Instructions to use Lie24/Role_LLM_Cube_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Lie24/Role_LLM_Cube_v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Lie24/Role_LLM_Cube_v1") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Lie24/Role_LLM_Cube_v1") model = AutoModelForCausalLM.from_pretrained("Lie24/Role_LLM_Cube_v1") 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 Lie24/Role_LLM_Cube_v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Lie24/Role_LLM_Cube_v1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Lie24/Role_LLM_Cube_v1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Lie24/Role_LLM_Cube_v1
- SGLang
How to use Lie24/Role_LLM_Cube_v1 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 "Lie24/Role_LLM_Cube_v1" \ --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": "Lie24/Role_LLM_Cube_v1", "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 "Lie24/Role_LLM_Cube_v1" \ --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": "Lie24/Role_LLM_Cube_v1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Lie24/Role_LLM_Cube_v1 with Docker Model Runner:
docker model run hf.co/Lie24/Role_LLM_Cube_v1
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 200, | |
| "global_step": 470, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02127659574468085, | |
| "grad_norm": 19.769559521884688, | |
| "learning_rate": 2.5000000000000004e-07, | |
| "loss": 1.5136, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0425531914893617, | |
| "grad_norm": 22.366909847966127, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 1.4656, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06382978723404255, | |
| "grad_norm": 27.397989604017898, | |
| "learning_rate": 7.5e-07, | |
| "loss": 1.5124, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": 18.58567583552412, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.5225, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10638297872340426, | |
| "grad_norm": 18.165996038203307, | |
| "learning_rate": 1.25e-06, | |
| "loss": 1.5576, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1276595744680851, | |
| "grad_norm": 13.681392535187342, | |
| "learning_rate": 1.5e-06, | |
| "loss": 1.4687, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14893617021276595, | |
| "grad_norm": 14.999691223127021, | |
| "learning_rate": 1.75e-06, | |
| "loss": 1.3933, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1702127659574468, | |
| "grad_norm": 9.360244090412072, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.4721, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.19148936170212766, | |
| "grad_norm": 11.174023539278728, | |
| "learning_rate": 2.25e-06, | |
| "loss": 1.44, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2127659574468085, | |
| "grad_norm": 9.866648780480253, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.2595, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.23404255319148937, | |
| "grad_norm": 9.512446051741868, | |
| "learning_rate": 2.7500000000000004e-06, | |
| "loss": 1.4442, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2553191489361702, | |
| "grad_norm": 8.670274331402473, | |
| "learning_rate": 3e-06, | |
| "loss": 1.2739, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2765957446808511, | |
| "grad_norm": 6.920817280642445, | |
| "learning_rate": 3.2500000000000002e-06, | |
| "loss": 1.276, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2978723404255319, | |
| "grad_norm": 7.10414215318037, | |
| "learning_rate": 3.5e-06, | |
| "loss": 1.2421, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3191489361702128, | |
| "grad_norm": 6.159725671936445, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 1.239, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 7.6873175205954825, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.2396, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3617021276595745, | |
| "grad_norm": 6.528518611068642, | |
| "learning_rate": 4.25e-06, | |
| "loss": 1.1543, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3829787234042553, | |
| "grad_norm": 6.77428307591927, | |
| "learning_rate": 4.5e-06, | |
| "loss": 1.1545, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.40425531914893614, | |
| "grad_norm": 6.417164213417, | |
| "learning_rate": 4.75e-06, | |
| "loss": 1.0959, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.425531914893617, | |
| "grad_norm": 6.180266176299509, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1381, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.44680851063829785, | |
| "grad_norm": 6.238735118043302, | |
| "learning_rate": 4.999939076763487e-06, | |
| "loss": 0.9938, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.46808510638297873, | |
| "grad_norm": 5.503542713382496, | |
| "learning_rate": 4.999756310023261e-06, | |
| "loss": 1.0336, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.48936170212765956, | |
| "grad_norm": 5.7109281559241305, | |
| "learning_rate": 4.999451708687114e-06, | |
| "loss": 1.0293, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5106382978723404, | |
| "grad_norm": 5.933533265865748, | |
| "learning_rate": 4.999025287600886e-06, | |
| "loss": 1.0838, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5319148936170213, | |
| "grad_norm": 6.058382477727568, | |
| "learning_rate": 4.99847706754774e-06, | |
| "loss": 1.147, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5531914893617021, | |
| "grad_norm": 5.039016064603872, | |
| "learning_rate": 4.997807075247147e-06, | |
| "loss": 1.0661, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.574468085106383, | |
| "grad_norm": 5.673653311719194, | |
| "learning_rate": 4.9970153433535855e-06, | |
| "loss": 1.1088, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5957446808510638, | |
| "grad_norm": 6.772514217020031, | |
| "learning_rate": 4.996101910454953e-06, | |
| "loss": 1.0398, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6170212765957447, | |
| "grad_norm": 7.261784604470834, | |
| "learning_rate": 4.9950668210706795e-06, | |
| "loss": 1.1197, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6382978723404256, | |
| "grad_norm": 5.125305508590899, | |
| "learning_rate": 4.993910125649561e-06, | |
| "loss": 1.0096, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6595744680851063, | |
| "grad_norm": 5.79320276945061, | |
| "learning_rate": 4.992631880567301e-06, | |
| "loss": 1.0418, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 6.583723424976928, | |
| "learning_rate": 4.9912321481237616e-06, | |
| "loss": 1.1084, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7021276595744681, | |
| "grad_norm": 5.166238541818618, | |
| "learning_rate": 4.989710996539926e-06, | |
| "loss": 1.0269, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.723404255319149, | |
| "grad_norm": 4.702597984819574, | |
| "learning_rate": 4.988068499954578e-06, | |
| "loss": 0.9362, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7446808510638298, | |
| "grad_norm": 5.035553587199529, | |
| "learning_rate": 4.986304738420684e-06, | |
| "loss": 1.0027, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7659574468085106, | |
| "grad_norm": 5.979469659293992, | |
| "learning_rate": 4.984419797901491e-06, | |
| "loss": 1.0197, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7872340425531915, | |
| "grad_norm": 7.251693613828905, | |
| "learning_rate": 4.9824137702663424e-06, | |
| "loss": 1.0665, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8085106382978723, | |
| "grad_norm": 5.336704026070371, | |
| "learning_rate": 4.980286753286196e-06, | |
| "loss": 1.0612, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8297872340425532, | |
| "grad_norm": 4.572621845298497, | |
| "learning_rate": 4.978038850628855e-06, | |
| "loss": 0.891, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 5.901358668805014, | |
| "learning_rate": 4.975670171853926e-06, | |
| "loss": 1.003, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8723404255319149, | |
| "grad_norm": 5.967637194891353, | |
| "learning_rate": 4.973180832407471e-06, | |
| "loss": 1.0412, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8936170212765957, | |
| "grad_norm": 4.651650771697547, | |
| "learning_rate": 4.970570953616383e-06, | |
| "loss": 0.905, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9148936170212766, | |
| "grad_norm": 4.40595275321189, | |
| "learning_rate": 4.96784066268247e-06, | |
| "loss": 0.9606, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9361702127659575, | |
| "grad_norm": 4.297391018229843, | |
| "learning_rate": 4.964990092676263e-06, | |
| "loss": 0.912, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9574468085106383, | |
| "grad_norm": 5.8520797403685565, | |
| "learning_rate": 4.962019382530521e-06, | |
| "loss": 0.99, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9787234042553191, | |
| "grad_norm": 4.460582020214977, | |
| "learning_rate": 4.958928677033465e-06, | |
| "loss": 0.9338, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 5.108150405797771, | |
| "learning_rate": 4.9557181268217225e-06, | |
| "loss": 0.8841, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0212765957446808, | |
| "grad_norm": 4.42640489710439, | |
| "learning_rate": 4.9523878883729794e-06, | |
| "loss": 0.6441, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0425531914893618, | |
| "grad_norm": 4.783433777129786, | |
| "learning_rate": 4.94893812399836e-06, | |
| "loss": 0.7076, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "grad_norm": 4.461478664530093, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "loss": 0.6507, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0851063829787233, | |
| "grad_norm": 4.659068920568944, | |
| "learning_rate": 4.9416806958354206e-06, | |
| "loss": 0.6388, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.1063829787234043, | |
| "grad_norm": 5.326272476452319, | |
| "learning_rate": 4.937873385763909e-06, | |
| "loss": 0.6629, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.127659574468085, | |
| "grad_norm": 4.42497697146127, | |
| "learning_rate": 4.933947257182901e-06, | |
| "loss": 0.6969, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.148936170212766, | |
| "grad_norm": 4.342156315066868, | |
| "learning_rate": 4.9299025014463665e-06, | |
| "loss": 0.6389, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.1702127659574468, | |
| "grad_norm": 5.535251688604961, | |
| "learning_rate": 4.925739315689991e-06, | |
| "loss": 0.6549, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.1914893617021276, | |
| "grad_norm": 4.098290419568537, | |
| "learning_rate": 4.921457902821578e-06, | |
| "loss": 0.6581, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.2127659574468086, | |
| "grad_norm": 4.804191552305714, | |
| "learning_rate": 4.917058471511149e-06, | |
| "loss": 0.6574, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.2340425531914894, | |
| "grad_norm": 4.661998643228261, | |
| "learning_rate": 4.912541236180779e-06, | |
| "loss": 0.6206, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.2553191489361701, | |
| "grad_norm": 5.457436437790183, | |
| "learning_rate": 4.907906416994146e-06, | |
| "loss": 0.6949, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.2765957446808511, | |
| "grad_norm": 5.287463616155875, | |
| "learning_rate": 4.903154239845798e-06, | |
| "loss": 0.6171, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.297872340425532, | |
| "grad_norm": 6.534162370166582, | |
| "learning_rate": 4.898284936350144e-06, | |
| "loss": 0.6738, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.3191489361702127, | |
| "grad_norm": 5.14242301334199, | |
| "learning_rate": 4.893298743830168e-06, | |
| "loss": 0.71, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.3404255319148937, | |
| "grad_norm": 4.864653117677477, | |
| "learning_rate": 4.888195905305859e-06, | |
| "loss": 0.6353, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.3617021276595744, | |
| "grad_norm": 4.469502230256778, | |
| "learning_rate": 4.882976669482368e-06, | |
| "loss": 0.6301, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.3829787234042552, | |
| "grad_norm": 4.650400360608429, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 0.6298, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.4042553191489362, | |
| "grad_norm": 4.75068049245489, | |
| "learning_rate": 4.8721900291112415e-06, | |
| "loss": 0.6132, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.425531914893617, | |
| "grad_norm": 5.406681668582622, | |
| "learning_rate": 4.866623150289241e-06, | |
| "loss": 0.6177, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.4468085106382977, | |
| "grad_norm": 4.689427420330228, | |
| "learning_rate": 4.860940925593703e-06, | |
| "loss": 0.601, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.4680851063829787, | |
| "grad_norm": 5.66362626435671, | |
| "learning_rate": 4.855143631968242e-06, | |
| "loss": 0.6987, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.4893617021276595, | |
| "grad_norm": 6.639330863120106, | |
| "learning_rate": 4.849231551964771e-06, | |
| "loss": 0.705, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.5106382978723403, | |
| "grad_norm": 5.15079243645691, | |
| "learning_rate": 4.84320497372973e-06, | |
| "loss": 0.6812, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.5319148936170213, | |
| "grad_norm": 5.318900788335571, | |
| "learning_rate": 4.837064190990036e-06, | |
| "loss": 0.6717, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.5531914893617023, | |
| "grad_norm": 4.39050844628742, | |
| "learning_rate": 4.830809503038781e-06, | |
| "loss": 0.5978, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.574468085106383, | |
| "grad_norm": 4.11981361882099, | |
| "learning_rate": 4.824441214720629e-06, | |
| "loss": 0.5789, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.5957446808510638, | |
| "grad_norm": 4.898106888331966, | |
| "learning_rate": 4.817959636416969e-06, | |
| "loss": 0.638, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.6170212765957448, | |
| "grad_norm": 4.144574853637901, | |
| "learning_rate": 4.811365084030784e-06, | |
| "loss": 0.6631, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.6382978723404256, | |
| "grad_norm": 4.236596267103849, | |
| "learning_rate": 4.804657878971252e-06, | |
| "loss": 0.5618, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.6595744680851063, | |
| "grad_norm": 4.772661867276851, | |
| "learning_rate": 4.7978383481380865e-06, | |
| "loss": 0.6064, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.6808510638297873, | |
| "grad_norm": 5.5176007762843335, | |
| "learning_rate": 4.790906823905599e-06, | |
| "loss": 0.6346, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.702127659574468, | |
| "grad_norm": 4.1371187239001825, | |
| "learning_rate": 4.783863644106502e-06, | |
| "loss": 0.598, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.7234042553191489, | |
| "grad_norm": 4.617726148114806, | |
| "learning_rate": 4.776709152015443e-06, | |
| "loss": 0.572, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.7446808510638299, | |
| "grad_norm": 4.389883430040871, | |
| "learning_rate": 4.769443696332272e-06, | |
| "loss": 0.6145, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.7659574468085106, | |
| "grad_norm": 5.027199601611735, | |
| "learning_rate": 4.762067631165049e-06, | |
| "loss": 0.6858, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.7872340425531914, | |
| "grad_norm": 4.990601804039334, | |
| "learning_rate": 4.754581316012785e-06, | |
| "loss": 0.561, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.8085106382978724, | |
| "grad_norm": 5.705018779334882, | |
| "learning_rate": 4.746985115747918e-06, | |
| "loss": 0.6323, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.8297872340425532, | |
| "grad_norm": 5.1505009350987265, | |
| "learning_rate": 4.7392794005985324e-06, | |
| "loss": 0.5952, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.851063829787234, | |
| "grad_norm": 5.16517962200903, | |
| "learning_rate": 4.731464546130315e-06, | |
| "loss": 0.6462, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.872340425531915, | |
| "grad_norm": 5.203202926098486, | |
| "learning_rate": 4.723540933228245e-06, | |
| "loss": 0.5949, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.8936170212765957, | |
| "grad_norm": 4.6706368589871134, | |
| "learning_rate": 4.715508948078037e-06, | |
| "loss": 0.5878, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.9148936170212765, | |
| "grad_norm": 4.351714864184194, | |
| "learning_rate": 4.707368982147318e-06, | |
| "loss": 0.6227, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.9361702127659575, | |
| "grad_norm": 5.11397965814302, | |
| "learning_rate": 4.699121432166542e-06, | |
| "loss": 0.6347, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.9574468085106385, | |
| "grad_norm": 5.875205347984843, | |
| "learning_rate": 4.690766700109659e-06, | |
| "loss": 0.5905, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.978723404255319, | |
| "grad_norm": 6.03539957826197, | |
| "learning_rate": 4.682305193174524e-06, | |
| "loss": 0.6894, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 3.8707434069223026, | |
| "learning_rate": 4.673737323763048e-06, | |
| "loss": 0.4095, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 2.021276595744681, | |
| "grad_norm": 4.967672001558827, | |
| "learning_rate": 4.665063509461098e-06, | |
| "loss": 0.3403, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 2.0425531914893615, | |
| "grad_norm": 3.5072435391900436, | |
| "learning_rate": 4.656284173018144e-06, | |
| "loss": 0.3736, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.0638297872340425, | |
| "grad_norm": 4.360376932941338, | |
| "learning_rate": 4.6473997423266615e-06, | |
| "loss": 0.4061, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 2.0851063829787235, | |
| "grad_norm": 4.224245961638772, | |
| "learning_rate": 4.638410650401267e-06, | |
| "loss": 0.3515, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 2.106382978723404, | |
| "grad_norm": 4.792845268520252, | |
| "learning_rate": 4.62931733535762e-06, | |
| "loss": 0.3432, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 2.127659574468085, | |
| "grad_norm": 4.9719261969262085, | |
| "learning_rate": 4.620120240391065e-06, | |
| "loss": 0.3495, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.148936170212766, | |
| "grad_norm": 3.9393952177630864, | |
| "learning_rate": 4.610819813755038e-06, | |
| "loss": 0.3505, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 2.1702127659574466, | |
| "grad_norm": 5.0676129989734084, | |
| "learning_rate": 4.601416508739211e-06, | |
| "loss": 0.345, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.1914893617021276, | |
| "grad_norm": 4.268873683189594, | |
| "learning_rate": 4.591910783647405e-06, | |
| "loss": 0.3411, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 2.2127659574468086, | |
| "grad_norm": 5.648372477585861, | |
| "learning_rate": 4.582303101775249e-06, | |
| "loss": 0.3414, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.2340425531914896, | |
| "grad_norm": 4.569109738179888, | |
| "learning_rate": 4.572593931387604e-06, | |
| "loss": 0.3107, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.25531914893617, | |
| "grad_norm": 5.986604177134095, | |
| "learning_rate": 4.562783745695738e-06, | |
| "loss": 0.358, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 2.276595744680851, | |
| "grad_norm": 4.593476704693552, | |
| "learning_rate": 4.55287302283426e-06, | |
| "loss": 0.3938, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 2.297872340425532, | |
| "grad_norm": 4.729132719197455, | |
| "learning_rate": 4.542862245837821e-06, | |
| "loss": 0.3445, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.3191489361702127, | |
| "grad_norm": 5.319389221723198, | |
| "learning_rate": 4.5327519026175694e-06, | |
| "loss": 0.3638, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 2.3404255319148937, | |
| "grad_norm": 4.9962223266535295, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 0.3151, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.3617021276595747, | |
| "grad_norm": 5.43349545021367, | |
| "learning_rate": 4.512234493389785e-06, | |
| "loss": 0.3386, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 2.382978723404255, | |
| "grad_norm": 4.228899687733491, | |
| "learning_rate": 4.501828427371834e-06, | |
| "loss": 0.3381, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.404255319148936, | |
| "grad_norm": 3.9364311500151214, | |
| "learning_rate": 4.491324795060491e-06, | |
| "loss": 0.3419, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 2.425531914893617, | |
| "grad_norm": 6.072764335330948, | |
| "learning_rate": 4.4807241083879774e-06, | |
| "loss": 0.3447, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.4468085106382977, | |
| "grad_norm": 4.690579387500509, | |
| "learning_rate": 4.470026884016805e-06, | |
| "loss": 0.3296, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.4680851063829787, | |
| "grad_norm": 4.772781283406453, | |
| "learning_rate": 4.4592336433146e-06, | |
| "loss": 0.3112, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.4893617021276597, | |
| "grad_norm": 4.222608771767499, | |
| "learning_rate": 4.448344912328686e-06, | |
| "loss": 0.3602, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 2.5106382978723403, | |
| "grad_norm": 4.806194387046772, | |
| "learning_rate": 4.437361221760449e-06, | |
| "loss": 0.3433, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.5319148936170213, | |
| "grad_norm": 4.610773667593825, | |
| "learning_rate": 4.426283106939474e-06, | |
| "loss": 0.3423, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 2.5531914893617023, | |
| "grad_norm": 3.9378113503820114, | |
| "learning_rate": 4.415111107797445e-06, | |
| "loss": 0.335, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.574468085106383, | |
| "grad_norm": 4.262317442324841, | |
| "learning_rate": 4.403845768841842e-06, | |
| "loss": 0.2964, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 2.595744680851064, | |
| "grad_norm": 4.586717288805483, | |
| "learning_rate": 4.3924876391293915e-06, | |
| "loss": 0.3503, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.617021276595745, | |
| "grad_norm": 4.420522314781192, | |
| "learning_rate": 4.381037272239311e-06, | |
| "loss": 0.348, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.6382978723404253, | |
| "grad_norm": 3.6908626258947694, | |
| "learning_rate": 4.36949522624633e-06, | |
| "loss": 0.3473, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.6595744680851063, | |
| "grad_norm": 4.276095484034931, | |
| "learning_rate": 4.357862063693486e-06, | |
| "loss": 0.3734, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.6808510638297873, | |
| "grad_norm": 4.16461417799402, | |
| "learning_rate": 4.346138351564711e-06, | |
| "loss": 0.3563, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.702127659574468, | |
| "grad_norm": 4.106373804902514, | |
| "learning_rate": 4.334324661257191e-06, | |
| "loss": 0.2954, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 2.723404255319149, | |
| "grad_norm": 4.113950324587281, | |
| "learning_rate": 4.322421568553529e-06, | |
| "loss": 0.3443, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.74468085106383, | |
| "grad_norm": 4.190826822795899, | |
| "learning_rate": 4.3104296535936695e-06, | |
| "loss": 0.3395, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.7659574468085104, | |
| "grad_norm": 4.9676092124733575, | |
| "learning_rate": 4.2983495008466285e-06, | |
| "loss": 0.3789, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.7872340425531914, | |
| "grad_norm": 4.175058791875455, | |
| "learning_rate": 4.286181699082008e-06, | |
| "loss": 0.3388, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 2.8085106382978724, | |
| "grad_norm": 5.475615243400478, | |
| "learning_rate": 4.273926841341303e-06, | |
| "loss": 0.3614, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.829787234042553, | |
| "grad_norm": 4.132179706281526, | |
| "learning_rate": 4.261585524908987e-06, | |
| "loss": 0.3031, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 2.851063829787234, | |
| "grad_norm": 4.52680856181224, | |
| "learning_rate": 4.249158351283414e-06, | |
| "loss": 0.3202, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.872340425531915, | |
| "grad_norm": 4.4158856257333206, | |
| "learning_rate": 4.236645926147493e-06, | |
| "loss": 0.3817, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.8936170212765955, | |
| "grad_norm": 4.131675629353336, | |
| "learning_rate": 4.224048859339175e-06, | |
| "loss": 0.325, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.9148936170212765, | |
| "grad_norm": 4.632609969168001, | |
| "learning_rate": 4.211367764821722e-06, | |
| "loss": 0.339, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 2.9361702127659575, | |
| "grad_norm": 4.238399617644217, | |
| "learning_rate": 4.198603260653792e-06, | |
| "loss": 0.3803, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.9574468085106385, | |
| "grad_norm": 4.990761801935908, | |
| "learning_rate": 4.185755968959308e-06, | |
| "loss": 0.3447, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 2.978723404255319, | |
| "grad_norm": 4.548241919258143, | |
| "learning_rate": 4.172826515897146e-06, | |
| "loss": 0.3518, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 3.430910087137401, | |
| "learning_rate": 4.159815531630604e-06, | |
| "loss": 0.2304, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 3.021276595744681, | |
| "grad_norm": 3.668126527915725, | |
| "learning_rate": 4.146723650296701e-06, | |
| "loss": 0.2235, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 3.0425531914893615, | |
| "grad_norm": 2.8667931520747327, | |
| "learning_rate": 4.133551509975264e-06, | |
| "loss": 0.1883, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 3.0638297872340425, | |
| "grad_norm": 3.5239577403765106, | |
| "learning_rate": 4.120299752657828e-06, | |
| "loss": 0.2217, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 3.0851063829787235, | |
| "grad_norm": 3.6921907938710308, | |
| "learning_rate": 4.106969024216348e-06, | |
| "loss": 0.2049, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 3.106382978723404, | |
| "grad_norm": 3.6392973250804577, | |
| "learning_rate": 4.093559974371725e-06, | |
| "loss": 0.1831, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 3.127659574468085, | |
| "grad_norm": 3.7365922708313133, | |
| "learning_rate": 4.080073256662128e-06, | |
| "loss": 0.198, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 3.148936170212766, | |
| "grad_norm": 4.42100805526352, | |
| "learning_rate": 4.066509528411151e-06, | |
| "loss": 0.1593, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 3.1702127659574466, | |
| "grad_norm": 3.701129708479829, | |
| "learning_rate": 4.052869450695776e-06, | |
| "loss": 0.1542, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 3.1914893617021276, | |
| "grad_norm": 3.9620190917388793, | |
| "learning_rate": 4.039153688314146e-06, | |
| "loss": 0.1673, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.2127659574468086, | |
| "grad_norm": 4.596659093022736, | |
| "learning_rate": 4.02536290975317e-06, | |
| "loss": 0.1781, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 3.2340425531914896, | |
| "grad_norm": 4.041018040517897, | |
| "learning_rate": 4.011497787155938e-06, | |
| "loss": 0.204, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 3.25531914893617, | |
| "grad_norm": 4.4750076668231324, | |
| "learning_rate": 3.997558996288965e-06, | |
| "loss": 0.2042, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 3.276595744680851, | |
| "grad_norm": 4.328565873011614, | |
| "learning_rate": 3.983547216509254e-06, | |
| "loss": 0.206, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 3.297872340425532, | |
| "grad_norm": 4.950916510385211, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 0.1735, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 3.3191489361702127, | |
| "grad_norm": 3.6634515919781356, | |
| "learning_rate": 3.955307425393224e-06, | |
| "loss": 0.2152, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 3.3404255319148937, | |
| "grad_norm": 3.5183557309327127, | |
| "learning_rate": 3.941080790424483e-06, | |
| "loss": 0.1788, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 3.3617021276595747, | |
| "grad_norm": 4.2312437308996245, | |
| "learning_rate": 3.92678391921108e-06, | |
| "loss": 0.1817, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 3.382978723404255, | |
| "grad_norm": 3.4224234758888654, | |
| "learning_rate": 3.912417508562345e-06, | |
| "loss": 0.1577, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 3.404255319148936, | |
| "grad_norm": 3.7251058715223597, | |
| "learning_rate": 3.897982258676867e-06, | |
| "loss": 0.2067, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.425531914893617, | |
| "grad_norm": 3.123331948611014, | |
| "learning_rate": 3.88347887310836e-06, | |
| "loss": 0.1867, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 3.4468085106382977, | |
| "grad_norm": 3.040022180599425, | |
| "learning_rate": 3.868908058731376e-06, | |
| "loss": 0.1488, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 3.4680851063829787, | |
| "grad_norm": 3.936251625166522, | |
| "learning_rate": 3.85427052570685e-06, | |
| "loss": 0.175, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 3.4893617021276597, | |
| "grad_norm": 3.35819244249543, | |
| "learning_rate": 3.839566987447492e-06, | |
| "loss": 0.1992, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 3.5106382978723403, | |
| "grad_norm": 3.8098483118828335, | |
| "learning_rate": 3.824798160583012e-06, | |
| "loss": 0.1677, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 3.5319148936170213, | |
| "grad_norm": 4.08720146453336, | |
| "learning_rate": 3.8099647649251984e-06, | |
| "loss": 0.1975, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 3.5531914893617023, | |
| "grad_norm": 3.546201338791242, | |
| "learning_rate": 3.795067523432826e-06, | |
| "loss": 0.1643, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 3.574468085106383, | |
| "grad_norm": 4.022986409946214, | |
| "learning_rate": 3.780107162176429e-06, | |
| "loss": 0.2025, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 3.595744680851064, | |
| "grad_norm": 4.116301951633153, | |
| "learning_rate": 3.7650844103029093e-06, | |
| "loss": 0.2063, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 3.617021276595745, | |
| "grad_norm": 5.498041562915274, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.1969, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.6382978723404253, | |
| "grad_norm": 3.571990562222316, | |
| "learning_rate": 3.7348546664605777e-06, | |
| "loss": 0.1946, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 3.6595744680851063, | |
| "grad_norm": 4.110746067790737, | |
| "learning_rate": 3.7196491478468322e-06, | |
| "loss": 0.192, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 3.6808510638297873, | |
| "grad_norm": 3.9747616004152984, | |
| "learning_rate": 3.7043841852542884e-06, | |
| "loss": 0.2076, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 3.702127659574468, | |
| "grad_norm": 4.049886537167864, | |
| "learning_rate": 3.689060522675689e-06, | |
| "loss": 0.1885, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 3.723404255319149, | |
| "grad_norm": 3.7605106851151593, | |
| "learning_rate": 3.6736789069647273e-06, | |
| "loss": 0.1819, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 3.74468085106383, | |
| "grad_norm": 4.293344674761706, | |
| "learning_rate": 3.658240087799655e-06, | |
| "loss": 0.1782, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 3.7659574468085104, | |
| "grad_norm": 3.094426165785156, | |
| "learning_rate": 3.642744817646736e-06, | |
| "loss": 0.1562, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 3.7872340425531914, | |
| "grad_norm": 4.471233004565249, | |
| "learning_rate": 3.627193851723577e-06, | |
| "loss": 0.1538, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 3.8085106382978724, | |
| "grad_norm": 3.8346276158744823, | |
| "learning_rate": 3.611587947962319e-06, | |
| "loss": 0.2037, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 3.829787234042553, | |
| "grad_norm": 4.6309266206267745, | |
| "learning_rate": 3.595927866972694e-06, | |
| "loss": 0.1706, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.851063829787234, | |
| "grad_norm": 3.574650150496055, | |
| "learning_rate": 3.5802143720049565e-06, | |
| "loss": 0.1793, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 3.872340425531915, | |
| "grad_norm": 4.104316685959246, | |
| "learning_rate": 3.564448228912682e-06, | |
| "loss": 0.1997, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 3.8936170212765955, | |
| "grad_norm": 3.7077174376752815, | |
| "learning_rate": 3.5486302061154433e-06, | |
| "loss": 0.2397, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 3.9148936170212765, | |
| "grad_norm": 3.8535618259715863, | |
| "learning_rate": 3.532761074561355e-06, | |
| "loss": 0.1724, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 3.9361702127659575, | |
| "grad_norm": 4.153454591162772, | |
| "learning_rate": 3.516841607689501e-06, | |
| "loss": 0.1879, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 3.9574468085106385, | |
| "grad_norm": 3.2186742898572254, | |
| "learning_rate": 3.5008725813922383e-06, | |
| "loss": 0.1793, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 3.978723404255319, | |
| "grad_norm": 3.8852555348009066, | |
| "learning_rate": 3.4848547739773782e-06, | |
| "loss": 0.2205, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 3.1773700849249984, | |
| "learning_rate": 3.4687889661302577e-06, | |
| "loss": 0.1375, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 4.0212765957446805, | |
| "grad_norm": 2.909112047920458, | |
| "learning_rate": 3.452675940875686e-06, | |
| "loss": 0.1081, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 4.042553191489362, | |
| "grad_norm": 2.5683738553439794, | |
| "learning_rate": 3.436516483539781e-06, | |
| "loss": 0.0953, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.0638297872340425, | |
| "grad_norm": 2.9198721500124845, | |
| "learning_rate": 3.4203113817116955e-06, | |
| "loss": 0.1053, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 4.085106382978723, | |
| "grad_norm": 2.24010493827577, | |
| "learning_rate": 3.4040614252052305e-06, | |
| "loss": 0.0927, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 4.1063829787234045, | |
| "grad_norm": 2.878670182658427, | |
| "learning_rate": 3.387767406020343e-06, | |
| "loss": 0.103, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 4.127659574468085, | |
| "grad_norm": 3.1788187649976978, | |
| "learning_rate": 3.3714301183045382e-06, | |
| "loss": 0.1118, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 4.148936170212766, | |
| "grad_norm": 3.3067413198545634, | |
| "learning_rate": 3.3550503583141726e-06, | |
| "loss": 0.1099, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 4.170212765957447, | |
| "grad_norm": 2.319050087976373, | |
| "learning_rate": 3.338628924375638e-06, | |
| "loss": 0.0898, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 4.191489361702128, | |
| "grad_norm": 2.6474547453865895, | |
| "learning_rate": 3.3221666168464584e-06, | |
| "loss": 0.0915, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 4.212765957446808, | |
| "grad_norm": 3.2898592433873217, | |
| "learning_rate": 3.3056642380762783e-06, | |
| "loss": 0.076, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 4.23404255319149, | |
| "grad_norm": 3.7084220696956685, | |
| "learning_rate": 3.2891225923677565e-06, | |
| "loss": 0.0832, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 4.25531914893617, | |
| "grad_norm": 3.853474111497437, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 0.1113, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.25531914893617, | |
| "eval_loss": 1.3551427125930786, | |
| "eval_runtime": 1.3449, | |
| "eval_samples_per_second": 17.102, | |
| "eval_steps_per_second": 0.744, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.276595744680851, | |
| "grad_norm": 3.1480732576505686, | |
| "learning_rate": 3.2559247268761117e-06, | |
| "loss": 0.0894, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 4.297872340425532, | |
| "grad_norm": 4.224708808728799, | |
| "learning_rate": 3.2392701251101172e-06, | |
| "loss": 0.1037, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 4.319148936170213, | |
| "grad_norm": 3.127550241031144, | |
| "learning_rate": 3.222579492361179e-06, | |
| "loss": 0.1193, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 4.340425531914893, | |
| "grad_norm": 3.358278204814404, | |
| "learning_rate": 3.205853642107192e-06, | |
| "loss": 0.1088, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 4.361702127659575, | |
| "grad_norm": 3.5723872992052668, | |
| "learning_rate": 3.189093389542498e-06, | |
| "loss": 0.1156, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 4.382978723404255, | |
| "grad_norm": 3.3910498011991863, | |
| "learning_rate": 3.1722995515381644e-06, | |
| "loss": 0.0813, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 4.404255319148936, | |
| "grad_norm": 3.987898875106463, | |
| "learning_rate": 3.155472946602162e-06, | |
| "loss": 0.1063, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 4.425531914893617, | |
| "grad_norm": 3.0288381078835416, | |
| "learning_rate": 3.1386143948394764e-06, | |
| "loss": 0.1089, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 4.446808510638298, | |
| "grad_norm": 3.3307094726424635, | |
| "learning_rate": 3.121724717912138e-06, | |
| "loss": 0.1142, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 4.468085106382979, | |
| "grad_norm": 2.9848172012011664, | |
| "learning_rate": 3.1048047389991693e-06, | |
| "loss": 0.1157, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 4.48936170212766, | |
| "grad_norm": 2.978438802813703, | |
| "learning_rate": 3.087855282756475e-06, | |
| "loss": 0.0942, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 4.51063829787234, | |
| "grad_norm": 2.8670301514814565, | |
| "learning_rate": 3.0708771752766397e-06, | |
| "loss": 0.0876, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 4.531914893617021, | |
| "grad_norm": 3.0160259648937626, | |
| "learning_rate": 3.053871244048669e-06, | |
| "loss": 0.1057, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 4.553191489361702, | |
| "grad_norm": 3.552730667163276, | |
| "learning_rate": 3.0368383179176584e-06, | |
| "loss": 0.0681, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 4.574468085106383, | |
| "grad_norm": 3.0671796344169744, | |
| "learning_rate": 3.019779227044398e-06, | |
| "loss": 0.1052, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 4.595744680851064, | |
| "grad_norm": 3.4917736614570343, | |
| "learning_rate": 3.002694802864912e-06, | |
| "loss": 0.1131, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 4.617021276595745, | |
| "grad_norm": 2.997068423954694, | |
| "learning_rate": 2.98558587804993e-06, | |
| "loss": 0.1249, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 4.638297872340425, | |
| "grad_norm": 2.945598337302224, | |
| "learning_rate": 2.9684532864643123e-06, | |
| "loss": 0.0916, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 4.659574468085106, | |
| "grad_norm": 2.5534208875346494, | |
| "learning_rate": 2.9512978631264006e-06, | |
| "loss": 0.0834, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 4.680851063829787, | |
| "grad_norm": 2.3947639549989144, | |
| "learning_rate": 2.9341204441673267e-06, | |
| "loss": 0.0974, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.702127659574468, | |
| "grad_norm": 3.3251173109542074, | |
| "learning_rate": 2.9169218667902562e-06, | |
| "loss": 0.1011, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 4.723404255319149, | |
| "grad_norm": 3.059268693430171, | |
| "learning_rate": 2.8997029692295875e-06, | |
| "loss": 0.0821, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 4.74468085106383, | |
| "grad_norm": 3.5597698182253965, | |
| "learning_rate": 2.8824645907100957e-06, | |
| "loss": 0.0856, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 4.76595744680851, | |
| "grad_norm": 3.3566578614960423, | |
| "learning_rate": 2.8652075714060296e-06, | |
| "loss": 0.132, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 4.787234042553192, | |
| "grad_norm": 3.470592088594595, | |
| "learning_rate": 2.847932752400164e-06, | |
| "loss": 0.0958, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 4.808510638297872, | |
| "grad_norm": 2.911346797843613, | |
| "learning_rate": 2.8306409756428067e-06, | |
| "loss": 0.0894, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 4.829787234042553, | |
| "grad_norm": 4.613111358505509, | |
| "learning_rate": 2.813333083910761e-06, | |
| "loss": 0.1166, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 4.851063829787234, | |
| "grad_norm": 3.015962228404618, | |
| "learning_rate": 2.7960099207662535e-06, | |
| "loss": 0.1155, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 4.872340425531915, | |
| "grad_norm": 2.987399829854267, | |
| "learning_rate": 2.778672330515814e-06, | |
| "loss": 0.1104, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 4.8936170212765955, | |
| "grad_norm": 2.829987084084442, | |
| "learning_rate": 2.761321158169134e-06, | |
| "loss": 0.1066, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.914893617021277, | |
| "grad_norm": 3.708679514606222, | |
| "learning_rate": 2.743957249397874e-06, | |
| "loss": 0.1048, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 4.9361702127659575, | |
| "grad_norm": 2.749591872522463, | |
| "learning_rate": 2.726581450494451e-06, | |
| "loss": 0.1159, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 4.957446808510638, | |
| "grad_norm": 3.776661504783798, | |
| "learning_rate": 2.70919460833079e-06, | |
| "loss": 0.1167, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 4.9787234042553195, | |
| "grad_norm": 3.091697194785843, | |
| "learning_rate": 2.6917975703170466e-06, | |
| "loss": 0.1174, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 2.8077659070563192, | |
| "learning_rate": 2.6743911843603134e-06, | |
| "loss": 0.0737, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 5.0212765957446805, | |
| "grad_norm": 1.9864860542138973, | |
| "learning_rate": 2.6569762988232838e-06, | |
| "loss": 0.0498, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 5.042553191489362, | |
| "grad_norm": 2.080148938371656, | |
| "learning_rate": 2.63955376248291e-06, | |
| "loss": 0.0588, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 5.0638297872340425, | |
| "grad_norm": 2.4271830087344215, | |
| "learning_rate": 2.6221244244890336e-06, | |
| "loss": 0.04, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 5.085106382978723, | |
| "grad_norm": 2.182065583755821, | |
| "learning_rate": 2.604689134322999e-06, | |
| "loss": 0.0635, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 5.1063829787234045, | |
| "grad_norm": 2.3865912853026727, | |
| "learning_rate": 2.587248741756253e-06, | |
| "loss": 0.0602, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 5.127659574468085, | |
| "grad_norm": 2.3131711827099832, | |
| "learning_rate": 2.569804096808923e-06, | |
| "loss": 0.0709, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 5.148936170212766, | |
| "grad_norm": 2.3050528514219004, | |
| "learning_rate": 2.5523560497083927e-06, | |
| "loss": 0.0547, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 5.170212765957447, | |
| "grad_norm": 2.124162166492525, | |
| "learning_rate": 2.5349054508478636e-06, | |
| "loss": 0.046, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 5.191489361702128, | |
| "grad_norm": 1.9773286780066965, | |
| "learning_rate": 2.517453150744904e-06, | |
| "loss": 0.0432, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 5.212765957446808, | |
| "grad_norm": 3.116678592316818, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0634, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 5.23404255319149, | |
| "grad_norm": 2.504016738413573, | |
| "learning_rate": 2.482546849255096e-06, | |
| "loss": 0.0589, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 5.25531914893617, | |
| "grad_norm": 3.505324999262586, | |
| "learning_rate": 2.4650945491521372e-06, | |
| "loss": 0.0547, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 5.276595744680851, | |
| "grad_norm": 2.2697348908750974, | |
| "learning_rate": 2.447643950291608e-06, | |
| "loss": 0.0608, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 5.297872340425532, | |
| "grad_norm": 2.8775304018384986, | |
| "learning_rate": 2.4301959031910785e-06, | |
| "loss": 0.0765, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 5.319148936170213, | |
| "grad_norm": 2.4093465444498614, | |
| "learning_rate": 2.4127512582437486e-06, | |
| "loss": 0.0583, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 5.340425531914893, | |
| "grad_norm": 2.365667376680801, | |
| "learning_rate": 2.3953108656770018e-06, | |
| "loss": 0.0629, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 5.361702127659575, | |
| "grad_norm": 2.713559880628167, | |
| "learning_rate": 2.377875575510967e-06, | |
| "loss": 0.0669, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 5.382978723404255, | |
| "grad_norm": 2.999000225951145, | |
| "learning_rate": 2.3604462375170905e-06, | |
| "loss": 0.0617, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 5.404255319148936, | |
| "grad_norm": 2.6164170571843512, | |
| "learning_rate": 2.3430237011767166e-06, | |
| "loss": 0.0582, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 5.425531914893617, | |
| "grad_norm": 2.4039871330574796, | |
| "learning_rate": 2.325608815639687e-06, | |
| "loss": 0.0578, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 5.446808510638298, | |
| "grad_norm": 2.97747740854911, | |
| "learning_rate": 2.3082024296829538e-06, | |
| "loss": 0.0659, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 5.468085106382979, | |
| "grad_norm": 2.336759542261552, | |
| "learning_rate": 2.290805391669212e-06, | |
| "loss": 0.0548, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 5.48936170212766, | |
| "grad_norm": 3.1670650790685846, | |
| "learning_rate": 2.2734185495055503e-06, | |
| "loss": 0.0585, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 5.51063829787234, | |
| "grad_norm": 3.2034707124777952, | |
| "learning_rate": 2.256042750602127e-06, | |
| "loss": 0.0593, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 5.531914893617021, | |
| "grad_norm": 2.3348070175379503, | |
| "learning_rate": 2.238678841830867e-06, | |
| "loss": 0.0547, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 5.553191489361702, | |
| "grad_norm": 2.608427512535968, | |
| "learning_rate": 2.2213276694841866e-06, | |
| "loss": 0.0643, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 5.574468085106383, | |
| "grad_norm": 2.4848496472118495, | |
| "learning_rate": 2.2039900792337477e-06, | |
| "loss": 0.0608, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 5.595744680851064, | |
| "grad_norm": 1.886510569911626, | |
| "learning_rate": 2.186666916089239e-06, | |
| "loss": 0.0599, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 5.617021276595745, | |
| "grad_norm": 2.8635289633291547, | |
| "learning_rate": 2.1693590243571937e-06, | |
| "loss": 0.0515, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 5.638297872340425, | |
| "grad_norm": 2.854324373551202, | |
| "learning_rate": 2.1520672475998374e-06, | |
| "loss": 0.0554, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 5.659574468085106, | |
| "grad_norm": 1.8544197687406436, | |
| "learning_rate": 2.134792428593971e-06, | |
| "loss": 0.0421, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 5.680851063829787, | |
| "grad_norm": 2.6205983731152322, | |
| "learning_rate": 2.117535409289905e-06, | |
| "loss": 0.0457, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 5.702127659574468, | |
| "grad_norm": 1.7630228804740633, | |
| "learning_rate": 2.1002970307704134e-06, | |
| "loss": 0.0369, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 5.723404255319149, | |
| "grad_norm": 2.638068560108755, | |
| "learning_rate": 2.0830781332097446e-06, | |
| "loss": 0.0583, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 5.74468085106383, | |
| "grad_norm": 3.1753027345645646, | |
| "learning_rate": 2.0658795558326745e-06, | |
| "loss": 0.0674, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 5.76595744680851, | |
| "grad_norm": 2.2642667997058257, | |
| "learning_rate": 2.0487021368736002e-06, | |
| "loss": 0.064, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 5.787234042553192, | |
| "grad_norm": 2.559426313332899, | |
| "learning_rate": 2.031546713535688e-06, | |
| "loss": 0.0549, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 5.808510638297872, | |
| "grad_norm": 2.878855059930482, | |
| "learning_rate": 2.0144141219500707e-06, | |
| "loss": 0.0559, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 5.829787234042553, | |
| "grad_norm": 2.283778113411308, | |
| "learning_rate": 1.997305197135089e-06, | |
| "loss": 0.0548, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 5.851063829787234, | |
| "grad_norm": 2.4192051614394003, | |
| "learning_rate": 1.9802207729556023e-06, | |
| "loss": 0.0502, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 5.872340425531915, | |
| "grad_norm": 2.322479824517103, | |
| "learning_rate": 1.963161682082342e-06, | |
| "loss": 0.064, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 5.8936170212765955, | |
| "grad_norm": 2.4593833670456005, | |
| "learning_rate": 1.946128755951332e-06, | |
| "loss": 0.058, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 5.914893617021277, | |
| "grad_norm": 2.5251545274407907, | |
| "learning_rate": 1.9291228247233607e-06, | |
| "loss": 0.0522, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 5.9361702127659575, | |
| "grad_norm": 1.8104094730869373, | |
| "learning_rate": 1.912144717243525e-06, | |
| "loss": 0.0296, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 5.957446808510638, | |
| "grad_norm": 2.689146388919388, | |
| "learning_rate": 1.895195261000831e-06, | |
| "loss": 0.0407, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.9787234042553195, | |
| "grad_norm": 1.8669924342723785, | |
| "learning_rate": 1.8782752820878636e-06, | |
| "loss": 0.0495, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 2.271539062015242, | |
| "learning_rate": 1.8613856051605242e-06, | |
| "loss": 0.0455, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 6.0212765957446805, | |
| "grad_norm": 1.525504212144237, | |
| "learning_rate": 1.8445270533978387e-06, | |
| "loss": 0.0377, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 6.042553191489362, | |
| "grad_norm": 1.0859867252268387, | |
| "learning_rate": 1.827700448461836e-06, | |
| "loss": 0.0221, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 6.0638297872340425, | |
| "grad_norm": 1.6689218206446002, | |
| "learning_rate": 1.8109066104575023e-06, | |
| "loss": 0.0237, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 6.085106382978723, | |
| "grad_norm": 1.7091034732477, | |
| "learning_rate": 1.7941463578928088e-06, | |
| "loss": 0.0316, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 6.1063829787234045, | |
| "grad_norm": 1.473946493341099, | |
| "learning_rate": 1.7774205076388207e-06, | |
| "loss": 0.0301, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 6.127659574468085, | |
| "grad_norm": 1.9210720976922275, | |
| "learning_rate": 1.7607298748898844e-06, | |
| "loss": 0.0241, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 6.148936170212766, | |
| "grad_norm": 2.2803503758262504, | |
| "learning_rate": 1.744075273123889e-06, | |
| "loss": 0.0454, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 6.170212765957447, | |
| "grad_norm": 2.024197465049683, | |
| "learning_rate": 1.7274575140626318e-06, | |
| "loss": 0.0362, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 6.191489361702128, | |
| "grad_norm": 1.84667704080016, | |
| "learning_rate": 1.7108774076322443e-06, | |
| "loss": 0.0403, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 6.212765957446808, | |
| "grad_norm": 1.695502301672247, | |
| "learning_rate": 1.6943357619237227e-06, | |
| "loss": 0.0306, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 6.23404255319149, | |
| "grad_norm": 1.6806451272904126, | |
| "learning_rate": 1.677833383153542e-06, | |
| "loss": 0.0284, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 6.25531914893617, | |
| "grad_norm": 2.9118161159346854, | |
| "learning_rate": 1.661371075624363e-06, | |
| "loss": 0.0256, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 6.276595744680851, | |
| "grad_norm": 1.8173030910949344, | |
| "learning_rate": 1.6449496416858285e-06, | |
| "loss": 0.0284, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 6.297872340425532, | |
| "grad_norm": 2.223540017311328, | |
| "learning_rate": 1.6285698816954626e-06, | |
| "loss": 0.0443, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 6.319148936170213, | |
| "grad_norm": 1.4963288286875704, | |
| "learning_rate": 1.612232593979658e-06, | |
| "loss": 0.0367, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 6.340425531914893, | |
| "grad_norm": 1.3236418660083258, | |
| "learning_rate": 1.5959385747947697e-06, | |
| "loss": 0.0168, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 6.361702127659575, | |
| "grad_norm": 2.1082580928006704, | |
| "learning_rate": 1.5796886182883053e-06, | |
| "loss": 0.0384, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 6.382978723404255, | |
| "grad_norm": 2.0461518407784665, | |
| "learning_rate": 1.56348351646022e-06, | |
| "loss": 0.0348, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.404255319148936, | |
| "grad_norm": 1.9027154330548208, | |
| "learning_rate": 1.547324059124315e-06, | |
| "loss": 0.0409, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 6.425531914893617, | |
| "grad_norm": 1.8430627981587546, | |
| "learning_rate": 1.5312110338697427e-06, | |
| "loss": 0.0336, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 6.446808510638298, | |
| "grad_norm": 2.013051690553332, | |
| "learning_rate": 1.5151452260226224e-06, | |
| "loss": 0.0361, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 6.468085106382979, | |
| "grad_norm": 2.1207015485047753, | |
| "learning_rate": 1.4991274186077632e-06, | |
| "loss": 0.0405, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 6.48936170212766, | |
| "grad_norm": 1.3483418905294124, | |
| "learning_rate": 1.4831583923105e-06, | |
| "loss": 0.0264, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 6.51063829787234, | |
| "grad_norm": 1.2898003351353924, | |
| "learning_rate": 1.467238925438646e-06, | |
| "loss": 0.0326, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 6.531914893617021, | |
| "grad_norm": 1.83413124159608, | |
| "learning_rate": 1.4513697938845571e-06, | |
| "loss": 0.0329, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 6.553191489361702, | |
| "grad_norm": 1.9300831447222762, | |
| "learning_rate": 1.4355517710873184e-06, | |
| "loss": 0.0342, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 6.574468085106383, | |
| "grad_norm": 2.46498295305994, | |
| "learning_rate": 1.419785627995044e-06, | |
| "loss": 0.0293, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 6.595744680851064, | |
| "grad_norm": 1.8810365903428496, | |
| "learning_rate": 1.4040721330273063e-06, | |
| "loss": 0.0385, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 6.617021276595745, | |
| "grad_norm": 1.7341556708700896, | |
| "learning_rate": 1.388412052037682e-06, | |
| "loss": 0.0373, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 6.638297872340425, | |
| "grad_norm": 1.4886715538593713, | |
| "learning_rate": 1.3728061482764238e-06, | |
| "loss": 0.0374, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 6.659574468085106, | |
| "grad_norm": 1.8999495842705894, | |
| "learning_rate": 1.3572551823532654e-06, | |
| "loss": 0.0316, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 6.680851063829787, | |
| "grad_norm": 1.464463066404411, | |
| "learning_rate": 1.3417599122003464e-06, | |
| "loss": 0.033, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 6.702127659574468, | |
| "grad_norm": 1.8396892711483188, | |
| "learning_rate": 1.3263210930352737e-06, | |
| "loss": 0.0351, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 6.723404255319149, | |
| "grad_norm": 1.555502571877375, | |
| "learning_rate": 1.3109394773243117e-06, | |
| "loss": 0.0333, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 6.74468085106383, | |
| "grad_norm": 2.124808645505887, | |
| "learning_rate": 1.2956158147457116e-06, | |
| "loss": 0.0294, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 6.76595744680851, | |
| "grad_norm": 1.7688895712588661, | |
| "learning_rate": 1.280350852153168e-06, | |
| "loss": 0.0242, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 6.787234042553192, | |
| "grad_norm": 2.0383431308499325, | |
| "learning_rate": 1.2651453335394232e-06, | |
| "loss": 0.0353, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 6.808510638297872, | |
| "grad_norm": 1.7645071618559023, | |
| "learning_rate": 1.2500000000000007e-06, | |
| "loss": 0.0299, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 6.829787234042553, | |
| "grad_norm": 2.0474065053014217, | |
| "learning_rate": 1.234915589697091e-06, | |
| "loss": 0.0297, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 6.851063829787234, | |
| "grad_norm": 1.7823278045268314, | |
| "learning_rate": 1.2198928378235717e-06, | |
| "loss": 0.038, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 6.872340425531915, | |
| "grad_norm": 1.2380075941515003, | |
| "learning_rate": 1.204932476567175e-06, | |
| "loss": 0.031, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 6.8936170212765955, | |
| "grad_norm": 1.9796302395422996, | |
| "learning_rate": 1.1900352350748026e-06, | |
| "loss": 0.0381, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 6.914893617021277, | |
| "grad_norm": 1.3804831755312008, | |
| "learning_rate": 1.1752018394169882e-06, | |
| "loss": 0.0316, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 6.9361702127659575, | |
| "grad_norm": 1.6152383977065423, | |
| "learning_rate": 1.160433012552508e-06, | |
| "loss": 0.0343, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 6.957446808510638, | |
| "grad_norm": 1.69638635732096, | |
| "learning_rate": 1.1457294742931508e-06, | |
| "loss": 0.0296, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 6.9787234042553195, | |
| "grad_norm": 2.0806576931686456, | |
| "learning_rate": 1.1310919412686248e-06, | |
| "loss": 0.0341, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 1.8303598912826444, | |
| "learning_rate": 1.11652112689164e-06, | |
| "loss": 0.0405, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 7.0212765957446805, | |
| "grad_norm": 1.5859756930815514, | |
| "learning_rate": 1.1020177413231334e-06, | |
| "loss": 0.0252, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 7.042553191489362, | |
| "grad_norm": 0.7609936522020677, | |
| "learning_rate": 1.0875824914376555e-06, | |
| "loss": 0.0158, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 7.0638297872340425, | |
| "grad_norm": 2.0790528777967188, | |
| "learning_rate": 1.073216080788921e-06, | |
| "loss": 0.0175, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 7.085106382978723, | |
| "grad_norm": 1.0895054515077724, | |
| "learning_rate": 1.0589192095755172e-06, | |
| "loss": 0.0217, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 7.1063829787234045, | |
| "grad_norm": 1.0138202696131422, | |
| "learning_rate": 1.0446925746067768e-06, | |
| "loss": 0.0189, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 7.127659574468085, | |
| "grad_norm": 0.931336055385696, | |
| "learning_rate": 1.0305368692688175e-06, | |
| "loss": 0.0209, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 7.148936170212766, | |
| "grad_norm": 1.214374992403074, | |
| "learning_rate": 1.0164527834907468e-06, | |
| "loss": 0.0218, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 7.170212765957447, | |
| "grad_norm": 1.5245924187989146, | |
| "learning_rate": 1.0024410037110358e-06, | |
| "loss": 0.022, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 7.191489361702128, | |
| "grad_norm": 1.0820503643925237, | |
| "learning_rate": 9.88502212844063e-07, | |
| "loss": 0.0171, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 7.212765957446808, | |
| "grad_norm": 0.8009422999145568, | |
| "learning_rate": 9.746370902468311e-07, | |
| "loss": 0.0179, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 7.23404255319149, | |
| "grad_norm": 1.245836157318975, | |
| "learning_rate": 9.608463116858544e-07, | |
| "loss": 0.0196, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 7.25531914893617, | |
| "grad_norm": 0.9189114786673717, | |
| "learning_rate": 9.471305493042243e-07, | |
| "loss": 0.0206, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 7.276595744680851, | |
| "grad_norm": 1.2781854766390135, | |
| "learning_rate": 9.334904715888496e-07, | |
| "loss": 0.0164, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 7.297872340425532, | |
| "grad_norm": 1.5271374445001962, | |
| "learning_rate": 9.199267433378728e-07, | |
| "loss": 0.02, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 7.319148936170213, | |
| "grad_norm": 0.946456072976271, | |
| "learning_rate": 9.064400256282757e-07, | |
| "loss": 0.0214, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 7.340425531914893, | |
| "grad_norm": 1.270831674714735, | |
| "learning_rate": 8.930309757836517e-07, | |
| "loss": 0.0216, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 7.361702127659575, | |
| "grad_norm": 0.9172465899189646, | |
| "learning_rate": 8.797002473421729e-07, | |
| "loss": 0.0172, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 7.382978723404255, | |
| "grad_norm": 0.9762896610645739, | |
| "learning_rate": 8.664484900247363e-07, | |
| "loss": 0.0196, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 7.404255319148936, | |
| "grad_norm": 1.2366903890873284, | |
| "learning_rate": 8.532763497032987e-07, | |
| "loss": 0.0192, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 7.425531914893617, | |
| "grad_norm": 0.8921247183956026, | |
| "learning_rate": 8.40184468369396e-07, | |
| "loss": 0.0138, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 7.446808510638298, | |
| "grad_norm": 1.371683786414812, | |
| "learning_rate": 8.271734841028553e-07, | |
| "loss": 0.0257, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 7.468085106382979, | |
| "grad_norm": 1.6706279670454172, | |
| "learning_rate": 8.142440310406923e-07, | |
| "loss": 0.0221, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 7.48936170212766, | |
| "grad_norm": 1.0048836984452958, | |
| "learning_rate": 8.013967393462094e-07, | |
| "loss": 0.0179, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 7.51063829787234, | |
| "grad_norm": 1.028897861820127, | |
| "learning_rate": 7.886322351782782e-07, | |
| "loss": 0.0173, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 7.531914893617021, | |
| "grad_norm": 0.9414634888570663, | |
| "learning_rate": 7.759511406608255e-07, | |
| "loss": 0.0194, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 7.553191489361702, | |
| "grad_norm": 1.3421193366601667, | |
| "learning_rate": 7.633540738525066e-07, | |
| "loss": 0.0155, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 7.574468085106383, | |
| "grad_norm": 1.3991724028833572, | |
| "learning_rate": 7.508416487165862e-07, | |
| "loss": 0.0242, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 7.595744680851064, | |
| "grad_norm": 3.4908651855373067, | |
| "learning_rate": 7.384144750910133e-07, | |
| "loss": 0.0201, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 7.617021276595745, | |
| "grad_norm": 1.1125708607058544, | |
| "learning_rate": 7.260731586586983e-07, | |
| "loss": 0.0181, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 7.638297872340425, | |
| "grad_norm": 2.003422428134198, | |
| "learning_rate": 7.138183009179922e-07, | |
| "loss": 0.0244, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 7.659574468085106, | |
| "grad_norm": 0.8666069576765489, | |
| "learning_rate": 7.016504991533727e-07, | |
| "loss": 0.0231, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 7.680851063829787, | |
| "grad_norm": 0.8225857804515108, | |
| "learning_rate": 6.895703464063319e-07, | |
| "loss": 0.0127, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 7.702127659574468, | |
| "grad_norm": 1.2220101527746525, | |
| "learning_rate": 6.775784314464717e-07, | |
| "loss": 0.0261, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 7.723404255319149, | |
| "grad_norm": 1.291947063153676, | |
| "learning_rate": 6.656753387428089e-07, | |
| "loss": 0.024, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 7.74468085106383, | |
| "grad_norm": 1.288638995380391, | |
| "learning_rate": 6.538616484352902e-07, | |
| "loss": 0.016, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 7.76595744680851, | |
| "grad_norm": 1.3674238710009354, | |
| "learning_rate": 6.421379363065142e-07, | |
| "loss": 0.0253, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 7.787234042553192, | |
| "grad_norm": 0.877515831783811, | |
| "learning_rate": 6.305047737536707e-07, | |
| "loss": 0.0162, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 7.808510638297872, | |
| "grad_norm": 1.1630712659406794, | |
| "learning_rate": 6.189627277606894e-07, | |
| "loss": 0.0227, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 7.829787234042553, | |
| "grad_norm": 1.2379019290179472, | |
| "learning_rate": 6.075123608706093e-07, | |
| "loss": 0.0179, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 7.851063829787234, | |
| "grad_norm": 0.9761836229980341, | |
| "learning_rate": 5.961542311581586e-07, | |
| "loss": 0.017, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 7.872340425531915, | |
| "grad_norm": 1.2905446310752584, | |
| "learning_rate": 5.848888922025553e-07, | |
| "loss": 0.0237, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 7.8936170212765955, | |
| "grad_norm": 1.0599111161417107, | |
| "learning_rate": 5.737168930605272e-07, | |
| "loss": 0.0193, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 7.914893617021277, | |
| "grad_norm": 0.9002316779352258, | |
| "learning_rate": 5.626387782395512e-07, | |
| "loss": 0.0219, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 7.9361702127659575, | |
| "grad_norm": 1.0871181403304409, | |
| "learning_rate": 5.516550876713142e-07, | |
| "loss": 0.0202, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 7.957446808510638, | |
| "grad_norm": 0.7739867037107642, | |
| "learning_rate": 5.407663566854008e-07, | |
| "loss": 0.0141, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 7.9787234042553195, | |
| "grad_norm": 1.1646231525599027, | |
| "learning_rate": 5.299731159831953e-07, | |
| "loss": 0.0199, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.8486174354933951, | |
| "learning_rate": 5.192758916120236e-07, | |
| "loss": 0.0183, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 8.02127659574468, | |
| "grad_norm": 0.5857908765113855, | |
| "learning_rate": 5.086752049395094e-07, | |
| "loss": 0.0154, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 8.042553191489361, | |
| "grad_norm": 0.820073038781464, | |
| "learning_rate": 4.981715726281666e-07, | |
| "loss": 0.0162, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 8.063829787234043, | |
| "grad_norm": 0.5353750025209411, | |
| "learning_rate": 4.87765506610215e-07, | |
| "loss": 0.0117, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 8.085106382978724, | |
| "grad_norm": 0.6641723492880932, | |
| "learning_rate": 4.774575140626317e-07, | |
| "loss": 0.0155, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 8.106382978723405, | |
| "grad_norm": 1.5478055693073858, | |
| "learning_rate": 4.672480973824312e-07, | |
| "loss": 0.0138, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 8.127659574468085, | |
| "grad_norm": 0.5935452327954517, | |
| "learning_rate": 4.5713775416217884e-07, | |
| "loss": 0.0128, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 8.148936170212766, | |
| "grad_norm": 0.45835158236977624, | |
| "learning_rate": 4.4712697716573994e-07, | |
| "loss": 0.014, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 8.170212765957446, | |
| "grad_norm": 0.495302571001091, | |
| "learning_rate": 4.372162543042624e-07, | |
| "loss": 0.0135, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 8.191489361702128, | |
| "grad_norm": 0.4653447676593763, | |
| "learning_rate": 4.27406068612396e-07, | |
| "loss": 0.0113, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 8.212765957446809, | |
| "grad_norm": 0.5764443378886089, | |
| "learning_rate": 4.1769689822475147e-07, | |
| "loss": 0.0149, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 8.23404255319149, | |
| "grad_norm": 0.34507606047404416, | |
| "learning_rate": 4.0808921635259595e-07, | |
| "loss": 0.0096, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 8.25531914893617, | |
| "grad_norm": 0.6316918421422608, | |
| "learning_rate": 3.9858349126078945e-07, | |
| "loss": 0.0149, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 8.27659574468085, | |
| "grad_norm": 1.13945433310328, | |
| "learning_rate": 3.891801862449629e-07, | |
| "loss": 0.0171, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 8.297872340425531, | |
| "grad_norm": 1.6671178791582812, | |
| "learning_rate": 3.798797596089351e-07, | |
| "loss": 0.0162, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 8.319148936170214, | |
| "grad_norm": 0.6242884167930942, | |
| "learning_rate": 3.7068266464238085e-07, | |
| "loss": 0.0171, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 8.340425531914894, | |
| "grad_norm": 0.6157189166745389, | |
| "learning_rate": 3.615893495987335e-07, | |
| "loss": 0.0083, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 8.361702127659575, | |
| "grad_norm": 1.187375482456905, | |
| "learning_rate": 3.5260025767333894e-07, | |
| "loss": 0.0133, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 8.382978723404255, | |
| "grad_norm": 0.9198827823698973, | |
| "learning_rate": 3.4371582698185636e-07, | |
| "loss": 0.0168, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 8.404255319148936, | |
| "grad_norm": 0.9127337383828107, | |
| "learning_rate": 3.3493649053890325e-07, | |
| "loss": 0.0167, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 8.425531914893616, | |
| "grad_norm": 0.4716697636311403, | |
| "learning_rate": 3.262626762369525e-07, | |
| "loss": 0.0134, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 8.446808510638299, | |
| "grad_norm": 0.5430698963916597, | |
| "learning_rate": 3.176948068254762e-07, | |
| "loss": 0.0115, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 8.46808510638298, | |
| "grad_norm": 0.5589379122310724, | |
| "learning_rate": 3.092332998903416e-07, | |
| "loss": 0.0134, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 8.48936170212766, | |
| "grad_norm": 1.0297905449956246, | |
| "learning_rate": 3.0087856783345916e-07, | |
| "loss": 0.0165, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 8.51063829787234, | |
| "grad_norm": 0.5586126342363132, | |
| "learning_rate": 2.9263101785268253e-07, | |
| "loss": 0.0129, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 8.51063829787234, | |
| "eval_loss": 1.6673990488052368, | |
| "eval_runtime": 1.6235, | |
| "eval_samples_per_second": 14.167, | |
| "eval_steps_per_second": 0.616, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 8.53191489361702, | |
| "grad_norm": 0.5428039786664497, | |
| "learning_rate": 2.844910519219632e-07, | |
| "loss": 0.0128, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 8.553191489361701, | |
| "grad_norm": 0.633307262716061, | |
| "learning_rate": 2.764590667717562e-07, | |
| "loss": 0.0161, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 8.574468085106384, | |
| "grad_norm": 0.5251963830034382, | |
| "learning_rate": 2.6853545386968607e-07, | |
| "loss": 0.0115, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 8.595744680851064, | |
| "grad_norm": 0.48124935494240734, | |
| "learning_rate": 2.6072059940146775e-07, | |
| "loss": 0.0097, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 8.617021276595745, | |
| "grad_norm": 0.5546850016440125, | |
| "learning_rate": 2.53014884252083e-07, | |
| "loss": 0.0095, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 8.638297872340425, | |
| "grad_norm": 0.6870597575288601, | |
| "learning_rate": 2.454186839872158e-07, | |
| "loss": 0.0161, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 8.659574468085106, | |
| "grad_norm": 0.5075138452670342, | |
| "learning_rate": 2.3793236883495164e-07, | |
| "loss": 0.0137, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 8.680851063829786, | |
| "grad_norm": 0.7184250889463067, | |
| "learning_rate": 2.3055630366772857e-07, | |
| "loss": 0.0124, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 8.702127659574469, | |
| "grad_norm": 0.6095068862526991, | |
| "learning_rate": 2.2329084798455747e-07, | |
| "loss": 0.0145, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 8.72340425531915, | |
| "grad_norm": 0.5513423746444825, | |
| "learning_rate": 2.1613635589349756e-07, | |
| "loss": 0.0155, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 8.74468085106383, | |
| "grad_norm": 0.5875898983901224, | |
| "learning_rate": 2.0909317609440093e-07, | |
| "loss": 0.0146, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 8.76595744680851, | |
| "grad_norm": 0.5750560265603247, | |
| "learning_rate": 2.0216165186191406e-07, | |
| "loss": 0.0131, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 8.787234042553191, | |
| "grad_norm": 0.6746724848758707, | |
| "learning_rate": 1.95342121028749e-07, | |
| "loss": 0.0118, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 8.808510638297872, | |
| "grad_norm": 0.6972301523231518, | |
| "learning_rate": 1.8863491596921745e-07, | |
| "loss": 0.0143, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 8.829787234042554, | |
| "grad_norm": 0.7525328974002997, | |
| "learning_rate": 1.8204036358303173e-07, | |
| "loss": 0.0144, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 8.851063829787234, | |
| "grad_norm": 0.5087036176440635, | |
| "learning_rate": 1.7555878527937164e-07, | |
| "loss": 0.0117, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 8.872340425531915, | |
| "grad_norm": 0.6061494141417032, | |
| "learning_rate": 1.6919049696121957e-07, | |
| "loss": 0.0168, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 8.893617021276595, | |
| "grad_norm": 0.6674633587572225, | |
| "learning_rate": 1.629358090099639e-07, | |
| "loss": 0.0154, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 8.914893617021276, | |
| "grad_norm": 0.6381527241007888, | |
| "learning_rate": 1.567950262702714e-07, | |
| "loss": 0.0118, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 8.936170212765958, | |
| "grad_norm": 0.5652826587480684, | |
| "learning_rate": 1.507684480352292e-07, | |
| "loss": 0.0142, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 8.957446808510639, | |
| "grad_norm": 0.5390136780396995, | |
| "learning_rate": 1.4485636803175828e-07, | |
| "loss": 0.0153, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 8.97872340425532, | |
| "grad_norm": 0.4433110433252025, | |
| "learning_rate": 1.3905907440629752e-07, | |
| "loss": 0.0128, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.3937254962258607, | |
| "learning_rate": 1.3337684971075932e-07, | |
| "loss": 0.0141, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 9.02127659574468, | |
| "grad_norm": 0.42872899914768886, | |
| "learning_rate": 1.278099708887587e-07, | |
| "loss": 0.0139, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 9.042553191489361, | |
| "grad_norm": 0.43176685764328526, | |
| "learning_rate": 1.223587092621162e-07, | |
| "loss": 0.01, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 9.063829787234043, | |
| "grad_norm": 0.3743485104670554, | |
| "learning_rate": 1.1702333051763271e-07, | |
| "loss": 0.0082, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 9.085106382978724, | |
| "grad_norm": 0.39987032601374245, | |
| "learning_rate": 1.1180409469414094e-07, | |
| "loss": 0.0125, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 9.106382978723405, | |
| "grad_norm": 0.39568260783662074, | |
| "learning_rate": 1.067012561698319e-07, | |
| "loss": 0.0099, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 9.127659574468085, | |
| "grad_norm": 0.4002164747878374, | |
| "learning_rate": 1.0171506364985622e-07, | |
| "loss": 0.0141, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 9.148936170212766, | |
| "grad_norm": 0.3140844748261339, | |
| "learning_rate": 9.684576015420277e-08, | |
| "loss": 0.0083, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 9.170212765957446, | |
| "grad_norm": 3.0839571989766026, | |
| "learning_rate": 9.209358300585474e-08, | |
| "loss": 0.0107, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 9.191489361702128, | |
| "grad_norm": 0.43386426711502496, | |
| "learning_rate": 8.745876381922147e-08, | |
| "loss": 0.0114, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 9.212765957446809, | |
| "grad_norm": 0.49575077577441945, | |
| "learning_rate": 8.294152848885156e-08, | |
| "loss": 0.0122, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 9.23404255319149, | |
| "grad_norm": 0.42605421543375827, | |
| "learning_rate": 7.854209717842231e-08, | |
| "loss": 0.0123, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 9.25531914893617, | |
| "grad_norm": 0.4159085198061852, | |
| "learning_rate": 7.426068431000883e-08, | |
| "loss": 0.011, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 9.27659574468085, | |
| "grad_norm": 0.4297510739797917, | |
| "learning_rate": 7.009749855363457e-08, | |
| "loss": 0.0096, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 9.297872340425531, | |
| "grad_norm": 0.39770284394181865, | |
| "learning_rate": 6.605274281709929e-08, | |
| "loss": 0.0108, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 9.319148936170214, | |
| "grad_norm": 0.3799358013058963, | |
| "learning_rate": 6.212661423609184e-08, | |
| "loss": 0.0135, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 9.340425531914894, | |
| "grad_norm": 0.40685286788703806, | |
| "learning_rate": 5.83193041645802e-08, | |
| "loss": 0.0105, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 9.361702127659575, | |
| "grad_norm": 0.5276489442708509, | |
| "learning_rate": 5.463099816548578e-08, | |
| "loss": 0.0159, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 9.382978723404255, | |
| "grad_norm": 0.3398816914667588, | |
| "learning_rate": 5.106187600163987e-08, | |
| "loss": 0.01, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 9.404255319148936, | |
| "grad_norm": 0.43060715328426347, | |
| "learning_rate": 4.761211162702117e-08, | |
| "loss": 0.0109, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 9.425531914893616, | |
| "grad_norm": 0.6155281563788073, | |
| "learning_rate": 4.428187317827848e-08, | |
| "loss": 0.0107, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 9.446808510638299, | |
| "grad_norm": 0.4920360355401412, | |
| "learning_rate": 4.1071322966535487e-08, | |
| "loss": 0.0139, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 9.46808510638298, | |
| "grad_norm": 0.44825099453614115, | |
| "learning_rate": 3.798061746947995e-08, | |
| "loss": 0.0113, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 9.48936170212766, | |
| "grad_norm": 0.48315881463136157, | |
| "learning_rate": 3.5009907323737826e-08, | |
| "loss": 0.0131, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 9.51063829787234, | |
| "grad_norm": 0.3897061025707457, | |
| "learning_rate": 3.2159337317530234e-08, | |
| "loss": 0.0131, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 9.53191489361702, | |
| "grad_norm": 0.3845441440160021, | |
| "learning_rate": 2.9429046383618042e-08, | |
| "loss": 0.0094, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 9.553191489361701, | |
| "grad_norm": 0.4018776472448016, | |
| "learning_rate": 2.681916759252917e-08, | |
| "loss": 0.0117, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 9.574468085106384, | |
| "grad_norm": 0.3789922116838833, | |
| "learning_rate": 2.4329828146074096e-08, | |
| "loss": 0.0099, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 9.595744680851064, | |
| "grad_norm": 0.47356186931300714, | |
| "learning_rate": 2.1961149371145795e-08, | |
| "loss": 0.012, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 9.617021276595745, | |
| "grad_norm": 0.5175691416116797, | |
| "learning_rate": 1.9713246713805588e-08, | |
| "loss": 0.0137, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 9.638297872340425, | |
| "grad_norm": 0.35550871415754165, | |
| "learning_rate": 1.7586229733657646e-08, | |
| "loss": 0.0126, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 9.659574468085106, | |
| "grad_norm": 0.4521940543192018, | |
| "learning_rate": 1.5580202098509078e-08, | |
| "loss": 0.0123, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 9.680851063829786, | |
| "grad_norm": 0.3645510186204655, | |
| "learning_rate": 1.3695261579316776e-08, | |
| "loss": 0.0099, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 9.702127659574469, | |
| "grad_norm": 0.5052016943572653, | |
| "learning_rate": 1.193150004542204e-08, | |
| "loss": 0.0108, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 9.72340425531915, | |
| "grad_norm": 0.4591420783076054, | |
| "learning_rate": 1.0289003460074165e-08, | |
| "loss": 0.0136, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 9.74468085106383, | |
| "grad_norm": 0.3979451604394145, | |
| "learning_rate": 8.767851876239075e-09, | |
| "loss": 0.0124, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 9.76595744680851, | |
| "grad_norm": 0.4508311448933257, | |
| "learning_rate": 7.368119432699383e-09, | |
| "loss": 0.0117, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 9.787234042553191, | |
| "grad_norm": 0.48162461236003445, | |
| "learning_rate": 6.089874350439507e-09, | |
| "loss": 0.0131, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 9.808510638297872, | |
| "grad_norm": 0.3727617520322409, | |
| "learning_rate": 4.933178929321103e-09, | |
| "loss": 0.0092, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 9.829787234042554, | |
| "grad_norm": 0.37748204227545856, | |
| "learning_rate": 3.8980895450474455e-09, | |
| "loss": 0.0108, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 9.851063829787234, | |
| "grad_norm": 0.30954369790579545, | |
| "learning_rate": 2.984656646415063e-09, | |
| "loss": 0.0082, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 9.872340425531915, | |
| "grad_norm": 0.441565820890093, | |
| "learning_rate": 2.192924752854042e-09, | |
| "loss": 0.014, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 9.893617021276595, | |
| "grad_norm": 0.42642106144925446, | |
| "learning_rate": 1.5229324522605949e-09, | |
| "loss": 0.0086, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 9.914893617021276, | |
| "grad_norm": 0.3393626098420996, | |
| "learning_rate": 9.747123991141193e-10, | |
| "loss": 0.008, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 9.936170212765958, | |
| "grad_norm": 0.4441469010998739, | |
| "learning_rate": 5.48291312886251e-10, | |
| "loss": 0.0135, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 9.957446808510639, | |
| "grad_norm": 0.44011051414564956, | |
| "learning_rate": 2.43689976739403e-10, | |
| "loss": 0.0117, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 9.97872340425532, | |
| "grad_norm": 0.47111655728750834, | |
| "learning_rate": 6.092323651313293e-11, | |
| "loss": 0.0104, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.5133248194623898, | |
| "learning_rate": 0.0, | |
| "loss": 0.0161, | |
| "step": 470 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 470, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 32811979898880.0, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |