265758514, | |
| "step": 1410, | |
| "valid_targets_mean": 8547.8, | |
| "valid_targets_min": 3952 | |
| }, | |
| { | |
| "epoch": 4.288461538461538, | |
| "grad_norm": 0.1278560738811349, | |
| "learning_rate": 2.4413532865263533e-06, | |
| "loss": 0.072, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.024781126528978348, | |
| "step": 1415, | |
| "valid_targets_mean": 9005.2, | |
| "valid_targets_min": 2636 | |
| }, | |
| { | |
| "epoch": 4.303643724696356, | |
| "grad_norm": 0.1245128472681352, | |
| "learning_rate": 2.3410481428214602e-06, | |
| "loss": 0.0707, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.026396561414003372, | |
| "step": 1420, | |
| "valid_targets_mean": 8887.3, | |
| "valid_targets_min": 2725 | |
| }, | |
| { | |
| "epoch": 4.318825910931174, | |
| "grad_norm": 0.12744289391808303, | |
| "learning_rate": 2.242718820675718e-06, | |
| "loss": 0.0713, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02669454738497734, | |
| "step": 1425, | |
| "valid_targets_mean": 9474.6, | |
| "valid_targets_min": 1683 | |
| }, | |
| { | |
| "epoch": 4.334008097165992, | |
| "grad_norm": 0.12657620323873767, | |
| "learning_rate": 2.1463763219422495e-06, | |
| "loss": 0.0731, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0257745161652565, | |
| "step": 1430, | |
| "valid_targets_mean": 8637.2, | |
| "valid_targets_min": 2038 | |
| }, | |
| { | |
| "epoch": 4.34919028340081, | |
| "grad_norm": 0.1366020490148325, | |
| "learning_rate": 2.0520314261728357e-06, | |
| "loss": 0.0735, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02611927129328251, | |
| "step": 1435, | |
| "valid_targets_mean": 8192.0, | |
| "valid_targets_min": 2257 | |
| }, | |
| { | |
| "epoch": 4.364372469635628, | |
| "grad_norm": 0.131237059398244, | |
| "learning_rate": 1.9596946894118306e-06, | |
| "loss": 0.071, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.01905817724764347, | |
| "step": 1440, | |
| "valid_targets_mean": 7382.0, | |
| "valid_targets_min": 1700 | |
| }, | |
| { | |
| "epoch": 4.379554655870446, | |
| "grad_norm": 0.12605322401744387, | |
| "learning_rate": 1.8693764430150696e-06, | |
| "loss": 0.0724, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.027004193514585495, | |
| "step": 1445, | |
| "valid_targets_mean": 8745.8, | |
| "valid_targets_min": 2841 | |
| }, | |
| { | |
| "epoch": 4.394736842105263, | |
| "grad_norm": 0.12554630307236384, | |
| "learning_rate": 1.7810867924938978e-06, | |
| "loss": 0.0721, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02082369476556778, | |
| "step": 1450, | |
| "valid_targets_mean": 8288.6, | |
| "valid_targets_min": 2254 | |
| }, | |
| { | |
| "epoch": 4.409919028340081, | |
| "grad_norm": 0.12395828958901728, | |
| "learning_rate": 1.6948356163845048e-06, | |
| "loss": 0.0727, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.025294356048107147, | |
| "step": 1455, | |
| "valid_targets_mean": 9465.1, | |
| "valid_targets_min": 3617 | |
| }, | |
| { | |
| "epoch": 4.425101214574899, | |
| "grad_norm": 0.12975788177308706, | |
| "learning_rate": 1.610632565142627e-06, | |
| "loss": 0.0725, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.025481922551989555, | |
| "step": 1460, | |
| "valid_targets_mean": 8532.7, | |
| "valid_targets_min": 2906 | |
| }, | |
| { | |
| "epoch": 4.440283400809717, | |
| "grad_norm": 0.1308679306751898, | |
| "learning_rate": 1.5284870600637813e-06, | |
| "loss": 0.0708, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.025269974023103714, | |
| "step": 1465, | |
| "valid_targets_mean": 8441.8, | |
| "valid_targets_min": 2005 | |
| }, | |
| { | |
| "epoch": 4.455465587044534, | |
| "grad_norm": 0.1265218507421822, | |
| "learning_rate": 1.4484082922291376e-06, | |
| "loss": 0.0722, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.022256912663578987, | |
| "step": 1470, | |
| "valid_targets_mean": 8762.0, | |
| "valid_targets_min": 2716 | |
| }, | |
| { | |
| "epoch": 4.470647773279352, | |
| "grad_norm": 0.12265741949311111, | |
| "learning_rate": 1.3704052214771513e-06, | |
| "loss": 0.0714, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.021536782383918762, | |
| "step": 1475, | |
| "valid_targets_mean": 8773.9, | |
| "valid_targets_min": 2646 | |
| }, | |
| { | |
| "epoch": 4.48582995951417, | |
| "grad_norm": 0.12666571179500055, | |
| "learning_rate": 1.2944865754010682e-06, | |
| "loss": 0.0722, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02351006679236889, | |
| "step": 1480, | |
| "valid_targets_mean": 8156.3, | |
| "valid_targets_min": 2213 | |
| }, | |
| { | |
| "epoch": 4.501012145748988, | |
| "grad_norm": 0.13593735929884912, | |
| "learning_rate": 1.2206608483724013e-06, | |
| "loss": 0.0714, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0233116764575243, | |
| "step": 1485, | |
| "valid_targets_mean": 8738.2, | |
| "valid_targets_min": 2078 | |
| }, | |
| { | |
| "epoch": 4.516194331983805, | |
| "grad_norm": 0.12418680882420231, | |
| "learning_rate": 1.1489363005905241e-06, | |
| "loss": 0.0718, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.022058848291635513, | |
| "step": 1490, | |
| "valid_targets_mean": 8502.8, | |
| "valid_targets_min": 1574 | |
| }, | |
| { | |
| "epoch": 4.531376518218623, | |
| "grad_norm": 0.13085570988549858, | |
| "learning_rate": 1.0793209571584562e-06, | |
| "loss": 0.073, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.022707901895046234, | |
| "step": 1495, | |
| "valid_targets_mean": 9104.2, | |
| "valid_targets_min": 2926 | |
| }, | |
| { | |
| "epoch": 4.5465587044534415, | |
| "grad_norm": 0.12140580846634531, | |
| "learning_rate": 1.0118226071849424e-06, | |
| "loss": 0.0717, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02317274548113346, | |
| "step": 1500, | |
| "valid_targets_mean": 9152.1, | |
| "valid_targets_min": 4467 | |
| }, | |
| { | |
| "epoch": 4.5617408906882595, | |
| "grad_norm": 0.1254411918279589, | |
| "learning_rate": 9.464488029129581e-07, | |
| "loss": 0.0722, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.026645243167877197, | |
| "step": 1505, | |
| "valid_targets_mean": 8585.3, | |
| "valid_targets_min": 2815 | |
| }, | |
| { | |
| "epoch": 4.576923076923077, | |
| "grad_norm": 0.1264429352134972, | |
| "learning_rate": 8.832068588746945e-07, | |
| "loss": 0.0725, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02284093201160431, | |
| "step": 1510, | |
| "valid_targets_mean": 8010.6, | |
| "valid_targets_min": 2141 | |
| }, | |
| { | |
| "epoch": 4.592105263157895, | |
| "grad_norm": 0.12926976250810449, | |
| "learning_rate": 8.221038510731704e-07, | |
| "loss": 0.0714, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.022103577852249146, | |
| "step": 1515, | |
| "valid_targets_mean": 8595.7, | |
| "valid_targets_min": 4041 | |
| }, | |
| { | |
| "epoch": 4.607287449392713, | |
| "grad_norm": 0.1288565994256354, | |
| "learning_rate": 7.631466161904821e-07, | |
| "loss": 0.0738, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.023180749267339706, | |
| "step": 1520, | |
| "valid_targets_mean": 8275.9, | |
| "valid_targets_min": 2662 | |
| }, | |
| { | |
| "epoch": 4.62246963562753, | |
| "grad_norm": 0.12711807371997574, | |
| "learning_rate": 7.063417508228876e-07, | |
| "loss": 0.0706, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.021609291434288025, | |
| "step": 1525, | |
| "valid_targets_mean": 8159.9, | |
| "valid_targets_min": 3255 | |
| }, | |
| { | |
| "epoch": 4.637651821862348, | |
| "grad_norm": 0.12661608320296658, | |
| "learning_rate": 6.516956107427241e-07, | |
| "loss": 0.0725, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.022947082296013832, | |
| "step": 1530, | |
| "valid_targets_mean": 8213.2, | |
| "valid_targets_min": 1555 | |
| }, | |
| { | |
| "epoch": 4.652834008097166, | |
| "grad_norm": 0.1194308714070705, | |
| "learning_rate": 5.992143101872638e-07, | |
| "loss": 0.0715, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.023615509271621704, | |
| "step": 1535, | |
| "valid_targets_mean": 9385.9, | |
| "valid_targets_min": 3903 | |
| }, | |
| { | |
| "epoch": 4.668016194331984, | |
| "grad_norm": 0.13346540976580576, | |
| "learning_rate": 5.489037211746184e-07, | |
| "loss": 0.0722, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.020034413784742355, | |
| "step": 1540, | |
| "valid_targets_mean": 8017.1, | |
| "valid_targets_min": 2164 | |
| }, | |
| { | |
| "epoch": 4.683198380566802, | |
| "grad_norm": 0.12936052277695234, | |
| "learning_rate": 5.007694728467228e-07, | |
| "loss": 0.0742, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.025388283655047417, | |
| "step": 1545, | |
| "valid_targets_mean": 9148.4, | |
| "valid_targets_min": 2683 | |
| }, | |
| { | |
| "epoch": 4.698380566801619, | |
| "grad_norm": 0.12695562404078126, | |
| "learning_rate": 4.548169508395028e-07, | |
| "loss": 0.0715, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.020865799859166145, | |
| "step": 1550, | |
| "valid_targets_mean": 7729.2, | |
| "valid_targets_min": 2551 | |
| }, | |
| { | |
| "epoch": 4.713562753036437, | |
| "grad_norm": 0.12741751888125938, | |
| "learning_rate": 4.1105129668029595e-07, | |
| "loss": 0.0713, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.028738906607031822, | |
| "step": 1555, | |
| "valid_targets_mean": 9254.6, | |
| "valid_targets_min": 3327 | |
| }, | |
| { | |
| "epoch": 4.728744939271255, | |
| "grad_norm": 0.13573266225420322, | |
| "learning_rate": 3.6947740721257066e-07, | |
| "loss": 0.0728, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02248196490108967, | |
| "step": 1560, | |
| "valid_targets_mean": 8169.5, | |
| "valid_targets_min": 4188 | |
| }, | |
| { | |
| "epoch": 4.743927125506072, | |
| "grad_norm": 0.12660404161193903, | |
| "learning_rate": 3.3009993404802486e-07, | |
| "loss": 0.0716, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02639317885041237, | |
| "step": 1565, | |
| "valid_targets_mean": 9472.7, | |
| "valid_targets_min": 2863 | |
| }, | |
| { | |
| "epoch": 4.7591093117408905, | |
| "grad_norm": 0.1252730277763274, | |
| "learning_rate": 2.929232830461404e-07, | |
| "loss": 0.0699, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02120678685605526, | |
| "step": 1570, | |
| "valid_targets_mean": 8510.4, | |
| "valid_targets_min": 2062 | |
| }, | |
| { | |
| "epoch": 4.7742914979757085, | |
| "grad_norm": 0.12237800537919756, | |
| "learning_rate": 2.579516138212101e-07, | |
| "loss": 0.0719, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02240080013871193, | |
| "step": 1575, | |
| "valid_targets_mean": 9388.8, | |
| "valid_targets_min": 5430 | |
| }, | |
| { | |
| "epoch": 4.7894736842105265, | |
| "grad_norm": 0.12178956138357477, | |
| "learning_rate": 2.2518883927692857e-07, | |
| "loss": 0.0716, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02241118624806404, | |
| "step": 1580, | |
| "valid_targets_mean": 8235.3, | |
| "valid_targets_min": 3600 | |
| }, | |
| { | |
| "epoch": 4.804655870445345, | |
| "grad_norm": 0.13158926499890516, | |
| "learning_rate": 1.9463862516859277e-07, | |
| "loss": 0.0707, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.025818781927227974, | |
| "step": 1585, | |
| "valid_targets_mean": 8914.3, | |
| "valid_targets_min": 2429 | |
| }, | |
| { | |
| "epoch": 4.819838056680162, | |
| "grad_norm": 0.1265169786496303, | |
| "learning_rate": 1.6630438969294615e-07, | |
| "loss": 0.0727, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.028851158916950226, | |
| "step": 1590, | |
| "valid_targets_mean": 8687.8, | |
| "valid_targets_min": 2578 | |
| }, | |
| { | |
| "epoch": 4.83502024291498, | |
| "grad_norm": 0.13041199237094378, | |
| "learning_rate": 1.4018930310571553e-07, | |
| "loss": 0.0732, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.025533903390169144, | |
| "step": 1595, | |
| "valid_targets_mean": 9375.7, | |
| "valid_targets_min": 3546 | |
| }, | |
| { | |
| "epoch": 4.850202429149798, | |
| "grad_norm": 0.12530012860057868, | |
| "learning_rate": 1.1629628736690824e-07, | |
| "loss": 0.0726, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.022670645266771317, | |
| "step": 1600, | |
| "valid_targets_mean": 9248.8, | |
| "valid_targets_min": 2347 | |
| }, | |
| { | |
| "epoch": 4.865384615384615, | |
| "grad_norm": 0.12113310987540254, | |
| "learning_rate": 9.46280158138757e-08, | |
| "loss": 0.0712, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.025158431380987167, | |
| "step": 1605, | |
| "valid_targets_mean": 9779.1, | |
| "valid_targets_min": 4292 | |
| }, | |
| { | |
| "epoch": 4.880566801619433, | |
| "grad_norm": 0.12098660135329019, | |
| "learning_rate": 7.518691286220625e-08, | |
| "loss": 0.0724, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.027931446209549904, | |
| "step": 1610, | |
| "valid_targets_mean": 9244.1, | |
| "valid_targets_min": 2925 | |
| }, | |
| { | |
| "epoch": 4.895748987854251, | |
| "grad_norm": 0.1210606979114355, | |
| "learning_rate": 5.797515373445084e-08, | |
| "loss": 0.0704, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.025138217955827713, | |
| "step": 1615, | |
| "valid_targets_mean": 9484.2, | |
| "valid_targets_min": 2717 | |
| }, | |
| { | |
| "epoch": 4.910931174089069, | |
| "grad_norm": 0.1234360894494375, | |
| "learning_rate": 4.299466421675113e-08, | |
| "loss": 0.0688, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.023699194192886353, | |
| "step": 1620, | |
| "valid_targets_mean": 8797.8, | |
| "valid_targets_min": 3872 | |
| }, | |
| { | |
| "epoch": 4.926113360323887, | |
| "grad_norm": 0.1262637958671771, | |
| "learning_rate": 3.0247120443362976e-08, | |
| "loss": 0.0734, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.028194915503263474, | |
| "step": 1625, | |
| "valid_targets_mean": 9223.1, | |
| "valid_targets_min": 3599 | |
| }, | |
| { | |
| "epoch": 4.941295546558704, | |
| "grad_norm": 0.12122303749027276, | |
| "learning_rate": 1.973394870912193e-08, | |
| "loss": 0.0722, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.024861667305231094, | |
| "step": 1630, | |
| "valid_targets_mean": 9132.6, | |
| "valid_targets_min": 1977 | |
| }, | |
| { | |
| "epoch": 4.956477732793522, | |
| "grad_norm": 0.1286610374430596, | |
| "learning_rate": 1.145632530985541e-08, | |
| "loss": 0.0724, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.025673091411590576, | |
| "step": 1635, | |
| "valid_targets_mean": 9088.0, | |
| "valid_targets_min": 2783 | |
| }, | |
| { | |
| "epoch": 4.97165991902834, | |
| "grad_norm": 0.13084914628395353, | |
| "learning_rate": 5.415176410765721e-09, | |
| "loss": 0.0717, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02327067032456398, | |
| "step": 1640, | |
| "valid_targets_mean": 8506.6, | |
| "valid_targets_min": 2766 | |
| }, | |
| { | |
| "epoch": 4.9868421052631575, | |
| "grad_norm": 0.12658662256402115, | |
| "learning_rate": 1.611177942812958e-09, | |
| "loss": 0.0698, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.02067500166594982, | |
| "step": 1645, | |
| "valid_targets_mean": 8407.2, | |
| "valid_targets_min": 4752 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.20833718869014947, | |
| "learning_rate": 4.475552707772224e-11, | |
| "loss": 0.0693, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.06724487245082855, | |
| "step": 1650, | |
| "valid_targets_mean": 8702.3, | |
| "valid_targets_min": 3856 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 1650, | |
| "total_flos": 1.2268634506918887e+19, | |
| "train_loss": 0.0, | |
| "train_runtime": 7.0047, | |
| "train_samples_per_second": 22556.197, | |
| "train_steps_per_second": 235.555 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1650, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 300, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2268634506918887e+19, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |