Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use tzchen07/g2_X9h with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tzchen07/g2_X9h with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="tzchen07/g2_X9h") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("tzchen07/g2_X9h") model = AutoModelForMultimodalLM.from_pretrained("tzchen07/g2_X9h") 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 tzchen07/g2_X9h with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tzchen07/g2_X9h" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tzchen07/g2_X9h", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/tzchen07/g2_X9h
- SGLang
How to use tzchen07/g2_X9h 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 "tzchen07/g2_X9h" \ --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": "tzchen07/g2_X9h", "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 "tzchen07/g2_X9h" \ --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": "tzchen07/g2_X9h", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use tzchen07/g2_X9h with Docker Model Runner:
docker model run hf.co/tzchen07/g2_X9h
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 747, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02009545340366742, | |
| "grad_norm": 101.4629135131836, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 2.9256, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04019090680733484, | |
| "grad_norm": 83.51904296875, | |
| "learning_rate": 9.000000000000001e-07, | |
| "loss": 2.7459, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06028636021100226, | |
| "grad_norm": 25.10388946533203, | |
| "learning_rate": 1.4000000000000001e-06, | |
| "loss": 1.637, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08038181361466969, | |
| "grad_norm": 13.024300575256348, | |
| "learning_rate": 1.9000000000000002e-06, | |
| "loss": 1.1459, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1004772670183371, | |
| "grad_norm": 8.315956115722656, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 0.7456, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12057272042200452, | |
| "grad_norm": 8.930346488952637, | |
| "learning_rate": 2.9e-06, | |
| "loss": 0.5717, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14066817382567195, | |
| "grad_norm": 7.356456756591797, | |
| "learning_rate": 3.4000000000000005e-06, | |
| "loss": 0.414, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16076362722933937, | |
| "grad_norm": 5.648008346557617, | |
| "learning_rate": 3.900000000000001e-06, | |
| "loss": 0.2577, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1808590806330068, | |
| "grad_norm": 6.329988956451416, | |
| "learning_rate": 4.4e-06, | |
| "loss": 0.2394, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2009545340366742, | |
| "grad_norm": 5.1738080978393555, | |
| "learning_rate": 4.9000000000000005e-06, | |
| "loss": 0.1848, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22104998744034163, | |
| "grad_norm": 4.86478853225708, | |
| "learning_rate": 4.999016565957633e-06, | |
| "loss": 0.2195, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.24114544084400905, | |
| "grad_norm": 4.442976474761963, | |
| "learning_rate": 4.995022691166621e-06, | |
| "loss": 0.1582, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.26124089424767644, | |
| "grad_norm": 3.704345941543579, | |
| "learning_rate": 4.987961816680493e-06, | |
| "loss": 0.183, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2813363476513439, | |
| "grad_norm": 3.772160768508911, | |
| "learning_rate": 4.977842622059546e-06, | |
| "loss": 0.164, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.30143180105501133, | |
| "grad_norm": 3.2532081604003906, | |
| "learning_rate": 4.96467754629559e-06, | |
| "loss": 0.1781, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.32152725445867875, | |
| "grad_norm": 2.893615484237671, | |
| "learning_rate": 4.948482772521346e-06, | |
| "loss": 0.1288, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.34162270786234616, | |
| "grad_norm": 4.654979705810547, | |
| "learning_rate": 4.929278208117378e-06, | |
| "loss": 0.1444, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3617181612660136, | |
| "grad_norm": 2.8989882469177246, | |
| "learning_rate": 4.907087460240999e-06, | |
| "loss": 0.1151, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.381813614669681, | |
| "grad_norm": 3.7547988891601562, | |
| "learning_rate": 4.881937806807241e-06, | |
| "loss": 0.1197, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.4019090680733484, | |
| "grad_norm": 2.273831605911255, | |
| "learning_rate": 4.8538601629575525e-06, | |
| "loss": 0.0966, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.42200452147701584, | |
| "grad_norm": 2.4642996788024902, | |
| "learning_rate": 4.822889043057446e-06, | |
| "loss": 0.1088, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.44209997488068326, | |
| "grad_norm": 3.29301381111145, | |
| "learning_rate": 4.789062518269812e-06, | |
| "loss": 0.1163, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4621954282843507, | |
| "grad_norm": 2.45603084564209, | |
| "learning_rate": 4.752422169756048e-06, | |
| "loss": 0.1151, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.4822908816880181, | |
| "grad_norm": 3.199894666671753, | |
| "learning_rate": 4.713013037562531e-06, | |
| "loss": 0.098, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5023863350916855, | |
| "grad_norm": 1.7128061056137085, | |
| "learning_rate": 4.670883565255264e-06, | |
| "loss": 0.0968, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5224817884953529, | |
| "grad_norm": 2.645235776901245, | |
| "learning_rate": 4.6260855403707625e-06, | |
| "loss": 0.1068, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5425772418990203, | |
| "grad_norm": 2.3140530586242676, | |
| "learning_rate": 4.578674030756364e-06, | |
| "loss": 0.0914, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5626726953026878, | |
| "grad_norm": 1.8588067293167114, | |
| "learning_rate": 4.528707316878233e-06, | |
| "loss": 0.0995, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5827681487063552, | |
| "grad_norm": 1.9172967672348022, | |
| "learning_rate": 4.476246820180259e-06, | |
| "loss": 0.08, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6028636021100227, | |
| "grad_norm": 2.9082584381103516, | |
| "learning_rate": 4.421357027581921e-06, | |
| "loss": 0.1066, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.62295905551369, | |
| "grad_norm": 3.6944031715393066, | |
| "learning_rate": 4.364105412207914e-06, | |
| "loss": 0.1124, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.6430545089173575, | |
| "grad_norm": 1.5622600317001343, | |
| "learning_rate": 4.304562350447008e-06, | |
| "loss": 0.0856, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6631499623210249, | |
| "grad_norm": 2.388239860534668, | |
| "learning_rate": 4.242801035442059e-06, | |
| "loss": 0.0766, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.6832454157246923, | |
| "grad_norm": 1.7182718515396118, | |
| "learning_rate": 4.178897387117547e-06, | |
| "loss": 0.104, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7033408691283597, | |
| "grad_norm": 2.2367119789123535, | |
| "learning_rate": 4.11292995885522e-06, | |
| "loss": 0.0737, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.7234363225320272, | |
| "grad_norm": 2.007200241088867, | |
| "learning_rate": 4.044979840932567e-06, | |
| "loss": 0.0893, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7435317759356945, | |
| "grad_norm": 2.6910905838012695, | |
| "learning_rate": 3.975130560842821e-06, | |
| "loss": 0.0944, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.763627229339362, | |
| "grad_norm": 2.042320489883423, | |
| "learning_rate": 3.9034679806190204e-06, | |
| "loss": 0.0843, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7837226827430294, | |
| "grad_norm": 2.700977087020874, | |
| "learning_rate": 3.830080191288342e-06, | |
| "loss": 0.0669, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.8038181361466968, | |
| "grad_norm": 3.0307390689849854, | |
| "learning_rate": 3.755057404586455e-06, | |
| "loss": 0.0955, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8239135895503642, | |
| "grad_norm": 1.3993719816207886, | |
| "learning_rate": 2.666666666666667e-07, | |
| "loss": 0.099, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.8440090429540317, | |
| "grad_norm": 1.7611238956451416, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 0.0771, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.864104496357699, | |
| "grad_norm": 2.088745594024658, | |
| "learning_rate": 9.333333333333334e-07, | |
| "loss": 0.0911, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.8841999497613665, | |
| "grad_norm": 2.071209669113159, | |
| "learning_rate": 1.2666666666666669e-06, | |
| "loss": 0.0757, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9042954031650339, | |
| "grad_norm": 2.046583414077759, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 0.0609, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.9243908565687013, | |
| "grad_norm": 2.160752534866333, | |
| "learning_rate": 1.9333333333333336e-06, | |
| "loss": 0.1033, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9444863099723687, | |
| "grad_norm": 1.2902394533157349, | |
| "learning_rate": 2.266666666666667e-06, | |
| "loss": 0.0987, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.9645817633760362, | |
| "grad_norm": 2.7047502994537354, | |
| "learning_rate": 2.6e-06, | |
| "loss": 0.084, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.9846772167797035, | |
| "grad_norm": 1.3737807273864746, | |
| "learning_rate": 2.9333333333333338e-06, | |
| "loss": 0.0879, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.0040190906807336, | |
| "grad_norm": 1.6534603834152222, | |
| "learning_rate": 3.266666666666667e-06, | |
| "loss": 0.0933, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.0241145440844008, | |
| "grad_norm": 1.805727481842041, | |
| "learning_rate": 3.6000000000000003e-06, | |
| "loss": 0.0528, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.0442099974880683, | |
| "grad_norm": 1.864627480506897, | |
| "learning_rate": 3.9333333333333335e-06, | |
| "loss": 0.0678, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0643054508917358, | |
| "grad_norm": 3.2414352893829346, | |
| "learning_rate": 4.266666666666668e-06, | |
| "loss": 0.0671, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.0844009042954033, | |
| "grad_norm": 2.1301753520965576, | |
| "learning_rate": 4.600000000000001e-06, | |
| "loss": 0.0666, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.1044963576990705, | |
| "grad_norm": 1.5783054828643799, | |
| "learning_rate": 4.933333333333334e-06, | |
| "loss": 0.061, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.124591811102738, | |
| "grad_norm": 1.8704148530960083, | |
| "learning_rate": 4.999562902281866e-06, | |
| "loss": 0.067, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.1446872645064055, | |
| "grad_norm": 3.888225555419922, | |
| "learning_rate": 4.997787454752217e-06, | |
| "loss": 0.0629, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.164782717910073, | |
| "grad_norm": 3.0024731159210205, | |
| "learning_rate": 4.994647308096509e-06, | |
| "loss": 0.0734, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.1848781713137402, | |
| "grad_norm": 1.866017460823059, | |
| "learning_rate": 4.99014417797529e-06, | |
| "loss": 0.076, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.2049736247174077, | |
| "grad_norm": 2.368576765060425, | |
| "learning_rate": 4.984280524733107e-06, | |
| "loss": 0.0722, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.2250690781210751, | |
| "grad_norm": 1.0686993598937988, | |
| "learning_rate": 4.97705955205426e-06, | |
| "loss": 0.0564, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 1.2451645315247426, | |
| "grad_norm": 2.0142111778259277, | |
| "learning_rate": 4.968485205212429e-06, | |
| "loss": 0.069, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.2652599849284099, | |
| "grad_norm": 1.7636579275131226, | |
| "learning_rate": 4.958562168915121e-06, | |
| "loss": 0.0748, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.2853554383320773, | |
| "grad_norm": 2.050908327102661, | |
| "learning_rate": 4.947295864744121e-06, | |
| "loss": 0.0636, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.3054508917357448, | |
| "grad_norm": 2.618356227874756, | |
| "learning_rate": 4.9346924481933345e-06, | |
| "loss": 0.06, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.3255463451394123, | |
| "grad_norm": 2.7333900928497314, | |
| "learning_rate": 4.920758805305654e-06, | |
| "loss": 0.0714, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.3456417985430797, | |
| "grad_norm": 1.96294105052948, | |
| "learning_rate": 4.905502548910681e-06, | |
| "loss": 0.0599, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.365737251946747, | |
| "grad_norm": 1.5320404767990112, | |
| "learning_rate": 4.8889320144653525e-06, | |
| "loss": 0.0618, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.3858327053504145, | |
| "grad_norm": 1.1524103879928589, | |
| "learning_rate": 4.871056255499758e-06, | |
| "loss": 0.058, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 1.405928158754082, | |
| "grad_norm": 1.3121646642684937, | |
| "learning_rate": 4.851885038670618e-06, | |
| "loss": 0.0684, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.4260236121577492, | |
| "grad_norm": 6.67919397354126, | |
| "learning_rate": 4.831428838425153e-06, | |
| "loss": 0.0766, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 1.4461190655614167, | |
| "grad_norm": 1.1791391372680664, | |
| "learning_rate": 4.809698831278217e-06, | |
| "loss": 0.0705, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.4662145189650841, | |
| "grad_norm": 0.794983983039856, | |
| "learning_rate": 4.7867068897058725e-06, | |
| "loss": 0.0654, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 1.4863099723687516, | |
| "grad_norm": 1.4783415794372559, | |
| "learning_rate": 4.7624655756587e-06, | |
| "loss": 0.0644, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.506405425772419, | |
| "grad_norm": 2.592212200164795, | |
| "learning_rate": 4.736988133698416e-06, | |
| "loss": 0.0621, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.5265008791760866, | |
| "grad_norm": 16.9811954498291, | |
| "learning_rate": 4.710288483761524e-06, | |
| "loss": 0.0824, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.5465963325797538, | |
| "grad_norm": 1.3936235904693604, | |
| "learning_rate": 4.682381213553986e-06, | |
| "loss": 0.069, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.5666917859834213, | |
| "grad_norm": 1.3866426944732666, | |
| "learning_rate": 4.653281570581023e-06, | |
| "loss": 0.0612, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.5867872393870885, | |
| "grad_norm": 4.862287521362305, | |
| "learning_rate": 4.623005453816447e-06, | |
| "loss": 0.0592, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.606882692790756, | |
| "grad_norm": 1.4648241996765137, | |
| "learning_rate": 4.59156940501605e-06, | |
| "loss": 0.0656, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.6269781461944235, | |
| "grad_norm": 1.3857091665267944, | |
| "learning_rate": 4.558990599679787e-06, | |
| "loss": 0.053, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.647073599598091, | |
| "grad_norm": 1.5649819374084473, | |
| "learning_rate": 4.525286837667726e-06, | |
| "loss": 0.0679, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.6671690530017584, | |
| "grad_norm": 1.6404094696044922, | |
| "learning_rate": 4.490476533474854e-06, | |
| "loss": 0.0593, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.687264506405426, | |
| "grad_norm": 2.027069091796875, | |
| "learning_rate": 4.454578706170075e-06, | |
| "loss": 0.066, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.7073599598090932, | |
| "grad_norm": 1.5853019952774048, | |
| "learning_rate": 4.4176129690048905e-06, | |
| "loss": 0.0575, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.7274554132127606, | |
| "grad_norm": 1.673964262008667, | |
| "learning_rate": 4.379599518697444e-06, | |
| "loss": 0.0699, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.747550866616428, | |
| "grad_norm": 1.7655727863311768, | |
| "learning_rate": 4.340559124397774e-06, | |
| "loss": 0.0648, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.7676463200200954, | |
| "grad_norm": 1.7724250555038452, | |
| "learning_rate": 4.300513116340317e-06, | |
| "loss": 0.0649, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.7877417734237628, | |
| "grad_norm": 2.0756025314331055, | |
| "learning_rate": 4.259483374189851e-06, | |
| "loss": 0.0671, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 1.8078372268274303, | |
| "grad_norm": 1.371147871017456, | |
| "learning_rate": 4.217492315087255e-06, | |
| "loss": 0.0577, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.8279326802310978, | |
| "grad_norm": 1.650765061378479, | |
| "learning_rate": 4.174562881401602e-06, | |
| "loss": 0.0529, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.8480281336347653, | |
| "grad_norm": 1.710800290107727, | |
| "learning_rate": 4.130718528195303e-06, | |
| "loss": 0.0773, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.8681235870384325, | |
| "grad_norm": 1.3324027061462402, | |
| "learning_rate": 4.085983210409114e-06, | |
| "loss": 0.0489, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.8882190404421, | |
| "grad_norm": 1.2311439514160156, | |
| "learning_rate": 4.040381369774045e-06, | |
| "loss": 0.0626, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.9083144938457672, | |
| "grad_norm": 1.9271433353424072, | |
| "learning_rate": 3.993937921457292e-06, | |
| "loss": 0.0552, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.9284099472494347, | |
| "grad_norm": 1.261828899383545, | |
| "learning_rate": 3.946678240449515e-06, | |
| "loss": 0.0566, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.9485054006531022, | |
| "grad_norm": 0.6837953329086304, | |
| "learning_rate": 3.898628147700869e-06, | |
| "loss": 0.0536, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 1.9686008540567697, | |
| "grad_norm": 1.0735151767730713, | |
| "learning_rate": 3.849813896013392e-06, | |
| "loss": 0.05, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.9886963074604371, | |
| "grad_norm": 0.8213454484939575, | |
| "learning_rate": 3.8002621556974367e-06, | |
| "loss": 0.0586, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 2.008038181361467, | |
| "grad_norm": 0.6580628156661987, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.06, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.028133634765134, | |
| "grad_norm": 0.7195087671279907, | |
| "learning_rate": 3.699054890312892e-06, | |
| "loss": 0.045, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 2.0482290881688017, | |
| "grad_norm": 1.023980736732483, | |
| "learning_rate": 3.6474546611688446e-06, | |
| "loss": 0.0411, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.068324541572469, | |
| "grad_norm": 2.1551263332366943, | |
| "learning_rate": 3.595227505033747e-06, | |
| "loss": 0.0445, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 2.0884199949761366, | |
| "grad_norm": 1.0194848775863647, | |
| "learning_rate": 3.542401956903321e-06, | |
| "loss": 0.0435, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.108515448379804, | |
| "grad_norm": 1.3117692470550537, | |
| "learning_rate": 3.4890068787126475e-06, | |
| "loss": 0.0425, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.1286109017834716, | |
| "grad_norm": 1.0447578430175781, | |
| "learning_rate": 3.4350714435670706e-06, | |
| "loss": 0.0457, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.148706355187139, | |
| "grad_norm": 1.320180058479309, | |
| "learning_rate": 3.3806251198030843e-06, | |
| "loss": 0.0451, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 2.1688018085908065, | |
| "grad_norm": 1.2361814975738525, | |
| "learning_rate": 3.3256976548879183e-06, | |
| "loss": 0.0399, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.188897261994474, | |
| "grad_norm": 1.0395464897155762, | |
| "learning_rate": 3.2703190591666174e-06, | |
| "loss": 0.044, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 2.208992715398141, | |
| "grad_norm": 1.1011066436767578, | |
| "learning_rate": 3.2145195894654947e-06, | |
| "loss": 0.0475, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.2290881688018085, | |
| "grad_norm": 1.1726021766662598, | |
| "learning_rate": 3.1583297325609117e-06, | |
| "loss": 0.0388, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 2.249183622205476, | |
| "grad_norm": 0.5452726483345032, | |
| "learning_rate": 3.1017801885224332e-06, | |
| "loss": 0.0397, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.2692790756091434, | |
| "grad_norm": 0.5013831853866577, | |
| "learning_rate": 3.0449018539394274e-06, | |
| "loss": 0.0416, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 2.289374529012811, | |
| "grad_norm": 1.811000108718872, | |
| "learning_rate": 2.9877258050403214e-06, | |
| "loss": 0.0446, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.3094699824164784, | |
| "grad_norm": 0.47706952691078186, | |
| "learning_rate": 2.93028328071368e-06, | |
| "loss": 0.0401, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 2.329565435820146, | |
| "grad_norm": 0.6600978970527649, | |
| "learning_rate": 2.872605665440436e-06, | |
| "loss": 0.038, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.349660889223813, | |
| "grad_norm": 0.7098400592803955, | |
| "learning_rate": 2.814724472146564e-06, | |
| "loss": 0.0417, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 2.3697563426274804, | |
| "grad_norm": 1.493393063545227, | |
| "learning_rate": 2.7566713249855715e-06, | |
| "loss": 0.0454, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.389851796031148, | |
| "grad_norm": 1.273262619972229, | |
| "learning_rate": 2.6984779420602324e-06, | |
| "loss": 0.044, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 2.4099472494348153, | |
| "grad_norm": 0.6910083293914795, | |
| "learning_rate": 2.6401761180929798e-06, | |
| "loss": 0.0411, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.430042702838483, | |
| "grad_norm": 0.8312556743621826, | |
| "learning_rate": 2.5817977070544408e-06, | |
| "loss": 0.0417, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 2.4501381562421503, | |
| "grad_norm": 0.5327412486076355, | |
| "learning_rate": 2.5233746047595984e-06, | |
| "loss": 0.0466, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.4702336096458177, | |
| "grad_norm": 0.7914028167724609, | |
| "learning_rate": 2.464938731441095e-06, | |
| "loss": 0.044, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 2.490329063049485, | |
| "grad_norm": 0.6906220316886902, | |
| "learning_rate": 2.4065220143091863e-06, | |
| "loss": 0.0397, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.5104245164531527, | |
| "grad_norm": 0.6936028003692627, | |
| "learning_rate": 2.348156370107897e-06, | |
| "loss": 0.0435, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.5305199698568197, | |
| "grad_norm": 1.5331124067306519, | |
| "learning_rate": 2.2898736876768816e-06, | |
| "loss": 0.0425, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.550615423260487, | |
| "grad_norm": 1.3947535753250122, | |
| "learning_rate": 2.231705810528534e-06, | |
| "loss": 0.044, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 2.5707108766641547, | |
| "grad_norm": 0.6972404718399048, | |
| "learning_rate": 2.173684519449872e-06, | |
| "loss": 0.0409, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.590806330067822, | |
| "grad_norm": 0.8982294201850891, | |
| "learning_rate": 2.1158415151386746e-06, | |
| "loss": 0.0405, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 2.6109017834714896, | |
| "grad_norm": 0.7696537971496582, | |
| "learning_rate": 2.0582084008834003e-06, | |
| "loss": 0.0388, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.630997236875157, | |
| "grad_norm": 1.5828746557235718, | |
| "learning_rate": 2.000816665296302e-06, | |
| "loss": 0.0412, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 2.6510926902788245, | |
| "grad_norm": 0.7513744831085205, | |
| "learning_rate": 1.9436976651092143e-06, | |
| "loss": 0.0406, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.6711881436824916, | |
| "grad_norm": 1.0159986019134521, | |
| "learning_rate": 1.8868826080413876e-06, | |
| "loss": 0.0414, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 2.6912835970861595, | |
| "grad_norm": 1.909378170967102, | |
| "learning_rate": 1.8304025357487427e-06, | |
| "loss": 0.0405, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.7113790504898265, | |
| "grad_norm": 0.875823974609375, | |
| "learning_rate": 1.7742883068638447e-06, | |
| "loss": 0.0413, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 2.731474503893494, | |
| "grad_norm": 1.1646164655685425, | |
| "learning_rate": 1.7185705801358892e-06, | |
| "loss": 0.0431, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.7515699572971615, | |
| "grad_norm": 0.9963555335998535, | |
| "learning_rate": 1.6632797976798887e-06, | |
| "loss": 0.0481, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 2.771665410700829, | |
| "grad_norm": 1.4356679916381836, | |
| "learning_rate": 1.6084461683442176e-06, | |
| "loss": 0.0449, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.7917608641044964, | |
| "grad_norm": 1.0450688600540161, | |
| "learning_rate": 1.5540996512056164e-06, | |
| "loss": 0.0401, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 2.811856317508164, | |
| "grad_norm": 1.4896055459976196, | |
| "learning_rate": 1.500269939200648e-06, | |
| "loss": 0.036, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.8319517709118314, | |
| "grad_norm": 1.0106236934661865, | |
| "learning_rate": 1.446986442902574e-06, | |
| "loss": 0.0428, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 2.8520472243154984, | |
| "grad_norm": 1.2998173236846924, | |
| "learning_rate": 1.3942782744524974e-06, | |
| "loss": 0.0412, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.8721426777191663, | |
| "grad_norm": 0.6855912804603577, | |
| "learning_rate": 1.342174231653564e-06, | |
| "loss": 0.042, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 2.8922381311228333, | |
| "grad_norm": 0.4582258462905884, | |
| "learning_rate": 1.2907027822369006e-06, | |
| "loss": 0.0356, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.912333584526501, | |
| "grad_norm": 0.9219332337379456, | |
| "learning_rate": 1.2398920483078939e-06, | |
| "loss": 0.0359, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 2.9324290379301683, | |
| "grad_norm": 1.0564415454864502, | |
| "learning_rate": 1.1897697909813058e-06, | |
| "loss": 0.0406, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.9525244913338358, | |
| "grad_norm": 2.999720811843872, | |
| "learning_rate": 1.140363395213629e-06, | |
| "loss": 0.0397, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 2.9726199447375032, | |
| "grad_norm": 0.8473829030990601, | |
| "learning_rate": 1.0916998548409449e-06, | |
| "loss": 0.0363, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.9927153981411707, | |
| "grad_norm": 0.6004119515419006, | |
| "learning_rate": 1.043805757830495e-06, | |
| "loss": 0.0365, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 747, | |
| "total_flos": 1.9266920499218227e+18, | |
| "train_loss": 0.04098171001696682, | |
| "train_runtime": 11305.9315, | |
| "train_samples_per_second": 4.225, | |
| "train_steps_per_second": 0.066 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 747, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9266920499218227e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |