Text Generation
Transformers
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use rzheng18/Qwen3_8B_Android_RAG_T3A_long with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rzheng18/Qwen3_8B_Android_RAG_T3A_long with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="rzheng18/Qwen3_8B_Android_RAG_T3A_long") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("rzheng18/Qwen3_8B_Android_RAG_T3A_long") model = AutoModelForCausalLM.from_pretrained("rzheng18/Qwen3_8B_Android_RAG_T3A_long", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use rzheng18/Qwen3_8B_Android_RAG_T3A_long with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "rzheng18/Qwen3_8B_Android_RAG_T3A_long" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rzheng18/Qwen3_8B_Android_RAG_T3A_long", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/rzheng18/Qwen3_8B_Android_RAG_T3A_long
- SGLang
How to use rzheng18/Qwen3_8B_Android_RAG_T3A_long 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 "rzheng18/Qwen3_8B_Android_RAG_T3A_long" \ --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": "rzheng18/Qwen3_8B_Android_RAG_T3A_long", "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 "rzheng18/Qwen3_8B_Android_RAG_T3A_long" \ --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": "rzheng18/Qwen3_8B_Android_RAG_T3A_long", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use rzheng18/Qwen3_8B_Android_RAG_T3A_long with Docker Model Runner:
docker model run hf.co/rzheng18/Qwen3_8B_Android_RAG_T3A_long
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 406, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0049261083743842365, | |
| "grad_norm": 44.8963182967931, | |
| "learning_rate": 2.439024390243903e-07, | |
| "loss": 2.7368, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009852216748768473, | |
| "grad_norm": 46.099422906910696, | |
| "learning_rate": 7.317073170731707e-07, | |
| "loss": 2.6542, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014778325123152709, | |
| "grad_norm": 37.72438176973727, | |
| "learning_rate": 1.2195121951219514e-06, | |
| "loss": 2.564, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019704433497536946, | |
| "grad_norm": 30.905649297924665, | |
| "learning_rate": 1.707317073170732e-06, | |
| "loss": 2.3725, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.024630541871921183, | |
| "grad_norm": 20.167136286002773, | |
| "learning_rate": 2.1951219512195125e-06, | |
| "loss": 2.2302, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029556650246305417, | |
| "grad_norm": 17.951667751127044, | |
| "learning_rate": 2.682926829268293e-06, | |
| "loss": 1.9045, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.034482758620689655, | |
| "grad_norm": 10.584616140095706, | |
| "learning_rate": 3.1707317073170736e-06, | |
| "loss": 1.391, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03940886699507389, | |
| "grad_norm": 8.757345877051158, | |
| "learning_rate": 3.6585365853658537e-06, | |
| "loss": 1.2174, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04433497536945813, | |
| "grad_norm": 6.146785745333218, | |
| "learning_rate": 4.146341463414634e-06, | |
| "loss": 1.068, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04926108374384237, | |
| "grad_norm": 4.867523307880614, | |
| "learning_rate": 4.634146341463416e-06, | |
| "loss": 0.911, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.054187192118226604, | |
| "grad_norm": 4.291449245234032, | |
| "learning_rate": 5.121951219512195e-06, | |
| "loss": 0.7771, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.059113300492610835, | |
| "grad_norm": 4.1822006229540545, | |
| "learning_rate": 5.609756097560977e-06, | |
| "loss": 0.6809, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06403940886699508, | |
| "grad_norm": 3.779065050501749, | |
| "learning_rate": 6.0975609756097564e-06, | |
| "loss": 0.6695, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06896551724137931, | |
| "grad_norm": 3.967079021897462, | |
| "learning_rate": 6.585365853658538e-06, | |
| "loss": 0.5092, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07389162561576355, | |
| "grad_norm": 3.567614905808945, | |
| "learning_rate": 7.0731707317073175e-06, | |
| "loss": 0.5443, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07881773399014778, | |
| "grad_norm": 3.1591426447329325, | |
| "learning_rate": 7.560975609756098e-06, | |
| "loss": 0.5302, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08374384236453201, | |
| "grad_norm": 2.9212653434319007, | |
| "learning_rate": 8.048780487804879e-06, | |
| "loss": 0.5566, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08866995073891626, | |
| "grad_norm": 2.955708095388518, | |
| "learning_rate": 8.536585365853658e-06, | |
| "loss": 0.5093, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09359605911330049, | |
| "grad_norm": 2.9023135018884854, | |
| "learning_rate": 9.02439024390244e-06, | |
| "loss": 0.5186, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09852216748768473, | |
| "grad_norm": 2.7975674817527976, | |
| "learning_rate": 9.51219512195122e-06, | |
| "loss": 0.4822, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10344827586206896, | |
| "grad_norm": 2.767875473585203, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4753, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10837438423645321, | |
| "grad_norm": 2.7943441568844105, | |
| "learning_rate": 9.999259196045581e-06, | |
| "loss": 0.471, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11330049261083744, | |
| "grad_norm": 2.840550133917755, | |
| "learning_rate": 9.997037003698524e-06, | |
| "loss": 0.4963, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11822660098522167, | |
| "grad_norm": 2.5222476466040353, | |
| "learning_rate": 9.993334081442382e-06, | |
| "loss": 0.4568, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12315270935960591, | |
| "grad_norm": 2.228693301443623, | |
| "learning_rate": 9.98815152653293e-06, | |
| "loss": 0.4265, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12807881773399016, | |
| "grad_norm": 2.027857924767705, | |
| "learning_rate": 9.98149087467304e-06, | |
| "loss": 0.4281, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.1330049261083744, | |
| "grad_norm": 2.6667021098732584, | |
| "learning_rate": 9.973354099557606e-06, | |
| "loss": 0.4485, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "grad_norm": 2.300682237213937, | |
| "learning_rate": 9.963743612288701e-06, | |
| "loss": 0.4556, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 2.276024376552029, | |
| "learning_rate": 9.952662260661115e-06, | |
| "loss": 0.433, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.1477832512315271, | |
| "grad_norm": 2.327596886044256, | |
| "learning_rate": 9.940113328318489e-06, | |
| "loss": 0.4636, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15270935960591134, | |
| "grad_norm": 2.323569750905077, | |
| "learning_rate": 9.926100533780304e-06, | |
| "loss": 0.44, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.15763546798029557, | |
| "grad_norm": 2.199619581535263, | |
| "learning_rate": 9.910628029340004e-06, | |
| "loss": 0.4067, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.1625615763546798, | |
| "grad_norm": 2.3325202778262497, | |
| "learning_rate": 9.893700399834577e-06, | |
| "loss": 0.434, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.16748768472906403, | |
| "grad_norm": 2.4365973357095236, | |
| "learning_rate": 9.875322661285976e-06, | |
| "loss": 0.4217, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.1724137931034483, | |
| "grad_norm": 2.1936256909743923, | |
| "learning_rate": 9.855500259414752e-06, | |
| "loss": 0.3997, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17733990147783252, | |
| "grad_norm": 2.261945626911862, | |
| "learning_rate": 9.834239068026388e-06, | |
| "loss": 0.3969, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.18226600985221675, | |
| "grad_norm": 2.334966897596132, | |
| "learning_rate": 9.811545387270745e-06, | |
| "loss": 0.443, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.18719211822660098, | |
| "grad_norm": 2.375705122789641, | |
| "learning_rate": 9.787425941775197e-06, | |
| "loss": 0.423, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.1921182266009852, | |
| "grad_norm": 2.322212257975809, | |
| "learning_rate": 9.761887878651987e-06, | |
| "loss": 0.4519, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.19704433497536947, | |
| "grad_norm": 2.294071256512972, | |
| "learning_rate": 9.734938765380377e-06, | |
| "loss": 0.4341, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2019704433497537, | |
| "grad_norm": 2.3462823337496, | |
| "learning_rate": 9.706586587564236e-06, | |
| "loss": 0.4269, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.20689655172413793, | |
| "grad_norm": 2.0614365702056556, | |
| "learning_rate": 9.676839746565743e-06, | |
| "loss": 0.4081, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.21182266009852216, | |
| "grad_norm": 2.1324298184869797, | |
| "learning_rate": 9.645707057015872e-06, | |
| "loss": 0.392, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.21674876847290642, | |
| "grad_norm": 1.9235935662736439, | |
| "learning_rate": 9.613197744202437e-06, | |
| "loss": 0.3837, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.22167487684729065, | |
| "grad_norm": 2.256676114867014, | |
| "learning_rate": 9.579321441336436e-06, | |
| "loss": 0.3853, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22660098522167488, | |
| "grad_norm": 1.8780989965433945, | |
| "learning_rate": 9.544088186697515e-06, | |
| "loss": 0.3783, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.2315270935960591, | |
| "grad_norm": 2.2896147832428984, | |
| "learning_rate": 9.507508420659422e-06, | |
| "loss": 0.3838, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.23645320197044334, | |
| "grad_norm": 2.081385045857516, | |
| "learning_rate": 9.469592982596286e-06, | |
| "loss": 0.3865, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.2413793103448276, | |
| "grad_norm": 4.753269011190599, | |
| "learning_rate": 9.430353107670691e-06, | |
| "loss": 0.4101, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.24630541871921183, | |
| "grad_norm": 1.941290823137089, | |
| "learning_rate": 9.389800423504442e-06, | |
| "loss": 0.3886, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2512315270935961, | |
| "grad_norm": 2.0138324422328036, | |
| "learning_rate": 9.347946946733055e-06, | |
| "loss": 0.3481, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.2561576354679803, | |
| "grad_norm": 1.9789776247147852, | |
| "learning_rate": 9.304805079444972e-06, | |
| "loss": 0.3974, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.26108374384236455, | |
| "grad_norm": 1.7037873292960362, | |
| "learning_rate": 9.260387605506547e-06, | |
| "loss": 0.3116, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.2660098522167488, | |
| "grad_norm": 1.951407100374748, | |
| "learning_rate": 9.214707686773915e-06, | |
| "loss": 0.3658, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.270935960591133, | |
| "grad_norm": 2.1438613631812853, | |
| "learning_rate": 9.167778859192851e-06, | |
| "loss": 0.3759, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 2.324445803574347, | |
| "learning_rate": 9.119615028787771e-06, | |
| "loss": 0.3797, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.28078817733990147, | |
| "grad_norm": 2.2349031999805367, | |
| "learning_rate": 9.07023046754109e-06, | |
| "loss": 0.4004, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 2.124648784241559, | |
| "learning_rate": 9.019639809164107e-06, | |
| "loss": 0.3938, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.29064039408866993, | |
| "grad_norm": 1.8592057932403692, | |
| "learning_rate": 8.967858044760737e-06, | |
| "loss": 0.4124, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.2955665024630542, | |
| "grad_norm": 2.0590472319329884, | |
| "learning_rate": 8.914900518385314e-06, | |
| "loss": 0.3819, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.30049261083743845, | |
| "grad_norm": 2.196495117430516, | |
| "learning_rate": 8.860782922495821e-06, | |
| "loss": 0.3816, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.3054187192118227, | |
| "grad_norm": 2.2173246255523864, | |
| "learning_rate": 8.805521293303874e-06, | |
| "loss": 0.4009, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.3103448275862069, | |
| "grad_norm": 1.9077749030279627, | |
| "learning_rate": 8.749132006022843e-06, | |
| "loss": 0.3883, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.31527093596059114, | |
| "grad_norm": 2.187382570547577, | |
| "learning_rate": 8.691631770015534e-06, | |
| "loss": 0.4243, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.32019704433497537, | |
| "grad_norm": 2.359836837581651, | |
| "learning_rate": 8.633037623842828e-06, | |
| "loss": 0.4029, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3251231527093596, | |
| "grad_norm": 1.9766864796512795, | |
| "learning_rate": 8.573366930214807e-06, | |
| "loss": 0.359, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.33004926108374383, | |
| "grad_norm": 1.87128068237922, | |
| "learning_rate": 8.512637370845785e-06, | |
| "loss": 0.3682, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.33497536945812806, | |
| "grad_norm": 1.7512659209304051, | |
| "learning_rate": 8.45086694121486e-06, | |
| "loss": 0.343, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.3399014778325123, | |
| "grad_norm": 1.8687173959305177, | |
| "learning_rate": 8.388073945233446e-06, | |
| "loss": 0.3799, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 2.2552072791932325, | |
| "learning_rate": 8.324276989821433e-06, | |
| "loss": 0.3571, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3497536945812808, | |
| "grad_norm": 2.1968732450513326, | |
| "learning_rate": 8.259494979393563e-06, | |
| "loss": 0.3785, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.35467980295566504, | |
| "grad_norm": 2.0370499043464902, | |
| "learning_rate": 8.193747110257638e-06, | |
| "loss": 0.3839, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.35960591133004927, | |
| "grad_norm": 2.0699862544297005, | |
| "learning_rate": 8.127052864926233e-06, | |
| "loss": 0.4082, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.3645320197044335, | |
| "grad_norm": 2.116660725996167, | |
| "learning_rate": 8.059432006343623e-06, | |
| "loss": 0.329, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.3694581280788177, | |
| "grad_norm": 2.4052693290135156, | |
| "learning_rate": 7.990904572029584e-06, | |
| "loss": 0.3925, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.37438423645320196, | |
| "grad_norm": 1.851663759806883, | |
| "learning_rate": 7.921490868141843e-06, | |
| "loss": 0.3627, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.3793103448275862, | |
| "grad_norm": 1.8406848182077862, | |
| "learning_rate": 7.851211463458936e-06, | |
| "loss": 0.3879, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.3842364532019704, | |
| "grad_norm": 1.8443757372821195, | |
| "learning_rate": 7.780087183285224e-06, | |
| "loss": 0.359, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.3891625615763547, | |
| "grad_norm": 2.1204872904029726, | |
| "learning_rate": 7.708139103279908e-06, | |
| "loss": 0.3813, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.39408866995073893, | |
| "grad_norm": 1.6914595313144445, | |
| "learning_rate": 7.635388543211862e-06, | |
| "loss": 0.3073, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.39901477832512317, | |
| "grad_norm": 1.695198000675222, | |
| "learning_rate": 7.56185706064212e-06, | |
| "loss": 0.3221, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.4039408866995074, | |
| "grad_norm": 2.133553608073776, | |
| "learning_rate": 7.487566444535904e-06, | |
| "loss": 0.4021, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.4088669950738916, | |
| "grad_norm": 1.8380222153600023, | |
| "learning_rate": 7.412538708806093e-06, | |
| "loss": 0.323, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.41379310344827586, | |
| "grad_norm": 1.877505662143193, | |
| "learning_rate": 7.336796085790012e-06, | |
| "loss": 0.3795, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.4187192118226601, | |
| "grad_norm": 1.7822157427026055, | |
| "learning_rate": 7.260361019661523e-06, | |
| "loss": 0.3345, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4236453201970443, | |
| "grad_norm": 1.9658143203094556, | |
| "learning_rate": 7.183256159780321e-06, | |
| "loss": 0.3913, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 1.6493741345874358, | |
| "learning_rate": 7.105504353980448e-06, | |
| "loss": 0.3796, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.43349753694581283, | |
| "grad_norm": 2.0145568637517037, | |
| "learning_rate": 7.027128641799987e-06, | |
| "loss": 0.312, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.43842364532019706, | |
| "grad_norm": 1.8397794869453532, | |
| "learning_rate": 6.948152247653941e-06, | |
| "loss": 0.352, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.4433497536945813, | |
| "grad_norm": 2.232391075413934, | |
| "learning_rate": 6.868598573952345e-06, | |
| "loss": 0.4125, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4482758620689655, | |
| "grad_norm": 1.7942665055078924, | |
| "learning_rate": 6.788491194165629e-06, | |
| "loss": 0.3322, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.45320197044334976, | |
| "grad_norm": 1.9440566865171862, | |
| "learning_rate": 6.707853845839278e-06, | |
| "loss": 0.3957, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.458128078817734, | |
| "grad_norm": 1.7676017770997519, | |
| "learning_rate": 6.626710423559902e-06, | |
| "loss": 0.3803, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.4630541871921182, | |
| "grad_norm": 2.096439602794133, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.3583, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.46798029556650245, | |
| "grad_norm": 1.9130298649415463, | |
| "learning_rate": 6.463001678166744e-06, | |
| "loss": 0.3362, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4729064039408867, | |
| "grad_norm": 2.0426443678704165, | |
| "learning_rate": 6.380484865487346e-06, | |
| "loss": 0.4137, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.47783251231527096, | |
| "grad_norm": 2.1667979521464016, | |
| "learning_rate": 6.297558985348999e-06, | |
| "loss": 0.3572, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.4827586206896552, | |
| "grad_norm": 1.8442582167893449, | |
| "learning_rate": 6.2142486104796795e-06, | |
| "loss": 0.3572, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.4876847290640394, | |
| "grad_norm": 1.776091134770769, | |
| "learning_rate": 6.130578427541441e-06, | |
| "loss": 0.3407, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.49261083743842365, | |
| "grad_norm": 1.8814727438834467, | |
| "learning_rate": 6.046573229815244e-06, | |
| "loss": 0.3783, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4975369458128079, | |
| "grad_norm": 1.810594835363692, | |
| "learning_rate": 5.96225790985415e-06, | |
| "loss": 0.357, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.5024630541871922, | |
| "grad_norm": 1.707212513496614, | |
| "learning_rate": 5.877657452107142e-06, | |
| "loss": 0.3411, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.5073891625615764, | |
| "grad_norm": 1.9493727830455976, | |
| "learning_rate": 5.792796925515673e-06, | |
| "loss": 0.379, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.5123152709359606, | |
| "grad_norm": 1.7158219522029339, | |
| "learning_rate": 5.707701476085217e-06, | |
| "loss": 0.3837, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.5172413793103449, | |
| "grad_norm": 1.6415086987891507, | |
| "learning_rate": 5.622396319433947e-06, | |
| "loss": 0.3445, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5221674876847291, | |
| "grad_norm": 1.7016455148083767, | |
| "learning_rate": 5.536906733320816e-06, | |
| "loss": 0.3639, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.5270935960591133, | |
| "grad_norm": 1.8345273292692599, | |
| "learning_rate": 5.451258050155206e-06, | |
| "loss": 0.3517, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.5320197044334976, | |
| "grad_norm": 2.0637240565451593, | |
| "learning_rate": 5.365475649490388e-06, | |
| "loss": 0.3494, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.5369458128078818, | |
| "grad_norm": 1.8737621809932734, | |
| "learning_rate": 5.279584950503017e-06, | |
| "loss": 0.3747, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.541871921182266, | |
| "grad_norm": 1.8408707483852216, | |
| "learning_rate": 5.193611404460873e-06, | |
| "loss": 0.3509, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5467980295566502, | |
| "grad_norm": 1.7294537624623878, | |
| "learning_rate": 5.107580487181112e-06, | |
| "loss": 0.3524, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": 1.6924139244897671, | |
| "learning_rate": 5.0215176914812215e-06, | |
| "loss": 0.3242, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.5566502463054187, | |
| "grad_norm": 1.8703453876763778, | |
| "learning_rate": 4.935448519624955e-06, | |
| "loss": 0.3765, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.5615763546798029, | |
| "grad_norm": 1.859694701181906, | |
| "learning_rate": 4.84939847576546e-06, | |
| "loss": 0.3357, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.5665024630541872, | |
| "grad_norm": 1.8276186736007791, | |
| "learning_rate": 4.763393058387841e-06, | |
| "loss": 0.3601, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 2.1365192167376166, | |
| "learning_rate": 4.6774577527534195e-06, | |
| "loss": 0.3703, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.5763546798029556, | |
| "grad_norm": 1.703940000641382, | |
| "learning_rate": 4.591618023347888e-06, | |
| "loss": 0.3424, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.5812807881773399, | |
| "grad_norm": 1.957087035322277, | |
| "learning_rate": 4.505899306335643e-06, | |
| "loss": 0.3734, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.5862068965517241, | |
| "grad_norm": 1.7316486849924828, | |
| "learning_rate": 4.420327002022498e-06, | |
| "loss": 0.3379, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.5911330049261084, | |
| "grad_norm": 1.8263162323751754, | |
| "learning_rate": 4.334926467329021e-06, | |
| "loss": 0.3375, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5960591133004927, | |
| "grad_norm": 1.7437801971776299, | |
| "learning_rate": 4.249723008276737e-06, | |
| "loss": 0.3434, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.6009852216748769, | |
| "grad_norm": 1.7503579720856823, | |
| "learning_rate": 4.164741872489405e-06, | |
| "loss": 0.3447, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.6059113300492611, | |
| "grad_norm": 1.762767146058859, | |
| "learning_rate": 4.0800082417116e-06, | |
| "loss": 0.3284, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.6108374384236454, | |
| "grad_norm": 1.8779288840963184, | |
| "learning_rate": 3.995547224346824e-06, | |
| "loss": 0.3583, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.6157635467980296, | |
| "grad_norm": 1.6488701546072537, | |
| "learning_rate": 3.9113838480173415e-06, | |
| "loss": 0.2981, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6206896551724138, | |
| "grad_norm": 1.8104146259621938, | |
| "learning_rate": 3.827543052147952e-06, | |
| "loss": 0.3383, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.625615763546798, | |
| "grad_norm": 1.7227029120034105, | |
| "learning_rate": 3.7440496805759048e-06, | |
| "loss": 0.3096, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.6305418719211823, | |
| "grad_norm": 1.8587300648176028, | |
| "learning_rate": 3.6609284741891295e-06, | |
| "loss": 0.3388, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.6354679802955665, | |
| "grad_norm": 1.9060120183010216, | |
| "learning_rate": 3.578204063594982e-06, | |
| "loss": 0.3474, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.6403940886699507, | |
| "grad_norm": 1.7415388075997358, | |
| "learning_rate": 3.495900961821662e-06, | |
| "loss": 0.3422, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.645320197044335, | |
| "grad_norm": 1.6498328724255078, | |
| "learning_rate": 3.4140435570544708e-06, | |
| "loss": 0.3157, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.6502463054187192, | |
| "grad_norm": 1.8712030560240966, | |
| "learning_rate": 3.3326561054090663e-06, | |
| "loss": 0.3362, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.6551724137931034, | |
| "grad_norm": 1.901603601605235, | |
| "learning_rate": 3.2517627237438583e-06, | |
| "loss": 0.3405, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.6600985221674877, | |
| "grad_norm": 1.8721451562026015, | |
| "learning_rate": 3.1713873825136543e-06, | |
| "loss": 0.3343, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.6650246305418719, | |
| "grad_norm": 1.8287062237927403, | |
| "learning_rate": 3.0915538986667056e-06, | |
| "loss": 0.3658, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6699507389162561, | |
| "grad_norm": 1.9605103250424178, | |
| "learning_rate": 3.0122859285872214e-06, | |
| "loss": 0.3433, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.6748768472906403, | |
| "grad_norm": 1.851305784616147, | |
| "learning_rate": 2.933606961085479e-06, | |
| "loss": 0.393, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.6798029556650246, | |
| "grad_norm": 1.7172768426115934, | |
| "learning_rate": 2.8555403104375826e-06, | |
| "loss": 0.322, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.6847290640394089, | |
| "grad_norm": 1.7987012083048666, | |
| "learning_rate": 2.7781091094769342e-06, | |
| "loss": 0.3272, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "grad_norm": 1.8515924782201856, | |
| "learning_rate": 2.70133630273948e-06, | |
| "loss": 0.3291, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6945812807881774, | |
| "grad_norm": 1.6306433948913968, | |
| "learning_rate": 2.6252446396647503e-06, | |
| "loss": 0.3448, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.6995073891625616, | |
| "grad_norm": 2.0809019934786392, | |
| "learning_rate": 2.5498566678547045e-06, | |
| "loss": 0.384, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.7044334975369458, | |
| "grad_norm": 1.5943573601880225, | |
| "learning_rate": 2.475194726392398e-06, | |
| "loss": 0.3166, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.7093596059113301, | |
| "grad_norm": 1.6246550529785988, | |
| "learning_rate": 2.401280939222423e-06, | |
| "loss": 0.3429, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 2.189080194676372, | |
| "learning_rate": 2.3281372085951072e-06, | |
| "loss": 0.3915, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7192118226600985, | |
| "grad_norm": 1.757426014511556, | |
| "learning_rate": 2.2557852085764053e-06, | |
| "loss": 0.3184, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.7241379310344828, | |
| "grad_norm": 1.6427418777994036, | |
| "learning_rate": 2.184246378625407e-06, | |
| "loss": 0.3209, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.729064039408867, | |
| "grad_norm": 1.6531176927275917, | |
| "learning_rate": 2.1135419172413642e-06, | |
| "loss": 0.3291, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.7339901477832512, | |
| "grad_norm": 1.96453811009946, | |
| "learning_rate": 2.0436927756821095e-06, | |
| "loss": 0.3654, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.7389162561576355, | |
| "grad_norm": 1.7982136556444481, | |
| "learning_rate": 1.974719651755756e-06, | |
| "loss": 0.3472, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7438423645320197, | |
| "grad_norm": 1.89976119570655, | |
| "learning_rate": 1.9066429836874844e-06, | |
| "loss": 0.3413, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.7487684729064039, | |
| "grad_norm": 2.012364568957732, | |
| "learning_rate": 1.8394829440632567e-06, | |
| "loss": 0.3895, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.7536945812807881, | |
| "grad_norm": 1.8310127989905465, | |
| "learning_rate": 1.7732594338522496e-06, | |
| "loss": 0.3736, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.7586206896551724, | |
| "grad_norm": 1.5809916612129833, | |
| "learning_rate": 1.7079920765097563e-06, | |
| "loss": 0.318, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.7635467980295566, | |
| "grad_norm": 1.7067656827305038, | |
| "learning_rate": 1.6437002121623436e-06, | |
| "loss": 0.341, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7684729064039408, | |
| "grad_norm": 1.6331008773821312, | |
| "learning_rate": 1.5804028918769488e-06, | |
| "loss": 0.3134, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.7733990147783252, | |
| "grad_norm": 1.6904384406255728, | |
| "learning_rate": 1.5181188720156392e-06, | |
| "loss": 0.3057, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.7783251231527094, | |
| "grad_norm": 1.8039885623765064, | |
| "learning_rate": 1.4568666086777021e-06, | |
| "loss": 0.348, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.7832512315270936, | |
| "grad_norm": 1.880132868839055, | |
| "learning_rate": 1.3966642522306956e-06, | |
| "loss": 0.3371, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.7881773399014779, | |
| "grad_norm": 1.8545596828098443, | |
| "learning_rate": 1.3375296419321072e-06, | |
| "loss": 0.3624, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7931034482758621, | |
| "grad_norm": 1.7242914287045228, | |
| "learning_rate": 1.2794803006431984e-06, | |
| "loss": 0.2858, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.7980295566502463, | |
| "grad_norm": 1.9260680738540965, | |
| "learning_rate": 1.2225334296365988e-06, | |
| "loss": 0.3483, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.8029556650246306, | |
| "grad_norm": 1.8070609954281276, | |
| "learning_rate": 1.1667059034992051e-06, | |
| "loss": 0.3114, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.8078817733990148, | |
| "grad_norm": 1.7681175716169353, | |
| "learning_rate": 1.1120142651318666e-06, | |
| "loss": 0.3101, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.812807881773399, | |
| "grad_norm": 1.680096409224379, | |
| "learning_rate": 1.058474720847374e-06, | |
| "loss": 0.3118, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8177339901477833, | |
| "grad_norm": 1.7473080488187867, | |
| "learning_rate": 1.0061031355681766e-06, | |
| "loss": 0.3478, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.8226600985221675, | |
| "grad_norm": 1.6297901340514978, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 0.3029, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.8275862068965517, | |
| "grad_norm": 1.5025171606930632, | |
| "learning_rate": 9.049255666596013e-07, | |
| "loss": 0.339, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.8325123152709359, | |
| "grad_norm": 1.9444387046313547, | |
| "learning_rate": 8.561495641274825e-07, | |
| "loss": 0.3206, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.8374384236453202, | |
| "grad_norm": 1.6912663794104235, | |
| "learning_rate": 8.086014739111298e-07, | |
| "loss": 0.3231, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8423645320197044, | |
| "grad_norm": 1.544677734443626, | |
| "learning_rate": 7.622953855358456e-07, | |
| "loss": 0.3208, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.8472906403940886, | |
| "grad_norm": 1.714744670154245, | |
| "learning_rate": 7.172450204949822e-07, | |
| "loss": 0.3431, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.8522167487684729, | |
| "grad_norm": 1.7315257351030213, | |
| "learning_rate": 6.734637281839701e-07, | |
| "loss": 0.3192, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 1.9370755101393182, | |
| "learning_rate": 6.30964481944597e-07, | |
| "loss": 0.3282, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.8620689655172413, | |
| "grad_norm": 1.7909794798811995, | |
| "learning_rate": 5.897598752207328e-07, | |
| "loss": 0.2913, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8669950738916257, | |
| "grad_norm": 1.8593927899874703, | |
| "learning_rate": 5.498621178266167e-07, | |
| "loss": 0.3322, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.8719211822660099, | |
| "grad_norm": 1.7527860166701459, | |
| "learning_rate": 5.112830323288315e-07, | |
| "loss": 0.3374, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.8768472906403941, | |
| "grad_norm": 1.6872323575327233, | |
| "learning_rate": 4.74034050543013e-07, | |
| "loss": 0.329, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.8817733990147784, | |
| "grad_norm": 1.6811841955249374, | |
| "learning_rate": 4.3812621014636405e-07, | |
| "loss": 0.3113, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.8866995073891626, | |
| "grad_norm": 1.81640314795809, | |
| "learning_rate": 4.0357015140694843e-07, | |
| "loss": 0.3294, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8916256157635468, | |
| "grad_norm": 1.7159301839517571, | |
| "learning_rate": 3.70376114030751e-07, | |
| "loss": 0.2838, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.896551724137931, | |
| "grad_norm": 1.7134959910640768, | |
| "learning_rate": 3.385539341274335e-07, | |
| "loss": 0.3564, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.9014778325123153, | |
| "grad_norm": 1.8422465642095602, | |
| "learning_rate": 3.0811304129567955e-07, | |
| "loss": 0.3368, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.9064039408866995, | |
| "grad_norm": 1.6033644817417168, | |
| "learning_rate": 2.790624558290034e-07, | |
| "loss": 0.2802, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.9113300492610837, | |
| "grad_norm": 1.9181368150312297, | |
| "learning_rate": 2.5141078604284107e-07, | |
| "loss": 0.3319, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.916256157635468, | |
| "grad_norm": 1.9193135461415896, | |
| "learning_rate": 2.2516622572372416e-07, | |
| "loss": 0.3559, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.9211822660098522, | |
| "grad_norm": 1.8940678146420356, | |
| "learning_rate": 2.003365517012773e-07, | |
| "loss": 0.3467, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.9261083743842364, | |
| "grad_norm": 1.640578933728653, | |
| "learning_rate": 1.7692912154378295e-07, | |
| "loss": 0.3313, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.9310344827586207, | |
| "grad_norm": 1.6485929089101314, | |
| "learning_rate": 1.549508713779696e-07, | |
| "loss": 0.3175, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.9359605911330049, | |
| "grad_norm": 1.730275403219221, | |
| "learning_rate": 1.3440831383369045e-07, | |
| "loss": 0.3866, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9408866995073891, | |
| "grad_norm": 1.9075041198984353, | |
| "learning_rate": 1.1530753611409151e-07, | |
| "loss": 0.3819, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.9458128078817734, | |
| "grad_norm": 1.7099459563394726, | |
| "learning_rate": 9.765419819183996e-08, | |
| "loss": 0.3534, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.9507389162561576, | |
| "grad_norm": 1.6910194312648175, | |
| "learning_rate": 8.145353113195143e-08, | |
| "loss": 0.3289, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.9556650246305419, | |
| "grad_norm": 1.7951039469035281, | |
| "learning_rate": 6.67103355417148e-08, | |
| "loss": 0.3622, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.9605911330049262, | |
| "grad_norm": 1.8373342900874141, | |
| "learning_rate": 5.342898014816855e-08, | |
| "loss": 0.3372, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9655172413793104, | |
| "grad_norm": 1.6079339251044082, | |
| "learning_rate": 4.1613400503550114e-08, | |
| "loss": 0.2975, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.9704433497536946, | |
| "grad_norm": 1.6452433665425827, | |
| "learning_rate": 3.126709781910986e-08, | |
| "loss": 0.3424, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.9753694581280788, | |
| "grad_norm": 1.8265195165729584, | |
| "learning_rate": 2.2393137927623766e-08, | |
| "loss": 0.3294, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.9802955665024631, | |
| "grad_norm": 1.765524747384538, | |
| "learning_rate": 1.4994150374924576e-08, | |
| "loss": 0.3569, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.9852216748768473, | |
| "grad_norm": 1.6837166678617568, | |
| "learning_rate": 9.072327640706758e-09, | |
| "loss": 0.3276, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9901477832512315, | |
| "grad_norm": 1.6616062126615554, | |
| "learning_rate": 4.629424488850065e-09, | |
| "loss": 0.2919, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.9950738916256158, | |
| "grad_norm": 1.6453259760008279, | |
| "learning_rate": 1.666757447443823e-09, | |
| "loss": 0.2974, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.6811794231076687, | |
| "learning_rate": 1.8520441867231342e-10, | |
| "loss": 0.3207, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 406, | |
| "total_flos": 64023949017088.0, | |
| "train_loss": 0.4480156045535515, | |
| "train_runtime": 8935.3013, | |
| "train_samples_per_second": 0.727, | |
| "train_steps_per_second": 0.045 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 406, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 64023949017088.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |