Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use AgPerry/Qwen2.5-Coder-7B-Instruct-num05-accumulate_16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AgPerry/Qwen2.5-Coder-7B-Instruct-num05-accumulate_16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AgPerry/Qwen2.5-Coder-7B-Instruct-num05-accumulate_16") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("AgPerry/Qwen2.5-Coder-7B-Instruct-num05-accumulate_16") model = AutoModelForCausalLM.from_pretrained("AgPerry/Qwen2.5-Coder-7B-Instruct-num05-accumulate_16") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use AgPerry/Qwen2.5-Coder-7B-Instruct-num05-accumulate_16 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AgPerry/Qwen2.5-Coder-7B-Instruct-num05-accumulate_16" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AgPerry/Qwen2.5-Coder-7B-Instruct-num05-accumulate_16", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/AgPerry/Qwen2.5-Coder-7B-Instruct-num05-accumulate_16
- SGLang
How to use AgPerry/Qwen2.5-Coder-7B-Instruct-num05-accumulate_16 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 "AgPerry/Qwen2.5-Coder-7B-Instruct-num05-accumulate_16" \ --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": "AgPerry/Qwen2.5-Coder-7B-Instruct-num05-accumulate_16", "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 "AgPerry/Qwen2.5-Coder-7B-Instruct-num05-accumulate_16" \ --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": "AgPerry/Qwen2.5-Coder-7B-Instruct-num05-accumulate_16", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use AgPerry/Qwen2.5-Coder-7B-Instruct-num05-accumulate_16 with Docker Model Runner:
docker model run hf.co/AgPerry/Qwen2.5-Coder-7B-Instruct-num05-accumulate_16
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2751, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036357025995273585, | |
| "grad_norm": 2.5542567038381727, | |
| "learning_rate": 3.2608695652173915e-07, | |
| "loss": 0.8192, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007271405199054717, | |
| "grad_norm": 1.6840845127706614, | |
| "learning_rate": 6.884057971014494e-07, | |
| "loss": 0.7993, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010907107798582076, | |
| "grad_norm": 1.1024644310656107, | |
| "learning_rate": 1.0507246376811594e-06, | |
| "loss": 0.7578, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014542810398109434, | |
| "grad_norm": 0.8391202445675546, | |
| "learning_rate": 1.4130434782608697e-06, | |
| "loss": 0.703, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018178512997636793, | |
| "grad_norm": 0.6387875979570747, | |
| "learning_rate": 1.77536231884058e-06, | |
| "loss": 0.6679, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.021814215597164153, | |
| "grad_norm": 0.5293560692158165, | |
| "learning_rate": 2.13768115942029e-06, | |
| "loss": 0.6262, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.025449918196691512, | |
| "grad_norm": 0.4769703141630787, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.6165, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.029085620796218868, | |
| "grad_norm": 0.49426470609436557, | |
| "learning_rate": 2.8623188405797105e-06, | |
| "loss": 0.6095, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03272132339574623, | |
| "grad_norm": 0.47809567840037087, | |
| "learning_rate": 3.2246376811594203e-06, | |
| "loss": 0.5983, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03635702599527359, | |
| "grad_norm": 0.5072826426104683, | |
| "learning_rate": 3.5869565217391305e-06, | |
| "loss": 0.5848, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03999272859480094, | |
| "grad_norm": 0.4572327452452194, | |
| "learning_rate": 3.949275362318841e-06, | |
| "loss": 0.5802, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.043628431194328306, | |
| "grad_norm": 0.4810771922067728, | |
| "learning_rate": 4.3115942028985515e-06, | |
| "loss": 0.5685, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.04726413379385566, | |
| "grad_norm": 0.4580229624134198, | |
| "learning_rate": 4.673913043478261e-06, | |
| "loss": 0.5587, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.050899836393383024, | |
| "grad_norm": 0.46576040527729806, | |
| "learning_rate": 5.036231884057972e-06, | |
| "loss": 0.5605, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.05453553899291038, | |
| "grad_norm": 0.5348307609583014, | |
| "learning_rate": 5.398550724637681e-06, | |
| "loss": 0.559, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.058171241592437736, | |
| "grad_norm": 0.4787369411427498, | |
| "learning_rate": 5.760869565217392e-06, | |
| "loss": 0.5554, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0618069441919651, | |
| "grad_norm": 0.5050963339800372, | |
| "learning_rate": 6.123188405797102e-06, | |
| "loss": 0.5516, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.06544264679149246, | |
| "grad_norm": 0.5091817663303461, | |
| "learning_rate": 6.485507246376812e-06, | |
| "loss": 0.5456, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.06907834939101981, | |
| "grad_norm": 0.4952416204700452, | |
| "learning_rate": 6.847826086956523e-06, | |
| "loss": 0.5412, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.07271405199054717, | |
| "grad_norm": 0.5383390392600178, | |
| "learning_rate": 7.210144927536233e-06, | |
| "loss": 0.5473, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07634975459007454, | |
| "grad_norm": 0.5165675810240311, | |
| "learning_rate": 7.572463768115943e-06, | |
| "loss": 0.5336, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.07998545718960189, | |
| "grad_norm": 0.4919677447858993, | |
| "learning_rate": 7.934782608695653e-06, | |
| "loss": 0.5397, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.08362115978912925, | |
| "grad_norm": 0.5329864256931945, | |
| "learning_rate": 8.297101449275364e-06, | |
| "loss": 0.5331, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.08725686238865661, | |
| "grad_norm": 0.5199161519458958, | |
| "learning_rate": 8.659420289855073e-06, | |
| "loss": 0.5325, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.09089256498818396, | |
| "grad_norm": 0.5072496956016589, | |
| "learning_rate": 9.021739130434784e-06, | |
| "loss": 0.527, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.09452826758771132, | |
| "grad_norm": 0.502918920573189, | |
| "learning_rate": 9.384057971014492e-06, | |
| "loss": 0.5193, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.09816397018723869, | |
| "grad_norm": 0.6518040786610404, | |
| "learning_rate": 9.746376811594203e-06, | |
| "loss": 0.5371, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.10179967278676605, | |
| "grad_norm": 0.49757098182482185, | |
| "learning_rate": 9.999963748053354e-06, | |
| "loss": 0.5246, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.1054353753862934, | |
| "grad_norm": 0.5326361139485778, | |
| "learning_rate": 9.999319283625641e-06, | |
| "loss": 0.5318, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.10907107798582076, | |
| "grad_norm": 0.5258718780090955, | |
| "learning_rate": 9.997869339902043e-06, | |
| "loss": 0.5311, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.11270678058534812, | |
| "grad_norm": 0.5200368968513526, | |
| "learning_rate": 9.995614150494293e-06, | |
| "loss": 0.5202, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.11634248318487547, | |
| "grad_norm": 0.5121978872821166, | |
| "learning_rate": 9.992554078753534e-06, | |
| "loss": 0.5157, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.11997818578440284, | |
| "grad_norm": 0.503153118808014, | |
| "learning_rate": 9.988689617711777e-06, | |
| "loss": 0.514, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.1236138883839302, | |
| "grad_norm": 0.6549012255626758, | |
| "learning_rate": 9.984021390002458e-06, | |
| "loss": 0.5192, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.12724959098345756, | |
| "grad_norm": 0.5311045896699705, | |
| "learning_rate": 9.978550147760133e-06, | |
| "loss": 0.5241, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.13088529358298492, | |
| "grad_norm": 0.5686109082908248, | |
| "learning_rate": 9.972276772499281e-06, | |
| "loss": 0.509, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.13452099618251226, | |
| "grad_norm": 0.5234640596564708, | |
| "learning_rate": 9.965202274972288e-06, | |
| "loss": 0.5181, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.13815669878203962, | |
| "grad_norm": 0.5022886513572414, | |
| "learning_rate": 9.957327795006589e-06, | |
| "loss": 0.5068, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.14179240138156698, | |
| "grad_norm": 0.7845925493558181, | |
| "learning_rate": 9.94865460132103e-06, | |
| "loss": 0.5108, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.14542810398109435, | |
| "grad_norm": 0.5076808100322107, | |
| "learning_rate": 9.939184091321445e-06, | |
| "loss": 0.5259, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1490638065806217, | |
| "grad_norm": 0.4994009407139292, | |
| "learning_rate": 9.928917790875519e-06, | |
| "loss": 0.5043, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.15269950918014907, | |
| "grad_norm": 0.5657922372896571, | |
| "learning_rate": 9.91785735406693e-06, | |
| "loss": 0.5124, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.15633521177967644, | |
| "grad_norm": 0.5062077867796483, | |
| "learning_rate": 9.906004562928865e-06, | |
| "loss": 0.5083, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.15997091437920377, | |
| "grad_norm": 0.5085173829463484, | |
| "learning_rate": 9.893361327156887e-06, | |
| "loss": 0.5037, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.16360661697873113, | |
| "grad_norm": 0.5474641284130445, | |
| "learning_rate": 9.879929683801254e-06, | |
| "loss": 0.5145, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.1672423195782585, | |
| "grad_norm": 0.5735480776623142, | |
| "learning_rate": 9.86571179693872e-06, | |
| "loss": 0.5061, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.17087802217778586, | |
| "grad_norm": 0.5742302198308427, | |
| "learning_rate": 9.850709957323855e-06, | |
| "loss": 0.5154, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.17451372477731322, | |
| "grad_norm": 0.54806841942205, | |
| "learning_rate": 9.834926582019968e-06, | |
| "loss": 0.5058, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.17814942737684059, | |
| "grad_norm": 0.5944657562188465, | |
| "learning_rate": 9.81836421400967e-06, | |
| "loss": 0.5061, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.18178512997636792, | |
| "grad_norm": 0.5126067457263382, | |
| "learning_rate": 9.80102552178517e-06, | |
| "loss": 0.5078, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18542083257589528, | |
| "grad_norm": 0.6052321595104998, | |
| "learning_rate": 9.782913298918311e-06, | |
| "loss": 0.5067, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.18905653517542265, | |
| "grad_norm": 0.531743888377215, | |
| "learning_rate": 9.76403046361049e-06, | |
| "loss": 0.5025, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.19269223777495, | |
| "grad_norm": 0.5395822315917106, | |
| "learning_rate": 9.744380058222483e-06, | |
| "loss": 0.5037, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.19632794037447737, | |
| "grad_norm": 0.5411082503028966, | |
| "learning_rate": 9.723965248784264e-06, | |
| "loss": 0.501, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.19996364297400473, | |
| "grad_norm": 0.5538762305387136, | |
| "learning_rate": 9.702789324484898e-06, | |
| "loss": 0.5069, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.2035993455735321, | |
| "grad_norm": 0.5570421552319754, | |
| "learning_rate": 9.680855697142601e-06, | |
| "loss": 0.4944, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.20723504817305943, | |
| "grad_norm": 2.3792790728403377, | |
| "learning_rate": 9.658167900655032e-06, | |
| "loss": 0.5023, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.2108707507725868, | |
| "grad_norm": 0.5019520057613756, | |
| "learning_rate": 9.634729590429917e-06, | |
| "loss": 0.5032, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.21450645337211416, | |
| "grad_norm": 0.5180606840693017, | |
| "learning_rate": 9.610544542796101e-06, | |
| "loss": 0.4949, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.21814215597164152, | |
| "grad_norm": 0.5565436679077056, | |
| "learning_rate": 9.585616654395113e-06, | |
| "loss": 0.5059, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.22177785857116888, | |
| "grad_norm": 0.5254764402634797, | |
| "learning_rate": 9.559949941553351e-06, | |
| "loss": 0.4919, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.22541356117069625, | |
| "grad_norm": 0.57400898518425, | |
| "learning_rate": 9.533548539634971e-06, | |
| "loss": 0.4979, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.22904926377022358, | |
| "grad_norm": 0.5336519460399675, | |
| "learning_rate": 9.506416702375618e-06, | |
| "loss": 0.4864, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.23268496636975095, | |
| "grad_norm": 0.517212842625867, | |
| "learning_rate": 9.478558801197065e-06, | |
| "loss": 0.4998, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.2363206689692783, | |
| "grad_norm": 0.5016544590902606, | |
| "learning_rate": 9.449979324502905e-06, | |
| "loss": 0.4952, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.23995637156880567, | |
| "grad_norm": 0.5311590482916726, | |
| "learning_rate": 9.420682876955382e-06, | |
| "loss": 0.4902, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.24359207416833303, | |
| "grad_norm": 1.28989128820584, | |
| "learning_rate": 9.390674178733508e-06, | |
| "loss": 0.49, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.2472277767678604, | |
| "grad_norm": 0.4806268559161153, | |
| "learning_rate": 9.359958064772547e-06, | |
| "loss": 0.497, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.25086347936738773, | |
| "grad_norm": 0.5465705012971989, | |
| "learning_rate": 9.328539483985031e-06, | |
| "loss": 0.4935, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.2544991819669151, | |
| "grad_norm": 0.4942024204554198, | |
| "learning_rate": 9.296423498463396e-06, | |
| "loss": 0.4988, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.25813488456644246, | |
| "grad_norm": 0.47927969303011475, | |
| "learning_rate": 9.26361528266439e-06, | |
| "loss": 0.4896, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.26177058716596985, | |
| "grad_norm": 0.5388248768052577, | |
| "learning_rate": 9.230120122575376e-06, | |
| "loss": 0.4959, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.2654062897654972, | |
| "grad_norm": 0.47361603639036765, | |
| "learning_rate": 9.195943414862667e-06, | |
| "loss": 0.4895, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.2690419923650245, | |
| "grad_norm": 0.5070100760119046, | |
| "learning_rate": 9.161090666002029e-06, | |
| "loss": 0.4817, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.2726776949645519, | |
| "grad_norm": 0.5101057512379583, | |
| "learning_rate": 9.125567491391476e-06, | |
| "loss": 0.4991, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.27631339756407924, | |
| "grad_norm": 0.4876093660505719, | |
| "learning_rate": 9.089379614446554e-06, | |
| "loss": 0.4916, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.27994910016360663, | |
| "grad_norm": 0.6118479654908368, | |
| "learning_rate": 9.052532865678171e-06, | |
| "loss": 0.488, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.28358480276313397, | |
| "grad_norm": 0.4856780879464445, | |
| "learning_rate": 9.015033181753219e-06, | |
| "loss": 0.4876, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.28722050536266136, | |
| "grad_norm": 0.5093511993940713, | |
| "learning_rate": 8.976886604538055e-06, | |
| "loss": 0.4862, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.2908562079621887, | |
| "grad_norm": 0.4818588345949805, | |
| "learning_rate": 8.938099280125064e-06, | |
| "loss": 0.493, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.29449191056171603, | |
| "grad_norm": 0.4977991661233151, | |
| "learning_rate": 8.898677457842394e-06, | |
| "loss": 0.4921, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.2981276131612434, | |
| "grad_norm": 1.5238109089913658, | |
| "learning_rate": 8.858627489247105e-06, | |
| "loss": 0.4831, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.30176331576077076, | |
| "grad_norm": 0.49437394232039367, | |
| "learning_rate": 8.817955827101794e-06, | |
| "loss": 0.4905, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.30539901836029815, | |
| "grad_norm": 0.5679936450058084, | |
| "learning_rate": 8.776669024334955e-06, | |
| "loss": 0.4851, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.3090347209598255, | |
| "grad_norm": 0.4823418939638443, | |
| "learning_rate": 8.734773732985186e-06, | |
| "loss": 0.4857, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.3126704235593529, | |
| "grad_norm": 0.5063024654327302, | |
| "learning_rate": 8.692276703129421e-06, | |
| "loss": 0.491, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.3163061261588802, | |
| "grad_norm": 0.48665137111179807, | |
| "learning_rate": 8.649184781795367e-06, | |
| "loss": 0.4876, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.31994182875840754, | |
| "grad_norm": 0.5092645610957066, | |
| "learning_rate": 8.605504911858347e-06, | |
| "loss": 0.4868, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.32357753135793493, | |
| "grad_norm": 0.5647552140171497, | |
| "learning_rate": 8.561244130922658e-06, | |
| "loss": 0.4909, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.32721323395746227, | |
| "grad_norm": 0.5531040193640844, | |
| "learning_rate": 8.516409570187698e-06, | |
| "loss": 0.4873, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.33084893655698966, | |
| "grad_norm": 0.49756669094294076, | |
| "learning_rate": 8.471008453298998e-06, | |
| "loss": 0.4824, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.334484639156517, | |
| "grad_norm": 0.5195975092484353, | |
| "learning_rate": 8.42504809518437e-06, | |
| "loss": 0.4906, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.33812034175604433, | |
| "grad_norm": 0.5062730437183878, | |
| "learning_rate": 8.37853590087534e-06, | |
| "loss": 0.4848, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.3417560443555717, | |
| "grad_norm": 0.48265809325204573, | |
| "learning_rate": 8.33147936431406e-06, | |
| "loss": 0.4816, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.34539174695509905, | |
| "grad_norm": 0.4910060616705745, | |
| "learning_rate": 8.283886067145908e-06, | |
| "loss": 0.4832, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.34902744955462645, | |
| "grad_norm": 0.5125310752311819, | |
| "learning_rate": 8.235763677497945e-06, | |
| "loss": 0.477, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.3526631521541538, | |
| "grad_norm": 0.5250568609050469, | |
| "learning_rate": 8.18711994874345e-06, | |
| "loss": 0.4832, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.35629885475368117, | |
| "grad_norm": 0.47836219161492916, | |
| "learning_rate": 8.1379627182527e-06, | |
| "loss": 0.4857, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.3599345573532085, | |
| "grad_norm": 0.47439007998750055, | |
| "learning_rate": 8.088299906130252e-06, | |
| "loss": 0.4781, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.36357025995273584, | |
| "grad_norm": 0.49377085985480135, | |
| "learning_rate": 8.038139513938847e-06, | |
| "loss": 0.4882, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.36720596255226323, | |
| "grad_norm": 0.5263220925520542, | |
| "learning_rate": 7.987489623410236e-06, | |
| "loss": 0.4797, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.37084166515179057, | |
| "grad_norm": 0.4648220239135295, | |
| "learning_rate": 7.936358395143065e-06, | |
| "loss": 0.4777, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.37447736775131796, | |
| "grad_norm": 0.465584633325096, | |
| "learning_rate": 7.884754067288047e-06, | |
| "loss": 0.4825, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.3781130703508453, | |
| "grad_norm": 0.4876332690849426, | |
| "learning_rate": 7.832684954220664e-06, | |
| "loss": 0.4781, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.3817487729503727, | |
| "grad_norm": 0.501393591697854, | |
| "learning_rate": 7.780159445201562e-06, | |
| "loss": 0.4869, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.3853844755499, | |
| "grad_norm": 0.4845939514295346, | |
| "learning_rate": 7.727186003024902e-06, | |
| "loss": 0.4717, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.38902017814942735, | |
| "grad_norm": 0.4899764285727021, | |
| "learning_rate": 7.673773162654836e-06, | |
| "loss": 0.4777, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.39265588074895474, | |
| "grad_norm": 0.48478478383197704, | |
| "learning_rate": 7.619929529850397e-06, | |
| "loss": 0.4745, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.3962915833484821, | |
| "grad_norm": 0.4621206976060152, | |
| "learning_rate": 7.5656637797789335e-06, | |
| "loss": 0.4813, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.39992728594800947, | |
| "grad_norm": 0.5019544820278233, | |
| "learning_rate": 7.510984655618407e-06, | |
| "loss": 0.4816, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.4035629885475368, | |
| "grad_norm": 0.46639356606341964, | |
| "learning_rate": 7.4559009671486906e-06, | |
| "loss": 0.4681, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.4071986911470642, | |
| "grad_norm": 0.4728577911203865, | |
| "learning_rate": 7.400421589332175e-06, | |
| "loss": 0.4803, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.41083439374659153, | |
| "grad_norm": 0.4800482747617377, | |
| "learning_rate": 7.34455546088384e-06, | |
| "loss": 0.477, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.41447009634611887, | |
| "grad_norm": 0.5600386401489504, | |
| "learning_rate": 7.288311582831078e-06, | |
| "loss": 0.4635, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.41810579894564626, | |
| "grad_norm": 0.4959194946164877, | |
| "learning_rate": 7.23169901706346e-06, | |
| "loss": 0.4812, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.4217415015451736, | |
| "grad_norm": 0.5149644009966434, | |
| "learning_rate": 7.174726884872716e-06, | |
| "loss": 0.468, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.425377204144701, | |
| "grad_norm": 0.4866073941196498, | |
| "learning_rate": 7.117404365483116e-06, | |
| "loss": 0.4801, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.4290129067442283, | |
| "grad_norm": 0.5236518230635645, | |
| "learning_rate": 7.059740694572545e-06, | |
| "loss": 0.4759, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.4326486093437557, | |
| "grad_norm": 0.47781506154853676, | |
| "learning_rate": 7.0017451627844765e-06, | |
| "loss": 0.4721, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.43628431194328304, | |
| "grad_norm": 0.4975038663141837, | |
| "learning_rate": 6.943427114231064e-06, | |
| "loss": 0.4776, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.4399200145428104, | |
| "grad_norm": 0.4666469505582421, | |
| "learning_rate": 6.884795944987661e-06, | |
| "loss": 0.4693, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.44355571714233777, | |
| "grad_norm": 0.5219519656223606, | |
| "learning_rate": 6.825861101578931e-06, | |
| "loss": 0.4758, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.4471914197418651, | |
| "grad_norm": 0.5063916933024516, | |
| "learning_rate": 6.766632079456852e-06, | |
| "loss": 0.4743, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.4508271223413925, | |
| "grad_norm": 0.4685229097073194, | |
| "learning_rate": 6.707118421470822e-06, | |
| "loss": 0.4774, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.45446282494091983, | |
| "grad_norm": 0.4717991999133757, | |
| "learning_rate": 6.6473297163301485e-06, | |
| "loss": 0.4766, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.45809852754044716, | |
| "grad_norm": 0.5363682289647845, | |
| "learning_rate": 6.587275597059125e-06, | |
| "loss": 0.465, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.46173423013997456, | |
| "grad_norm": 0.5435017738447794, | |
| "learning_rate": 6.526965739444988e-06, | |
| "loss": 0.469, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.4653699327395019, | |
| "grad_norm": 0.4639117917019373, | |
| "learning_rate": 6.466409860478967e-06, | |
| "loss": 0.473, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.4690056353390293, | |
| "grad_norm": 0.5621851603984803, | |
| "learning_rate": 6.405617716790714e-06, | |
| "loss": 0.4662, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.4726413379385566, | |
| "grad_norm": 0.4809648503411264, | |
| "learning_rate": 6.344599103076329e-06, | |
| "loss": 0.4772, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.476277040538084, | |
| "grad_norm": 0.47163222068970184, | |
| "learning_rate": 6.2833638505202635e-06, | |
| "loss": 0.4694, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.47991274313761134, | |
| "grad_norm": 0.7951911468346275, | |
| "learning_rate": 6.221921825211342e-06, | |
| "loss": 0.4764, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.4835484457371387, | |
| "grad_norm": 0.4865248290655842, | |
| "learning_rate": 6.1602829265531585e-06, | |
| "loss": 0.4733, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.48718414833666607, | |
| "grad_norm": 0.5082890661672131, | |
| "learning_rate": 6.0984570856691046e-06, | |
| "loss": 0.4713, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.4908198509361934, | |
| "grad_norm": 0.4997424800053115, | |
| "learning_rate": 6.036454263802297e-06, | |
| "loss": 0.4761, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.4944555535357208, | |
| "grad_norm": 0.48754794843779725, | |
| "learning_rate": 5.974284450710631e-06, | |
| "loss": 0.4667, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.49809125613524813, | |
| "grad_norm": 0.5184357345641504, | |
| "learning_rate": 5.911957663057264e-06, | |
| "loss": 0.4733, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.5017269587347755, | |
| "grad_norm": 0.5114995027300243, | |
| "learning_rate": 5.849483942796747e-06, | |
| "loss": 0.4692, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.5053626613343029, | |
| "grad_norm": 0.508447512688554, | |
| "learning_rate": 5.78687335555709e-06, | |
| "loss": 0.4725, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.5089983639338302, | |
| "grad_norm": 0.4778391429982246, | |
| "learning_rate": 5.724135989018007e-06, | |
| "loss": 0.469, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.5126340665333575, | |
| "grad_norm": 0.549325516339993, | |
| "learning_rate": 5.661281951285613e-06, | |
| "loss": 0.4722, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.5162697691328849, | |
| "grad_norm": 0.48092733764405454, | |
| "learning_rate": 5.59832136926383e-06, | |
| "loss": 0.4607, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.5199054717324123, | |
| "grad_norm": 0.5769124183929066, | |
| "learning_rate": 5.53526438702276e-06, | |
| "loss": 0.4633, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.5235411743319397, | |
| "grad_norm": 0.49168310969175155, | |
| "learning_rate": 5.472121164164295e-06, | |
| "loss": 0.4618, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.527176876931467, | |
| "grad_norm": 0.5567279209075545, | |
| "learning_rate": 5.4089018741852264e-06, | |
| "loss": 0.4712, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.5308125795309944, | |
| "grad_norm": 0.49627446825911625, | |
| "learning_rate": 5.345616702838111e-06, | |
| "loss": 0.4626, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.5344482821305218, | |
| "grad_norm": 0.49582976649235855, | |
| "learning_rate": 5.282275846490169e-06, | |
| "loss": 0.4701, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.538083984730049, | |
| "grad_norm": 0.49825003870799145, | |
| "learning_rate": 5.21888951048046e-06, | |
| "loss": 0.4698, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.5417196873295764, | |
| "grad_norm": 0.48281867930621913, | |
| "learning_rate": 5.155467907475632e-06, | |
| "loss": 0.4593, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.5453553899291038, | |
| "grad_norm": 0.4764603302373525, | |
| "learning_rate": 5.092021255824471e-06, | |
| "loss": 0.4681, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.5489910925286312, | |
| "grad_norm": 0.48896004976931123, | |
| "learning_rate": 5.028559777911543e-06, | |
| "loss": 0.4595, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.5526267951281585, | |
| "grad_norm": 0.5324971873593392, | |
| "learning_rate": 4.965093698510192e-06, | |
| "loss": 0.4751, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.5562624977276859, | |
| "grad_norm": 0.468092518090719, | |
| "learning_rate": 4.901633243135144e-06, | |
| "loss": 0.4677, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.5598982003272133, | |
| "grad_norm": 0.47564151569385843, | |
| "learning_rate": 4.8381886363949956e-06, | |
| "loss": 0.4618, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.5635339029267405, | |
| "grad_norm": 0.5150014422595901, | |
| "learning_rate": 4.774770100344838e-06, | |
| "loss": 0.4708, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.5671696055262679, | |
| "grad_norm": 0.5587615356398489, | |
| "learning_rate": 4.71138785283932e-06, | |
| "loss": 0.4626, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.5708053081257953, | |
| "grad_norm": 0.49021360496671623, | |
| "learning_rate": 4.6480521058863546e-06, | |
| "loss": 0.463, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.5744410107253227, | |
| "grad_norm": 0.45504707914946996, | |
| "learning_rate": 4.5847730640017926e-06, | |
| "loss": 0.4705, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.57807671332485, | |
| "grad_norm": 0.49707118128311006, | |
| "learning_rate": 4.521560922565282e-06, | |
| "loss": 0.4641, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.5817124159243774, | |
| "grad_norm": 0.4717345687730965, | |
| "learning_rate": 4.458425866177628e-06, | |
| "loss": 0.4639, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.5853481185239048, | |
| "grad_norm": 0.47407400333758115, | |
| "learning_rate": 4.395378067019854e-06, | |
| "loss": 0.4629, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.5889838211234321, | |
| "grad_norm": 0.4951372796438499, | |
| "learning_rate": 4.332427683214295e-06, | |
| "loss": 0.464, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.5926195237229595, | |
| "grad_norm": 0.4791565652555133, | |
| "learning_rate": 4.269584857187942e-06, | |
| "loss": 0.4732, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.5962552263224868, | |
| "grad_norm": 0.4783285781382308, | |
| "learning_rate": 4.2068597140383084e-06, | |
| "loss": 0.4675, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.5998909289220142, | |
| "grad_norm": 0.47796760895514884, | |
| "learning_rate": 4.144262359902104e-06, | |
| "loss": 0.4725, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.6035266315215415, | |
| "grad_norm": 0.4632759665926115, | |
| "learning_rate": 4.081802880326955e-06, | |
| "loss": 0.4568, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.6071623341210689, | |
| "grad_norm": 0.4859662751177091, | |
| "learning_rate": 4.0194913386464445e-06, | |
| "loss": 0.4659, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.6107980367205963, | |
| "grad_norm": 0.46406543319745136, | |
| "learning_rate": 3.957337774358725e-06, | |
| "loss": 0.4701, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.6144337393201236, | |
| "grad_norm": 0.4733170226589245, | |
| "learning_rate": 3.895352201508981e-06, | |
| "loss": 0.4606, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.618069441919651, | |
| "grad_norm": 0.4957885956685627, | |
| "learning_rate": 3.833544607075986e-06, | |
| "loss": 0.4702, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.6217051445191784, | |
| "grad_norm": 0.4849524483162158, | |
| "learning_rate": 3.77192494936303e-06, | |
| "loss": 0.4596, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.6253408471187057, | |
| "grad_norm": 0.47235984448417717, | |
| "learning_rate": 3.710503156393441e-06, | |
| "loss": 0.46, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.628976549718233, | |
| "grad_norm": 0.6455899443109117, | |
| "learning_rate": 3.6492891243110283e-06, | |
| "loss": 0.4558, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.6326122523177604, | |
| "grad_norm": 0.45919477055164243, | |
| "learning_rate": 3.5882927157856175e-06, | |
| "loss": 0.4592, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.6362479549172878, | |
| "grad_norm": 0.4843392695435344, | |
| "learning_rate": 3.527523758424013e-06, | |
| "loss": 0.4705, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.6398836575168151, | |
| "grad_norm": 0.45359838182470663, | |
| "learning_rate": 3.46699204318658e-06, | |
| "loss": 0.4576, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.6435193601163425, | |
| "grad_norm": 0.48852088769983365, | |
| "learning_rate": 3.4067073228097656e-06, | |
| "loss": 0.4629, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.6471550627158699, | |
| "grad_norm": 0.4587200490693114, | |
| "learning_rate": 3.346679310234744e-06, | |
| "loss": 0.4645, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.6507907653153971, | |
| "grad_norm": 0.4504564951337433, | |
| "learning_rate": 3.2869176770424976e-06, | |
| "loss": 0.4576, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.6544264679149245, | |
| "grad_norm": 0.4871215348453017, | |
| "learning_rate": 3.22743205189555e-06, | |
| "loss": 0.4613, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.6580621705144519, | |
| "grad_norm": 0.4934087980535958, | |
| "learning_rate": 3.1682320189866133e-06, | |
| "loss": 0.4565, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.6616978731139793, | |
| "grad_norm": 0.6125659095856281, | |
| "learning_rate": 3.1093271164944116e-06, | |
| "loss": 0.467, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.6653335757135066, | |
| "grad_norm": 0.4843617677830728, | |
| "learning_rate": 3.05072683504691e-06, | |
| "loss": 0.4653, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.668969278313034, | |
| "grad_norm": 0.4775067201123396, | |
| "learning_rate": 2.992440616192197e-06, | |
| "loss": 0.4606, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.6726049809125614, | |
| "grad_norm": 0.4917120021208802, | |
| "learning_rate": 2.934477850877292e-06, | |
| "loss": 0.4598, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.6762406835120887, | |
| "grad_norm": 0.5230461776009433, | |
| "learning_rate": 2.8768478779350927e-06, | |
| "loss": 0.4599, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.679876386111616, | |
| "grad_norm": 0.5452221136473905, | |
| "learning_rate": 2.8195599825797233e-06, | |
| "loss": 0.4645, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.6835120887111434, | |
| "grad_norm": 0.4784584130073042, | |
| "learning_rate": 2.7626233949105252e-06, | |
| "loss": 0.4634, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.6871477913106708, | |
| "grad_norm": 0.4838258924260306, | |
| "learning_rate": 2.7060472884249145e-06, | |
| "loss": 0.4658, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.6907834939101981, | |
| "grad_norm": 0.48532254245951134, | |
| "learning_rate": 2.6498407785403794e-06, | |
| "loss": 0.4548, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.6944191965097255, | |
| "grad_norm": 0.45354695797734684, | |
| "learning_rate": 2.5940129211258147e-06, | |
| "loss": 0.4557, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.6980548991092529, | |
| "grad_norm": 0.5107453374700672, | |
| "learning_rate": 2.5385727110424697e-06, | |
| "loss": 0.4565, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.7016906017087802, | |
| "grad_norm": 0.5017653107973621, | |
| "learning_rate": 2.4835290806947047e-06, | |
| "loss": 0.4595, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.7053263043083076, | |
| "grad_norm": 0.4868047993646277, | |
| "learning_rate": 2.4288908985908304e-06, | |
| "loss": 0.4588, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.708962006907835, | |
| "grad_norm": 0.48740400803881145, | |
| "learning_rate": 2.3746669679142315e-06, | |
| "loss": 0.4618, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.7125977095073623, | |
| "grad_norm": 0.4797836540298589, | |
| "learning_rate": 2.320866025105016e-06, | |
| "loss": 0.4584, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.7162334121068896, | |
| "grad_norm": 0.482700658498575, | |
| "learning_rate": 2.2674967384524237e-06, | |
| "loss": 0.4525, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.719869114706417, | |
| "grad_norm": 0.4845409391794202, | |
| "learning_rate": 2.2145677066981948e-06, | |
| "loss": 0.4597, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.7235048173059444, | |
| "grad_norm": 0.4596362822493429, | |
| "learning_rate": 2.162087457651183e-06, | |
| "loss": 0.4651, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.7271405199054717, | |
| "grad_norm": 0.4822455417594266, | |
| "learning_rate": 2.1100644468133574e-06, | |
| "loss": 0.4587, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7307762225049991, | |
| "grad_norm": 0.5097275411531803, | |
| "learning_rate": 2.0585070560174807e-06, | |
| "loss": 0.4556, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.7344119251045265, | |
| "grad_norm": 0.5839380110909984, | |
| "learning_rate": 2.007423592076629e-06, | |
| "loss": 0.4536, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.7380476277040539, | |
| "grad_norm": 0.44857851226221945, | |
| "learning_rate": 1.9568222854458403e-06, | |
| "loss": 0.4574, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.7416833303035811, | |
| "grad_norm": 0.47049022745539104, | |
| "learning_rate": 1.9067112888960283e-06, | |
| "loss": 0.4578, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.7453190329031085, | |
| "grad_norm": 0.47714438215979904, | |
| "learning_rate": 1.8570986762004246e-06, | |
| "loss": 0.463, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.7489547355026359, | |
| "grad_norm": 0.5208882670799284, | |
| "learning_rate": 1.807992440833754e-06, | |
| "loss": 0.4551, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.7525904381021632, | |
| "grad_norm": 0.5442592319438936, | |
| "learning_rate": 1.7594004946843458e-06, | |
| "loss": 0.4674, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.7562261407016906, | |
| "grad_norm": 0.48254170721644596, | |
| "learning_rate": 1.711330666779385e-06, | |
| "loss": 0.4677, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.759861843301218, | |
| "grad_norm": 0.4814874170107103, | |
| "learning_rate": 1.6637907020235117e-06, | |
| "loss": 0.4597, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.7634975459007454, | |
| "grad_norm": 0.4739270617198922, | |
| "learning_rate": 1.6167882599509904e-06, | |
| "loss": 0.4579, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.7671332485002726, | |
| "grad_norm": 0.4490225695145959, | |
| "learning_rate": 1.5703309134916116e-06, | |
| "loss": 0.4599, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.7707689510998, | |
| "grad_norm": 0.5163514733876741, | |
| "learning_rate": 1.5244261477505678e-06, | |
| "loss": 0.461, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.7744046536993274, | |
| "grad_norm": 0.4578320108199828, | |
| "learning_rate": 1.4790813588024584e-06, | |
| "loss": 0.4524, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.7780403562988547, | |
| "grad_norm": 0.46097525067009587, | |
| "learning_rate": 1.4343038524996645e-06, | |
| "loss": 0.4469, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.7816760588983821, | |
| "grad_norm": 0.4597501024666662, | |
| "learning_rate": 1.3901008432952323e-06, | |
| "loss": 0.456, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.7853117614979095, | |
| "grad_norm": 0.45054776020061243, | |
| "learning_rate": 1.3464794530805076e-06, | |
| "loss": 0.4542, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.7889474640974369, | |
| "grad_norm": 0.5135955631738628, | |
| "learning_rate": 1.3034467100376624e-06, | |
| "loss": 0.4595, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.7925831666969642, | |
| "grad_norm": 0.8051954052504948, | |
| "learning_rate": 1.2610095475073415e-06, | |
| "loss": 0.4582, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.7962188692964915, | |
| "grad_norm": 0.5545838814342399, | |
| "learning_rate": 1.2191748028715632e-06, | |
| "loss": 0.4573, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.7998545718960189, | |
| "grad_norm": 0.4717805012305005, | |
| "learning_rate": 1.1779492164521117e-06, | |
| "loss": 0.4572, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.8034902744955462, | |
| "grad_norm": 0.47047774538883685, | |
| "learning_rate": 1.137339430424535e-06, | |
| "loss": 0.4463, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.8071259770950736, | |
| "grad_norm": 0.49160915268963123, | |
| "learning_rate": 1.0973519877479878e-06, | |
| "loss": 0.4544, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.810761679694601, | |
| "grad_norm": 0.5277329087760968, | |
| "learning_rate": 1.057993331111029e-06, | |
| "loss": 0.4601, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.8143973822941284, | |
| "grad_norm": 0.5030946496850482, | |
| "learning_rate": 1.019269801893606e-06, | |
| "loss": 0.451, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.8180330848936557, | |
| "grad_norm": 0.4691577738903578, | |
| "learning_rate": 9.811876391453296e-07, | |
| "loss": 0.4569, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.8216687874931831, | |
| "grad_norm": 0.5060156909470946, | |
| "learning_rate": 9.437529785802647e-07, | |
| "loss": 0.4541, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.8253044900927105, | |
| "grad_norm": 0.5597539733092323, | |
| "learning_rate": 9.069718515883524e-07, | |
| "loss": 0.4571, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.8289401926922377, | |
| "grad_norm": 0.6205399488788043, | |
| "learning_rate": 8.708501842636441e-07, | |
| "loss": 0.4533, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.8325758952917651, | |
| "grad_norm": 0.6091964354151129, | |
| "learning_rate": 8.353937964495029e-07, | |
| "loss": 0.4547, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.8362115978912925, | |
| "grad_norm": 0.4823913556529928, | |
| "learning_rate": 8.006084008009285e-07, | |
| "loss": 0.4633, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.8398473004908199, | |
| "grad_norm": 0.4836149591285523, | |
| "learning_rate": 7.664996018641413e-07, | |
| "loss": 0.4594, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.8434830030903472, | |
| "grad_norm": 0.5151003588756417, | |
| "learning_rate": 7.330728951735916e-07, | |
| "loss": 0.4594, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.8471187056898746, | |
| "grad_norm": 0.49212530275663835, | |
| "learning_rate": 7.003336663665294e-07, | |
| "loss": 0.4541, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.850754408289402, | |
| "grad_norm": 0.45463900824583864, | |
| "learning_rate": 6.682871903152888e-07, | |
| "loss": 0.4574, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.8543901108889292, | |
| "grad_norm": 0.4612071403655604, | |
| "learning_rate": 6.36938630277405e-07, | |
| "loss": 0.4574, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.8580258134884566, | |
| "grad_norm": 0.450894369412524, | |
| "learning_rate": 6.06293037063726e-07, | |
| "loss": 0.4497, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.861661516087984, | |
| "grad_norm": 0.6606390701483983, | |
| "learning_rate": 5.76355348224632e-07, | |
| "loss": 0.4564, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.8652972186875114, | |
| "grad_norm": 0.504111016168876, | |
| "learning_rate": 5.471303872545175e-07, | |
| "loss": 0.4533, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.8689329212870387, | |
| "grad_norm": 0.4794898132062981, | |
| "learning_rate": 5.186228628146317e-07, | |
| "loss": 0.4552, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.8725686238865661, | |
| "grad_norm": 0.46501232916266055, | |
| "learning_rate": 4.908373679744316e-07, | |
| "loss": 0.4549, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.8762043264860935, | |
| "grad_norm": 0.4664753040463795, | |
| "learning_rate": 4.637783794715589e-07, | |
| "loss": 0.4508, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.8798400290856208, | |
| "grad_norm": 0.4724075498889921, | |
| "learning_rate": 4.37450256990557e-07, | |
| "loss": 0.4452, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.8834757316851481, | |
| "grad_norm": 0.44884858999793636, | |
| "learning_rate": 4.118572424604489e-07, | |
| "loss": 0.4559, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.8871114342846755, | |
| "grad_norm": 0.5146747185106016, | |
| "learning_rate": 3.8700345937128346e-07, | |
| "loss": 0.4553, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.8907471368842028, | |
| "grad_norm": 0.4818934639838168, | |
| "learning_rate": 3.628929121097707e-07, | |
| "loss": 0.4555, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.8943828394837302, | |
| "grad_norm": 0.48523647646838824, | |
| "learning_rate": 3.3952948531410566e-07, | |
| "loss": 0.4627, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.8980185420832576, | |
| "grad_norm": 0.4875433558969186, | |
| "learning_rate": 3.1691694324808063e-07, | |
| "loss": 0.4527, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.901654244682785, | |
| "grad_norm": 0.4758499098103746, | |
| "learning_rate": 2.950589291945954e-07, | |
| "loss": 0.4531, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.9052899472823123, | |
| "grad_norm": 0.4992557309702915, | |
| "learning_rate": 2.7395896486866193e-07, | |
| "loss": 0.4586, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.9089256498818397, | |
| "grad_norm": 0.4767031299121917, | |
| "learning_rate": 2.536204498499922e-07, | |
| "loss": 0.4579, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.912561352481367, | |
| "grad_norm": 0.49392056665149014, | |
| "learning_rate": 2.3404666103526542e-07, | |
| "loss": 0.4508, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.9161970550808943, | |
| "grad_norm": 0.5094688415649842, | |
| "learning_rate": 2.1524075211016014e-07, | |
| "loss": 0.4586, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.9198327576804217, | |
| "grad_norm": 0.4601369037837206, | |
| "learning_rate": 1.9720575304124135e-07, | |
| "loss": 0.4464, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.9234684602799491, | |
| "grad_norm": 0.5126766072948435, | |
| "learning_rate": 1.799445695877805e-07, | |
| "loss": 0.4538, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.9271041628794765, | |
| "grad_norm": 0.4850010127835303, | |
| "learning_rate": 1.6345998283358145e-07, | |
| "loss": 0.4639, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.9307398654790038, | |
| "grad_norm": 0.4835231314824377, | |
| "learning_rate": 1.4775464873890256e-07, | |
| "loss": 0.4523, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.9343755680785312, | |
| "grad_norm": 0.4847433627202371, | |
| "learning_rate": 1.3283109771252966e-07, | |
| "loss": 0.4702, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.9380112706780586, | |
| "grad_norm": 0.4754213280562048, | |
| "learning_rate": 1.1869173420408886e-07, | |
| "loss": 0.4553, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.9416469732775858, | |
| "grad_norm": 0.5010724703288434, | |
| "learning_rate": 1.0533883631663966e-07, | |
| "loss": 0.4508, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.9452826758771132, | |
| "grad_norm": 0.4786208644219983, | |
| "learning_rate": 9.277455543963809e-08, | |
| "loss": 0.4532, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.9489183784766406, | |
| "grad_norm": 0.45474358563185757, | |
| "learning_rate": 8.100091590230618e-08, | |
| "loss": 0.4584, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.952554081076168, | |
| "grad_norm": 0.572173942440635, | |
| "learning_rate": 7.001981464747565e-08, | |
| "loss": 0.4549, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.9561897836756953, | |
| "grad_norm": 0.4499204563848751, | |
| "learning_rate": 5.983302092595955e-08, | |
| "loss": 0.4542, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.9598254862752227, | |
| "grad_norm": 0.5598350970975273, | |
| "learning_rate": 5.044217601149371e-08, | |
| "loss": 0.4516, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.9634611888747501, | |
| "grad_norm": 0.47015970674737495, | |
| "learning_rate": 4.1848792936297064e-08, | |
| "loss": 0.4581, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.9670968914742774, | |
| "grad_norm": 0.49724329959849795, | |
| "learning_rate": 3.405425624729619e-08, | |
| "loss": 0.4499, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.9707325940738047, | |
| "grad_norm": 0.521794534931598, | |
| "learning_rate": 2.705982178304922e-08, | |
| "loss": 0.4599, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.9743682966733321, | |
| "grad_norm": 0.449015502180019, | |
| "learning_rate": 2.0866616471409974e-08, | |
| "loss": 0.4536, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.9780039992728595, | |
| "grad_norm": 0.5046143330215167, | |
| "learning_rate": 1.5475638147957607e-08, | |
| "loss": 0.4547, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.9816397018723868, | |
| "grad_norm": 0.4772589719210184, | |
| "learning_rate": 1.0887755395228018e-08, | |
| "loss": 0.4539, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.9852754044719142, | |
| "grad_norm": 0.46672756743132343, | |
| "learning_rate": 7.103707402771887e-09, | |
| "loss": 0.4442, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.9889111070714416, | |
| "grad_norm": 0.4928379794589844, | |
| "learning_rate": 4.1241038480543945e-09, | |
| "loss": 0.4518, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.9925468096709689, | |
| "grad_norm": 0.480930854863133, | |
| "learning_rate": 1.9494247982282386e-09, | |
| "loss": 0.4559, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.9961825122704963, | |
| "grad_norm": 0.4943717001645737, | |
| "learning_rate": 5.800206327855051e-10, | |
| "loss": 0.4491, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.9998182148700236, | |
| "grad_norm": 0.47728279974357224, | |
| "learning_rate": 1.6111987103939464e-11, | |
| "loss": 0.4601, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 2751, | |
| "total_flos": 7.127360308661715e+18, | |
| "train_loss": 0.4852235563687089, | |
| "train_runtime": 49681.7563, | |
| "train_samples_per_second": 7.086, | |
| "train_steps_per_second": 0.055 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2751, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.127360308661715e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |