Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use Kendamarron/model-calm3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Kendamarron/model-calm3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Kendamarron/model-calm3") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Kendamarron/model-calm3") model = AutoModelForCausalLM.from_pretrained("Kendamarron/model-calm3", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Kendamarron/model-calm3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Kendamarron/model-calm3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Kendamarron/model-calm3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Kendamarron/model-calm3
- SGLang
How to use Kendamarron/model-calm3 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 "Kendamarron/model-calm3" \ --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": "Kendamarron/model-calm3", "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 "Kendamarron/model-calm3" \ --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": "Kendamarron/model-calm3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Kendamarron/model-calm3 with Docker Model Runner:
docker model run hf.co/Kendamarron/model-calm3
Download trainer_state.json from Kendamarron/model-calm3: direct link, hf CLI and curl.
- Browser
- Download file 85.5 kB
-
https://huggingface.co/Kendamarron/model-calm3/resolve/main/trainer_state.json
- Command line
-
hf download hf://Kendamarron/model-calm3/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/Kendamarron/model-calm3/resolve/main/trainer_state.json
85.5 kB
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 492, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0040650406504065045, | |
| "grad_norm": 7.601864633791059, | |
| "learning_rate": 2.0000000000000002e-07, | |
| "loss": 1.6619, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008130081300813009, | |
| "grad_norm": 8.90950489095892, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 1.6939, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012195121951219513, | |
| "grad_norm": 8.653661544119263, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 1.6815, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.016260162601626018, | |
| "grad_norm": 8.19389905975729, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 1.6773, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02032520325203252, | |
| "grad_norm": 7.660785574860422, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.6592, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.024390243902439025, | |
| "grad_norm": 7.52084161369647, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 1.5694, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028455284552845527, | |
| "grad_norm": 7.899024403331175, | |
| "learning_rate": 1.4000000000000001e-06, | |
| "loss": 1.6924, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.032520325203252036, | |
| "grad_norm": 6.509312845370045, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 1.7214, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.036585365853658534, | |
| "grad_norm": 5.841824414556262, | |
| "learning_rate": 1.8000000000000001e-06, | |
| "loss": 1.6014, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04065040650406504, | |
| "grad_norm": 5.9478840184326796, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.5693, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.044715447154471545, | |
| "grad_norm": 4.622354276343799, | |
| "learning_rate": 2.2e-06, | |
| "loss": 1.5511, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04878048780487805, | |
| "grad_norm": 5.333135757501214, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 1.5934, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.052845528455284556, | |
| "grad_norm": 4.933827488901234, | |
| "learning_rate": 2.6e-06, | |
| "loss": 1.5078, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.056910569105691054, | |
| "grad_norm": 4.384469679367266, | |
| "learning_rate": 2.8000000000000003e-06, | |
| "loss": 1.4271, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06097560975609756, | |
| "grad_norm": 5.201629229354225, | |
| "learning_rate": 3e-06, | |
| "loss": 1.4909, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06504065040650407, | |
| "grad_norm": 5.370469326586405, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 1.2898, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06910569105691057, | |
| "grad_norm": 4.594077436852246, | |
| "learning_rate": 3.4000000000000005e-06, | |
| "loss": 1.6093, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07317073170731707, | |
| "grad_norm": 4.562436798697651, | |
| "learning_rate": 3.6000000000000003e-06, | |
| "loss": 1.533, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07723577235772358, | |
| "grad_norm": 3.9560249475105427, | |
| "learning_rate": 3.8000000000000005e-06, | |
| "loss": 1.5155, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08130081300813008, | |
| "grad_norm": 4.107368289795713, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.5223, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08536585365853659, | |
| "grad_norm": 4.217408440842752, | |
| "learning_rate": 4.2000000000000004e-06, | |
| "loss": 1.4386, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08943089430894309, | |
| "grad_norm": 4.3572778395491625, | |
| "learning_rate": 4.4e-06, | |
| "loss": 1.4819, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09349593495934959, | |
| "grad_norm": 3.960914517136647, | |
| "learning_rate": 4.600000000000001e-06, | |
| "loss": 1.4183, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 4.277795090912468, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 1.4352, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1016260162601626, | |
| "grad_norm": 3.662410257559992, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3187, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10569105691056911, | |
| "grad_norm": 3.632520878287309, | |
| "learning_rate": 5.2e-06, | |
| "loss": 1.3634, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10975609756097561, | |
| "grad_norm": 3.7695635315480516, | |
| "learning_rate": 5.400000000000001e-06, | |
| "loss": 1.3945, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11382113821138211, | |
| "grad_norm": 4.618813786367727, | |
| "learning_rate": 5.600000000000001e-06, | |
| "loss": 1.4065, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11788617886178862, | |
| "grad_norm": 4.360295729569898, | |
| "learning_rate": 5.8e-06, | |
| "loss": 1.4983, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.12195121951219512, | |
| "grad_norm": 3.4401062155218174, | |
| "learning_rate": 6e-06, | |
| "loss": 1.3678, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12601626016260162, | |
| "grad_norm": 3.3378295453212403, | |
| "learning_rate": 6.200000000000001e-06, | |
| "loss": 1.422, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.13008130081300814, | |
| "grad_norm": 3.7133755764351424, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 1.3796, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.13414634146341464, | |
| "grad_norm": 3.6484038120294344, | |
| "learning_rate": 6.600000000000001e-06, | |
| "loss": 1.3597, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.13821138211382114, | |
| "grad_norm": 3.9758580501492196, | |
| "learning_rate": 6.800000000000001e-06, | |
| "loss": 1.4014, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.14227642276422764, | |
| "grad_norm": 3.7673644641995727, | |
| "learning_rate": 7e-06, | |
| "loss": 1.3976, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14634146341463414, | |
| "grad_norm": 3.4986919364189983, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 1.3708, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.15040650406504066, | |
| "grad_norm": 3.642524443198873, | |
| "learning_rate": 7.4e-06, | |
| "loss": 1.4249, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.15447154471544716, | |
| "grad_norm": 3.6896856780557825, | |
| "learning_rate": 7.600000000000001e-06, | |
| "loss": 1.4171, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.15853658536585366, | |
| "grad_norm": 3.5980645790229913, | |
| "learning_rate": 7.800000000000002e-06, | |
| "loss": 1.4014, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.16260162601626016, | |
| "grad_norm": 3.7186995729013836, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.3785, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 3.5494019559541923, | |
| "learning_rate": 8.2e-06, | |
| "loss": 1.3188, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.17073170731707318, | |
| "grad_norm": 3.6394025889041965, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 1.3922, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.17479674796747968, | |
| "grad_norm": 3.4664594843390253, | |
| "learning_rate": 8.6e-06, | |
| "loss": 1.3229, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.17886178861788618, | |
| "grad_norm": 3.5077042343329436, | |
| "learning_rate": 8.8e-06, | |
| "loss": 1.2871, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.18292682926829268, | |
| "grad_norm": 3.7315881333644576, | |
| "learning_rate": 9e-06, | |
| "loss": 1.2928, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18699186991869918, | |
| "grad_norm": 3.5393367592332163, | |
| "learning_rate": 9.200000000000002e-06, | |
| "loss": 1.2226, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1910569105691057, | |
| "grad_norm": 3.218556473562904, | |
| "learning_rate": 9.4e-06, | |
| "loss": 1.2773, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 2.977113069721881, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 1.1747, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1991869918699187, | |
| "grad_norm": 3.8506682201925, | |
| "learning_rate": 9.800000000000001e-06, | |
| "loss": 1.3404, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2032520325203252, | |
| "grad_norm": 3.2240933605706497, | |
| "learning_rate": 1e-05, | |
| "loss": 1.264, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2073170731707317, | |
| "grad_norm": 3.333549619646554, | |
| "learning_rate": 9.999873702897528e-06, | |
| "loss": 1.2899, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.21138211382113822, | |
| "grad_norm": 4.403650985310743, | |
| "learning_rate": 9.999494817970498e-06, | |
| "loss": 1.3726, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.21544715447154472, | |
| "grad_norm": 3.8361682976277383, | |
| "learning_rate": 9.998863364359734e-06, | |
| "loss": 1.3113, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.21951219512195122, | |
| "grad_norm": 3.534046334234316, | |
| "learning_rate": 9.997979373965542e-06, | |
| "loss": 1.2444, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.22357723577235772, | |
| "grad_norm": 3.4704662905451182, | |
| "learning_rate": 9.996842891446092e-06, | |
| "loss": 1.2575, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.22764227642276422, | |
| "grad_norm": 3.3962483960282213, | |
| "learning_rate": 9.995453974215164e-06, | |
| "loss": 1.3113, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.23170731707317074, | |
| "grad_norm": 3.9086253718511066, | |
| "learning_rate": 9.993812692439247e-06, | |
| "loss": 1.3813, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.23577235772357724, | |
| "grad_norm": 3.843292149715078, | |
| "learning_rate": 9.991919129033994e-06, | |
| "loss": 1.353, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.23983739837398374, | |
| "grad_norm": 3.9260638911409473, | |
| "learning_rate": 9.98977337966003e-06, | |
| "loss": 1.3387, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.24390243902439024, | |
| "grad_norm": 3.795877124355826, | |
| "learning_rate": 9.987375552718133e-06, | |
| "loss": 1.3114, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.24796747967479674, | |
| "grad_norm": 3.5580148523465, | |
| "learning_rate": 9.984725769343737e-06, | |
| "loss": 1.2415, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.25203252032520324, | |
| "grad_norm": 3.9767665126163902, | |
| "learning_rate": 9.981824163400827e-06, | |
| "loss": 1.4033, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.25609756097560976, | |
| "grad_norm": 3.55177606133293, | |
| "learning_rate": 9.978670881475173e-06, | |
| "loss": 1.3146, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.2601626016260163, | |
| "grad_norm": 3.6363875922745357, | |
| "learning_rate": 9.975266082866923e-06, | |
| "loss": 1.2341, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.26422764227642276, | |
| "grad_norm": 3.737770535479784, | |
| "learning_rate": 9.971609939582556e-06, | |
| "loss": 1.2754, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2682926829268293, | |
| "grad_norm": 3.037718171173777, | |
| "learning_rate": 9.967702636326195e-06, | |
| "loss": 1.3051, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.27235772357723576, | |
| "grad_norm": 3.2961244132241916, | |
| "learning_rate": 9.96354437049027e-06, | |
| "loss": 1.2848, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.2764227642276423, | |
| "grad_norm": 3.2454017036305434, | |
| "learning_rate": 9.959135352145552e-06, | |
| "loss": 1.3085, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2804878048780488, | |
| "grad_norm": 3.5811119753587786, | |
| "learning_rate": 9.954475804030539e-06, | |
| "loss": 1.2777, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.2845528455284553, | |
| "grad_norm": 3.5163568542082952, | |
| "learning_rate": 9.9495659615402e-06, | |
| "loss": 1.3014, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2886178861788618, | |
| "grad_norm": 3.7745745640357073, | |
| "learning_rate": 9.944406072714086e-06, | |
| "loss": 1.3298, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 3.442814199481373, | |
| "learning_rate": 9.938996398223802e-06, | |
| "loss": 1.2849, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.2967479674796748, | |
| "grad_norm": 3.5095835123074837, | |
| "learning_rate": 9.933337211359833e-06, | |
| "loss": 1.2972, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.3008130081300813, | |
| "grad_norm": 3.380832113619762, | |
| "learning_rate": 9.927428798017738e-06, | |
| "loss": 1.2526, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.3048780487804878, | |
| "grad_norm": 3.549622447623024, | |
| "learning_rate": 9.921271456683716e-06, | |
| "loss": 1.3452, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3089430894308943, | |
| "grad_norm": 3.4510120500688486, | |
| "learning_rate": 9.91486549841951e-06, | |
| "loss": 1.2526, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.3130081300813008, | |
| "grad_norm": 2.842150717683876, | |
| "learning_rate": 9.908211246846708e-06, | |
| "loss": 1.0849, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.3170731707317073, | |
| "grad_norm": 3.3573562351627873, | |
| "learning_rate": 9.901309038130392e-06, | |
| "loss": 1.3273, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.32113821138211385, | |
| "grad_norm": 3.170270363953111, | |
| "learning_rate": 9.894159220962138e-06, | |
| "loss": 1.1891, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.3252032520325203, | |
| "grad_norm": 3.160386778853492, | |
| "learning_rate": 9.886762156542428e-06, | |
| "loss": 1.2224, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.32926829268292684, | |
| "grad_norm": 4.360816086949134, | |
| "learning_rate": 9.879118218562384e-06, | |
| "loss": 1.2974, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 3.548780694975849, | |
| "learning_rate": 9.871227793184893e-06, | |
| "loss": 1.2506, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.33739837398373984, | |
| "grad_norm": 3.5704089080384436, | |
| "learning_rate": 9.863091279025095e-06, | |
| "loss": 1.3203, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.34146341463414637, | |
| "grad_norm": 3.553759595140404, | |
| "learning_rate": 9.854709087130261e-06, | |
| "loss": 1.2636, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.34552845528455284, | |
| "grad_norm": 3.3202811856289087, | |
| "learning_rate": 9.846081640959008e-06, | |
| "loss": 1.2846, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.34959349593495936, | |
| "grad_norm": 3.6676665259046386, | |
| "learning_rate": 9.837209376359918e-06, | |
| "loss": 1.28, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.35365853658536583, | |
| "grad_norm": 3.5592429684221054, | |
| "learning_rate": 9.828092741549513e-06, | |
| "loss": 1.349, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.35772357723577236, | |
| "grad_norm": 3.415634726891849, | |
| "learning_rate": 9.81873219708962e-06, | |
| "loss": 1.3083, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.3617886178861789, | |
| "grad_norm": 4.020648891307815, | |
| "learning_rate": 9.809128215864096e-06, | |
| "loss": 1.375, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.36585365853658536, | |
| "grad_norm": 3.613669367094324, | |
| "learning_rate": 9.79928128305494e-06, | |
| "loss": 1.2763, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3699186991869919, | |
| "grad_norm": 3.7024304415446605, | |
| "learning_rate": 9.789191896117786e-06, | |
| "loss": 1.3228, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.37398373983739835, | |
| "grad_norm": 3.3762140596742096, | |
| "learning_rate": 9.778860564756769e-06, | |
| "loss": 1.2107, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.3780487804878049, | |
| "grad_norm": 3.568415339282542, | |
| "learning_rate": 9.768287810898773e-06, | |
| "loss": 1.3002, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.3821138211382114, | |
| "grad_norm": 3.3507745036610443, | |
| "learning_rate": 9.757474168667072e-06, | |
| "loss": 1.272, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.3861788617886179, | |
| "grad_norm": 3.683831331611201, | |
| "learning_rate": 9.746420184354334e-06, | |
| "loss": 1.2288, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 3.4564185979654702, | |
| "learning_rate": 9.73512641639504e-06, | |
| "loss": 1.2283, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.3943089430894309, | |
| "grad_norm": 3.486110029080406, | |
| "learning_rate": 9.723593435337252e-06, | |
| "loss": 1.2981, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.3983739837398374, | |
| "grad_norm": 3.4443364500039455, | |
| "learning_rate": 9.711821823813812e-06, | |
| "loss": 1.2062, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.4024390243902439, | |
| "grad_norm": 3.887062505086485, | |
| "learning_rate": 9.699812176512887e-06, | |
| "loss": 1.3186, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.4065040650406504, | |
| "grad_norm": 3.496296402696931, | |
| "learning_rate": 9.68756510014794e-06, | |
| "loss": 1.2149, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4105691056910569, | |
| "grad_norm": 3.5683061924181265, | |
| "learning_rate": 9.675081213427076e-06, | |
| "loss": 1.2889, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.4146341463414634, | |
| "grad_norm": 3.422166716374822, | |
| "learning_rate": 9.66236114702178e-06, | |
| "loss": 1.2545, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.4186991869918699, | |
| "grad_norm": 3.5935070368338975, | |
| "learning_rate": 9.649405543535067e-06, | |
| "loss": 1.2812, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.42276422764227645, | |
| "grad_norm": 3.2791252508657887, | |
| "learning_rate": 9.636215057469009e-06, | |
| "loss": 1.2451, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.4268292682926829, | |
| "grad_norm": 3.751079391290334, | |
| "learning_rate": 9.622790355191672e-06, | |
| "loss": 1.2478, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.43089430894308944, | |
| "grad_norm": 3.837109939185116, | |
| "learning_rate": 9.609132114903458e-06, | |
| "loss": 1.3266, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.4349593495934959, | |
| "grad_norm": 3.284057289104673, | |
| "learning_rate": 9.595241026602836e-06, | |
| "loss": 1.3096, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.43902439024390244, | |
| "grad_norm": 3.353970714894927, | |
| "learning_rate": 9.581117792051487e-06, | |
| "loss": 1.3307, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.44308943089430897, | |
| "grad_norm": 3.4407863626104738, | |
| "learning_rate": 9.56676312473885e-06, | |
| "loss": 1.2742, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.44715447154471544, | |
| "grad_norm": 3.274727411422373, | |
| "learning_rate": 9.552177749846083e-06, | |
| "loss": 1.1484, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.45121951219512196, | |
| "grad_norm": 3.686780707426172, | |
| "learning_rate": 9.537362404209419e-06, | |
| "loss": 1.2624, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.45528455284552843, | |
| "grad_norm": 3.130585181158449, | |
| "learning_rate": 9.522317836282949e-06, | |
| "loss": 1.1935, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.45934959349593496, | |
| "grad_norm": 3.1546672900599075, | |
| "learning_rate": 9.507044806100806e-06, | |
| "loss": 1.3123, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.4634146341463415, | |
| "grad_norm": 3.1583283930267627, | |
| "learning_rate": 9.491544085238778e-06, | |
| "loss": 1.254, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.46747967479674796, | |
| "grad_norm": 3.8792518686316257, | |
| "learning_rate": 9.475816456775313e-06, | |
| "loss": 1.2213, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.4715447154471545, | |
| "grad_norm": 3.632580019405141, | |
| "learning_rate": 9.459862715251973e-06, | |
| "loss": 1.1208, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.47560975609756095, | |
| "grad_norm": 3.406515110364018, | |
| "learning_rate": 9.44368366663329e-06, | |
| "loss": 1.2806, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.4796747967479675, | |
| "grad_norm": 3.257262930401774, | |
| "learning_rate": 9.427280128266049e-06, | |
| "loss": 1.2638, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.483739837398374, | |
| "grad_norm": 3.384791751364498, | |
| "learning_rate": 9.410652928837998e-06, | |
| "loss": 1.2427, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 3.4993557102778667, | |
| "learning_rate": 9.393802908335978e-06, | |
| "loss": 1.3081, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.491869918699187, | |
| "grad_norm": 3.5191969210120044, | |
| "learning_rate": 9.376730918003495e-06, | |
| "loss": 1.2625, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.4959349593495935, | |
| "grad_norm": 3.45753132618439, | |
| "learning_rate": 9.359437820297716e-06, | |
| "loss": 1.3023, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 3.2143713848767095, | |
| "learning_rate": 9.341924488845892e-06, | |
| "loss": 1.1889, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.5040650406504065, | |
| "grad_norm": 3.394160025526671, | |
| "learning_rate": 9.324191808401235e-06, | |
| "loss": 1.225, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.508130081300813, | |
| "grad_norm": 3.3553054022592272, | |
| "learning_rate": 9.306240674798203e-06, | |
| "loss": 1.2471, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5121951219512195, | |
| "grad_norm": 3.5363040242500414, | |
| "learning_rate": 9.288071994907262e-06, | |
| "loss": 1.2121, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.516260162601626, | |
| "grad_norm": 3.5513644491592378, | |
| "learning_rate": 9.269686686589063e-06, | |
| "loss": 1.2605, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.5203252032520326, | |
| "grad_norm": 3.2096183499210684, | |
| "learning_rate": 9.251085678648072e-06, | |
| "loss": 1.2181, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.524390243902439, | |
| "grad_norm": 3.8349171328561047, | |
| "learning_rate": 9.232269910785651e-06, | |
| "loss": 1.2922, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.5284552845528455, | |
| "grad_norm": 3.3870433308761685, | |
| "learning_rate": 9.213240333552589e-06, | |
| "loss": 1.3359, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.532520325203252, | |
| "grad_norm": 3.119886674331583, | |
| "learning_rate": 9.193997908301069e-06, | |
| "loss": 1.2201, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.5365853658536586, | |
| "grad_norm": 3.4328684239264073, | |
| "learning_rate": 9.174543607136111e-06, | |
| "loss": 1.2733, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.540650406504065, | |
| "grad_norm": 3.5211778075079745, | |
| "learning_rate": 9.154878412866465e-06, | |
| "loss": 1.1865, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.5447154471544715, | |
| "grad_norm": 3.8457560436654905, | |
| "learning_rate": 9.135003318954954e-06, | |
| "loss": 1.2656, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.5487804878048781, | |
| "grad_norm": 2.860252954067704, | |
| "learning_rate": 9.114919329468283e-06, | |
| "loss": 1.0367, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5528455284552846, | |
| "grad_norm": 3.1966625529009525, | |
| "learning_rate": 9.094627459026326e-06, | |
| "loss": 1.1913, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.556910569105691, | |
| "grad_norm": 3.3586333848047687, | |
| "learning_rate": 9.074128732750859e-06, | |
| "loss": 1.1965, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.5609756097560976, | |
| "grad_norm": 3.309006715689175, | |
| "learning_rate": 9.053424186213776e-06, | |
| "loss": 1.2739, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.5650406504065041, | |
| "grad_norm": 3.610998899181065, | |
| "learning_rate": 9.032514865384767e-06, | |
| "loss": 1.2361, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.5691056910569106, | |
| "grad_norm": 3.4092607492941123, | |
| "learning_rate": 9.011401826578492e-06, | |
| "loss": 1.2756, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.573170731707317, | |
| "grad_norm": 3.123803335281385, | |
| "learning_rate": 8.990086136401199e-06, | |
| "loss": 1.2046, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.5772357723577236, | |
| "grad_norm": 3.2180832415739746, | |
| "learning_rate": 8.968568871696847e-06, | |
| "loss": 1.2454, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.5813008130081301, | |
| "grad_norm": 3.392256479625929, | |
| "learning_rate": 8.946851119492717e-06, | |
| "loss": 1.2346, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 3.5203027610167994, | |
| "learning_rate": 8.924933976944474e-06, | |
| "loss": 1.2098, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.5894308943089431, | |
| "grad_norm": 3.293995047135828, | |
| "learning_rate": 8.902818551280758e-06, | |
| "loss": 1.249, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5934959349593496, | |
| "grad_norm": 2.8665049252390253, | |
| "learning_rate": 8.880505959747245e-06, | |
| "loss": 1.0725, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.5975609756097561, | |
| "grad_norm": 3.2594550044177524, | |
| "learning_rate": 8.857997329550195e-06, | |
| "loss": 1.2146, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.6016260162601627, | |
| "grad_norm": 3.445446281697995, | |
| "learning_rate": 8.835293797799517e-06, | |
| "loss": 1.3262, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.6056910569105691, | |
| "grad_norm": 3.9317510029226934, | |
| "learning_rate": 8.812396511451324e-06, | |
| "loss": 1.3188, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.6097560975609756, | |
| "grad_norm": 3.198084168395092, | |
| "learning_rate": 8.789306627249985e-06, | |
| "loss": 1.3008, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6138211382113821, | |
| "grad_norm": 3.063778345515228, | |
| "learning_rate": 8.766025311669685e-06, | |
| "loss": 0.9978, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.6178861788617886, | |
| "grad_norm": 3.2905300689457637, | |
| "learning_rate": 8.742553740855507e-06, | |
| "loss": 1.2479, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.6219512195121951, | |
| "grad_norm": 3.395304079212877, | |
| "learning_rate": 8.718893100564002e-06, | |
| "loss": 1.2713, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.6260162601626016, | |
| "grad_norm": 3.522348630348412, | |
| "learning_rate": 8.695044586103297e-06, | |
| "loss": 1.2753, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.6300813008130082, | |
| "grad_norm": 3.2582864801451987, | |
| "learning_rate": 8.6710094022727e-06, | |
| "loss": 1.2243, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.6341463414634146, | |
| "grad_norm": 3.8766071391892125, | |
| "learning_rate": 8.646788763301842e-06, | |
| "loss": 1.2652, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.6382113821138211, | |
| "grad_norm": 2.9196919853077503, | |
| "learning_rate": 8.62238389278933e-06, | |
| "loss": 1.1576, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.6422764227642277, | |
| "grad_norm": 3.247641592653831, | |
| "learning_rate": 8.59779602364094e-06, | |
| "loss": 1.3151, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.6463414634146342, | |
| "grad_norm": 3.025628331987507, | |
| "learning_rate": 8.573026398007323e-06, | |
| "loss": 1.245, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.6504065040650406, | |
| "grad_norm": 3.1296381446742427, | |
| "learning_rate": 8.548076267221258e-06, | |
| "loss": 1.2281, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6544715447154471, | |
| "grad_norm": 3.7321890066352874, | |
| "learning_rate": 8.52294689173443e-06, | |
| "loss": 1.2551, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.6585365853658537, | |
| "grad_norm": 3.0970454939543113, | |
| "learning_rate": 8.497639541053769e-06, | |
| "loss": 1.1847, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.6626016260162602, | |
| "grad_norm": 3.0874953153607043, | |
| "learning_rate": 8.472155493677299e-06, | |
| "loss": 1.2401, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 3.5716326976346977, | |
| "learning_rate": 8.446496037029555e-06, | |
| "loss": 1.2741, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.6707317073170732, | |
| "grad_norm": 3.274519329536325, | |
| "learning_rate": 8.420662467396548e-06, | |
| "loss": 1.2243, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.6747967479674797, | |
| "grad_norm": 3.0273430953677285, | |
| "learning_rate": 8.394656089860274e-06, | |
| "loss": 1.2116, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.6788617886178862, | |
| "grad_norm": 3.7987378754555903, | |
| "learning_rate": 8.368478218232787e-06, | |
| "loss": 1.2516, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.6829268292682927, | |
| "grad_norm": 3.1571140529158686, | |
| "learning_rate": 8.342130174989819e-06, | |
| "loss": 1.2202, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.6869918699186992, | |
| "grad_norm": 3.4795978849026015, | |
| "learning_rate": 8.315613291203977e-06, | |
| "loss": 1.2015, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.6910569105691057, | |
| "grad_norm": 3.356846206738464, | |
| "learning_rate": 8.288928906477497e-06, | |
| "loss": 1.2784, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6951219512195121, | |
| "grad_norm": 2.975674164772659, | |
| "learning_rate": 8.262078368874566e-06, | |
| "loss": 1.2806, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.6991869918699187, | |
| "grad_norm": 3.342698854245282, | |
| "learning_rate": 8.235063034853228e-06, | |
| "loss": 1.2434, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.7032520325203252, | |
| "grad_norm": 3.0021574646304265, | |
| "learning_rate": 8.207884269196845e-06, | |
| "loss": 1.2371, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.7073170731707317, | |
| "grad_norm": 3.371641208018489, | |
| "learning_rate": 8.180543444945154e-06, | |
| "loss": 1.2584, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.7113821138211383, | |
| "grad_norm": 3.4756530230066836, | |
| "learning_rate": 8.153041943324912e-06, | |
| "loss": 1.2621, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.7154471544715447, | |
| "grad_norm": 3.677440247481686, | |
| "learning_rate": 8.125381153680103e-06, | |
| "loss": 1.291, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.7195121951219512, | |
| "grad_norm": 3.724344603809136, | |
| "learning_rate": 8.097562473401764e-06, | |
| "loss": 1.1983, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.7235772357723578, | |
| "grad_norm": 3.881220605239073, | |
| "learning_rate": 8.069587307857377e-06, | |
| "loss": 1.3263, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.7276422764227642, | |
| "grad_norm": 3.2310425283801596, | |
| "learning_rate": 8.041457070319884e-06, | |
| "loss": 1.2153, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.7317073170731707, | |
| "grad_norm": 3.3870881335987857, | |
| "learning_rate": 8.013173181896283e-06, | |
| "loss": 1.3346, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7357723577235772, | |
| "grad_norm": 3.1452509757261056, | |
| "learning_rate": 7.984737071455834e-06, | |
| "loss": 1.2516, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.7398373983739838, | |
| "grad_norm": 3.173497495557972, | |
| "learning_rate": 7.95615017555788e-06, | |
| "loss": 1.2476, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.7439024390243902, | |
| "grad_norm": 3.539096701539341, | |
| "learning_rate": 7.927413938379268e-06, | |
| "loss": 1.1907, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.7479674796747967, | |
| "grad_norm": 3.8034573367911424, | |
| "learning_rate": 7.898529811641393e-06, | |
| "loss": 1.2354, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.7520325203252033, | |
| "grad_norm": 3.6222299487232985, | |
| "learning_rate": 7.869499254536865e-06, | |
| "loss": 1.1107, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.7560975609756098, | |
| "grad_norm": 3.353460855074601, | |
| "learning_rate": 7.84032373365578e-06, | |
| "loss": 1.2157, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.7601626016260162, | |
| "grad_norm": 3.5757972164092418, | |
| "learning_rate": 7.811004722911637e-06, | |
| "loss": 1.2422, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.7642276422764228, | |
| "grad_norm": 3.200921333461777, | |
| "learning_rate": 7.781543703466881e-06, | |
| "loss": 1.3359, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.7682926829268293, | |
| "grad_norm": 3.37458572836464, | |
| "learning_rate": 7.751942163658066e-06, | |
| "loss": 1.2325, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.7723577235772358, | |
| "grad_norm": 3.336790278155762, | |
| "learning_rate": 7.722201598920673e-06, | |
| "loss": 1.289, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7764227642276422, | |
| "grad_norm": 3.6578390679880677, | |
| "learning_rate": 7.692323511713568e-06, | |
| "loss": 1.2832, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 3.7372849061035307, | |
| "learning_rate": 7.662309411443084e-06, | |
| "loss": 1.2682, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.7845528455284553, | |
| "grad_norm": 3.4787988556346177, | |
| "learning_rate": 7.63216081438678e-06, | |
| "loss": 1.2566, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.7886178861788617, | |
| "grad_norm": 3.2972501647590295, | |
| "learning_rate": 7.601879243616838e-06, | |
| "loss": 1.2405, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.7926829268292683, | |
| "grad_norm": 3.08018485547122, | |
| "learning_rate": 7.571466228923115e-06, | |
| "loss": 1.2073, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.7967479674796748, | |
| "grad_norm": 3.4711819604946346, | |
| "learning_rate": 7.540923306735868e-06, | |
| "loss": 1.2299, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.8008130081300813, | |
| "grad_norm": 2.965090576227292, | |
| "learning_rate": 7.510252020048121e-06, | |
| "loss": 1.219, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.8048780487804879, | |
| "grad_norm": 3.430612679713931, | |
| "learning_rate": 7.479453918337733e-06, | |
| "loss": 1.1801, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.8089430894308943, | |
| "grad_norm": 3.5256924218857364, | |
| "learning_rate": 7.448530557489105e-06, | |
| "loss": 1.2364, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.8130081300813008, | |
| "grad_norm": 3.3729004326724232, | |
| "learning_rate": 7.417483499714589e-06, | |
| "loss": 1.2172, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8170731707317073, | |
| "grad_norm": 3.704140279583858, | |
| "learning_rate": 7.386314313475557e-06, | |
| "loss": 1.2462, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.8211382113821138, | |
| "grad_norm": 2.859256884612927, | |
| "learning_rate": 7.355024573403174e-06, | |
| "loss": 1.1915, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.8252032520325203, | |
| "grad_norm": 3.9308992936564455, | |
| "learning_rate": 7.323615860218844e-06, | |
| "loss": 1.2587, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.8292682926829268, | |
| "grad_norm": 3.4198261126400498, | |
| "learning_rate": 7.292089760654352e-06, | |
| "loss": 1.2962, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 3.3412036255224433, | |
| "learning_rate": 7.2604478673717095e-06, | |
| "loss": 1.2395, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.8373983739837398, | |
| "grad_norm": 3.556537641445364, | |
| "learning_rate": 7.2286917788826926e-06, | |
| "loss": 1.2526, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.8414634146341463, | |
| "grad_norm": 3.18197682179574, | |
| "learning_rate": 7.196823099468084e-06, | |
| "loss": 1.2601, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.8455284552845529, | |
| "grad_norm": 3.395646140761288, | |
| "learning_rate": 7.1648434390966356e-06, | |
| "loss": 1.23, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.8495934959349594, | |
| "grad_norm": 3.3928578867441, | |
| "learning_rate": 7.132754413343721e-06, | |
| "loss": 1.2609, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.8536585365853658, | |
| "grad_norm": 3.1283882470236106, | |
| "learning_rate": 7.100557643309732e-06, | |
| "loss": 1.1809, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8577235772357723, | |
| "grad_norm": 3.675071025819942, | |
| "learning_rate": 7.0682547555381734e-06, | |
| "loss": 1.2448, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.8617886178861789, | |
| "grad_norm": 3.0075418776078444, | |
| "learning_rate": 7.035847381933494e-06, | |
| "loss": 1.21, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.8658536585365854, | |
| "grad_norm": 3.457597870123879, | |
| "learning_rate": 7.003337159678649e-06, | |
| "loss": 1.2674, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.8699186991869918, | |
| "grad_norm": 3.394032369643457, | |
| "learning_rate": 6.970725731152389e-06, | |
| "loss": 1.2701, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.8739837398373984, | |
| "grad_norm": 3.348683954925548, | |
| "learning_rate": 6.938014743846285e-06, | |
| "loss": 1.2723, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.8780487804878049, | |
| "grad_norm": 3.380614445439332, | |
| "learning_rate": 6.905205850281502e-06, | |
| "loss": 1.3185, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.8821138211382114, | |
| "grad_norm": 2.82083389946448, | |
| "learning_rate": 6.872300707925319e-06, | |
| "loss": 1.0479, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.8861788617886179, | |
| "grad_norm": 3.2273081078802806, | |
| "learning_rate": 6.8393009791073895e-06, | |
| "loss": 1.2017, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.8902439024390244, | |
| "grad_norm": 2.9799477568840613, | |
| "learning_rate": 6.806208330935766e-06, | |
| "loss": 1.1383, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.8943089430894309, | |
| "grad_norm": 3.2837120753465037, | |
| "learning_rate": 6.773024435212678e-06, | |
| "loss": 1.2259, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8983739837398373, | |
| "grad_norm": 3.6449591162008486, | |
| "learning_rate": 6.739750968350081e-06, | |
| "loss": 1.2948, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.9024390243902439, | |
| "grad_norm": 3.225238120108855, | |
| "learning_rate": 6.706389611284953e-06, | |
| "loss": 1.1855, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.9065040650406504, | |
| "grad_norm": 3.432916919843375, | |
| "learning_rate": 6.6729420493943875e-06, | |
| "loss": 1.247, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.9105691056910569, | |
| "grad_norm": 3.0718472155542353, | |
| "learning_rate": 6.639409972410446e-06, | |
| "loss": 1.1905, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.9146341463414634, | |
| "grad_norm": 3.3699226964349522, | |
| "learning_rate": 6.605795074334793e-06, | |
| "loss": 1.2424, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.9186991869918699, | |
| "grad_norm": 3.3821914270422027, | |
| "learning_rate": 6.57209905335312e-06, | |
| "loss": 1.2114, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.9227642276422764, | |
| "grad_norm": 3.025222008403353, | |
| "learning_rate": 6.538323611749351e-06, | |
| "loss": 1.1519, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.926829268292683, | |
| "grad_norm": 3.42250194898501, | |
| "learning_rate": 6.504470455819651e-06, | |
| "loss": 1.2768, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.9308943089430894, | |
| "grad_norm": 3.446861559528364, | |
| "learning_rate": 6.470541295786222e-06, | |
| "loss": 1.2202, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.9349593495934959, | |
| "grad_norm": 3.3472872172040646, | |
| "learning_rate": 6.436537845710904e-06, | |
| "loss": 1.2408, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9390243902439024, | |
| "grad_norm": 3.435994418242901, | |
| "learning_rate": 6.402461823408584e-06, | |
| "loss": 1.193, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.943089430894309, | |
| "grad_norm": 3.9739734441369365, | |
| "learning_rate": 6.368314950360416e-06, | |
| "loss": 1.2113, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.9471544715447154, | |
| "grad_norm": 3.394258791013482, | |
| "learning_rate": 6.334098951626847e-06, | |
| "loss": 1.2076, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.9512195121951219, | |
| "grad_norm": 3.531729806577509, | |
| "learning_rate": 6.299815555760478e-06, | |
| "loss": 1.2218, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.9552845528455285, | |
| "grad_norm": 3.014602089114332, | |
| "learning_rate": 6.265466494718731e-06, | |
| "loss": 1.1879, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.959349593495935, | |
| "grad_norm": 3.33204325952638, | |
| "learning_rate": 6.231053503776363e-06, | |
| "loss": 1.2008, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.9634146341463414, | |
| "grad_norm": 3.344568538684679, | |
| "learning_rate": 6.1965783214377895e-06, | |
| "loss": 1.1897, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.967479674796748, | |
| "grad_norm": 3.4113570652803076, | |
| "learning_rate": 6.1620426893492645e-06, | |
| "loss": 1.2736, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.9715447154471545, | |
| "grad_norm": 3.4879360711731593, | |
| "learning_rate": 6.127448352210894e-06, | |
| "loss": 1.1798, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 3.7021368783212942, | |
| "learning_rate": 6.092797057688496e-06, | |
| "loss": 1.1927, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.9796747967479674, | |
| "grad_norm": 3.2380601035094934, | |
| "learning_rate": 6.058090556325305e-06, | |
| "loss": 1.1896, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.983739837398374, | |
| "grad_norm": 3.3467517032738994, | |
| "learning_rate": 6.0233306014535505e-06, | |
| "loss": 1.2357, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.9878048780487805, | |
| "grad_norm": 3.3216338993009034, | |
| "learning_rate": 5.988518949105862e-06, | |
| "loss": 1.1884, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.991869918699187, | |
| "grad_norm": 3.2077249913458985, | |
| "learning_rate": 5.953657357926569e-06, | |
| "loss": 1.2504, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.9959349593495935, | |
| "grad_norm": 3.326332160803518, | |
| "learning_rate": 5.918747589082853e-06, | |
| "loss": 1.2548, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 3.3151307527051257, | |
| "learning_rate": 5.883791406175775e-06, | |
| "loss": 1.1878, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 1.0040650406504066, | |
| "grad_norm": 4.323555049169963, | |
| "learning_rate": 5.848790575151181e-06, | |
| "loss": 0.9153, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 1.008130081300813, | |
| "grad_norm": 3.465939989112603, | |
| "learning_rate": 5.813746864210489e-06, | |
| "loss": 0.8676, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 1.0121951219512195, | |
| "grad_norm": 3.6801149888116336, | |
| "learning_rate": 5.778662043721359e-06, | |
| "loss": 0.926, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 1.016260162601626, | |
| "grad_norm": 3.0713182769499987, | |
| "learning_rate": 5.743537886128258e-06, | |
| "loss": 0.8602, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.0203252032520325, | |
| "grad_norm": 3.557190687922137, | |
| "learning_rate": 5.708376165862921e-06, | |
| "loss": 0.9028, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 1.024390243902439, | |
| "grad_norm": 3.3051978717310186, | |
| "learning_rate": 5.673178659254698e-06, | |
| "loss": 0.8645, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.0284552845528456, | |
| "grad_norm": 3.6105207649370628, | |
| "learning_rate": 5.637947144440832e-06, | |
| "loss": 0.857, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 1.032520325203252, | |
| "grad_norm": 3.4764241585248548, | |
| "learning_rate": 5.6026834012766155e-06, | |
| "loss": 0.8952, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 1.0365853658536586, | |
| "grad_norm": 3.6901515484750727, | |
| "learning_rate": 5.567389211245486e-06, | |
| "loss": 0.8852, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.040650406504065, | |
| "grad_norm": 2.797763471477429, | |
| "learning_rate": 5.532066357369012e-06, | |
| "loss": 0.8064, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 1.0447154471544715, | |
| "grad_norm": 6.8675497317344405, | |
| "learning_rate": 5.496716624116836e-06, | |
| "loss": 0.8803, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 1.048780487804878, | |
| "grad_norm": 3.874898167456331, | |
| "learning_rate": 5.46134179731651e-06, | |
| "loss": 0.7879, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 1.0528455284552845, | |
| "grad_norm": 3.3839912626060116, | |
| "learning_rate": 5.425943664063284e-06, | |
| "loss": 0.8645, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 1.056910569105691, | |
| "grad_norm": 3.3351665786851945, | |
| "learning_rate": 5.390524012629824e-06, | |
| "loss": 0.9009, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0609756097560976, | |
| "grad_norm": 3.15122789490253, | |
| "learning_rate": 5.3550846323758666e-06, | |
| "loss": 0.8388, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 1.065040650406504, | |
| "grad_norm": 3.3003260837011807, | |
| "learning_rate": 5.319627313657829e-06, | |
| "loss": 0.8363, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 1.0691056910569106, | |
| "grad_norm": 2.936698289474364, | |
| "learning_rate": 5.284153847738356e-06, | |
| "loss": 0.8473, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 1.0731707317073171, | |
| "grad_norm": 3.572322782052897, | |
| "learning_rate": 5.248666026695835e-06, | |
| "loss": 0.8801, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 1.0772357723577235, | |
| "grad_norm": 3.129199412648207, | |
| "learning_rate": 5.213165643333851e-06, | |
| "loss": 0.8512, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.08130081300813, | |
| "grad_norm": 3.0887292783736577, | |
| "learning_rate": 5.177654491090627e-06, | |
| "loss": 0.8383, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 1.0853658536585367, | |
| "grad_norm": 3.381314067942086, | |
| "learning_rate": 5.1421343639484165e-06, | |
| "loss": 0.8487, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 1.089430894308943, | |
| "grad_norm": 3.6057501707631037, | |
| "learning_rate": 5.1066070563428736e-06, | |
| "loss": 0.8413, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 1.0934959349593496, | |
| "grad_norm": 2.9732383695526634, | |
| "learning_rate": 5.071074363072403e-06, | |
| "loss": 0.7804, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 1.0975609756097562, | |
| "grad_norm": 3.460563360283899, | |
| "learning_rate": 5.035538079207488e-06, | |
| "loss": 0.8791, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.1016260162601625, | |
| "grad_norm": 3.2682949069300333, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8705, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 1.1056910569105691, | |
| "grad_norm": 3.308698310047778, | |
| "learning_rate": 4.964461920792512e-06, | |
| "loss": 0.8671, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 1.1097560975609757, | |
| "grad_norm": 3.1081622158579787, | |
| "learning_rate": 4.928925636927597e-06, | |
| "loss": 0.8352, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 1.113821138211382, | |
| "grad_norm": 3.5089544730564337, | |
| "learning_rate": 4.893392943657127e-06, | |
| "loss": 0.8125, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 1.1178861788617886, | |
| "grad_norm": 3.324066226795555, | |
| "learning_rate": 4.857865636051586e-06, | |
| "loss": 0.9, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.1219512195121952, | |
| "grad_norm": 2.9061490782523673, | |
| "learning_rate": 4.822345508909376e-06, | |
| "loss": 0.8462, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 1.1260162601626016, | |
| "grad_norm": 2.7881013420756418, | |
| "learning_rate": 4.786834356666153e-06, | |
| "loss": 0.8066, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 1.1300813008130082, | |
| "grad_norm": 3.141214336537279, | |
| "learning_rate": 4.751333973304166e-06, | |
| "loss": 0.8701, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 1.1341463414634148, | |
| "grad_norm": 2.888872540331265, | |
| "learning_rate": 4.715846152261645e-06, | |
| "loss": 0.8046, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 1.1382113821138211, | |
| "grad_norm": 3.353720993292887, | |
| "learning_rate": 4.680372686342173e-06, | |
| "loss": 0.8393, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.1422764227642277, | |
| "grad_norm": 3.4262846056368845, | |
| "learning_rate": 4.644915367624134e-06, | |
| "loss": 0.7747, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 1.146341463414634, | |
| "grad_norm": 3.2239577090327893, | |
| "learning_rate": 4.609475987370177e-06, | |
| "loss": 0.797, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 1.1504065040650406, | |
| "grad_norm": 3.223343944139248, | |
| "learning_rate": 4.5740563359367164e-06, | |
| "loss": 0.8407, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 1.1544715447154472, | |
| "grad_norm": 3.1818064609840198, | |
| "learning_rate": 4.53865820268349e-06, | |
| "loss": 0.8241, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 1.1585365853658536, | |
| "grad_norm": 3.1906411149160525, | |
| "learning_rate": 4.503283375883165e-06, | |
| "loss": 0.8057, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.1626016260162602, | |
| "grad_norm": 3.632793987489528, | |
| "learning_rate": 4.467933642630989e-06, | |
| "loss": 0.8379, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 1.1666666666666667, | |
| "grad_norm": 2.794213331335638, | |
| "learning_rate": 4.432610788754517e-06, | |
| "loss": 0.6732, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 1.170731707317073, | |
| "grad_norm": 3.436978769265818, | |
| "learning_rate": 4.397316598723385e-06, | |
| "loss": 0.8999, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 1.1747967479674797, | |
| "grad_norm": 3.5914755495139032, | |
| "learning_rate": 4.362052855559171e-06, | |
| "loss": 0.9225, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 1.1788617886178863, | |
| "grad_norm": 3.044495214801385, | |
| "learning_rate": 4.326821340745304e-06, | |
| "loss": 0.8492, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.1829268292682926, | |
| "grad_norm": 2.9176213210346478, | |
| "learning_rate": 4.291623834137082e-06, | |
| "loss": 0.6663, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 1.1869918699186992, | |
| "grad_norm": 3.263437323837356, | |
| "learning_rate": 4.256462113871741e-06, | |
| "loss": 0.8919, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 1.1910569105691058, | |
| "grad_norm": 3.420956911951543, | |
| "learning_rate": 4.2213379562786406e-06, | |
| "loss": 0.834, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 1.1951219512195121, | |
| "grad_norm": 2.967387533543618, | |
| "learning_rate": 4.186253135789511e-06, | |
| "loss": 0.8238, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 1.1991869918699187, | |
| "grad_norm": 3.2109782296405425, | |
| "learning_rate": 4.15120942484882e-06, | |
| "loss": 0.8617, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.203252032520325, | |
| "grad_norm": 3.483436429896311, | |
| "learning_rate": 4.116208593824227e-06, | |
| "loss": 0.9088, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 1.2073170731707317, | |
| "grad_norm": 3.103671650986791, | |
| "learning_rate": 4.081252410917148e-06, | |
| "loss": 0.8458, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 1.2113821138211383, | |
| "grad_norm": 3.4106408241432598, | |
| "learning_rate": 4.046342642073433e-06, | |
| "loss": 0.8274, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 1.2154471544715446, | |
| "grad_norm": 3.2949066557526288, | |
| "learning_rate": 4.01148105089414e-06, | |
| "loss": 0.8096, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 1.2195121951219512, | |
| "grad_norm": 3.3675251909490402, | |
| "learning_rate": 3.976669398546451e-06, | |
| "loss": 0.894, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.2235772357723578, | |
| "grad_norm": 3.0572162762552217, | |
| "learning_rate": 3.941909443674696e-06, | |
| "loss": 0.8826, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 1.2276422764227641, | |
| "grad_norm": 3.0686786710141747, | |
| "learning_rate": 3.907202942311506e-06, | |
| "loss": 0.8403, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 1.2317073170731707, | |
| "grad_norm": 3.3850347568207306, | |
| "learning_rate": 3.872551647789108e-06, | |
| "loss": 0.9008, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 1.2357723577235773, | |
| "grad_norm": 3.568496760837224, | |
| "learning_rate": 3.837957310650738e-06, | |
| "loss": 0.8299, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 1.2398373983739837, | |
| "grad_norm": 3.081234179900163, | |
| "learning_rate": 3.803421678562213e-06, | |
| "loss": 0.7561, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 1.2439024390243902, | |
| "grad_norm": 3.0395181179956294, | |
| "learning_rate": 3.7689464962236367e-06, | |
| "loss": 0.8344, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 1.2479674796747968, | |
| "grad_norm": 2.9387819795914165, | |
| "learning_rate": 3.734533505281269e-06, | |
| "loss": 0.8067, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 1.2520325203252032, | |
| "grad_norm": 3.362022257660303, | |
| "learning_rate": 3.700184444239524e-06, | |
| "loss": 0.8437, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 1.2560975609756098, | |
| "grad_norm": 3.0339266148997295, | |
| "learning_rate": 3.6659010483731543e-06, | |
| "loss": 0.814, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 1.2601626016260163, | |
| "grad_norm": 3.141762645727816, | |
| "learning_rate": 3.6316850496395863e-06, | |
| "loss": 0.8294, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.2642276422764227, | |
| "grad_norm": 3.4348088918026662, | |
| "learning_rate": 3.597538176591417e-06, | |
| "loss": 0.7657, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 1.2682926829268293, | |
| "grad_norm": 3.054857603912505, | |
| "learning_rate": 3.563462154289098e-06, | |
| "loss": 0.7799, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.2723577235772359, | |
| "grad_norm": 3.4737488253418425, | |
| "learning_rate": 3.5294587042137796e-06, | |
| "loss": 0.8867, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 1.2764227642276422, | |
| "grad_norm": 3.10636831049777, | |
| "learning_rate": 3.49552954418035e-06, | |
| "loss": 0.7944, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 1.2804878048780488, | |
| "grad_norm": 3.0056066846766196, | |
| "learning_rate": 3.461676388250651e-06, | |
| "loss": 0.806, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.2845528455284554, | |
| "grad_norm": 3.22935213051317, | |
| "learning_rate": 3.4279009466468825e-06, | |
| "loss": 0.803, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 1.2886178861788617, | |
| "grad_norm": 3.586063282737165, | |
| "learning_rate": 3.3942049256652093e-06, | |
| "loss": 0.889, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 1.2926829268292683, | |
| "grad_norm": 3.290341852319477, | |
| "learning_rate": 3.3605900275895565e-06, | |
| "loss": 0.8793, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.296747967479675, | |
| "grad_norm": 2.963322253867672, | |
| "learning_rate": 3.3270579506056146e-06, | |
| "loss": 0.8032, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 1.3008130081300813, | |
| "grad_norm": 3.2168072401660703, | |
| "learning_rate": 3.2936103887150484e-06, | |
| "loss": 0.8563, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.3048780487804879, | |
| "grad_norm": 3.1570333927956424, | |
| "learning_rate": 3.2602490316499197e-06, | |
| "loss": 0.8603, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 1.3089430894308944, | |
| "grad_norm": 3.2845649650072812, | |
| "learning_rate": 3.226975564787322e-06, | |
| "loss": 0.8787, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 1.3130081300813008, | |
| "grad_norm": 3.2182847820601146, | |
| "learning_rate": 3.1937916690642356e-06, | |
| "loss": 0.8411, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 1.3170731707317074, | |
| "grad_norm": 3.398939591260855, | |
| "learning_rate": 3.1606990208926125e-06, | |
| "loss": 0.855, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.321138211382114, | |
| "grad_norm": 2.706198394059073, | |
| "learning_rate": 3.127699292074683e-06, | |
| "loss": 0.7856, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.3252032520325203, | |
| "grad_norm": 3.263791744218598, | |
| "learning_rate": 3.0947941497184985e-06, | |
| "loss": 0.9305, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 1.329268292682927, | |
| "grad_norm": 3.638027473310664, | |
| "learning_rate": 3.0619852561537165e-06, | |
| "loss": 0.8801, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 3.4194690003320964, | |
| "learning_rate": 3.0292742688476125e-06, | |
| "loss": 0.8694, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 1.3373983739837398, | |
| "grad_norm": 2.8625969545690473, | |
| "learning_rate": 2.9966628403213528e-06, | |
| "loss": 0.8601, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 1.3414634146341464, | |
| "grad_norm": 3.149728494159807, | |
| "learning_rate": 2.964152618066508e-06, | |
| "loss": 0.8055, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.3455284552845528, | |
| "grad_norm": 3.1471735889701895, | |
| "learning_rate": 2.93174524446183e-06, | |
| "loss": 0.8029, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 1.3495934959349594, | |
| "grad_norm": 3.737033991986332, | |
| "learning_rate": 2.899442356690271e-06, | |
| "loss": 0.8433, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 1.3536585365853657, | |
| "grad_norm": 3.038148294937328, | |
| "learning_rate": 2.8672455866562797e-06, | |
| "loss": 0.7904, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.3577235772357723, | |
| "grad_norm": 3.49987749409302, | |
| "learning_rate": 2.835156560903365e-06, | |
| "loss": 0.8513, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 1.3617886178861789, | |
| "grad_norm": 3.4423408822147623, | |
| "learning_rate": 2.803176900531915e-06, | |
| "loss": 0.8699, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.3658536585365852, | |
| "grad_norm": 3.0989763636949776, | |
| "learning_rate": 2.771308221117309e-06, | |
| "loss": 0.828, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 1.3699186991869918, | |
| "grad_norm": 3.570239925753034, | |
| "learning_rate": 2.7395521326282913e-06, | |
| "loss": 0.9138, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 1.3739837398373984, | |
| "grad_norm": 2.9867469290330146, | |
| "learning_rate": 2.7079102393456503e-06, | |
| "loss": 0.774, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 1.3780487804878048, | |
| "grad_norm": 3.2405869730657257, | |
| "learning_rate": 2.6763841397811576e-06, | |
| "loss": 0.7736, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 1.3821138211382114, | |
| "grad_norm": 3.3013068491566235, | |
| "learning_rate": 2.6449754265968263e-06, | |
| "loss": 0.8141, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.386178861788618, | |
| "grad_norm": 2.9459262525676406, | |
| "learning_rate": 2.6136856865244443e-06, | |
| "loss": 0.8195, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 1.3902439024390243, | |
| "grad_norm": 3.1841733357674364, | |
| "learning_rate": 2.5825165002854124e-06, | |
| "loss": 0.8344, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 1.3943089430894309, | |
| "grad_norm": 3.5810707392643293, | |
| "learning_rate": 2.5514694425108968e-06, | |
| "loss": 0.8499, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 1.3983739837398375, | |
| "grad_norm": 2.9742861052640874, | |
| "learning_rate": 2.5205460816622684e-06, | |
| "loss": 0.8667, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 1.4024390243902438, | |
| "grad_norm": 3.1444266229672575, | |
| "learning_rate": 2.4897479799518797e-06, | |
| "loss": 0.8924, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 1.4065040650406504, | |
| "grad_norm": 3.3362745541137597, | |
| "learning_rate": 2.4590766932641353e-06, | |
| "loss": 0.9045, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 1.410569105691057, | |
| "grad_norm": 3.3267334401886193, | |
| "learning_rate": 2.4285337710768843e-06, | |
| "loss": 0.8234, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 1.4146341463414633, | |
| "grad_norm": 3.1893552375875918, | |
| "learning_rate": 2.3981207563831633e-06, | |
| "loss": 0.8079, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 1.41869918699187, | |
| "grad_norm": 3.2683250472050847, | |
| "learning_rate": 2.3678391856132203e-06, | |
| "loss": 0.8218, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 1.4227642276422765, | |
| "grad_norm": 3.448624987848759, | |
| "learning_rate": 2.3376905885569185e-06, | |
| "loss": 0.8476, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.4268292682926829, | |
| "grad_norm": 3.670635888853914, | |
| "learning_rate": 2.3076764882864333e-06, | |
| "loss": 0.8716, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 1.4308943089430894, | |
| "grad_norm": 3.516539819419681, | |
| "learning_rate": 2.2777984010793264e-06, | |
| "loss": 0.8524, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 1.434959349593496, | |
| "grad_norm": 3.228259726275918, | |
| "learning_rate": 2.2480578363419363e-06, | |
| "loss": 0.7901, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 1.4390243902439024, | |
| "grad_norm": 3.553218992889345, | |
| "learning_rate": 2.2184562965331203e-06, | |
| "loss": 0.8905, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 1.443089430894309, | |
| "grad_norm": 3.6137062298684923, | |
| "learning_rate": 2.1889952770883644e-06, | |
| "loss": 0.7972, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 1.4471544715447155, | |
| "grad_norm": 3.3416767625599335, | |
| "learning_rate": 2.159676266344222e-06, | |
| "loss": 0.886, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 1.451219512195122, | |
| "grad_norm": 3.3906959649699715, | |
| "learning_rate": 2.130500745463136e-06, | |
| "loss": 0.8919, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 1.4552845528455285, | |
| "grad_norm": 3.6314079403765747, | |
| "learning_rate": 2.1014701883586087e-06, | |
| "loss": 0.8765, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 1.459349593495935, | |
| "grad_norm": 3.057301186038854, | |
| "learning_rate": 2.072586061620735e-06, | |
| "loss": 0.8237, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 1.4634146341463414, | |
| "grad_norm": 3.564428107436926, | |
| "learning_rate": 2.043849824442124e-06, | |
| "loss": 0.7742, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.467479674796748, | |
| "grad_norm": 3.178787951259167, | |
| "learning_rate": 2.0152629285441668e-06, | |
| "loss": 0.8365, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 1.4715447154471546, | |
| "grad_norm": 3.181406467166967, | |
| "learning_rate": 1.9868268181037186e-06, | |
| "loss": 0.8645, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 1.475609756097561, | |
| "grad_norm": 3.066096619760171, | |
| "learning_rate": 1.958542929680117e-06, | |
| "loss": 0.7604, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 1.4796747967479675, | |
| "grad_norm": 3.0788381680120604, | |
| "learning_rate": 1.9304126921426235e-06, | |
| "loss": 0.8887, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 1.4837398373983741, | |
| "grad_norm": 3.615003637576646, | |
| "learning_rate": 1.9024375265982386e-06, | |
| "loss": 0.8805, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 1.4878048780487805, | |
| "grad_norm": 2.8227276452116423, | |
| "learning_rate": 1.8746188463198983e-06, | |
| "loss": 0.758, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 1.491869918699187, | |
| "grad_norm": 3.3074090748960923, | |
| "learning_rate": 1.8469580566750911e-06, | |
| "loss": 0.8227, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 1.4959349593495934, | |
| "grad_norm": 2.971853438307015, | |
| "learning_rate": 1.8194565550548477e-06, | |
| "loss": 0.8551, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 3.5958157882917297, | |
| "learning_rate": 1.7921157308031567e-06, | |
| "loss": 0.7877, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 1.5040650406504064, | |
| "grad_norm": 3.099263275691927, | |
| "learning_rate": 1.764936965146773e-06, | |
| "loss": 0.9031, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.5081300813008132, | |
| "grad_norm": 3.7318628452131315, | |
| "learning_rate": 1.7379216311254339e-06, | |
| "loss": 0.8878, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 1.5121951219512195, | |
| "grad_norm": 3.414259418138962, | |
| "learning_rate": 1.7110710935225055e-06, | |
| "loss": 0.8567, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 1.5162601626016259, | |
| "grad_norm": 3.183690273924712, | |
| "learning_rate": 1.6843867087960252e-06, | |
| "loss": 0.8205, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 1.5203252032520327, | |
| "grad_norm": 3.208728871947272, | |
| "learning_rate": 1.6578698250101828e-06, | |
| "loss": 0.7876, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 1.524390243902439, | |
| "grad_norm": 3.049914247780551, | |
| "learning_rate": 1.6315217817672142e-06, | |
| "loss": 0.8012, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.5284552845528454, | |
| "grad_norm": 3.463789080277346, | |
| "learning_rate": 1.6053439101397257e-06, | |
| "loss": 0.8196, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 1.532520325203252, | |
| "grad_norm": 3.462794776018169, | |
| "learning_rate": 1.5793375326034539e-06, | |
| "loss": 0.8383, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 1.5365853658536586, | |
| "grad_norm": 3.1335857420520377, | |
| "learning_rate": 1.5535039629704467e-06, | |
| "loss": 0.8113, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.540650406504065, | |
| "grad_norm": 3.3079378565371274, | |
| "learning_rate": 1.5278445063227038e-06, | |
| "loss": 0.8283, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 1.5447154471544715, | |
| "grad_norm": 3.0120012731369843, | |
| "learning_rate": 1.502360458946232e-06, | |
| "loss": 0.8099, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.548780487804878, | |
| "grad_norm": 3.229793041226319, | |
| "learning_rate": 1.4770531082655704e-06, | |
| "loss": 0.8109, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 1.5528455284552845, | |
| "grad_norm": 3.511162269109416, | |
| "learning_rate": 1.451923732778745e-06, | |
| "loss": 0.8976, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 1.556910569105691, | |
| "grad_norm": 2.9067244803834713, | |
| "learning_rate": 1.4269736019926778e-06, | |
| "loss": 0.8148, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 1.5609756097560976, | |
| "grad_norm": 2.930774964453727, | |
| "learning_rate": 1.4022039763590595e-06, | |
| "loss": 0.7621, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 1.565040650406504, | |
| "grad_norm": 3.717522923760932, | |
| "learning_rate": 1.3776161072106703e-06, | |
| "loss": 0.8789, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.5691056910569106, | |
| "grad_norm": 3.094979402727913, | |
| "learning_rate": 1.3532112366981598e-06, | |
| "loss": 0.8271, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 1.5731707317073171, | |
| "grad_norm": 2.950304755367332, | |
| "learning_rate": 1.3289905977273027e-06, | |
| "loss": 0.7035, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 1.5772357723577235, | |
| "grad_norm": 3.236742910261528, | |
| "learning_rate": 1.3049554138967052e-06, | |
| "loss": 0.7916, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 1.58130081300813, | |
| "grad_norm": 3.5425830591951066, | |
| "learning_rate": 1.2811068994359992e-06, | |
| "loss": 0.8277, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 1.5853658536585367, | |
| "grad_norm": 3.3428841825375515, | |
| "learning_rate": 1.257446259144494e-06, | |
| "loss": 0.8651, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.589430894308943, | |
| "grad_norm": 3.2634832061442762, | |
| "learning_rate": 1.233974688330315e-06, | |
| "loss": 0.8235, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 1.5934959349593496, | |
| "grad_norm": 3.437454942801004, | |
| "learning_rate": 1.210693372750017e-06, | |
| "loss": 0.7957, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 1.5975609756097562, | |
| "grad_norm": 3.4099949882842244, | |
| "learning_rate": 1.1876034885486764e-06, | |
| "loss": 0.9101, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 1.6016260162601625, | |
| "grad_norm": 2.980999635502304, | |
| "learning_rate": 1.1647062022004845e-06, | |
| "loss": 0.7977, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 1.6056910569105691, | |
| "grad_norm": 3.3813769826015077, | |
| "learning_rate": 1.1420026704498077e-06, | |
| "loss": 0.8455, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.6097560975609757, | |
| "grad_norm": 3.031087545039113, | |
| "learning_rate": 1.1194940402527566e-06, | |
| "loss": 0.847, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 1.613821138211382, | |
| "grad_norm": 3.193358851750655, | |
| "learning_rate": 1.0971814487192429e-06, | |
| "loss": 0.8444, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 1.6178861788617886, | |
| "grad_norm": 3.311582664965811, | |
| "learning_rate": 1.075066023055527e-06, | |
| "loss": 0.8936, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 1.6219512195121952, | |
| "grad_norm": 3.31773166325498, | |
| "learning_rate": 1.0531488805072848e-06, | |
| "loss": 0.8469, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 1.6260162601626016, | |
| "grad_norm": 3.427286164377091, | |
| "learning_rate": 1.0314311283031531e-06, | |
| "loss": 0.8797, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.6300813008130082, | |
| "grad_norm": 3.4289554400406272, | |
| "learning_rate": 1.0099138635988026e-06, | |
| "loss": 0.7608, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 1.6341463414634148, | |
| "grad_norm": 3.1104366578535916, | |
| "learning_rate": 9.885981734215094e-07, | |
| "loss": 0.7867, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 1.6382113821138211, | |
| "grad_norm": 3.1085297250650936, | |
| "learning_rate": 9.67485134615232e-07, | |
| "loss": 0.859, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 1.6422764227642277, | |
| "grad_norm": 3.229541553690894, | |
| "learning_rate": 9.465758137862264e-07, | |
| "loss": 0.8225, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 1.6463414634146343, | |
| "grad_norm": 3.222195108635805, | |
| "learning_rate": 9.258712672491416e-07, | |
| "loss": 0.8448, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.6504065040650406, | |
| "grad_norm": 3.0614124706443473, | |
| "learning_rate": 9.053725409736752e-07, | |
| "loss": 0.8203, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 1.654471544715447, | |
| "grad_norm": 3.1258387440254856, | |
| "learning_rate": 8.850806705317183e-07, | |
| "loss": 0.7789, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 1.6585365853658538, | |
| "grad_norm": 3.626554828178778, | |
| "learning_rate": 8.649966810450472e-07, | |
| "loss": 0.8894, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 1.6626016260162602, | |
| "grad_norm": 3.5995551223443756, | |
| "learning_rate": 8.451215871335355e-07, | |
| "loss": 0.822, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 3.3166639434548397, | |
| "learning_rate": 8.254563928638892e-07, | |
| "loss": 0.9231, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.6707317073170733, | |
| "grad_norm": 3.2249012002856867, | |
| "learning_rate": 8.060020916989331e-07, | |
| "loss": 0.851, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 1.6747967479674797, | |
| "grad_norm": 2.8257286859743123, | |
| "learning_rate": 7.86759666447412e-07, | |
| "loss": 0.7384, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 1.678861788617886, | |
| "grad_norm": 3.2981372141944196, | |
| "learning_rate": 7.677300892143485e-07, | |
| "loss": 0.8421, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 1.6829268292682928, | |
| "grad_norm": 3.6902124358425397, | |
| "learning_rate": 7.489143213519301e-07, | |
| "loss": 0.8662, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 1.6869918699186992, | |
| "grad_norm": 3.425137543714528, | |
| "learning_rate": 7.303133134109391e-07, | |
| "loss": 0.8289, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.6910569105691056, | |
| "grad_norm": 3.496178705820734, | |
| "learning_rate": 7.119280050927407e-07, | |
| "loss": 0.8694, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 1.6951219512195121, | |
| "grad_norm": 2.839539588149697, | |
| "learning_rate": 6.937593252017983e-07, | |
| "loss": 0.7891, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 1.6991869918699187, | |
| "grad_norm": 3.080879219721373, | |
| "learning_rate": 6.758081915987669e-07, | |
| "loss": 0.7891, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 1.703252032520325, | |
| "grad_norm": 3.0791115992790323, | |
| "learning_rate": 6.580755111541076e-07, | |
| "loss": 0.8322, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 1.7073170731707317, | |
| "grad_norm": 2.9278088133369686, | |
| "learning_rate": 6.405621797022848e-07, | |
| "loss": 0.8086, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.7113821138211383, | |
| "grad_norm": 3.1748945383560585, | |
| "learning_rate": 6.232690819965065e-07, | |
| "loss": 0.8606, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 1.7154471544715446, | |
| "grad_norm": 2.9963551222576577, | |
| "learning_rate": 6.061970916640236e-07, | |
| "loss": 0.7758, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 1.7195121951219512, | |
| "grad_norm": 3.3204508942195208, | |
| "learning_rate": 5.893470711620036e-07, | |
| "loss": 0.8062, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 1.7235772357723578, | |
| "grad_norm": 3.1047623326730034, | |
| "learning_rate": 5.727198717339511e-07, | |
| "loss": 0.8458, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 1.7276422764227641, | |
| "grad_norm": 2.883736699872172, | |
| "learning_rate": 5.563163333667098e-07, | |
| "loss": 0.8158, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.7317073170731707, | |
| "grad_norm": 3.464283249925107, | |
| "learning_rate": 5.401372847480285e-07, | |
| "loss": 0.8775, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 1.7357723577235773, | |
| "grad_norm": 3.2318522436014643, | |
| "learning_rate": 5.241835432246888e-07, | |
| "loss": 0.8637, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 1.7398373983739837, | |
| "grad_norm": 3.495372221002809, | |
| "learning_rate": 5.084559147612244e-07, | |
| "loss": 0.8639, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 1.7439024390243902, | |
| "grad_norm": 2.9749780792757994, | |
| "learning_rate": 4.929551938991945e-07, | |
| "loss": 0.7603, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 1.7479674796747968, | |
| "grad_norm": 3.197313436921309, | |
| "learning_rate": 4.776821637170525e-07, | |
| "loss": 0.8309, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.7520325203252032, | |
| "grad_norm": 3.145931357107065, | |
| "learning_rate": 4.626375957905821e-07, | |
| "loss": 0.8166, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 1.7560975609756098, | |
| "grad_norm": 3.0662306892293656, | |
| "learning_rate": 4.4782225015391754e-07, | |
| "loss": 0.7913, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 1.7601626016260163, | |
| "grad_norm": 2.9353362672641454, | |
| "learning_rate": 4.3323687526115045e-07, | |
| "loss": 0.8546, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 1.7642276422764227, | |
| "grad_norm": 3.041591136273237, | |
| "learning_rate": 4.1888220794851386e-07, | |
| "loss": 0.8, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 1.7682926829268293, | |
| "grad_norm": 3.4652351611448085, | |
| "learning_rate": 4.0475897339716466e-07, | |
| "loss": 0.8203, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.7723577235772359, | |
| "grad_norm": 3.2128533211337524, | |
| "learning_rate": 3.908678850965425e-07, | |
| "loss": 0.8773, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 1.7764227642276422, | |
| "grad_norm": 2.9700193205991017, | |
| "learning_rate": 3.7720964480832847e-07, | |
| "loss": 0.7585, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 1.7804878048780488, | |
| "grad_norm": 2.811315266132522, | |
| "learning_rate": 3.6378494253099307e-07, | |
| "loss": 0.7523, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.7845528455284554, | |
| "grad_norm": 2.9602663398362776, | |
| "learning_rate": 3.505944564649344e-07, | |
| "loss": 0.8212, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 1.7886178861788617, | |
| "grad_norm": 3.495997606088944, | |
| "learning_rate": 3.3763885297822153e-07, | |
| "loss": 0.8602, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.7926829268292683, | |
| "grad_norm": 3.2511151625293073, | |
| "learning_rate": 3.2491878657292643e-07, | |
| "loss": 0.7997, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 1.796747967479675, | |
| "grad_norm": 3.223561679857347, | |
| "learning_rate": 3.1243489985206097e-07, | |
| "loss": 0.7926, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 1.8008130081300813, | |
| "grad_norm": 2.978010628782192, | |
| "learning_rate": 3.001878234871147e-07, | |
| "loss": 0.8289, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 1.8048780487804879, | |
| "grad_norm": 3.6335500484232224, | |
| "learning_rate": 2.8817817618618846e-07, | |
| "loss": 0.9546, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 1.8089430894308944, | |
| "grad_norm": 3.0880272844399235, | |
| "learning_rate": 2.7640656466274785e-07, | |
| "loss": 0.8269, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 1.8130081300813008, | |
| "grad_norm": 3.0476265842662986, | |
| "learning_rate": 2.648735836049615e-07, | |
| "loss": 0.8278, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 1.8170731707317072, | |
| "grad_norm": 3.2273714580514925, | |
| "learning_rate": 2.5357981564566647e-07, | |
| "loss": 0.8837, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 1.821138211382114, | |
| "grad_norm": 3.4019435379320826, | |
| "learning_rate": 2.4252583133292927e-07, | |
| "loss": 0.8814, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 1.8252032520325203, | |
| "grad_norm": 3.228180312848657, | |
| "learning_rate": 2.3171218910122695e-07, | |
| "loss": 0.8636, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 1.8292682926829267, | |
| "grad_norm": 4.328141458441057, | |
| "learning_rate": 2.2113943524323167e-07, | |
| "loss": 0.7793, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.8333333333333335, | |
| "grad_norm": 3.279705756080727, | |
| "learning_rate": 2.1080810388221406e-07, | |
| "loss": 0.8198, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 1.8373983739837398, | |
| "grad_norm": 3.1756945998316173, | |
| "learning_rate": 2.007187169450603e-07, | |
| "loss": 0.7677, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 1.8414634146341462, | |
| "grad_norm": 2.854224611559776, | |
| "learning_rate": 1.908717841359048e-07, | |
| "loss": 0.8073, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 1.845528455284553, | |
| "grad_norm": 3.3891650093131185, | |
| "learning_rate": 1.8126780291038037e-07, | |
| "loss": 0.8719, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 1.8495934959349594, | |
| "grad_norm": 3.2156232562918166, | |
| "learning_rate": 1.7190725845048827e-07, | |
| "loss": 0.8315, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.8536585365853657, | |
| "grad_norm": 3.191126485348018, | |
| "learning_rate": 1.6279062364008446e-07, | |
| "loss": 0.8338, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 1.8577235772357723, | |
| "grad_norm": 3.2502496128696023, | |
| "learning_rate": 1.5391835904099316e-07, | |
| "loss": 0.878, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 1.8617886178861789, | |
| "grad_norm": 2.9383307925800177, | |
| "learning_rate": 1.4529091286973994e-07, | |
| "loss": 0.7495, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 1.8658536585365852, | |
| "grad_norm": 3.8927814894460075, | |
| "learning_rate": 1.3690872097490481e-07, | |
| "loss": 0.8998, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 1.8699186991869918, | |
| "grad_norm": 3.4023619692967397, | |
| "learning_rate": 1.2877220681510927e-07, | |
| "loss": 0.9376, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.8739837398373984, | |
| "grad_norm": 3.2188298190967286, | |
| "learning_rate": 1.208817814376162e-07, | |
| "loss": 0.8344, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 1.8780487804878048, | |
| "grad_norm": 3.2462630804047654, | |
| "learning_rate": 1.1323784345757205e-07, | |
| "loss": 0.8377, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 1.8821138211382114, | |
| "grad_norm": 3.392899106863404, | |
| "learning_rate": 1.0584077903786238e-07, | |
| "loss": 0.8516, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 1.886178861788618, | |
| "grad_norm": 3.182002261377221, | |
| "learning_rate": 9.869096186961025e-08, | |
| "loss": 0.8085, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 1.8902439024390243, | |
| "grad_norm": 3.1650002830415613, | |
| "learning_rate": 9.178875315329183e-08, | |
| "loss": 0.8175, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.8943089430894309, | |
| "grad_norm": 3.218966966848088, | |
| "learning_rate": 8.513450158049109e-08, | |
| "loss": 0.8363, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 1.8983739837398375, | |
| "grad_norm": 3.408262645552228, | |
| "learning_rate": 7.872854331628599e-08, | |
| "loss": 0.9397, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 1.9024390243902438, | |
| "grad_norm": 3.8342857272726696, | |
| "learning_rate": 7.257120198226219e-08, | |
| "loss": 0.8542, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.9065040650406504, | |
| "grad_norm": 3.1564453475681287, | |
| "learning_rate": 6.666278864016884e-08, | |
| "loss": 0.8513, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 1.910569105691057, | |
| "grad_norm": 3.2217807303958064, | |
| "learning_rate": 6.100360177619946e-08, | |
| "loss": 0.8503, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.9146341463414633, | |
| "grad_norm": 3.2114649161235356, | |
| "learning_rate": 5.559392728591517e-08, | |
| "loss": 0.9171, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 1.91869918699187, | |
| "grad_norm": 3.352405009441328, | |
| "learning_rate": 5.0434038459801213e-08, | |
| "loss": 0.8159, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 1.9227642276422765, | |
| "grad_norm": 3.1814982432174093, | |
| "learning_rate": 4.5524195969461895e-08, | |
| "loss": 0.8304, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 1.9268292682926829, | |
| "grad_norm": 3.158205461981237, | |
| "learning_rate": 4.086464785444777e-08, | |
| "loss": 0.7888, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 1.9308943089430894, | |
| "grad_norm": 2.8037462602147545, | |
| "learning_rate": 3.645562950973014e-08, | |
| "loss": 0.6949, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.934959349593496, | |
| "grad_norm": 2.980787245749961, | |
| "learning_rate": 3.229736367380498e-08, | |
| "loss": 0.7739, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 1.9390243902439024, | |
| "grad_norm": 3.128680334368289, | |
| "learning_rate": 2.8390060417443632e-08, | |
| "loss": 0.8677, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 1.943089430894309, | |
| "grad_norm": 3.7477720931810956, | |
| "learning_rate": 2.4733917133077378e-08, | |
| "loss": 0.9261, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 1.9471544715447155, | |
| "grad_norm": 3.689456926619419, | |
| "learning_rate": 2.1329118524827662e-08, | |
| "loss": 0.9032, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 1.951219512195122, | |
| "grad_norm": 3.5300716074533813, | |
| "learning_rate": 1.8175836599173545e-08, | |
| "loss": 0.8511, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.9552845528455285, | |
| "grad_norm": 3.1505817427132325, | |
| "learning_rate": 1.5274230656263656e-08, | |
| "loss": 0.7846, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 1.959349593495935, | |
| "grad_norm": 3.022385863744955, | |
| "learning_rate": 1.2624447281867625e-08, | |
| "loss": 0.7325, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 1.9634146341463414, | |
| "grad_norm": 3.3794689368212647, | |
| "learning_rate": 1.0226620339969795e-08, | |
| "loss": 0.8091, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 1.967479674796748, | |
| "grad_norm": 2.9275122073562, | |
| "learning_rate": 8.080870966008513e-09, | |
| "loss": 0.7285, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 1.9715447154471546, | |
| "grad_norm": 3.3140577653029806, | |
| "learning_rate": 6.187307560754363e-09, | |
| "loss": 0.8462, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 1.975609756097561, | |
| "grad_norm": 3.0026431051566926, | |
| "learning_rate": 4.546025784837316e-09, | |
| "loss": 0.7951, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 1.9796747967479673, | |
| "grad_norm": 3.4729051127349893, | |
| "learning_rate": 3.1571085539089384e-09, | |
| "loss": 0.8688, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 1.9837398373983741, | |
| "grad_norm": 2.662940908363704, | |
| "learning_rate": 2.0206260344590724e-09, | |
| "loss": 0.6993, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 1.9878048780487805, | |
| "grad_norm": 3.6478034020803274, | |
| "learning_rate": 1.136635640267003e-09, | |
| "loss": 0.8605, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 1.9918699186991868, | |
| "grad_norm": 3.5646048965813932, | |
| "learning_rate": 5.051820295032262e-10, | |
| "loss": 0.8902, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.9959349593495936, | |
| "grad_norm": 3.0096957163094813, | |
| "learning_rate": 1.2629710247180626e-10, | |
| "loss": 0.8419, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 3.5971711883525903, | |
| "learning_rate": 0.0, | |
| "loss": 0.898, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 492, | |
| "total_flos": 10700496175104.0, | |
| "train_loss": 1.062965918483773, | |
| "train_runtime": 414.7958, | |
| "train_samples_per_second": 37.937, | |
| "train_steps_per_second": 1.186 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 492, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 10700496175104.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |