Text Generation
Transformers
Safetensors
English
llama
finance
financial-literacy
investment
banking
budgeting
accounting
lora
instruction-tuning
llama-3
adaption-labs
conversational
text-generation-inference
Instructions to use RayNene/MyFinanceExpertModel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RayNene/MyFinanceExpertModel with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RayNene/MyFinanceExpertModel") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("RayNene/MyFinanceExpertModel") model = AutoModelForCausalLM.from_pretrained("RayNene/MyFinanceExpertModel") 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 Settings
- vLLM
How to use RayNene/MyFinanceExpertModel with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RayNene/MyFinanceExpertModel" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RayNene/MyFinanceExpertModel", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/RayNene/MyFinanceExpertModel
- SGLang
How to use RayNene/MyFinanceExpertModel 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 "RayNene/MyFinanceExpertModel" \ --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": "RayNene/MyFinanceExpertModel", "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 "RayNene/MyFinanceExpertModel" \ --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": "RayNene/MyFinanceExpertModel", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use RayNene/MyFinanceExpertModel with Docker Model Runner:
docker model run hf.co/RayNene/MyFinanceExpertModel
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 36, | |
| "global_step": 184, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010869565217391304, | |
| "grad_norm": 0.18588238954544067, | |
| "learning_rate": 0.0, | |
| "loss": 1.4736328125, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021739130434782608, | |
| "grad_norm": 0.1947048008441925, | |
| "learning_rate": 1e-05, | |
| "loss": 1.5341796875, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03260869565217391, | |
| "grad_norm": 0.18918348848819733, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4052734375, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.043478260869565216, | |
| "grad_norm": 0.18988992273807526, | |
| "learning_rate": 3e-05, | |
| "loss": 1.30517578125, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05434782608695652, | |
| "grad_norm": 0.1465907096862793, | |
| "learning_rate": 4e-05, | |
| "loss": 1.349609375, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06521739130434782, | |
| "grad_norm": 0.12894085049629211, | |
| "learning_rate": 5e-05, | |
| "loss": 1.33447265625, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07608695652173914, | |
| "grad_norm": 0.10944489389657974, | |
| "learning_rate": 6e-05, | |
| "loss": 1.25830078125, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08695652173913043, | |
| "grad_norm": 0.11167462170124054, | |
| "learning_rate": 7e-05, | |
| "loss": 1.306640625, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09782608695652174, | |
| "grad_norm": 0.0900021567940712, | |
| "learning_rate": 8e-05, | |
| "loss": 1.23828125, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10869565217391304, | |
| "grad_norm": 0.13176031410694122, | |
| "learning_rate": 9e-05, | |
| "loss": 1.3193359375, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11956521739130435, | |
| "grad_norm": 0.1317533254623413, | |
| "learning_rate": 0.0001, | |
| "loss": 1.14404296875, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13043478260869565, | |
| "grad_norm": 0.13434647023677826, | |
| "learning_rate": 9.999266547540887e-05, | |
| "loss": 1.197265625, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14130434782608695, | |
| "grad_norm": 0.0930171012878418, | |
| "learning_rate": 9.997066429253547e-05, | |
| "loss": 1.22216796875, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15217391304347827, | |
| "grad_norm": 0.05628405511379242, | |
| "learning_rate": 9.993400362330058e-05, | |
| "loss": 1.05419921875, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16304347826086957, | |
| "grad_norm": 0.04639851301908493, | |
| "learning_rate": 9.988269541830775e-05, | |
| "loss": 1.1318359375, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17391304347826086, | |
| "grad_norm": 0.053449347615242004, | |
| "learning_rate": 9.98167564029477e-05, | |
| "loss": 1.04931640625, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18478260869565216, | |
| "grad_norm": 0.0613674633204937, | |
| "learning_rate": 9.97362080719462e-05, | |
| "loss": 1.17919921875, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1956521739130435, | |
| "grad_norm": 0.0489179864525795, | |
| "learning_rate": 9.964107668235719e-05, | |
| "loss": 0.9716796875, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.20652173913043478, | |
| "grad_norm": 0.0503905713558197, | |
| "learning_rate": 9.953139324500369e-05, | |
| "loss": 1.1591796875, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.21739130434782608, | |
| "grad_norm": 0.05160759389400482, | |
| "learning_rate": 9.940719351436869e-05, | |
| "loss": 0.9921875, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22826086956521738, | |
| "grad_norm": 0.05076571926474571, | |
| "learning_rate": 9.926851797694012e-05, | |
| "loss": 1.14013671875, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2391304347826087, | |
| "grad_norm": 0.050418201833963394, | |
| "learning_rate": 9.911541183801312e-05, | |
| "loss": 1.10205078125, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.044996920973062515, | |
| "learning_rate": 9.89479250069539e-05, | |
| "loss": 1.06689453125, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2608695652173913, | |
| "grad_norm": 0.0451265349984169, | |
| "learning_rate": 9.876611208093055e-05, | |
| "loss": 1.12060546875, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2717391304347826, | |
| "grad_norm": 0.04035104438662529, | |
| "learning_rate": 9.857003232711536e-05, | |
| "loss": 1.0703125, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2826086956521739, | |
| "grad_norm": 0.03495940566062927, | |
| "learning_rate": 9.835974966336503e-05, | |
| "loss": 0.88525390625, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.29347826086956524, | |
| "grad_norm": 0.05166083201766014, | |
| "learning_rate": 9.813533263738486e-05, | |
| "loss": 1.189453125, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.30434782608695654, | |
| "grad_norm": 0.038823310285806656, | |
| "learning_rate": 9.789685440438353e-05, | |
| "loss": 0.98779296875, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.31521739130434784, | |
| "grad_norm": 0.03691998869180679, | |
| "learning_rate": 9.764439270322611e-05, | |
| "loss": 1.1640625, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.32608695652173914, | |
| "grad_norm": 0.03796624019742012, | |
| "learning_rate": 9.737802983109287e-05, | |
| "loss": 1.02978515625, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.33695652173913043, | |
| "grad_norm": 0.04263104870915413, | |
| "learning_rate": 9.709785261665205e-05, | |
| "loss": 0.98974609375, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 0.044888075441122055, | |
| "learning_rate": 9.680395239175563e-05, | |
| "loss": 1.07470703125, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.358695652173913, | |
| "grad_norm": 0.04229896143078804, | |
| "learning_rate": 9.6496424961667e-05, | |
| "loss": 1.1181640625, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3695652173913043, | |
| "grad_norm": 0.04039580374956131, | |
| "learning_rate": 9.617537057383055e-05, | |
| "loss": 1.10107421875, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3804347826086957, | |
| "grad_norm": 0.03618437424302101, | |
| "learning_rate": 9.584089388519307e-05, | |
| "loss": 1.01708984375, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.391304347826087, | |
| "grad_norm": 0.03835980221629143, | |
| "learning_rate": 9.549310392808782e-05, | |
| "loss": 1.1201171875, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.40217391304347827, | |
| "grad_norm": 0.03548717126250267, | |
| "learning_rate": 9.513211407469221e-05, | |
| "loss": 0.94830322265625, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.41304347826086957, | |
| "grad_norm": 0.03912119194865227, | |
| "learning_rate": 9.475804200007104e-05, | |
| "loss": 1.11767578125, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.42391304347826086, | |
| "grad_norm": 0.04173147305846214, | |
| "learning_rate": 9.437100964381675e-05, | |
| "loss": 1.0810546875, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.43478260869565216, | |
| "grad_norm": 0.04037207365036011, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.0634765625, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.43478260869565216, | |
| "eval_loss": 1.04931640625, | |
| "eval_runtime": 6.3585, | |
| "eval_samples_per_second": 1.258, | |
| "eval_steps_per_second": 0.157, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.44565217391304346, | |
| "grad_norm": 0.04123736172914505, | |
| "learning_rate": 9.355857292754152e-05, | |
| "loss": 1.04931640625, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.45652173913043476, | |
| "grad_norm": 0.039305102080106735, | |
| "learning_rate": 9.313343340472388e-05, | |
| "loss": 1.0908203125, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4673913043478261, | |
| "grad_norm": 0.03992549329996109, | |
| "learning_rate": 9.269586318834841e-05, | |
| "loss": 1.05810546875, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4782608695652174, | |
| "grad_norm": 0.03971557691693306, | |
| "learning_rate": 9.224600491706008e-05, | |
| "loss": 1.154296875, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4891304347826087, | |
| "grad_norm": 0.03945128247141838, | |
| "learning_rate": 9.178400523515012e-05, | |
| "loss": 1.03857421875, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.036954931914806366, | |
| "learning_rate": 9.131001474475317e-05, | |
| "loss": 0.91845703125, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5108695652173914, | |
| "grad_norm": 0.041776467114686966, | |
| "learning_rate": 9.082418795675397e-05, | |
| "loss": 1.01220703125, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5217391304347826, | |
| "grad_norm": 0.038964807987213135, | |
| "learning_rate": 9.032668324042026e-05, | |
| "loss": 0.8963623046875, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.532608695652174, | |
| "grad_norm": 0.04493962973356247, | |
| "learning_rate": 8.981766277177764e-05, | |
| "loss": 0.8782958984375, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5434782608695652, | |
| "grad_norm": 0.04111941531300545, | |
| "learning_rate": 8.929729248074364e-05, | |
| "loss": 1.05712890625, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5543478260869565, | |
| "grad_norm": 0.045288294553756714, | |
| "learning_rate": 8.87657419970381e-05, | |
| "loss": 1.0810546875, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.5652173913043478, | |
| "grad_norm": 0.03733203932642937, | |
| "learning_rate": 8.822318459488744e-05, | |
| "loss": 0.77294921875, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.5760869565217391, | |
| "grad_norm": 0.04698137566447258, | |
| "learning_rate": 8.766979713654089e-05, | |
| "loss": 1.0654296875, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.5869565217391305, | |
| "grad_norm": 0.05637023597955704, | |
| "learning_rate": 8.71057600146172e-05, | |
| "loss": 1.06201171875, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.5978260869565217, | |
| "grad_norm": 0.04036635905504227, | |
| "learning_rate": 8.653125709330041e-05, | |
| "loss": 0.9677734375, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6086956521739131, | |
| "grad_norm": 0.04818817973136902, | |
| "learning_rate": 8.594647564840405e-05, | |
| "loss": 1.0546875, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.6195652173913043, | |
| "grad_norm": 0.04563218355178833, | |
| "learning_rate": 8.535160630632313e-05, | |
| "loss": 1.015625, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.6304347826086957, | |
| "grad_norm": 0.04481424391269684, | |
| "learning_rate": 8.474684298189402e-05, | |
| "loss": 1.00439453125, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.6413043478260869, | |
| "grad_norm": 0.0573306679725647, | |
| "learning_rate": 8.413238281518225e-05, | |
| "loss": 0.99609375, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.6521739130434783, | |
| "grad_norm": 0.04850015044212341, | |
| "learning_rate": 8.350842610721909e-05, | |
| "loss": 1.01025390625, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6630434782608695, | |
| "grad_norm": 0.044663649052381516, | |
| "learning_rate": 8.287517625470755e-05, | |
| "loss": 1.06005859375, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.6739130434782609, | |
| "grad_norm": 0.04311933368444443, | |
| "learning_rate": 8.223283968371944e-05, | |
| "loss": 0.916748046875, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.6847826086956522, | |
| "grad_norm": 0.04746570438146591, | |
| "learning_rate": 8.15816257824048e-05, | |
| "loss": 0.99072265625, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 0.04210105538368225, | |
| "learning_rate": 8.092174683273578e-05, | |
| "loss": 0.91845703125, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.7065217391304348, | |
| "grad_norm": 0.04694285988807678, | |
| "learning_rate": 8.025341794130722e-05, | |
| "loss": 0.9931640625, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.717391304347826, | |
| "grad_norm": 0.06701935827732086, | |
| "learning_rate": 7.957685696921636e-05, | |
| "loss": 1.00048828125, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.7282608695652174, | |
| "grad_norm": 0.06168576329946518, | |
| "learning_rate": 7.88922844610449e-05, | |
| "loss": 1.046875, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.7391304347826086, | |
| "grad_norm": 0.046262163668870926, | |
| "learning_rate": 7.819992357296598e-05, | |
| "loss": 1.01611328125, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.04800650104880333, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.87109375, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.7608695652173914, | |
| "grad_norm": 0.04885740950703621, | |
| "learning_rate": 7.679274190244287e-05, | |
| "loss": 1.0087890625, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7717391304347826, | |
| "grad_norm": 0.04720492660999298, | |
| "learning_rate": 7.607837983149056e-05, | |
| "loss": 1.02978515625, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.782608695652174, | |
| "grad_norm": 0.04430517181754112, | |
| "learning_rate": 7.535714665408423e-05, | |
| "loss": 0.848388671875, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.7934782608695652, | |
| "grad_norm": 0.04949856922030449, | |
| "learning_rate": 7.462927747700053e-05, | |
| "loss": 0.888671875, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.8043478260869565, | |
| "grad_norm": 0.053681328892707825, | |
| "learning_rate": 7.389500957021192e-05, | |
| "loss": 1.0283203125, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.8152173913043478, | |
| "grad_norm": 0.04809682071208954, | |
| "learning_rate": 7.31545822895414e-05, | |
| "loss": 1.02001953125, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8260869565217391, | |
| "grad_norm": 0.052168428897857666, | |
| "learning_rate": 7.240823699863777e-05, | |
| "loss": 1.02197265625, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.8260869565217391, | |
| "eval_loss": 0.99267578125, | |
| "eval_runtime": 6.384, | |
| "eval_samples_per_second": 1.253, | |
| "eval_steps_per_second": 0.157, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.8369565217391305, | |
| "grad_norm": 0.05126576125621796, | |
| "learning_rate": 7.165621699029615e-05, | |
| "loss": 0.95361328125, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.8478260869565217, | |
| "grad_norm": 0.0479954332113266, | |
| "learning_rate": 7.089876740714961e-05, | |
| "loss": 0.93212890625, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.8586956521739131, | |
| "grad_norm": 0.05192503705620766, | |
| "learning_rate": 7.013613516175788e-05, | |
| "loss": 0.9462890625, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.8695652173913043, | |
| "grad_norm": 0.05096974968910217, | |
| "learning_rate": 6.93685688561191e-05, | |
| "loss": 0.95166015625, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8804347826086957, | |
| "grad_norm": 0.0476989820599556, | |
| "learning_rate": 6.859631870063076e-05, | |
| "loss": 0.916015625, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.8913043478260869, | |
| "grad_norm": 0.12171965837478638, | |
| "learning_rate": 6.781963643252651e-05, | |
| "loss": 1.0029296875, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.9021739130434783, | |
| "grad_norm": 0.050482314079999924, | |
| "learning_rate": 6.703877523381496e-05, | |
| "loss": 1.001953125, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.9130434782608695, | |
| "grad_norm": 0.04611290618777275, | |
| "learning_rate": 6.625398964874784e-05, | |
| "loss": 0.8406982421875, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.9239130434782609, | |
| "grad_norm": 0.04967767000198364, | |
| "learning_rate": 6.546553550084398e-05, | |
| "loss": 0.8896484375, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.9347826086956522, | |
| "grad_norm": 0.055717870593070984, | |
| "learning_rate": 6.46736698094961e-05, | |
| "loss": 1.00537109375, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.9456521739130435, | |
| "grad_norm": 0.052366528660058975, | |
| "learning_rate": 6.3878650706188e-05, | |
| "loss": 1.01904296875, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.9565217391304348, | |
| "grad_norm": 0.07001721113920212, | |
| "learning_rate": 6.308073735034923e-05, | |
| "loss": 1.02001953125, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.967391304347826, | |
| "grad_norm": 0.04996788129210472, | |
| "learning_rate": 6.228018984487442e-05, | |
| "loss": 0.903076171875, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.9782608695652174, | |
| "grad_norm": 0.05138871446251869, | |
| "learning_rate": 6.147726915133536e-05, | |
| "loss": 0.96533203125, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.9891304347826086, | |
| "grad_norm": 0.05665658041834831, | |
| "learning_rate": 6.067223700491302e-05, | |
| "loss": 1.015625, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.05422813072800636, | |
| "learning_rate": 5.986535582907739e-05, | |
| "loss": 1.00537109375, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.0108695652173914, | |
| "grad_norm": 0.05152361840009689, | |
| "learning_rate": 5.9056888650042954e-05, | |
| "loss": 1.0166015625, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.0217391304347827, | |
| "grad_norm": 0.060649726539850235, | |
| "learning_rate": 5.8247099011027736e-05, | |
| "loss": 1.056640625, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.0326086956521738, | |
| "grad_norm": 0.046568043529987335, | |
| "learning_rate": 5.74362508863438e-05, | |
| "loss": 0.9560546875, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.0434782608695652, | |
| "grad_norm": 0.05016551539301872, | |
| "learning_rate": 5.662460859534714e-05, | |
| "loss": 0.882568359375, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.0543478260869565, | |
| "grad_norm": 0.05591215193271637, | |
| "learning_rate": 5.581243671627522e-05, | |
| "loss": 0.97021484375, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.065217391304348, | |
| "grad_norm": 0.05546316131949425, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.958984375, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.0760869565217392, | |
| "grad_norm": 0.060860466212034225, | |
| "learning_rate": 5.418756328372477e-05, | |
| "loss": 0.93408203125, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.0869565217391304, | |
| "grad_norm": 0.06850528717041016, | |
| "learning_rate": 5.337539140465287e-05, | |
| "loss": 0.9853515625, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0978260869565217, | |
| "grad_norm": 0.05219709500670433, | |
| "learning_rate": 5.2563749113656216e-05, | |
| "loss": 0.966796875, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.108695652173913, | |
| "grad_norm": 0.059890855103731155, | |
| "learning_rate": 5.175290098897229e-05, | |
| "loss": 1.03076171875, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.1195652173913044, | |
| "grad_norm": 0.061198536306619644, | |
| "learning_rate": 5.094311134995708e-05, | |
| "loss": 0.8857421875, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.1304347826086956, | |
| "grad_norm": 0.05207240954041481, | |
| "learning_rate": 5.013464417092263e-05, | |
| "loss": 0.9482421875, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.141304347826087, | |
| "grad_norm": 0.06015055254101753, | |
| "learning_rate": 4.932776299508699e-05, | |
| "loss": 0.98779296875, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.1521739130434783, | |
| "grad_norm": 0.06881439685821533, | |
| "learning_rate": 4.852273084866464e-05, | |
| "loss": 0.86865234375, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.1630434782608696, | |
| "grad_norm": 0.05143669992685318, | |
| "learning_rate": 4.771981015512559e-05, | |
| "loss": 0.93212890625, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.1739130434782608, | |
| "grad_norm": 0.05013814941048622, | |
| "learning_rate": 4.6919262649650776e-05, | |
| "loss": 0.87841796875, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.184782608695652, | |
| "grad_norm": 0.06504126638174057, | |
| "learning_rate": 4.612134929381201e-05, | |
| "loss": 0.9814453125, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.1956521739130435, | |
| "grad_norm": 0.04764424264431, | |
| "learning_rate": 4.532633019050392e-05, | |
| "loss": 0.811279296875, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.2065217391304348, | |
| "grad_norm": 0.05300690978765488, | |
| "learning_rate": 4.453446449915605e-05, | |
| "loss": 0.97021484375, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.2173913043478262, | |
| "grad_norm": 0.056520976126194, | |
| "learning_rate": 4.3746010351252174e-05, | |
| "loss": 0.835693359375, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.2173913043478262, | |
| "eval_loss": 0.9716796875, | |
| "eval_runtime": 6.3847, | |
| "eval_samples_per_second": 1.253, | |
| "eval_steps_per_second": 0.157, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.2282608695652173, | |
| "grad_norm": 0.05752632021903992, | |
| "learning_rate": 4.296122476618507e-05, | |
| "loss": 0.9580078125, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.2391304347826086, | |
| "grad_norm": 0.052798960357904434, | |
| "learning_rate": 4.21803635674735e-05, | |
| "loss": 0.9326171875, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.0545145682990551, | |
| "learning_rate": 4.1403681299369226e-05, | |
| "loss": 0.90185546875, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.2608695652173914, | |
| "grad_norm": 0.12075046449899673, | |
| "learning_rate": 4.0631431143880916e-05, | |
| "loss": 0.9541015625, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.2717391304347827, | |
| "grad_norm": 0.05467211827635765, | |
| "learning_rate": 3.986386483824212e-05, | |
| "loss": 0.92041015625, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.2826086956521738, | |
| "grad_norm": 0.058259688317775726, | |
| "learning_rate": 3.91012325928504e-05, | |
| "loss": 0.755859375, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.2934782608695652, | |
| "grad_norm": 0.057315390557050705, | |
| "learning_rate": 3.834378300970385e-05, | |
| "loss": 1.02392578125, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.3043478260869565, | |
| "grad_norm": 0.052486542612314224, | |
| "learning_rate": 3.7591763001362246e-05, | |
| "loss": 0.84228515625, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.315217391304348, | |
| "grad_norm": 0.052620261907577515, | |
| "learning_rate": 3.684541771045862e-05, | |
| "loss": 1.00146484375, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.3260869565217392, | |
| "grad_norm": 0.05407518520951271, | |
| "learning_rate": 3.61049904297881e-05, | |
| "loss": 0.8876953125, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.3369565217391304, | |
| "grad_norm": 0.061481185257434845, | |
| "learning_rate": 3.537072252299947e-05, | |
| "loss": 0.85791015625, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.3478260869565217, | |
| "grad_norm": 0.053316932171583176, | |
| "learning_rate": 3.464285334591579e-05, | |
| "loss": 0.9296875, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.358695652173913, | |
| "grad_norm": 0.053633544594049454, | |
| "learning_rate": 3.392162016850945e-05, | |
| "loss": 0.96484375, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.3695652173913042, | |
| "grad_norm": 0.054563552141189575, | |
| "learning_rate": 3.3207258097557136e-05, | |
| "loss": 0.95703125, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.3804347826086958, | |
| "grad_norm": 0.055144086480140686, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.886474609375, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.391304347826087, | |
| "grad_norm": 0.05462967976927757, | |
| "learning_rate": 3.180007642703402e-05, | |
| "loss": 0.986328125, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.4021739130434783, | |
| "grad_norm": 0.051473114639520645, | |
| "learning_rate": 3.1107715538955106e-05, | |
| "loss": 0.82843017578125, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.4130434782608696, | |
| "grad_norm": 0.06261783838272095, | |
| "learning_rate": 3.042314303078364e-05, | |
| "loss": 0.97509765625, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.4239130434782608, | |
| "grad_norm": 0.05514520779252052, | |
| "learning_rate": 2.97465820586928e-05, | |
| "loss": 0.9443359375, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.434782608695652, | |
| "grad_norm": 0.05541987344622612, | |
| "learning_rate": 2.9078253167264223e-05, | |
| "loss": 0.92919921875, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.4456521739130435, | |
| "grad_norm": 0.05705087631940842, | |
| "learning_rate": 2.8418374217595213e-05, | |
| "loss": 0.91845703125, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.4565217391304348, | |
| "grad_norm": 0.05676661804318428, | |
| "learning_rate": 2.7767160316280583e-05, | |
| "loss": 0.95703125, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.4673913043478262, | |
| "grad_norm": 0.056343358010053635, | |
| "learning_rate": 2.712482374529247e-05, | |
| "loss": 0.92138671875, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.4782608695652173, | |
| "grad_norm": 0.05837247893214226, | |
| "learning_rate": 2.649157389278094e-05, | |
| "loss": 1.01513671875, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.4891304347826086, | |
| "grad_norm": 0.05657912418246269, | |
| "learning_rate": 2.586761718481776e-05, | |
| "loss": 0.9130859375, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.10456497222185135, | |
| "learning_rate": 2.5253157018105993e-05, | |
| "loss": 0.803466796875, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.5108695652173914, | |
| "grad_norm": 0.06464536488056183, | |
| "learning_rate": 2.464839369367688e-05, | |
| "loss": 0.890625, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.5217391304347827, | |
| "grad_norm": 0.05322624742984772, | |
| "learning_rate": 2.4053524351595948e-05, | |
| "loss": 0.790924072265625, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.5326086956521738, | |
| "grad_norm": 0.05579627305269241, | |
| "learning_rate": 2.3468742906699597e-05, | |
| "loss": 0.77099609375, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.5434782608695652, | |
| "grad_norm": 0.06104826182126999, | |
| "learning_rate": 2.28942399853828e-05, | |
| "loss": 0.9365234375, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.5543478260869565, | |
| "grad_norm": 0.06145164743065834, | |
| "learning_rate": 2.2330202863459122e-05, | |
| "loss": 0.958984375, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.5652173913043477, | |
| "grad_norm": 0.05294163525104523, | |
| "learning_rate": 2.1776815405112568e-05, | |
| "loss": 0.6845703125, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.5760869565217392, | |
| "grad_norm": 0.0592268668115139, | |
| "learning_rate": 2.1234258002961897e-05, | |
| "loss": 0.9482421875, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.5869565217391304, | |
| "grad_norm": 0.06355844438076019, | |
| "learning_rate": 2.0702707519256364e-05, | |
| "loss": 0.9443359375, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.5978260869565217, | |
| "grad_norm": 0.05757714435458183, | |
| "learning_rate": 2.0182337228222365e-05, | |
| "loss": 0.859375, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.608695652173913, | |
| "grad_norm": 0.06119934096932411, | |
| "learning_rate": 1.967331675957975e-05, | |
| "loss": 0.94140625, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.608695652173913, | |
| "eval_loss": 0.9599609375, | |
| "eval_runtime": 6.387, | |
| "eval_samples_per_second": 1.253, | |
| "eval_steps_per_second": 0.157, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.6195652173913042, | |
| "grad_norm": 1.742512583732605, | |
| "learning_rate": 1.9175812043246033e-05, | |
| "loss": 0.9052734375, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.6304347826086958, | |
| "grad_norm": 0.06572595238685608, | |
| "learning_rate": 1.8689985255246834e-05, | |
| "loss": 0.8955078125, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.641304347826087, | |
| "grad_norm": 0.06171270087361336, | |
| "learning_rate": 1.821599476484987e-05, | |
| "loss": 0.888671875, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.6521739130434783, | |
| "grad_norm": 0.06164025515317917, | |
| "learning_rate": 1.775399508293993e-05, | |
| "loss": 0.9052734375, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.6630434782608696, | |
| "grad_norm": 0.06409742683172226, | |
| "learning_rate": 1.7304136811651596e-05, | |
| "loss": 0.947265625, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.6739130434782608, | |
| "grad_norm": 0.056571125984191895, | |
| "learning_rate": 1.6866566595276106e-05, | |
| "loss": 0.82403564453125, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.6847826086956523, | |
| "grad_norm": 0.07560455054044724, | |
| "learning_rate": 1.6441427072458494e-05, | |
| "loss": 0.888671875, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.6956521739130435, | |
| "grad_norm": 0.0648086741566658, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.82421875, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.7065217391304348, | |
| "grad_norm": 0.067837655544281, | |
| "learning_rate": 1.5628990356183268e-05, | |
| "loss": 0.890625, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.7173913043478262, | |
| "grad_norm": 0.0631956160068512, | |
| "learning_rate": 1.5241957999928974e-05, | |
| "loss": 0.89599609375, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.7282608695652173, | |
| "grad_norm": 0.07191090285778046, | |
| "learning_rate": 1.48678859253078e-05, | |
| "loss": 0.9482421875, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.7391304347826086, | |
| "grad_norm": 0.062349699437618256, | |
| "learning_rate": 1.4506896071912207e-05, | |
| "loss": 0.91552734375, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.06104462221264839, | |
| "learning_rate": 1.4159106114806942e-05, | |
| "loss": 0.7841796875, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.7608695652173914, | |
| "grad_norm": 0.060603346675634384, | |
| "learning_rate": 1.3824629426169453e-05, | |
| "loss": 0.91015625, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.7717391304347827, | |
| "grad_norm": 0.06206117570400238, | |
| "learning_rate": 1.350357503833301e-05, | |
| "loss": 0.93115234375, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.7826086956521738, | |
| "grad_norm": 0.06806284934282303, | |
| "learning_rate": 1.3196047608244389e-05, | |
| "loss": 0.7666015625, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.7934782608695652, | |
| "grad_norm": 0.05813819169998169, | |
| "learning_rate": 1.2902147383347959e-05, | |
| "loss": 0.80029296875, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.8043478260869565, | |
| "grad_norm": 0.06218123435974121, | |
| "learning_rate": 1.262197016890714e-05, | |
| "loss": 0.93408203125, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.8152173913043477, | |
| "grad_norm": 0.06234293431043625, | |
| "learning_rate": 1.2355607296773895e-05, | |
| "loss": 0.93017578125, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.8260869565217392, | |
| "grad_norm": 0.06383553892374039, | |
| "learning_rate": 1.2103145595616483e-05, | |
| "loss": 0.92626953125, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.8369565217391304, | |
| "grad_norm": 0.061867013573646545, | |
| "learning_rate": 1.1864667362615142e-05, | |
| "loss": 0.86474609375, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.8478260869565217, | |
| "grad_norm": 0.06146484985947609, | |
| "learning_rate": 1.164025033663497e-05, | |
| "loss": 0.84765625, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.858695652173913, | |
| "grad_norm": 0.06298917531967163, | |
| "learning_rate": 1.1429967672884653e-05, | |
| "loss": 0.865234375, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.8695652173913042, | |
| "grad_norm": 0.0625348687171936, | |
| "learning_rate": 1.1233887919069461e-05, | |
| "loss": 0.86865234375, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.8804347826086958, | |
| "grad_norm": 0.06479020416736603, | |
| "learning_rate": 1.1052074993046102e-05, | |
| "loss": 0.84033203125, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.891304347826087, | |
| "grad_norm": 0.06634494662284851, | |
| "learning_rate": 1.0884588161986892e-05, | |
| "loss": 0.91845703125, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.9021739130434783, | |
| "grad_norm": 0.06477183103561401, | |
| "learning_rate": 1.073148202305988e-05, | |
| "loss": 0.916015625, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.9130434782608696, | |
| "grad_norm": 0.060632795095443726, | |
| "learning_rate": 1.0592806485631325e-05, | |
| "loss": 0.773193359375, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.9239130434782608, | |
| "grad_norm": 0.06851464509963989, | |
| "learning_rate": 1.0468606754996326e-05, | |
| "loss": 0.81787109375, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.9347826086956523, | |
| "grad_norm": 0.06455637514591217, | |
| "learning_rate": 1.0358923317642806e-05, | |
| "loss": 0.923828125, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.9456521739130435, | |
| "grad_norm": 0.06511721760034561, | |
| "learning_rate": 1.0263791928053819e-05, | |
| "loss": 0.94091796875, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.9565217391304348, | |
| "grad_norm": 0.06577809900045395, | |
| "learning_rate": 1.0183243597052312e-05, | |
| "loss": 0.93994140625, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.9673913043478262, | |
| "grad_norm": 0.06064470857381821, | |
| "learning_rate": 1.0117304581692261e-05, | |
| "loss": 0.83453369140625, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.9782608695652173, | |
| "grad_norm": 0.06249881535768509, | |
| "learning_rate": 1.006599637669943e-05, | |
| "loss": 0.89453125, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.9891304347826086, | |
| "grad_norm": 0.0665738582611084, | |
| "learning_rate": 1.0029335707464538e-05, | |
| "loss": 0.9384765625, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.06674587726593018, | |
| "learning_rate": 1.0007334524591144e-05, | |
| "loss": 0.9150390625, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.95654296875, | |
| "eval_runtime": 6.4018, | |
| "eval_samples_per_second": 1.25, | |
| "eval_steps_per_second": 0.156, | |
| "step": 184 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 184, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5122809836124766e+19, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |