Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
unsloth
trl
sft
conversational
text-generation-inference
Instructions to use Ba2han/test_sft31 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/test_sft31 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ba2han/test_sft31") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ba2han/test_sft31") model = AutoModelForCausalLM.from_pretrained("Ba2han/test_sft31", 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 Ba2han/test_sft31 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ba2han/test_sft31" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/test_sft31", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Ba2han/test_sft31
- SGLang
How to use Ba2han/test_sft31 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 "Ba2han/test_sft31" \ --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": "Ba2han/test_sft31", "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 "Ba2han/test_sft31" \ --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": "Ba2han/test_sft31", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use Ba2han/test_sft31 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ba2han/test_sft31 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ba2han/test_sft31 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Ba2han/test_sft31 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Ba2han/test_sft31", max_seq_length=2048, ) - Docker Model Runner
How to use Ba2han/test_sft31 with Docker Model Runner:
docker model run hf.co/Ba2han/test_sft31
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18005887040379892, | |
| "eval_steps": 500, | |
| "global_step": 1384, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002602006797742759, | |
| "grad_norm": 0.521027684211731, | |
| "learning_rate": 4.3352601156069365e-06, | |
| "loss": 3.296633720397949, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005204013595485518, | |
| "grad_norm": 0.529604434967041, | |
| "learning_rate": 1.3005780346820809e-05, | |
| "loss": 3.42961049079895, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007806020393228277, | |
| "grad_norm": 0.4618305563926697, | |
| "learning_rate": 2.167630057803468e-05, | |
| "loss": 3.335054397583008, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010408027190971037, | |
| "grad_norm": 0.4985038638114929, | |
| "learning_rate": 3.0346820809248556e-05, | |
| "loss": 3.381575584411621, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013010033988713795, | |
| "grad_norm": 0.4767224192619324, | |
| "learning_rate": 3.901734104046243e-05, | |
| "loss": 3.4511144161224365, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0015612040786456554, | |
| "grad_norm": 0.4434731900691986, | |
| "learning_rate": 4.76878612716763e-05, | |
| "loss": 3.3980913162231445, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0018214047584199314, | |
| "grad_norm": 0.5170185565948486, | |
| "learning_rate": 5.6358381502890176e-05, | |
| "loss": 3.4509780406951904, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0020816054381942073, | |
| "grad_norm": 0.49620524048805237, | |
| "learning_rate": 6.502890173410404e-05, | |
| "loss": 3.425800323486328, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002341806117968483, | |
| "grad_norm": 0.3991275429725647, | |
| "learning_rate": 7.369942196531793e-05, | |
| "loss": 3.3160603046417236, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.002602006797742759, | |
| "grad_norm": 0.4144597053527832, | |
| "learning_rate": 8.23699421965318e-05, | |
| "loss": 3.3297767639160156, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002862207477517035, | |
| "grad_norm": 0.4789470434188843, | |
| "learning_rate": 9.104046242774567e-05, | |
| "loss": 3.307015895843506, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0031224081572913107, | |
| "grad_norm": 0.40658894181251526, | |
| "learning_rate": 9.971098265895953e-05, | |
| "loss": 3.4203081130981445, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003382608837065587, | |
| "grad_norm": 0.375639408826828, | |
| "learning_rate": 0.00010838150289017342, | |
| "loss": 3.364102840423584, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.003642809516839863, | |
| "grad_norm": 0.3961547315120697, | |
| "learning_rate": 0.0001170520231213873, | |
| "loss": 3.291555166244507, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0039030101966141388, | |
| "grad_norm": 0.4585370719432831, | |
| "learning_rate": 0.00012572254335260115, | |
| "loss": 3.4974162578582764, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004163210876388415, | |
| "grad_norm": 0.43081340193748474, | |
| "learning_rate": 0.00013439306358381504, | |
| "loss": 3.403614044189453, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.00442341155616269, | |
| "grad_norm": 0.37973612546920776, | |
| "learning_rate": 0.0001430635838150289, | |
| "loss": 3.296022415161133, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.004683612235936966, | |
| "grad_norm": 0.3765884041786194, | |
| "learning_rate": 0.00015173410404624278, | |
| "loss": 3.405014991760254, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.004943812915711243, | |
| "grad_norm": 0.38402050733566284, | |
| "learning_rate": 0.00016040462427745666, | |
| "loss": 3.428579092025757, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.005204013595485518, | |
| "grad_norm": 0.3614136576652527, | |
| "learning_rate": 0.00016907514450867052, | |
| "loss": 3.3713903427124023, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005464214275259794, | |
| "grad_norm": 0.41867804527282715, | |
| "learning_rate": 0.00017774566473988438, | |
| "loss": 3.461496353149414, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.00572441495503407, | |
| "grad_norm": 0.33046382665634155, | |
| "learning_rate": 0.00018641618497109826, | |
| "loss": 3.3089582920074463, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.005984615634808346, | |
| "grad_norm": 0.3859819769859314, | |
| "learning_rate": 0.00019508670520231212, | |
| "loss": 3.388202667236328, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0062448163145826215, | |
| "grad_norm": 0.3520834147930145, | |
| "learning_rate": 0.000203757225433526, | |
| "loss": 3.272517681121826, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.006505016994356898, | |
| "grad_norm": 0.3423490822315216, | |
| "learning_rate": 0.00021242774566473992, | |
| "loss": 3.260913848876953, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006765217674131174, | |
| "grad_norm": 0.35582831501960754, | |
| "learning_rate": 0.00022109826589595378, | |
| "loss": 3.4315755367279053, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0070254183539054495, | |
| "grad_norm": 0.3502774238586426, | |
| "learning_rate": 0.00022976878612716763, | |
| "loss": 3.317216634750366, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.007285619033679726, | |
| "grad_norm": 0.3774696886539459, | |
| "learning_rate": 0.00023843930635838152, | |
| "loss": 3.4877872467041016, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.007545819713454001, | |
| "grad_norm": 0.3579508662223816, | |
| "learning_rate": 0.0002471098265895954, | |
| "loss": 3.3067917823791504, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0078060203932282775, | |
| "grad_norm": 0.3545570969581604, | |
| "learning_rate": 0.00025578034682080926, | |
| "loss": 3.3747382164001465, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.008066221073002554, | |
| "grad_norm": 0.4066823124885559, | |
| "learning_rate": 0.0002644508670520231, | |
| "loss": 3.37534761428833, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.00832642175277683, | |
| "grad_norm": 0.3766571283340454, | |
| "learning_rate": 0.000273121387283237, | |
| "loss": 3.3921797275543213, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.008586622432551105, | |
| "grad_norm": 0.3474276661872864, | |
| "learning_rate": 0.00028179190751445083, | |
| "loss": 3.3073554039001465, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.00884682311232538, | |
| "grad_norm": 0.36787399649620056, | |
| "learning_rate": 0.00029046242774566475, | |
| "loss": 3.465327262878418, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.009107023792099657, | |
| "grad_norm": 0.3730259835720062, | |
| "learning_rate": 0.00029913294797687866, | |
| "loss": 3.3730597496032715, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.009367224471873933, | |
| "grad_norm": 0.3592052459716797, | |
| "learning_rate": 0.0003078034682080925, | |
| "loss": 3.369673013687134, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.009627425151648208, | |
| "grad_norm": 0.4704977869987488, | |
| "learning_rate": 0.0003164739884393064, | |
| "loss": 3.4094486236572266, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.009887625831422485, | |
| "grad_norm": 0.29093804955482483, | |
| "learning_rate": 0.00032514450867052023, | |
| "loss": 3.298234462738037, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.01014782651119676, | |
| "grad_norm": 0.30112385749816895, | |
| "learning_rate": 0.0003338150289017341, | |
| "loss": 3.164336681365967, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.010408027190971036, | |
| "grad_norm": 0.25602561235427856, | |
| "learning_rate": 0.000342485549132948, | |
| "loss": 3.2490344047546387, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.010668227870745312, | |
| "grad_norm": 0.27550992369651794, | |
| "learning_rate": 0.00035115606936416186, | |
| "loss": 3.2643542289733887, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.010928428550519589, | |
| "grad_norm": 0.3303152024745941, | |
| "learning_rate": 0.0003598265895953757, | |
| "loss": 3.289999485015869, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.011188629230293864, | |
| "grad_norm": 0.31836414337158203, | |
| "learning_rate": 0.0003684971098265896, | |
| "loss": 3.3413586616516113, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.01144882991006814, | |
| "grad_norm": 0.33070388436317444, | |
| "learning_rate": 0.0003771676300578035, | |
| "loss": 3.32738995552063, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.011709030589842417, | |
| "grad_norm": 0.30830368399620056, | |
| "learning_rate": 0.00038583815028901734, | |
| "loss": 3.349341869354248, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.011969231269616692, | |
| "grad_norm": 0.30990368127822876, | |
| "learning_rate": 0.00039450867052023126, | |
| "loss": 3.316821575164795, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.012229431949390968, | |
| "grad_norm": 0.3708277940750122, | |
| "learning_rate": 0.0004031791907514451, | |
| "loss": 3.3271565437316895, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.012489632629165243, | |
| "grad_norm": 0.28574034571647644, | |
| "learning_rate": 0.00041184971098265897, | |
| "loss": 3.293184280395508, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.01274983330893952, | |
| "grad_norm": 0.2940095365047455, | |
| "learning_rate": 0.00042052023121387283, | |
| "loss": 3.35920786857605, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.013010033988713796, | |
| "grad_norm": 0.30244606733322144, | |
| "learning_rate": 0.0004291907514450867, | |
| "loss": 3.350550889968872, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.013270234668488071, | |
| "grad_norm": 0.35780057311058044, | |
| "learning_rate": 0.0004378612716763006, | |
| "loss": 3.3532772064208984, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.013530435348262348, | |
| "grad_norm": 0.2902573347091675, | |
| "learning_rate": 0.00044653179190751446, | |
| "loss": 3.2327017784118652, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.013790636028036624, | |
| "grad_norm": 0.28510838747024536, | |
| "learning_rate": 0.0004552023121387283, | |
| "loss": 3.253952741622925, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.014050836707810899, | |
| "grad_norm": 0.31303301453590393, | |
| "learning_rate": 0.00046387283236994217, | |
| "loss": 3.320916175842285, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.014311037387585174, | |
| "grad_norm": 0.2602003812789917, | |
| "learning_rate": 0.00047254335260115603, | |
| "loss": 3.1783814430236816, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.014571238067359452, | |
| "grad_norm": 0.29427075386047363, | |
| "learning_rate": 0.00048121387283236994, | |
| "loss": 3.199770450592041, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.014831438747133727, | |
| "grad_norm": 0.2756480574607849, | |
| "learning_rate": 0.0004898843930635837, | |
| "loss": 3.276580333709717, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.015091639426908002, | |
| "grad_norm": 0.2712593674659729, | |
| "learning_rate": 0.0004985549132947977, | |
| "loss": 3.2717957496643066, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.015351840106682278, | |
| "grad_norm": 0.3133692443370819, | |
| "learning_rate": 0.0005072254335260116, | |
| "loss": 3.2784416675567627, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.015612040786456555, | |
| "grad_norm": 0.27181175351142883, | |
| "learning_rate": 0.0005158959537572255, | |
| "loss": 3.2424092292785645, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.01587224146623083, | |
| "grad_norm": 0.26740762591362, | |
| "learning_rate": 0.0005245664739884394, | |
| "loss": 3.268554210662842, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.016132442146005108, | |
| "grad_norm": 0.32215583324432373, | |
| "learning_rate": 0.0005332369942196532, | |
| "loss": 3.3126766681671143, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.01639264282577938, | |
| "grad_norm": 0.28776511549949646, | |
| "learning_rate": 0.0005419075144508671, | |
| "loss": 3.120931386947632, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.01665284350555366, | |
| "grad_norm": 0.25681668519973755, | |
| "learning_rate": 0.0005505780346820809, | |
| "loss": 3.2850513458251953, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.016913044185327936, | |
| "grad_norm": 0.2619856297969818, | |
| "learning_rate": 0.0005592485549132948, | |
| "loss": 3.2361326217651367, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01717324486510221, | |
| "grad_norm": 0.27186161279678345, | |
| "learning_rate": 0.0005679190751445087, | |
| "loss": 3.254220485687256, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.017433445544876486, | |
| "grad_norm": 0.30524536967277527, | |
| "learning_rate": 0.0005765895953757225, | |
| "loss": 3.230988025665283, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.01769364622465076, | |
| "grad_norm": 0.274209588766098, | |
| "learning_rate": 0.0005852601156069364, | |
| "loss": 3.2885119915008545, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.017953846904425037, | |
| "grad_norm": 0.2683689594268799, | |
| "learning_rate": 0.0005939306358381503, | |
| "loss": 3.2494893074035645, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.018214047584199314, | |
| "grad_norm": 0.2528843879699707, | |
| "learning_rate": 0.0006026011560693642, | |
| "loss": 3.2656893730163574, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.018474248263973588, | |
| "grad_norm": 0.2937518358230591, | |
| "learning_rate": 0.0006112716763005781, | |
| "loss": 3.2583231925964355, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.018734448943747865, | |
| "grad_norm": 0.25858423113822937, | |
| "learning_rate": 0.0006199421965317919, | |
| "loss": 3.245497703552246, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.018994649623522143, | |
| "grad_norm": 0.2764334976673126, | |
| "learning_rate": 0.0006286127167630058, | |
| "loss": 3.2706778049468994, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.019254850303296416, | |
| "grad_norm": 0.2558375895023346, | |
| "learning_rate": 0.0006372832369942196, | |
| "loss": 3.2925539016723633, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.019515050983070693, | |
| "grad_norm": 0.26449859142303467, | |
| "learning_rate": 0.0006459537572254335, | |
| "loss": 3.1974246501922607, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.01977525166284497, | |
| "grad_norm": 0.2643563449382782, | |
| "learning_rate": 0.0006546242774566474, | |
| "loss": 3.2013633251190186, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.020035452342619244, | |
| "grad_norm": 0.25999486446380615, | |
| "learning_rate": 0.0006632947976878612, | |
| "loss": 3.2912192344665527, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.02029565302239352, | |
| "grad_norm": 0.23230506479740143, | |
| "learning_rate": 0.0006719653179190752, | |
| "loss": 3.2590725421905518, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.0205558537021678, | |
| "grad_norm": 0.25524914264678955, | |
| "learning_rate": 0.000680635838150289, | |
| "loss": 3.253737449645996, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.020816054381942072, | |
| "grad_norm": 0.27695125341415405, | |
| "learning_rate": 0.000689306358381503, | |
| "loss": 3.1709330081939697, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.02107625506171635, | |
| "grad_norm": 0.2362748086452484, | |
| "learning_rate": 0.0006979768786127168, | |
| "loss": 3.2747771739959717, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.021336455741490623, | |
| "grad_norm": 0.23591399192810059, | |
| "learning_rate": 0.0007066473988439307, | |
| "loss": 3.18483304977417, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.0215966564212649, | |
| "grad_norm": 0.2665315866470337, | |
| "learning_rate": 0.0007153179190751446, | |
| "loss": 3.208442211151123, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.021856857101039177, | |
| "grad_norm": 0.25159355998039246, | |
| "learning_rate": 0.0007239884393063584, | |
| "loss": 3.2677812576293945, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.02211705778081345, | |
| "grad_norm": 0.2371087670326233, | |
| "learning_rate": 0.0007326589595375723, | |
| "loss": 3.1868972778320312, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.022377258460587728, | |
| "grad_norm": 0.3146700859069824, | |
| "learning_rate": 0.0007413294797687861, | |
| "loss": 3.123814582824707, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.022637459140362005, | |
| "grad_norm": 0.2549314796924591, | |
| "learning_rate": 0.00075, | |
| "loss": 3.2187676429748535, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.02289765982013628, | |
| "grad_norm": 0.2223459631204605, | |
| "learning_rate": 0.0007586705202312139, | |
| "loss": 3.2054901123046875, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.023157860499910556, | |
| "grad_norm": 0.2565750181674957, | |
| "learning_rate": 0.0007673410404624277, | |
| "loss": 3.207458972930908, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.023418061179684833, | |
| "grad_norm": 0.2476375699043274, | |
| "learning_rate": 0.0007760115606936418, | |
| "loss": 3.1795835494995117, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.023678261859459107, | |
| "grad_norm": 0.23969122767448425, | |
| "learning_rate": 0.0007846820809248554, | |
| "loss": 3.187877655029297, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.023938462539233384, | |
| "grad_norm": 0.23113180696964264, | |
| "learning_rate": 0.0007933526011560695, | |
| "loss": 3.1212964057922363, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.024198663219007658, | |
| "grad_norm": 0.21042431890964508, | |
| "learning_rate": 0.0008020231213872833, | |
| "loss": 3.155189275741577, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.024458863898781935, | |
| "grad_norm": 0.197580486536026, | |
| "learning_rate": 0.0008106936416184972, | |
| "loss": 3.1081671714782715, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.024719064578556212, | |
| "grad_norm": 0.21269115805625916, | |
| "learning_rate": 0.000819364161849711, | |
| "loss": 3.1772332191467285, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.024979265258330486, | |
| "grad_norm": 0.2827216386795044, | |
| "learning_rate": 0.0008280346820809249, | |
| "loss": 3.035491466522217, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.025239465938104763, | |
| "grad_norm": 0.2425803542137146, | |
| "learning_rate": 0.0008367052023121387, | |
| "loss": 3.096795082092285, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.02549966661787904, | |
| "grad_norm": 0.20268665254116058, | |
| "learning_rate": 0.0008453757225433526, | |
| "loss": 3.10842227935791, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.025759867297653314, | |
| "grad_norm": 0.24778003990650177, | |
| "learning_rate": 0.0008540462427745664, | |
| "loss": 3.1295409202575684, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.02602006797742759, | |
| "grad_norm": 0.2006409615278244, | |
| "learning_rate": 0.0008627167630057804, | |
| "loss": 3.1514291763305664, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02628026865720187, | |
| "grad_norm": 0.19448356330394745, | |
| "learning_rate": 0.0008713872832369941, | |
| "loss": 3.1217727661132812, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.026540469336976142, | |
| "grad_norm": 0.17982026934623718, | |
| "learning_rate": 0.0008800578034682082, | |
| "loss": 3.097832679748535, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.02680067001675042, | |
| "grad_norm": 0.2240755259990692, | |
| "learning_rate": 0.000888728323699422, | |
| "loss": 3.154944896697998, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.027060870696524696, | |
| "grad_norm": 0.19914984703063965, | |
| "learning_rate": 0.0008973988439306359, | |
| "loss": 3.128056049346924, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.02732107137629897, | |
| "grad_norm": 0.18972548842430115, | |
| "learning_rate": 0.0009060693641618497, | |
| "loss": 3.1953482627868652, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.027581272056073247, | |
| "grad_norm": 0.21920305490493774, | |
| "learning_rate": 0.0009147398843930636, | |
| "loss": 3.1071338653564453, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.02784147273584752, | |
| "grad_norm": 0.21467278897762299, | |
| "learning_rate": 0.0009234104046242776, | |
| "loss": 3.10892391204834, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.028101673415621798, | |
| "grad_norm": 0.19529728591442108, | |
| "learning_rate": 0.0009320809248554913, | |
| "loss": 3.0915136337280273, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.028361874095396075, | |
| "grad_norm": 0.2508365213871002, | |
| "learning_rate": 0.0009407514450867053, | |
| "loss": 3.0391974449157715, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.02862207477517035, | |
| "grad_norm": 0.18604034185409546, | |
| "learning_rate": 0.0009494219653179191, | |
| "loss": 3.029890537261963, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.028882275454944626, | |
| "grad_norm": 0.18298658728599548, | |
| "learning_rate": 0.000958092485549133, | |
| "loss": 3.0440821647644043, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.029142476134718903, | |
| "grad_norm": 0.19031928479671478, | |
| "learning_rate": 0.0009667630057803468, | |
| "loss": 3.0324721336364746, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.029402676814493177, | |
| "grad_norm": 0.2045256644487381, | |
| "learning_rate": 0.0009754335260115607, | |
| "loss": 3.027928352355957, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.029662877494267454, | |
| "grad_norm": 0.18090291321277618, | |
| "learning_rate": 0.0009841040462427746, | |
| "loss": 2.9796810150146484, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.02992307817404173, | |
| "grad_norm": 0.20732243359088898, | |
| "learning_rate": 0.0009927745664739885, | |
| "loss": 3.092945098876953, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.030183278853816005, | |
| "grad_norm": 0.19675296545028687, | |
| "learning_rate": 0.0010014450867052024, | |
| "loss": 3.1028237342834473, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.030443479533590282, | |
| "grad_norm": 0.2103000432252884, | |
| "learning_rate": 0.0010101156069364163, | |
| "loss": 3.0760812759399414, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.030703680213364556, | |
| "grad_norm": 0.18039967119693756, | |
| "learning_rate": 0.00101878612716763, | |
| "loss": 3.0807101726531982, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.030963880893138833, | |
| "grad_norm": 0.18566253781318665, | |
| "learning_rate": 0.001027456647398844, | |
| "loss": 3.0250244140625, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.03122408157291311, | |
| "grad_norm": 0.2228381484746933, | |
| "learning_rate": 0.0010361271676300578, | |
| "loss": 2.9628562927246094, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.03148428225268739, | |
| "grad_norm": 0.18055233359336853, | |
| "learning_rate": 0.0010447976878612717, | |
| "loss": 2.9055001735687256, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.03174448293246166, | |
| "grad_norm": 0.19681446254253387, | |
| "learning_rate": 0.0010534682080924854, | |
| "loss": 2.9425225257873535, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.032004683612235935, | |
| "grad_norm": 0.20274615287780762, | |
| "learning_rate": 0.0010621387283236995, | |
| "loss": 3.03011417388916, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.032264884292010215, | |
| "grad_norm": 0.1779792457818985, | |
| "learning_rate": 0.0010708092485549132, | |
| "loss": 3.05258846282959, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.03252508497178449, | |
| "grad_norm": 0.21098701655864716, | |
| "learning_rate": 0.0010794797687861271, | |
| "loss": 3.0425450801849365, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.03278528565155876, | |
| "grad_norm": 0.1870265156030655, | |
| "learning_rate": 0.001088150289017341, | |
| "loss": 2.993565082550049, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.03304548633133304, | |
| "grad_norm": 0.19540223479270935, | |
| "learning_rate": 0.001096820809248555, | |
| "loss": 2.9134411811828613, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.03330568701110732, | |
| "grad_norm": 0.21431873738765717, | |
| "learning_rate": 0.0011054913294797689, | |
| "loss": 2.93609619140625, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.03356588769088159, | |
| "grad_norm": 0.207144632935524, | |
| "learning_rate": 0.0011141618497109826, | |
| "loss": 2.9225587844848633, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.03382608837065587, | |
| "grad_norm": 0.2121778130531311, | |
| "learning_rate": 0.0011228323699421967, | |
| "loss": 3.0123167037963867, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.034086289050430145, | |
| "grad_norm": 0.18439042568206787, | |
| "learning_rate": 0.0011315028901734104, | |
| "loss": 2.919414520263672, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.03434648973020442, | |
| "grad_norm": 0.17453093826770782, | |
| "learning_rate": 0.0011401734104046243, | |
| "loss": 2.9711110591888428, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.0346066904099787, | |
| "grad_norm": 0.2020498514175415, | |
| "learning_rate": 0.0011488439306358382, | |
| "loss": 2.9616055488586426, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.03486689108975297, | |
| "grad_norm": 0.18789063394069672, | |
| "learning_rate": 0.0011575144508670521, | |
| "loss": 2.9807963371276855, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.03512709176952725, | |
| "grad_norm": 0.1720653921365738, | |
| "learning_rate": 0.0011661849710982658, | |
| "loss": 2.909268617630005, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.03538729244930152, | |
| "grad_norm": 0.22420282661914825, | |
| "learning_rate": 0.0011748554913294797, | |
| "loss": 2.9295620918273926, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.0356474931290758, | |
| "grad_norm": 0.1796054095029831, | |
| "learning_rate": 0.0011835260115606937, | |
| "loss": 2.838535785675049, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.035907693808850075, | |
| "grad_norm": 0.2178080528974533, | |
| "learning_rate": 0.0011921965317919076, | |
| "loss": 2.8897058963775635, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.03616789448862435, | |
| "grad_norm": 0.21806925535202026, | |
| "learning_rate": 0.0012008670520231213, | |
| "loss": 2.8932857513427734, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.03642809516839863, | |
| "grad_norm": 0.18577463924884796, | |
| "learning_rate": 0.0012095375722543354, | |
| "loss": 2.916924476623535, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.0366882958481729, | |
| "grad_norm": 0.2138700932264328, | |
| "learning_rate": 0.001218208092485549, | |
| "loss": 2.985546827316284, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.036948496527947176, | |
| "grad_norm": 0.22238318622112274, | |
| "learning_rate": 0.001226878612716763, | |
| "loss": 2.9146595001220703, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.03720869720772146, | |
| "grad_norm": 0.21025969088077545, | |
| "learning_rate": 0.001235549132947977, | |
| "loss": 2.892270088195801, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.03746889788749573, | |
| "grad_norm": 0.23840492963790894, | |
| "learning_rate": 0.0012442196531791908, | |
| "loss": 2.8415307998657227, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.037729098567270004, | |
| "grad_norm": 0.20167258381843567, | |
| "learning_rate": 0.0012528901734104047, | |
| "loss": 2.9031810760498047, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.037989299247044285, | |
| "grad_norm": 0.24544967710971832, | |
| "learning_rate": 0.0012615606936416184, | |
| "loss": 2.934631824493408, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.03824949992681856, | |
| "grad_norm": 0.3102674186229706, | |
| "learning_rate": 0.0012702312138728326, | |
| "loss": 2.924362897872925, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.03850970060659283, | |
| "grad_norm": 0.17447885870933533, | |
| "learning_rate": 0.0012789017341040463, | |
| "loss": 2.841254711151123, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.03876990128636711, | |
| "grad_norm": 0.26619958877563477, | |
| "learning_rate": 0.0012875722543352602, | |
| "loss": 2.873321056365967, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.03903010196614139, | |
| "grad_norm": 0.27165448665618896, | |
| "learning_rate": 0.001296242774566474, | |
| "loss": 2.942399501800537, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.03929030264591566, | |
| "grad_norm": 0.17484025657176971, | |
| "learning_rate": 0.001304913294797688, | |
| "loss": 2.8616087436676025, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.03955050332568994, | |
| "grad_norm": 0.21328718960285187, | |
| "learning_rate": 0.0013135838150289017, | |
| "loss": 2.7787179946899414, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.039810704005464215, | |
| "grad_norm": 0.21324102580547333, | |
| "learning_rate": 0.0013222543352601156, | |
| "loss": 2.8903517723083496, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.04007090468523849, | |
| "grad_norm": 0.21711313724517822, | |
| "learning_rate": 0.0013309248554913295, | |
| "loss": 2.7644217014312744, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.04033110536501277, | |
| "grad_norm": 0.2328975945711136, | |
| "learning_rate": 0.0013395953757225434, | |
| "loss": 2.868736505508423, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.04059130604478704, | |
| "grad_norm": 0.246817484498024, | |
| "learning_rate": 0.0013482658959537571, | |
| "loss": 2.910038948059082, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.040851506724561316, | |
| "grad_norm": 0.1926267296075821, | |
| "learning_rate": 0.0013569364161849712, | |
| "loss": 2.795515537261963, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.0411117074043356, | |
| "grad_norm": 0.19206106662750244, | |
| "learning_rate": 0.001365606936416185, | |
| "loss": 2.8028244972229004, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.04137190808410987, | |
| "grad_norm": 0.17958422005176544, | |
| "learning_rate": 0.0013742774566473989, | |
| "loss": 2.8207240104675293, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.041632108763884144, | |
| "grad_norm": 0.30933892726898193, | |
| "learning_rate": 0.0013829479768786128, | |
| "loss": 2.8685462474823, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.04189230944365842, | |
| "grad_norm": 0.20292924344539642, | |
| "learning_rate": 0.0013916184971098267, | |
| "loss": 2.8181519508361816, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.0421525101234327, | |
| "grad_norm": 0.27987852692604065, | |
| "learning_rate": 0.0014002890173410404, | |
| "loss": 2.791168689727783, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.04241271080320697, | |
| "grad_norm": 0.26813364028930664, | |
| "learning_rate": 0.0014089595375722543, | |
| "loss": 2.758394718170166, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.042672911482981246, | |
| "grad_norm": 0.2212570607662201, | |
| "learning_rate": 0.0014176300578034684, | |
| "loss": 2.833681583404541, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.04293311216275553, | |
| "grad_norm": 0.19662605226039886, | |
| "learning_rate": 0.001426300578034682, | |
| "loss": 2.8058218955993652, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.0431933128425298, | |
| "grad_norm": 0.29693248867988586, | |
| "learning_rate": 0.001434971098265896, | |
| "loss": 2.775289535522461, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.043453513522304074, | |
| "grad_norm": 0.19609500467777252, | |
| "learning_rate": 0.00144364161849711, | |
| "loss": 2.815795660018921, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.043713714202078355, | |
| "grad_norm": 0.21622313559055328, | |
| "learning_rate": 0.0014523121387283238, | |
| "loss": 2.8070521354675293, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.04397391488185263, | |
| "grad_norm": 0.18037623167037964, | |
| "learning_rate": 0.0014609826589595375, | |
| "loss": 2.72457218170166, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.0442341155616269, | |
| "grad_norm": 0.19943048059940338, | |
| "learning_rate": 0.0014696531791907514, | |
| "loss": 2.7480547428131104, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.04449431624140118, | |
| "grad_norm": 0.16557621955871582, | |
| "learning_rate": 0.0014783236994219654, | |
| "loss": 2.745342493057251, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.044754516921175456, | |
| "grad_norm": 0.17805889248847961, | |
| "learning_rate": 0.0014869942196531793, | |
| "loss": 2.753793239593506, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.04501471760094973, | |
| "grad_norm": 0.23548759520053864, | |
| "learning_rate": 0.001495664739884393, | |
| "loss": 2.8414790630340576, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.04527491828072401, | |
| "grad_norm": 0.1648837774991989, | |
| "learning_rate": 0.0015, | |
| "loss": 2.7620575428009033, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.045535118960498285, | |
| "grad_norm": 0.16259492933750153, | |
| "learning_rate": 0.0015, | |
| "loss": 2.7154746055603027, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.04579531964027256, | |
| "grad_norm": 0.17988084256649017, | |
| "learning_rate": 0.0015, | |
| "loss": 2.700965404510498, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.04605552032004684, | |
| "grad_norm": 0.16477294266223907, | |
| "learning_rate": 0.0015, | |
| "loss": 2.755967140197754, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.04631572099982111, | |
| "grad_norm": 0.21754054725170135, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6964268684387207, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.046575921679595386, | |
| "grad_norm": 0.1506672352552414, | |
| "learning_rate": 0.0015, | |
| "loss": 2.794830322265625, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.04683612235936967, | |
| "grad_norm": 0.1614987701177597, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6898601055145264, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.04709632303914394, | |
| "grad_norm": 0.18936215341091156, | |
| "learning_rate": 0.0015, | |
| "loss": 2.647334575653076, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.047356523718918214, | |
| "grad_norm": 0.20592817664146423, | |
| "learning_rate": 0.0015, | |
| "loss": 2.7215371131896973, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.047616724398692495, | |
| "grad_norm": 0.1782323271036148, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6734256744384766, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.04787692507846677, | |
| "grad_norm": 0.15602196753025055, | |
| "learning_rate": 0.0015, | |
| "loss": 2.667567729949951, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.04813712575824104, | |
| "grad_norm": 0.14590057730674744, | |
| "learning_rate": 0.0015, | |
| "loss": 2.7369422912597656, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.048397326438015316, | |
| "grad_norm": 0.16776956617832184, | |
| "learning_rate": 0.0015, | |
| "loss": 2.715961217880249, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.0486575271177896, | |
| "grad_norm": 0.13588234782218933, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6299777030944824, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.04891772779756387, | |
| "grad_norm": 0.19670580327510834, | |
| "learning_rate": 0.0015, | |
| "loss": 2.7056634426116943, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.049177928477338144, | |
| "grad_norm": 0.16066035628318787, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6497952938079834, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.049438129157112425, | |
| "grad_norm": 0.18578185141086578, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6196389198303223, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.0496983298368867, | |
| "grad_norm": 0.1641508936882019, | |
| "learning_rate": 0.0015, | |
| "loss": 2.64473819732666, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.04995853051666097, | |
| "grad_norm": 0.15967334806919098, | |
| "learning_rate": 0.0015, | |
| "loss": 2.610323905944824, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.05021873119643525, | |
| "grad_norm": 0.19882506132125854, | |
| "learning_rate": 0.0015, | |
| "loss": 2.580444574356079, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.050478931876209526, | |
| "grad_norm": 0.15675006806850433, | |
| "learning_rate": 0.0015, | |
| "loss": 2.666419267654419, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.0507391325559838, | |
| "grad_norm": 0.16099196672439575, | |
| "learning_rate": 0.0015, | |
| "loss": 2.681671619415283, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.05099933323575808, | |
| "grad_norm": 0.15766847133636475, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6991372108459473, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.051259533915532354, | |
| "grad_norm": 0.1549822986125946, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6909019947052, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.05151973459530663, | |
| "grad_norm": 0.17178906500339508, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6943092346191406, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.05177993527508091, | |
| "grad_norm": 0.15122868120670319, | |
| "learning_rate": 0.0015, | |
| "loss": 2.669128894805908, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.05204013595485518, | |
| "grad_norm": 0.13485313951969147, | |
| "learning_rate": 0.0015, | |
| "loss": 2.550992488861084, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.052300336634629456, | |
| "grad_norm": 0.13008184731006622, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6252386569976807, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.05256053731440374, | |
| "grad_norm": 0.1430431306362152, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6614580154418945, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.05282073799417801, | |
| "grad_norm": 0.15184569358825684, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5884804725646973, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.053080938673952284, | |
| "grad_norm": 0.15028434991836548, | |
| "learning_rate": 0.0015, | |
| "loss": 2.534207344055176, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.053341139353726565, | |
| "grad_norm": 0.1342860609292984, | |
| "learning_rate": 0.0015, | |
| "loss": 2.650566816329956, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.05360134003350084, | |
| "grad_norm": 0.14909809827804565, | |
| "learning_rate": 0.0015, | |
| "loss": 2.575770616531372, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.05386154071327511, | |
| "grad_norm": 0.1467573493719101, | |
| "learning_rate": 0.0015, | |
| "loss": 2.600891590118408, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.05412174139304939, | |
| "grad_norm": 0.14627805352210999, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6327264308929443, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.054381942072823666, | |
| "grad_norm": 0.11908523738384247, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6035282611846924, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.05464214275259794, | |
| "grad_norm": 0.16153444349765778, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6083431243896484, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.054902343432372214, | |
| "grad_norm": 0.12157187610864639, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6335573196411133, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.055162544112146494, | |
| "grad_norm": 0.12891489267349243, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6342296600341797, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.05542274479192077, | |
| "grad_norm": 0.1658623218536377, | |
| "learning_rate": 0.0015, | |
| "loss": 2.620544672012329, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.05568294547169504, | |
| "grad_norm": 0.14805150032043457, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6231179237365723, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.05594314615146932, | |
| "grad_norm": 0.12362580001354218, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6189422607421875, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.056203346831243596, | |
| "grad_norm": 0.14824257791042328, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5241830348968506, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.05646354751101787, | |
| "grad_norm": 0.11885982751846313, | |
| "learning_rate": 0.0015, | |
| "loss": 2.666518211364746, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.05672374819079215, | |
| "grad_norm": 0.12434994429349899, | |
| "learning_rate": 0.0015, | |
| "loss": 2.630044460296631, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.056983948870566424, | |
| "grad_norm": 0.13915260136127472, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5746140480041504, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.0572441495503407, | |
| "grad_norm": 0.1307705193758011, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5896520614624023, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.05750435023011498, | |
| "grad_norm": 0.14974114298820496, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6500778198242188, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.05776455090988925, | |
| "grad_norm": 0.19642087817192078, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6607859134674072, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.058024751589663526, | |
| "grad_norm": 0.1154959574341774, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5340981483459473, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.058284952269437806, | |
| "grad_norm": 0.14795628190040588, | |
| "learning_rate": 0.0015, | |
| "loss": 2.624563217163086, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.05854515294921208, | |
| "grad_norm": 0.1298312097787857, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5719261169433594, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.058805353628986354, | |
| "grad_norm": 0.14340487122535706, | |
| "learning_rate": 0.0015, | |
| "loss": 2.672295331954956, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.059065554308760634, | |
| "grad_norm": 0.12575502693653107, | |
| "learning_rate": 0.0015, | |
| "loss": 2.549506187438965, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.05932575498853491, | |
| "grad_norm": 0.14216049015522003, | |
| "learning_rate": 0.0015, | |
| "loss": 2.578552722930908, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.05958595566830918, | |
| "grad_norm": 0.15293440222740173, | |
| "learning_rate": 0.0015, | |
| "loss": 2.574181079864502, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.05984615634808346, | |
| "grad_norm": 0.1480940878391266, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6374359130859375, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.060106357027857736, | |
| "grad_norm": 0.1261841058731079, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5781521797180176, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.06036655770763201, | |
| "grad_norm": 0.14029991626739502, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5884461402893066, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.06062675838740629, | |
| "grad_norm": 0.12325909733772278, | |
| "learning_rate": 0.0015, | |
| "loss": 2.495574474334717, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.060886959067180564, | |
| "grad_norm": 0.11361188441514969, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4616265296936035, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.06114715974695484, | |
| "grad_norm": 0.18037493526935577, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6190497875213623, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.06140736042672911, | |
| "grad_norm": 0.12276580929756165, | |
| "learning_rate": 0.0015, | |
| "loss": 2.635545253753662, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.06166756110650339, | |
| "grad_norm": 0.13119857013225555, | |
| "learning_rate": 0.0015, | |
| "loss": 2.639622688293457, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.061927761786277666, | |
| "grad_norm": 0.2235397845506668, | |
| "learning_rate": 0.0015, | |
| "loss": 2.612959146499634, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.06218796246605194, | |
| "grad_norm": 0.137590229511261, | |
| "learning_rate": 0.0015, | |
| "loss": 2.549914836883545, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.06244816314582622, | |
| "grad_norm": 0.12429803609848022, | |
| "learning_rate": 0.0015, | |
| "loss": 2.582479476928711, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.0627083638256005, | |
| "grad_norm": 0.12502647936344147, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5637917518615723, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.06296856450537477, | |
| "grad_norm": 0.12629607319831848, | |
| "learning_rate": 0.0015, | |
| "loss": 2.54638671875, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.06322876518514904, | |
| "grad_norm": 0.14317424595355988, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5885047912597656, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.06348896586492332, | |
| "grad_norm": 0.20382775366306305, | |
| "learning_rate": 0.0015, | |
| "loss": 2.593700885772705, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.0637491665446976, | |
| "grad_norm": 0.11687522381544113, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5666115283966064, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.06400936722447187, | |
| "grad_norm": 0.183576762676239, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6373448371887207, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.06426956790424615, | |
| "grad_norm": 0.13087429106235504, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5889272689819336, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.06452976858402043, | |
| "grad_norm": 0.23603849112987518, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5812132358551025, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.0647899692637947, | |
| "grad_norm": 0.13527603447437286, | |
| "learning_rate": 0.0015, | |
| "loss": 2.565682888031006, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.06505016994356898, | |
| "grad_norm": 0.14632058143615723, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5053577423095703, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.06531037062334326, | |
| "grad_norm": 0.14276352524757385, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6023128032684326, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 0.06557057130311753, | |
| "grad_norm": 0.14910876750946045, | |
| "learning_rate": 0.0015, | |
| "loss": 2.53865122795105, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.0658307719828918, | |
| "grad_norm": 0.198433518409729, | |
| "learning_rate": 0.0015, | |
| "loss": 2.635589122772217, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 0.06609097266266609, | |
| "grad_norm": 0.1372203230857849, | |
| "learning_rate": 0.0015, | |
| "loss": 2.589325428009033, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 0.06635117334244035, | |
| "grad_norm": 0.18355733156204224, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5791945457458496, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.06661137402221463, | |
| "grad_norm": 0.11787902563810349, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6067702770233154, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 0.06687157470198891, | |
| "grad_norm": 0.20993410050868988, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5679943561553955, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 0.06713177538176318, | |
| "grad_norm": 0.1326153427362442, | |
| "learning_rate": 0.0015, | |
| "loss": 2.592912197113037, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.06739197606153746, | |
| "grad_norm": 0.15812049806118011, | |
| "learning_rate": 0.0015, | |
| "loss": 2.583249092102051, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.06765217674131174, | |
| "grad_norm": 0.22075560688972473, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6351144313812256, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.06791237742108601, | |
| "grad_norm": 0.16961787641048431, | |
| "learning_rate": 0.0015, | |
| "loss": 2.545294761657715, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 0.06817257810086029, | |
| "grad_norm": 0.18332639336585999, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6261959075927734, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 0.06843277878063457, | |
| "grad_norm": 0.1242636889219284, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4783449172973633, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 0.06869297946040884, | |
| "grad_norm": 0.11733566224575043, | |
| "learning_rate": 0.0015, | |
| "loss": 2.513880491256714, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 0.06895318014018312, | |
| "grad_norm": 0.14355388283729553, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5490798950195312, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.0692133808199574, | |
| "grad_norm": 0.1932661086320877, | |
| "learning_rate": 0.0015, | |
| "loss": 2.552743911743164, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.06947358149973167, | |
| "grad_norm": 0.12102755159139633, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5844340324401855, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.06973378217950595, | |
| "grad_norm": 0.1957508772611618, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4969468116760254, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 0.06999398285928023, | |
| "grad_norm": 0.13205446302890778, | |
| "learning_rate": 0.0015, | |
| "loss": 2.540651798248291, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 0.0702541835390545, | |
| "grad_norm": 0.19254012405872345, | |
| "learning_rate": 0.0015, | |
| "loss": 2.537437915802002, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.07051438421882877, | |
| "grad_norm": 0.12356755137443542, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5964531898498535, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 0.07077458489860304, | |
| "grad_norm": 0.11281155794858932, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5733652114868164, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 0.07103478557837732, | |
| "grad_norm": 0.1333414912223816, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5084149837493896, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.0712949862581516, | |
| "grad_norm": 0.19750361144542694, | |
| "learning_rate": 0.0015, | |
| "loss": 2.58596134185791, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 0.07155518693792587, | |
| "grad_norm": 0.11615125089883804, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4791383743286133, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.07181538761770015, | |
| "grad_norm": 0.23385246098041534, | |
| "learning_rate": 0.0015, | |
| "loss": 2.50321102142334, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 0.07207558829747443, | |
| "grad_norm": 0.17493095993995667, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6158947944641113, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 0.0723357889772487, | |
| "grad_norm": 0.1401086300611496, | |
| "learning_rate": 0.0015, | |
| "loss": 2.517688274383545, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 0.07259598965702298, | |
| "grad_norm": 0.2651103734970093, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4191396236419678, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.07285619033679726, | |
| "grad_norm": 0.1722913384437561, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5673346519470215, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.07311639101657152, | |
| "grad_norm": 0.12414658069610596, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6212687492370605, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 0.0733765916963458, | |
| "grad_norm": 0.12208303064107895, | |
| "learning_rate": 0.0015, | |
| "loss": 2.546102523803711, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 0.07363679237612009, | |
| "grad_norm": 0.18498128652572632, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5047688484191895, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 0.07389699305589435, | |
| "grad_norm": 0.11353137344121933, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6000404357910156, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 0.07415719373566863, | |
| "grad_norm": 0.11640340089797974, | |
| "learning_rate": 0.0015, | |
| "loss": 2.562701940536499, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.07441739441544291, | |
| "grad_norm": 0.16006167232990265, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5445828437805176, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.07467759509521718, | |
| "grad_norm": 0.12379810959100723, | |
| "learning_rate": 0.0015, | |
| "loss": 2.532503128051758, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 0.07493779577499146, | |
| "grad_norm": 0.20058363676071167, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4340412616729736, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 0.07519799645476574, | |
| "grad_norm": 0.14642098546028137, | |
| "learning_rate": 0.0015, | |
| "loss": 2.502790689468384, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 0.07545819713454001, | |
| "grad_norm": 0.14208285510540009, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6028313636779785, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.07571839781431429, | |
| "grad_norm": 0.16576264798641205, | |
| "learning_rate": 0.0015, | |
| "loss": 2.590580463409424, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.07597859849408857, | |
| "grad_norm": 0.1109340563416481, | |
| "learning_rate": 0.0015, | |
| "loss": 2.454275608062744, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 0.07623879917386284, | |
| "grad_norm": 0.11368656903505325, | |
| "learning_rate": 0.0015, | |
| "loss": 2.559783935546875, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 0.07649899985363712, | |
| "grad_norm": 0.18466179072856903, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5907435417175293, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.0767592005334114, | |
| "grad_norm": 0.15122883021831512, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5490379333496094, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.07701940121318566, | |
| "grad_norm": 0.1400233656167984, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5655360221862793, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 0.07727960189295995, | |
| "grad_norm": 0.12041738629341125, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5855493545532227, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 0.07753980257273423, | |
| "grad_norm": 0.11596609652042389, | |
| "learning_rate": 0.0015, | |
| "loss": 2.538209915161133, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 0.07780000325250849, | |
| "grad_norm": 0.11742275953292847, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4697577953338623, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 0.07806020393228277, | |
| "grad_norm": 0.1307411640882492, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5475921630859375, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.07832040461205705, | |
| "grad_norm": 0.12216457724571228, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4666059017181396, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.07858060529183132, | |
| "grad_norm": 0.1410822570323944, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5005970001220703, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 0.0788408059716056, | |
| "grad_norm": 0.12861311435699463, | |
| "learning_rate": 0.0015, | |
| "loss": 2.554330825805664, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 0.07910100665137988, | |
| "grad_norm": 0.13337506353855133, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5301127433776855, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 0.07936120733115415, | |
| "grad_norm": 0.15406863391399384, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5119733810424805, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.07962140801092843, | |
| "grad_norm": 0.17507420480251312, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5119690895080566, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 0.07988160869070271, | |
| "grad_norm": 0.11584312468767166, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5782370567321777, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 0.08014180937047698, | |
| "grad_norm": 0.14256927371025085, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5322585105895996, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 0.08040201005025126, | |
| "grad_norm": 0.16758249700069427, | |
| "learning_rate": 0.0015, | |
| "loss": 2.575878143310547, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 0.08066221073002554, | |
| "grad_norm": 0.13935622572898865, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5629076957702637, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.0809224114097998, | |
| "grad_norm": 0.12993550300598145, | |
| "learning_rate": 0.0015, | |
| "loss": 2.503211259841919, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 0.08118261208957409, | |
| "grad_norm": 0.15919028222560883, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6716480255126953, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.08144281276934837, | |
| "grad_norm": 0.11908809095621109, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5645601749420166, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 0.08170301344912263, | |
| "grad_norm": 0.11332940310239792, | |
| "learning_rate": 0.0015, | |
| "loss": 2.548771619796753, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 0.08196321412889691, | |
| "grad_norm": 0.1313566267490387, | |
| "learning_rate": 0.0015, | |
| "loss": 2.6182522773742676, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.0822234148086712, | |
| "grad_norm": 0.12268718332052231, | |
| "learning_rate": 0.0015, | |
| "loss": 2.489835262298584, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 0.08248361548844546, | |
| "grad_norm": 0.12420812249183655, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5113680362701416, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 0.08274381616821974, | |
| "grad_norm": 0.13908511400222778, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5134804248809814, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 0.08300401684799402, | |
| "grad_norm": 0.14693544805049896, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5647387504577637, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 0.08326421752776829, | |
| "grad_norm": 0.13369478285312653, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5393519401550293, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.08352441820754257, | |
| "grad_norm": 0.13182099163532257, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4621944427490234, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 0.08378461888731684, | |
| "grad_norm": 0.16078202426433563, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4677064418792725, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 0.08404481956709112, | |
| "grad_norm": 0.18532077968120575, | |
| "learning_rate": 0.0015, | |
| "loss": 2.477581739425659, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 0.0843050202468654, | |
| "grad_norm": 0.10907570272684097, | |
| "learning_rate": 0.0015, | |
| "loss": 2.524442672729492, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 0.08456522092663966, | |
| "grad_norm": 0.14104482531547546, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4496612548828125, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.08482542160641394, | |
| "grad_norm": 0.14776431024074554, | |
| "learning_rate": 0.0015, | |
| "loss": 2.530264377593994, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 0.08508562228618823, | |
| "grad_norm": 0.13904069364070892, | |
| "learning_rate": 0.0015, | |
| "loss": 2.604109287261963, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 0.08534582296596249, | |
| "grad_norm": 0.14588233828544617, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4963693618774414, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 0.08560602364573677, | |
| "grad_norm": 0.15345178544521332, | |
| "learning_rate": 0.0015, | |
| "loss": 2.531615734100342, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 0.08586622432551105, | |
| "grad_norm": 0.15590955317020416, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4773566722869873, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.08612642500528532, | |
| "grad_norm": 0.24131813645362854, | |
| "learning_rate": 0.0015, | |
| "loss": 2.534609317779541, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 0.0863866256850596, | |
| "grad_norm": 0.13829457759857178, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4890403747558594, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 0.08664682636483388, | |
| "grad_norm": 0.2665689289569855, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5261645317077637, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 0.08690702704460815, | |
| "grad_norm": 0.12278895080089569, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4704575538635254, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 0.08716722772438243, | |
| "grad_norm": 0.1457744985818863, | |
| "learning_rate": 0.0015, | |
| "loss": 2.527120590209961, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.08742742840415671, | |
| "grad_norm": 0.18936526775360107, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5764763355255127, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 0.08768762908393098, | |
| "grad_norm": 0.16044090688228607, | |
| "learning_rate": 0.0015, | |
| "loss": 2.557800531387329, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 0.08794782976370526, | |
| "grad_norm": 0.11910203844308853, | |
| "learning_rate": 0.0015, | |
| "loss": 2.515000820159912, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.08820803044347954, | |
| "grad_norm": 0.1980702430009842, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4426794052124023, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 0.0884682311232538, | |
| "grad_norm": 0.2644166052341461, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5487544536590576, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.08872843180302808, | |
| "grad_norm": 0.12081696093082428, | |
| "learning_rate": 0.0015, | |
| "loss": 2.489809036254883, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 0.08898863248280237, | |
| "grad_norm": 0.20768149197101593, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4334044456481934, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 0.08924883316257663, | |
| "grad_norm": 0.1605047881603241, | |
| "learning_rate": 0.0015, | |
| "loss": 2.412212371826172, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 0.08950903384235091, | |
| "grad_norm": 0.1852238029241562, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5724077224731445, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 0.0897692345221252, | |
| "grad_norm": 0.14606717228889465, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5150301456451416, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.09002943520189946, | |
| "grad_norm": 0.1127178892493248, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5333385467529297, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 0.09028963588167374, | |
| "grad_norm": 0.13244138658046722, | |
| "learning_rate": 0.0015, | |
| "loss": 2.506751537322998, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 0.09054983656144802, | |
| "grad_norm": 0.11649299412965775, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4993643760681152, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 0.09081003724122229, | |
| "grad_norm": 0.11965850740671158, | |
| "learning_rate": 0.0015, | |
| "loss": 2.530313491821289, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 0.09107023792099657, | |
| "grad_norm": 0.13063354790210724, | |
| "learning_rate": 0.0015, | |
| "loss": 2.541741371154785, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.09133043860077085, | |
| "grad_norm": 0.1462620198726654, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5551137924194336, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 0.09159063928054512, | |
| "grad_norm": 0.13256198167800903, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4662652015686035, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 0.0918508399603194, | |
| "grad_norm": 0.15502355992794037, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5150249004364014, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 0.09211104064009368, | |
| "grad_norm": 0.18196983635425568, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4843883514404297, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 0.09237124131986794, | |
| "grad_norm": 0.14866191148757935, | |
| "learning_rate": 0.0015, | |
| "loss": 2.496154308319092, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.09263144199964223, | |
| "grad_norm": 0.11658824980258942, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4449501037597656, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 0.0928916426794165, | |
| "grad_norm": 0.1440459042787552, | |
| "learning_rate": 0.0015, | |
| "loss": 2.490208625793457, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 0.09315184335919077, | |
| "grad_norm": 0.19502736628055573, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5548291206359863, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 0.09341204403896505, | |
| "grad_norm": 0.1289069652557373, | |
| "learning_rate": 0.0015, | |
| "loss": 2.445272445678711, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 0.09367224471873933, | |
| "grad_norm": 0.11711007356643677, | |
| "learning_rate": 0.0015, | |
| "loss": 2.469451427459717, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.0939324453985136, | |
| "grad_norm": 0.12621375918388367, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5695018768310547, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 0.09419264607828788, | |
| "grad_norm": 0.14285998046398163, | |
| "learning_rate": 0.0015, | |
| "loss": 2.477400302886963, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 0.09445284675806216, | |
| "grad_norm": 0.1324525624513626, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4934685230255127, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 0.09471304743783643, | |
| "grad_norm": 0.10702130198478699, | |
| "learning_rate": 0.0015, | |
| "loss": 2.478593349456787, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.09497324811761071, | |
| "grad_norm": 0.12025975435972214, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4158713817596436, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.09523344879738499, | |
| "grad_norm": 0.11236289143562317, | |
| "learning_rate": 0.0015, | |
| "loss": 2.529749870300293, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 0.09549364947715926, | |
| "grad_norm": 0.12934474647045135, | |
| "learning_rate": 0.0015, | |
| "loss": 2.531521797180176, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 0.09575385015693354, | |
| "grad_norm": 0.11176446080207825, | |
| "learning_rate": 0.0015, | |
| "loss": 2.436703681945801, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 0.09601405083670782, | |
| "grad_norm": 0.15079233050346375, | |
| "learning_rate": 0.0015, | |
| "loss": 2.425929069519043, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 0.09627425151648208, | |
| "grad_norm": 0.11708604544401169, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4982924461364746, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.09653445219625637, | |
| "grad_norm": 0.14889422059059143, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5074567794799805, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 0.09679465287603063, | |
| "grad_norm": 0.1744641363620758, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4625606536865234, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 0.09705485355580491, | |
| "grad_norm": 0.10757909715175629, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4002695083618164, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 0.0973150542355792, | |
| "grad_norm": 0.19156695902347565, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5078234672546387, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 0.09757525491535346, | |
| "grad_norm": 0.13070686161518097, | |
| "learning_rate": 0.0015, | |
| "loss": 2.481682777404785, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.09783545559512774, | |
| "grad_norm": 0.1559971421957016, | |
| "learning_rate": 0.0015, | |
| "loss": 2.483724594116211, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 0.09809565627490202, | |
| "grad_norm": 0.10168272256851196, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4188013076782227, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 0.09835585695467629, | |
| "grad_norm": 0.17042742669582367, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4481377601623535, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 0.09861605763445057, | |
| "grad_norm": 0.12191086262464523, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4696085453033447, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 0.09887625831422485, | |
| "grad_norm": 0.18985164165496826, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5029356479644775, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.09913645899399912, | |
| "grad_norm": 0.12053395062685013, | |
| "learning_rate": 0.0015, | |
| "loss": 2.471561908721924, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 0.0993966596737734, | |
| "grad_norm": 0.11260586231946945, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4876153469085693, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 0.09965686035354768, | |
| "grad_norm": 0.10991669446229935, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4546608924865723, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 0.09991706103332194, | |
| "grad_norm": 0.13373911380767822, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4511330127716064, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 0.10017726171309622, | |
| "grad_norm": 0.09733694046735764, | |
| "learning_rate": 0.0015, | |
| "loss": 2.398179292678833, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.1004374623928705, | |
| "grad_norm": 0.13615287840366364, | |
| "learning_rate": 0.0015, | |
| "loss": 2.476090908050537, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 0.10069766307264477, | |
| "grad_norm": 0.12906911969184875, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5038747787475586, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 0.10095786375241905, | |
| "grad_norm": 0.19029171764850616, | |
| "learning_rate": 0.0015, | |
| "loss": 2.515749454498291, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 0.10121806443219333, | |
| "grad_norm": 0.13701385259628296, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5420799255371094, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 0.1014782651119676, | |
| "grad_norm": 0.13473469018936157, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5171680450439453, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.10173846579174188, | |
| "grad_norm": 0.12206988036632538, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5140299797058105, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 0.10199866647151616, | |
| "grad_norm": 0.16678650677204132, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5734801292419434, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 0.10225886715129043, | |
| "grad_norm": 0.11919064074754715, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3694310188293457, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 0.10251906783106471, | |
| "grad_norm": 0.11366023868322372, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4591619968414307, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 0.10277926851083899, | |
| "grad_norm": 0.12312934547662735, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5185508728027344, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.10303946919061326, | |
| "grad_norm": 0.1520123928785324, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5622916221618652, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 0.10329966987038754, | |
| "grad_norm": 0.1643320620059967, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4844510555267334, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 0.10355987055016182, | |
| "grad_norm": 0.11246604472398758, | |
| "learning_rate": 0.0015, | |
| "loss": 2.424683094024658, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 0.10382007122993608, | |
| "grad_norm": 0.1600845605134964, | |
| "learning_rate": 0.0015, | |
| "loss": 2.467665672302246, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 0.10408027190971036, | |
| "grad_norm": 0.11838793009519577, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5429134368896484, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.10434047258948465, | |
| "grad_norm": 0.11583756655454636, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4626121520996094, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 0.10460067326925891, | |
| "grad_norm": 0.11499626189470291, | |
| "learning_rate": 0.0015, | |
| "loss": 2.497128486633301, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 0.10486087394903319, | |
| "grad_norm": 0.2323618233203888, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4246530532836914, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 0.10512107462880747, | |
| "grad_norm": 0.1438981145620346, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5071704387664795, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 0.10538127530858174, | |
| "grad_norm": 0.11748737841844559, | |
| "learning_rate": 0.0015, | |
| "loss": 2.476731300354004, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.10564147598835602, | |
| "grad_norm": 0.19243799149990082, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5406248569488525, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 0.1059016766681303, | |
| "grad_norm": 0.11459548771381378, | |
| "learning_rate": 0.0015, | |
| "loss": 2.415768623352051, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 0.10616187734790457, | |
| "grad_norm": 0.22774600982666016, | |
| "learning_rate": 0.0015, | |
| "loss": 2.455199718475342, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 0.10642207802767885, | |
| "grad_norm": 0.11443344503641129, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5359983444213867, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 0.10668227870745313, | |
| "grad_norm": 0.1261078417301178, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4155945777893066, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.1069424793872274, | |
| "grad_norm": 0.1700322926044464, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5150909423828125, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 0.10720268006700168, | |
| "grad_norm": 0.11378102749586105, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4695568084716797, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 0.10746288074677596, | |
| "grad_norm": 0.13540437817573547, | |
| "learning_rate": 0.0015, | |
| "loss": 2.515244960784912, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 0.10772308142655022, | |
| "grad_norm": 0.11232029646635056, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4454617500305176, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 0.1079832821063245, | |
| "grad_norm": 0.1433100700378418, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4610981941223145, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.10824348278609879, | |
| "grad_norm": 0.14747196435928345, | |
| "learning_rate": 0.0015, | |
| "loss": 2.512965440750122, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 0.10850368346587305, | |
| "grad_norm": 0.11969432234764099, | |
| "learning_rate": 0.0015, | |
| "loss": 2.528841018676758, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 0.10876388414564733, | |
| "grad_norm": 0.12883418798446655, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5040335655212402, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 0.10902408482542161, | |
| "grad_norm": 0.19044166803359985, | |
| "learning_rate": 0.0015, | |
| "loss": 2.478750228881836, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 0.10928428550519588, | |
| "grad_norm": 0.15454842150211334, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4856419563293457, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.10954448618497016, | |
| "grad_norm": 0.11819291859865189, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4163312911987305, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 0.10980468686474443, | |
| "grad_norm": 0.1892247349023819, | |
| "learning_rate": 0.0015, | |
| "loss": 2.396820545196533, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 0.11006488754451871, | |
| "grad_norm": 0.19431066513061523, | |
| "learning_rate": 0.0015, | |
| "loss": 2.537531614303589, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 0.11032508822429299, | |
| "grad_norm": 0.15151803195476532, | |
| "learning_rate": 0.0015, | |
| "loss": 2.440938949584961, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 0.11058528890406726, | |
| "grad_norm": 0.13907906413078308, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5495567321777344, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.11084548958384154, | |
| "grad_norm": 0.13976429402828217, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4400763511657715, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 0.11110569026361582, | |
| "grad_norm": 0.1101430281996727, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5156853199005127, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 0.11136589094339008, | |
| "grad_norm": 0.2034296840429306, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4110891819000244, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 0.11162609162316436, | |
| "grad_norm": 0.21087896823883057, | |
| "learning_rate": 0.0015, | |
| "loss": 2.423288583755493, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 0.11188629230293864, | |
| "grad_norm": 0.15142200887203217, | |
| "learning_rate": 0.0015, | |
| "loss": 2.473625659942627, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.11214649298271291, | |
| "grad_norm": 0.11025089025497437, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4484028816223145, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 0.11240669366248719, | |
| "grad_norm": 0.1491570919752121, | |
| "learning_rate": 0.0015, | |
| "loss": 2.505532741546631, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 0.11266689434226147, | |
| "grad_norm": 0.11216303706169128, | |
| "learning_rate": 0.0015, | |
| "loss": 2.548219680786133, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 0.11292709502203574, | |
| "grad_norm": 0.11430005729198456, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4133553504943848, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 0.11318729570181002, | |
| "grad_norm": 0.18291090428829193, | |
| "learning_rate": 0.0015, | |
| "loss": 2.507143497467041, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.1134474963815843, | |
| "grad_norm": 0.1979239135980606, | |
| "learning_rate": 0.0015, | |
| "loss": 2.412238359451294, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 0.11370769706135857, | |
| "grad_norm": 0.13865049183368683, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4398233890533447, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 0.11396789774113285, | |
| "grad_norm": 0.19918091595172882, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4988279342651367, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 0.11422809842090713, | |
| "grad_norm": 0.11325831711292267, | |
| "learning_rate": 0.0015, | |
| "loss": 2.494500160217285, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 0.1144882991006814, | |
| "grad_norm": 0.14829902350902557, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5095462799072266, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.11474849978045568, | |
| "grad_norm": 0.21892991662025452, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4745447635650635, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 0.11500870046022996, | |
| "grad_norm": 0.11891723424196243, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5164599418640137, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 0.11526890114000422, | |
| "grad_norm": 0.14889734983444214, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4883475303649902, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 0.1155291018197785, | |
| "grad_norm": 0.1462695151567459, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4669761657714844, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 0.11578930249955278, | |
| "grad_norm": 0.1408451497554779, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4396119117736816, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.11604950317932705, | |
| "grad_norm": 0.104103684425354, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4268996715545654, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 0.11630970385910133, | |
| "grad_norm": 0.1391294002532959, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3986964225769043, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 0.11656990453887561, | |
| "grad_norm": 0.16641506552696228, | |
| "learning_rate": 0.0015, | |
| "loss": 2.48289155960083, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 0.11683010521864988, | |
| "grad_norm": 0.14706654846668243, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5131571292877197, | |
| "step": 898 | |
| }, | |
| { | |
| "epoch": 0.11709030589842416, | |
| "grad_norm": 0.14331388473510742, | |
| "learning_rate": 0.0015, | |
| "loss": 2.481987714767456, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.11735050657819844, | |
| "grad_norm": 0.1329609900712967, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5684447288513184, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 0.11761070725797271, | |
| "grad_norm": 0.10474152863025665, | |
| "learning_rate": 0.0015, | |
| "loss": 2.496450424194336, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 0.11787090793774699, | |
| "grad_norm": 0.11489632725715637, | |
| "learning_rate": 0.0015, | |
| "loss": 2.486365556716919, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 0.11813110861752127, | |
| "grad_norm": 0.11455623060464859, | |
| "learning_rate": 0.0015, | |
| "loss": 2.392237901687622, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 0.11839130929729554, | |
| "grad_norm": 0.12375067919492722, | |
| "learning_rate": 0.0015, | |
| "loss": 2.416073799133301, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.11865150997706982, | |
| "grad_norm": 0.10999967157840729, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4682672023773193, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 0.1189117106568441, | |
| "grad_norm": 0.1222982406616211, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4839866161346436, | |
| "step": 914 | |
| }, | |
| { | |
| "epoch": 0.11917191133661836, | |
| "grad_norm": 0.13484585285186768, | |
| "learning_rate": 0.0015, | |
| "loss": 2.488656997680664, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 0.11943211201639264, | |
| "grad_norm": 0.10286282002925873, | |
| "learning_rate": 0.0015, | |
| "loss": 2.525235652923584, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 0.11969231269616692, | |
| "grad_norm": 0.11514491587877274, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5040040016174316, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.11995251337594119, | |
| "grad_norm": 0.12345292419195175, | |
| "learning_rate": 0.0015, | |
| "loss": 2.459651231765747, | |
| "step": 922 | |
| }, | |
| { | |
| "epoch": 0.12021271405571547, | |
| "grad_norm": 0.1070815771818161, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4803178310394287, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 0.12047291473548975, | |
| "grad_norm": 0.10990746319293976, | |
| "learning_rate": 0.0015, | |
| "loss": 2.457594394683838, | |
| "step": 926 | |
| }, | |
| { | |
| "epoch": 0.12073311541526402, | |
| "grad_norm": 0.13413861393928528, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4468042850494385, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 0.1209933160950383, | |
| "grad_norm": 0.11186478286981583, | |
| "learning_rate": 0.0015, | |
| "loss": 2.442903518676758, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.12125351677481258, | |
| "grad_norm": 0.12038417905569077, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3339438438415527, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 0.12151371745458685, | |
| "grad_norm": 0.17366178333759308, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4548568725585938, | |
| "step": 934 | |
| }, | |
| { | |
| "epoch": 0.12177391813436113, | |
| "grad_norm": 0.11260256916284561, | |
| "learning_rate": 0.0015, | |
| "loss": 2.439826250076294, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 0.12203411881413541, | |
| "grad_norm": 0.16781844198703766, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4350109100341797, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 0.12229431949390968, | |
| "grad_norm": 0.14944791793823242, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4554519653320312, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.12255452017368396, | |
| "grad_norm": 0.12105905264616013, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4930989742279053, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 0.12281472085345822, | |
| "grad_norm": 0.24054458737373352, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5314407348632812, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 0.1230749215332325, | |
| "grad_norm": 0.11755185574293137, | |
| "learning_rate": 0.0015, | |
| "loss": 2.433711051940918, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 0.12333512221300678, | |
| "grad_norm": 0.2742673456668854, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4475271701812744, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 0.12359532289278105, | |
| "grad_norm": 0.2013305127620697, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4712271690368652, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.12385552357255533, | |
| "grad_norm": 0.1352348029613495, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4669923782348633, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 0.12411572425232961, | |
| "grad_norm": 0.2573494017124176, | |
| "learning_rate": 0.0015, | |
| "loss": 2.403353214263916, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 0.12437592493210388, | |
| "grad_norm": 0.22976142168045044, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4728734493255615, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 0.12463612561187816, | |
| "grad_norm": 0.12941211462020874, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4981071949005127, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 0.12489632629165244, | |
| "grad_norm": 0.15471619367599487, | |
| "learning_rate": 0.0015, | |
| "loss": 2.483341693878174, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.1251565269714267, | |
| "grad_norm": 0.20464009046554565, | |
| "learning_rate": 0.0015, | |
| "loss": 2.348433017730713, | |
| "step": 962 | |
| }, | |
| { | |
| "epoch": 0.125416727651201, | |
| "grad_norm": 0.12188667058944702, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4026639461517334, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 0.12567692833097527, | |
| "grad_norm": 0.18323232233524323, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5070765018463135, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 0.12593712901074955, | |
| "grad_norm": 0.16702760756015778, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4475314617156982, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 0.12619732969052383, | |
| "grad_norm": 0.10072800517082214, | |
| "learning_rate": 0.0015, | |
| "loss": 2.398653030395508, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.12645753037029808, | |
| "grad_norm": 0.11068949848413467, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5137791633605957, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 0.12671773105007236, | |
| "grad_norm": 0.11984645575284958, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3543200492858887, | |
| "step": 974 | |
| }, | |
| { | |
| "epoch": 0.12697793172984664, | |
| "grad_norm": 0.1345328390598297, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5010509490966797, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 0.12723813240962092, | |
| "grad_norm": 0.10265976190567017, | |
| "learning_rate": 0.0015, | |
| "loss": 2.466796398162842, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 0.1274983330893952, | |
| "grad_norm": 0.1264086365699768, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5070204734802246, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.12775853376916949, | |
| "grad_norm": 0.19938229024410248, | |
| "learning_rate": 0.0015, | |
| "loss": 2.357666015625, | |
| "step": 982 | |
| }, | |
| { | |
| "epoch": 0.12801873444894374, | |
| "grad_norm": 0.12119675427675247, | |
| "learning_rate": 0.0015, | |
| "loss": 2.487483024597168, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 0.12827893512871802, | |
| "grad_norm": 0.1274806410074234, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4527902603149414, | |
| "step": 986 | |
| }, | |
| { | |
| "epoch": 0.1285391358084923, | |
| "grad_norm": 0.22585996985435486, | |
| "learning_rate": 0.0015, | |
| "loss": 2.494025707244873, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 0.12879933648826658, | |
| "grad_norm": 0.10816916823387146, | |
| "learning_rate": 0.0015, | |
| "loss": 2.49330472946167, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.12905953716804086, | |
| "grad_norm": 0.1344311386346817, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4067468643188477, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 0.1293197378478151, | |
| "grad_norm": 0.12150255590677261, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5098538398742676, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 0.1295799385275894, | |
| "grad_norm": 0.18154442310333252, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4638562202453613, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 0.12984013920736368, | |
| "grad_norm": 0.12289196997880936, | |
| "learning_rate": 0.0015, | |
| "loss": 2.472836494445801, | |
| "step": 998 | |
| }, | |
| { | |
| "epoch": 0.13010033988713796, | |
| "grad_norm": 0.22473278641700745, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4230082035064697, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.13036054056691224, | |
| "grad_norm": 0.15969176590442657, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4526515007019043, | |
| "step": 1002 | |
| }, | |
| { | |
| "epoch": 0.13062074124668652, | |
| "grad_norm": 0.12065639346837997, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5058422088623047, | |
| "step": 1004 | |
| }, | |
| { | |
| "epoch": 0.13088094192646077, | |
| "grad_norm": 0.1982503980398178, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3470046520233154, | |
| "step": 1006 | |
| }, | |
| { | |
| "epoch": 0.13114114260623505, | |
| "grad_norm": 0.11025986820459366, | |
| "learning_rate": 0.0015, | |
| "loss": 2.427471160888672, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 0.13140134328600933, | |
| "grad_norm": 0.1502007246017456, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4024569988250732, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.1316615439657836, | |
| "grad_norm": 0.1308867335319519, | |
| "learning_rate": 0.0015, | |
| "loss": 2.429893970489502, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 0.1319217446455579, | |
| "grad_norm": 0.13172170519828796, | |
| "learning_rate": 0.0015, | |
| "loss": 2.460587501525879, | |
| "step": 1014 | |
| }, | |
| { | |
| "epoch": 0.13218194532533217, | |
| "grad_norm": 0.1112113669514656, | |
| "learning_rate": 0.0015, | |
| "loss": 2.452357292175293, | |
| "step": 1016 | |
| }, | |
| { | |
| "epoch": 0.13244214600510643, | |
| "grad_norm": 0.10093437135219574, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4399003982543945, | |
| "step": 1018 | |
| }, | |
| { | |
| "epoch": 0.1327023466848807, | |
| "grad_norm": 0.1351321041584015, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5169358253479004, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.132962547364655, | |
| "grad_norm": 0.10677681118249893, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4662139415740967, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 0.13322274804442927, | |
| "grad_norm": 0.09946724027395248, | |
| "learning_rate": 0.0015, | |
| "loss": 2.460554599761963, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 0.13348294872420355, | |
| "grad_norm": 0.14991725981235504, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4160876274108887, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 0.13374314940397783, | |
| "grad_norm": 0.11871107667684555, | |
| "learning_rate": 0.0015, | |
| "loss": 2.395324230194092, | |
| "step": 1028 | |
| }, | |
| { | |
| "epoch": 0.13400335008375208, | |
| "grad_norm": 0.11057759076356888, | |
| "learning_rate": 0.0015, | |
| "loss": 2.472972869873047, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.13426355076352636, | |
| "grad_norm": 0.16956132650375366, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5264644622802734, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 0.13452375144330064, | |
| "grad_norm": 0.11181381344795227, | |
| "learning_rate": 0.0015, | |
| "loss": 2.468268394470215, | |
| "step": 1034 | |
| }, | |
| { | |
| "epoch": 0.13478395212307492, | |
| "grad_norm": 0.13414572179317474, | |
| "learning_rate": 0.0015, | |
| "loss": 2.362654447555542, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 0.1350441528028492, | |
| "grad_norm": 0.24919535219669342, | |
| "learning_rate": 0.0015, | |
| "loss": 2.483491897583008, | |
| "step": 1038 | |
| }, | |
| { | |
| "epoch": 0.13530435348262349, | |
| "grad_norm": 0.10450753569602966, | |
| "learning_rate": 0.0015, | |
| "loss": 2.523620128631592, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.13556455416239774, | |
| "grad_norm": 0.2184949815273285, | |
| "learning_rate": 0.0015, | |
| "loss": 2.386420249938965, | |
| "step": 1042 | |
| }, | |
| { | |
| "epoch": 0.13582475484217202, | |
| "grad_norm": 0.17390845715999603, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4747018814086914, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 0.1360849555219463, | |
| "grad_norm": 0.1654224693775177, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5035622119903564, | |
| "step": 1046 | |
| }, | |
| { | |
| "epoch": 0.13634515620172058, | |
| "grad_norm": 0.14311206340789795, | |
| "learning_rate": 0.0015, | |
| "loss": 2.499642848968506, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 0.13660535688149486, | |
| "grad_norm": 0.19418315589427948, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4356093406677246, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.13686555756126914, | |
| "grad_norm": 0.12149766087532043, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5009753704071045, | |
| "step": 1052 | |
| }, | |
| { | |
| "epoch": 0.1371257582410434, | |
| "grad_norm": 0.12303480505943298, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4662513732910156, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 0.13738595892081767, | |
| "grad_norm": 0.2106712907552719, | |
| "learning_rate": 0.0015, | |
| "loss": 2.441244602203369, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 0.13764615960059196, | |
| "grad_norm": 0.1418542116880417, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5022647380828857, | |
| "step": 1058 | |
| }, | |
| { | |
| "epoch": 0.13790636028036624, | |
| "grad_norm": 0.16257698833942413, | |
| "learning_rate": 0.0015, | |
| "loss": 2.45245361328125, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.13816656096014052, | |
| "grad_norm": 0.17792272567749023, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4715757369995117, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 0.1384267616399148, | |
| "grad_norm": 0.1103525310754776, | |
| "learning_rate": 0.0015, | |
| "loss": 2.407827377319336, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 0.13868696231968905, | |
| "grad_norm": 0.17640429735183716, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4953856468200684, | |
| "step": 1066 | |
| }, | |
| { | |
| "epoch": 0.13894716299946333, | |
| "grad_norm": 0.22436165809631348, | |
| "learning_rate": 0.0015, | |
| "loss": 2.515901565551758, | |
| "step": 1068 | |
| }, | |
| { | |
| "epoch": 0.1392073636792376, | |
| "grad_norm": 0.1928934007883072, | |
| "learning_rate": 0.0015, | |
| "loss": 2.436163902282715, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.1394675643590119, | |
| "grad_norm": 0.12063254415988922, | |
| "learning_rate": 0.0015, | |
| "loss": 2.388546943664551, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 0.13972776503878617, | |
| "grad_norm": 0.13112172484397888, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4899964332580566, | |
| "step": 1074 | |
| }, | |
| { | |
| "epoch": 0.13998796571856045, | |
| "grad_norm": 0.11329298466444016, | |
| "learning_rate": 0.0015, | |
| "loss": 2.474388837814331, | |
| "step": 1076 | |
| }, | |
| { | |
| "epoch": 0.1402481663983347, | |
| "grad_norm": 0.09997786581516266, | |
| "learning_rate": 0.0015, | |
| "loss": 2.440237045288086, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 0.140508367078109, | |
| "grad_norm": 0.16203705966472626, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4485199451446533, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.14076856775788327, | |
| "grad_norm": 0.1024545356631279, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4308876991271973, | |
| "step": 1082 | |
| }, | |
| { | |
| "epoch": 0.14102876843765755, | |
| "grad_norm": 0.12663713097572327, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4554238319396973, | |
| "step": 1084 | |
| }, | |
| { | |
| "epoch": 0.14128896911743183, | |
| "grad_norm": 0.17677250504493713, | |
| "learning_rate": 0.0015, | |
| "loss": 2.507059097290039, | |
| "step": 1086 | |
| }, | |
| { | |
| "epoch": 0.14154916979720608, | |
| "grad_norm": 0.11777018010616302, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4577083587646484, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 0.14180937047698036, | |
| "grad_norm": 0.1278468370437622, | |
| "learning_rate": 0.0015, | |
| "loss": 2.445704460144043, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.14206957115675464, | |
| "grad_norm": 0.13680873811244965, | |
| "learning_rate": 0.0015, | |
| "loss": 2.413355827331543, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 0.14232977183652892, | |
| "grad_norm": 0.11125652492046356, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4675405025482178, | |
| "step": 1094 | |
| }, | |
| { | |
| "epoch": 0.1425899725163032, | |
| "grad_norm": 0.11100263893604279, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3913791179656982, | |
| "step": 1096 | |
| }, | |
| { | |
| "epoch": 0.14285017319607748, | |
| "grad_norm": 0.11483151465654373, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3454768657684326, | |
| "step": 1098 | |
| }, | |
| { | |
| "epoch": 0.14311037387585174, | |
| "grad_norm": 0.10911301523447037, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4192733764648438, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.14337057455562602, | |
| "grad_norm": 0.1157718300819397, | |
| "learning_rate": 0.0015, | |
| "loss": 2.465139150619507, | |
| "step": 1102 | |
| }, | |
| { | |
| "epoch": 0.1436307752354003, | |
| "grad_norm": 0.11563188582658768, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4586434364318848, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 0.14389097591517458, | |
| "grad_norm": 0.11557405441999435, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4535820484161377, | |
| "step": 1106 | |
| }, | |
| { | |
| "epoch": 0.14415117659494886, | |
| "grad_norm": 0.12103701382875443, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3909735679626465, | |
| "step": 1108 | |
| }, | |
| { | |
| "epoch": 0.14441137727472314, | |
| "grad_norm": 0.18862950801849365, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3988637924194336, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.1446715779544974, | |
| "grad_norm": 0.17689956724643707, | |
| "learning_rate": 0.0015, | |
| "loss": 2.38931941986084, | |
| "step": 1112 | |
| }, | |
| { | |
| "epoch": 0.14493177863427167, | |
| "grad_norm": 0.22612197697162628, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3580808639526367, | |
| "step": 1114 | |
| }, | |
| { | |
| "epoch": 0.14519197931404595, | |
| "grad_norm": 0.12673230469226837, | |
| "learning_rate": 0.0015, | |
| "loss": 2.442720413208008, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 0.14545217999382024, | |
| "grad_norm": 0.17612653970718384, | |
| "learning_rate": 0.0015, | |
| "loss": 2.463355779647827, | |
| "step": 1118 | |
| }, | |
| { | |
| "epoch": 0.14571238067359452, | |
| "grad_norm": 0.12333007901906967, | |
| "learning_rate": 0.0015, | |
| "loss": 2.380070209503174, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.1459725813533688, | |
| "grad_norm": 0.1020858958363533, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4536514282226562, | |
| "step": 1122 | |
| }, | |
| { | |
| "epoch": 0.14623278203314305, | |
| "grad_norm": 0.32838383316993713, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4055564403533936, | |
| "step": 1124 | |
| }, | |
| { | |
| "epoch": 0.14649298271291733, | |
| "grad_norm": 0.19968973100185394, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4536662101745605, | |
| "step": 1126 | |
| }, | |
| { | |
| "epoch": 0.1467531833926916, | |
| "grad_norm": 0.18876910209655762, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4924776554107666, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 0.1470133840724659, | |
| "grad_norm": 0.1943730115890503, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4222571849823, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.14727358475224017, | |
| "grad_norm": 0.18540358543395996, | |
| "learning_rate": 0.0015, | |
| "loss": 2.411162853240967, | |
| "step": 1132 | |
| }, | |
| { | |
| "epoch": 0.14753378543201445, | |
| "grad_norm": 0.17939861118793488, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4838457107543945, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 0.1477939861117887, | |
| "grad_norm": 0.1577775776386261, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4425199031829834, | |
| "step": 1136 | |
| }, | |
| { | |
| "epoch": 0.14805418679156299, | |
| "grad_norm": 0.23459453880786896, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5058655738830566, | |
| "step": 1138 | |
| }, | |
| { | |
| "epoch": 0.14831438747133727, | |
| "grad_norm": 0.14127010107040405, | |
| "learning_rate": 0.0015, | |
| "loss": 2.405430793762207, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.14857458815111155, | |
| "grad_norm": 0.13933320343494415, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4516453742980957, | |
| "step": 1142 | |
| }, | |
| { | |
| "epoch": 0.14883478883088583, | |
| "grad_norm": 0.12083790451288223, | |
| "learning_rate": 0.0015, | |
| "loss": 2.441802501678467, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 0.1490949895106601, | |
| "grad_norm": 0.11597343534231186, | |
| "learning_rate": 0.0015, | |
| "loss": 2.44309663772583, | |
| "step": 1146 | |
| }, | |
| { | |
| "epoch": 0.14935519019043436, | |
| "grad_norm": 0.11108209192752838, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4176034927368164, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 0.14961539087020864, | |
| "grad_norm": 0.12201856821775436, | |
| "learning_rate": 0.0015, | |
| "loss": 2.441558361053467, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.14987559154998292, | |
| "grad_norm": 0.13071376085281372, | |
| "learning_rate": 0.0015, | |
| "loss": 2.429281711578369, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 0.1501357922297572, | |
| "grad_norm": 0.11141698807477951, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4551773071289062, | |
| "step": 1154 | |
| }, | |
| { | |
| "epoch": 0.15039599290953148, | |
| "grad_norm": 0.11565087735652924, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3742003440856934, | |
| "step": 1156 | |
| }, | |
| { | |
| "epoch": 0.15065619358930576, | |
| "grad_norm": 0.10863198339939117, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3950302600860596, | |
| "step": 1158 | |
| }, | |
| { | |
| "epoch": 0.15091639426908002, | |
| "grad_norm": 0.17658548057079315, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4297618865966797, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.1511765949488543, | |
| "grad_norm": 0.11242704093456268, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4334096908569336, | |
| "step": 1162 | |
| }, | |
| { | |
| "epoch": 0.15143679562862858, | |
| "grad_norm": 0.23384493589401245, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4612202644348145, | |
| "step": 1164 | |
| }, | |
| { | |
| "epoch": 0.15169699630840286, | |
| "grad_norm": 0.13724996149539948, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4340977668762207, | |
| "step": 1166 | |
| }, | |
| { | |
| "epoch": 0.15195719698817714, | |
| "grad_norm": 0.12144450843334198, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5139427185058594, | |
| "step": 1168 | |
| }, | |
| { | |
| "epoch": 0.15221739766795142, | |
| "grad_norm": 0.11372646689414978, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4092471599578857, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.15247759834772567, | |
| "grad_norm": 0.11893589049577713, | |
| "learning_rate": 0.0015, | |
| "loss": 2.365037441253662, | |
| "step": 1172 | |
| }, | |
| { | |
| "epoch": 0.15273779902749995, | |
| "grad_norm": 0.1765247881412506, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5289974212646484, | |
| "step": 1174 | |
| }, | |
| { | |
| "epoch": 0.15299799970727423, | |
| "grad_norm": 0.19714157283306122, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4510278701782227, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 0.15325820038704852, | |
| "grad_norm": 0.1067543625831604, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4470250606536865, | |
| "step": 1178 | |
| }, | |
| { | |
| "epoch": 0.1535184010668228, | |
| "grad_norm": 0.12346280366182327, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4941210746765137, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.15377860174659708, | |
| "grad_norm": 0.17956458032131195, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3808820247650146, | |
| "step": 1182 | |
| }, | |
| { | |
| "epoch": 0.15403880242637133, | |
| "grad_norm": 0.11279787123203278, | |
| "learning_rate": 0.0015, | |
| "loss": 2.402820110321045, | |
| "step": 1184 | |
| }, | |
| { | |
| "epoch": 0.1542990031061456, | |
| "grad_norm": 0.1782272905111313, | |
| "learning_rate": 0.0015, | |
| "loss": 2.454741954803467, | |
| "step": 1186 | |
| }, | |
| { | |
| "epoch": 0.1545592037859199, | |
| "grad_norm": 0.14567869901657104, | |
| "learning_rate": 0.0015, | |
| "loss": 2.387033700942993, | |
| "step": 1188 | |
| }, | |
| { | |
| "epoch": 0.15481940446569417, | |
| "grad_norm": 0.13391685485839844, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4758825302124023, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.15507960514546845, | |
| "grad_norm": 0.15669213235378265, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4722981452941895, | |
| "step": 1192 | |
| }, | |
| { | |
| "epoch": 0.1553398058252427, | |
| "grad_norm": 0.12036886811256409, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3432040214538574, | |
| "step": 1194 | |
| }, | |
| { | |
| "epoch": 0.15560000650501699, | |
| "grad_norm": 0.11269272118806839, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4520320892333984, | |
| "step": 1196 | |
| }, | |
| { | |
| "epoch": 0.15586020718479127, | |
| "grad_norm": 0.10365239530801773, | |
| "learning_rate": 0.0015, | |
| "loss": 2.447770595550537, | |
| "step": 1198 | |
| }, | |
| { | |
| "epoch": 0.15612040786456555, | |
| "grad_norm": 0.14448872208595276, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4342339038848877, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.15638060854433983, | |
| "grad_norm": 0.1512068510055542, | |
| "learning_rate": 0.0015, | |
| "loss": 2.44174861907959, | |
| "step": 1202 | |
| }, | |
| { | |
| "epoch": 0.1566408092241141, | |
| "grad_norm": 0.11856794357299805, | |
| "learning_rate": 0.0015, | |
| "loss": 2.462867498397827, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 0.15690100990388836, | |
| "grad_norm": 0.15060612559318542, | |
| "learning_rate": 0.0015, | |
| "loss": 2.444382429122925, | |
| "step": 1206 | |
| }, | |
| { | |
| "epoch": 0.15716121058366264, | |
| "grad_norm": 0.1236223429441452, | |
| "learning_rate": 0.0015, | |
| "loss": 2.432056188583374, | |
| "step": 1208 | |
| }, | |
| { | |
| "epoch": 0.15742141126343692, | |
| "grad_norm": 0.12084182351827621, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4530110359191895, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.1576816119432112, | |
| "grad_norm": 0.11235949397087097, | |
| "learning_rate": 0.0015, | |
| "loss": 2.417367458343506, | |
| "step": 1212 | |
| }, | |
| { | |
| "epoch": 0.15794181262298548, | |
| "grad_norm": 0.10813146084547043, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4447574615478516, | |
| "step": 1214 | |
| }, | |
| { | |
| "epoch": 0.15820201330275976, | |
| "grad_norm": 0.11305201053619385, | |
| "learning_rate": 0.0015, | |
| "loss": 2.458041191101074, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 0.15846221398253402, | |
| "grad_norm": 0.1399001181125641, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3876781463623047, | |
| "step": 1218 | |
| }, | |
| { | |
| "epoch": 0.1587224146623083, | |
| "grad_norm": 0.1301049292087555, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4322681427001953, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.15898261534208258, | |
| "grad_norm": 0.19871819019317627, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3859105110168457, | |
| "step": 1222 | |
| }, | |
| { | |
| "epoch": 0.15924281602185686, | |
| "grad_norm": 0.11344478279352188, | |
| "learning_rate": 0.0015, | |
| "loss": 2.411940813064575, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 0.15950301670163114, | |
| "grad_norm": 0.10705609619617462, | |
| "learning_rate": 0.0015, | |
| "loss": 2.471545696258545, | |
| "step": 1226 | |
| }, | |
| { | |
| "epoch": 0.15976321738140542, | |
| "grad_norm": 0.1352146714925766, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4263381958007812, | |
| "step": 1228 | |
| }, | |
| { | |
| "epoch": 0.16002341806117967, | |
| "grad_norm": 0.11733849346637726, | |
| "learning_rate": 0.0015, | |
| "loss": 2.527388572692871, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.16028361874095395, | |
| "grad_norm": 0.11473846435546875, | |
| "learning_rate": 0.0015, | |
| "loss": 2.457369804382324, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 0.16054381942072823, | |
| "grad_norm": 0.16299386322498322, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4419190883636475, | |
| "step": 1234 | |
| }, | |
| { | |
| "epoch": 0.16080402010050251, | |
| "grad_norm": 0.1583544909954071, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4358086585998535, | |
| "step": 1236 | |
| }, | |
| { | |
| "epoch": 0.1610642207802768, | |
| "grad_norm": 0.11408533900976181, | |
| "learning_rate": 0.0015, | |
| "loss": 2.431692600250244, | |
| "step": 1238 | |
| }, | |
| { | |
| "epoch": 0.16132442146005108, | |
| "grad_norm": 0.24136263132095337, | |
| "learning_rate": 0.0015, | |
| "loss": 2.461775302886963, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.16158462213982533, | |
| "grad_norm": 0.11955428868532181, | |
| "learning_rate": 0.0015, | |
| "loss": 2.428358793258667, | |
| "step": 1242 | |
| }, | |
| { | |
| "epoch": 0.1618448228195996, | |
| "grad_norm": 0.11306291073560715, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4026038646698, | |
| "step": 1244 | |
| }, | |
| { | |
| "epoch": 0.1621050234993739, | |
| "grad_norm": 0.16501212120056152, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4538371562957764, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 0.16236522417914817, | |
| "grad_norm": 0.1519465297460556, | |
| "learning_rate": 0.0015, | |
| "loss": 2.375150203704834, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 0.16262542485892245, | |
| "grad_norm": 0.11929146945476532, | |
| "learning_rate": 0.0015, | |
| "loss": 2.386366844177246, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.16288562553869673, | |
| "grad_norm": 0.13667862117290497, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4182510375976562, | |
| "step": 1252 | |
| }, | |
| { | |
| "epoch": 0.16314582621847099, | |
| "grad_norm": 0.12089703977108002, | |
| "learning_rate": 0.0015, | |
| "loss": 2.419919013977051, | |
| "step": 1254 | |
| }, | |
| { | |
| "epoch": 0.16340602689824527, | |
| "grad_norm": 0.15514126420021057, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4567313194274902, | |
| "step": 1256 | |
| }, | |
| { | |
| "epoch": 0.16366622757801955, | |
| "grad_norm": 0.11216102540493011, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4364237785339355, | |
| "step": 1258 | |
| }, | |
| { | |
| "epoch": 0.16392642825779383, | |
| "grad_norm": 0.10649251192808151, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3996036052703857, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.1641866289375681, | |
| "grad_norm": 0.10178853571414948, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3935763835906982, | |
| "step": 1262 | |
| }, | |
| { | |
| "epoch": 0.1644468296173424, | |
| "grad_norm": 0.13471631705760956, | |
| "learning_rate": 0.0015, | |
| "loss": 2.445880889892578, | |
| "step": 1264 | |
| }, | |
| { | |
| "epoch": 0.16470703029711664, | |
| "grad_norm": 0.10506339371204376, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4339776039123535, | |
| "step": 1266 | |
| }, | |
| { | |
| "epoch": 0.16496723097689092, | |
| "grad_norm": 0.11138959228992462, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4713330268859863, | |
| "step": 1268 | |
| }, | |
| { | |
| "epoch": 0.1652274316566652, | |
| "grad_norm": 0.10945623368024826, | |
| "learning_rate": 0.0015, | |
| "loss": 2.402653694152832, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.16548763233643948, | |
| "grad_norm": 0.10930269956588745, | |
| "learning_rate": 0.0015, | |
| "loss": 2.385347843170166, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 0.16574783301621376, | |
| "grad_norm": 0.11622707545757294, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4838743209838867, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 0.16600803369598804, | |
| "grad_norm": 0.12191583961248398, | |
| "learning_rate": 0.0015, | |
| "loss": 2.361172914505005, | |
| "step": 1276 | |
| }, | |
| { | |
| "epoch": 0.1662682343757623, | |
| "grad_norm": 0.12226612120866776, | |
| "learning_rate": 0.0015, | |
| "loss": 2.484133243560791, | |
| "step": 1278 | |
| }, | |
| { | |
| "epoch": 0.16652843505553658, | |
| "grad_norm": 0.16671867668628693, | |
| "learning_rate": 0.0015, | |
| "loss": 2.403444290161133, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.16678863573531086, | |
| "grad_norm": 0.11180184781551361, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4213948249816895, | |
| "step": 1282 | |
| }, | |
| { | |
| "epoch": 0.16704883641508514, | |
| "grad_norm": 0.14298300445079803, | |
| "learning_rate": 0.0015, | |
| "loss": 2.460801124572754, | |
| "step": 1284 | |
| }, | |
| { | |
| "epoch": 0.16730903709485942, | |
| "grad_norm": 0.21743375062942505, | |
| "learning_rate": 0.0015, | |
| "loss": 2.424553394317627, | |
| "step": 1286 | |
| }, | |
| { | |
| "epoch": 0.16756923777463367, | |
| "grad_norm": 0.1232086643576622, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4497733116149902, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 0.16782943845440795, | |
| "grad_norm": 0.11134848743677139, | |
| "learning_rate": 0.0015, | |
| "loss": 2.403141498565674, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.16808963913418223, | |
| "grad_norm": 0.15922418236732483, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3140456676483154, | |
| "step": 1292 | |
| }, | |
| { | |
| "epoch": 0.16834983981395651, | |
| "grad_norm": 0.1884986311197281, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4354138374328613, | |
| "step": 1294 | |
| }, | |
| { | |
| "epoch": 0.1686100404937308, | |
| "grad_norm": 0.11944177746772766, | |
| "learning_rate": 0.0015, | |
| "loss": 2.427903652191162, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 0.16887024117350508, | |
| "grad_norm": 0.2099335789680481, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5288753509521484, | |
| "step": 1298 | |
| }, | |
| { | |
| "epoch": 0.16913044185327933, | |
| "grad_norm": 0.108861044049263, | |
| "learning_rate": 0.0015, | |
| "loss": 2.431715488433838, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.1693906425330536, | |
| "grad_norm": 0.1470099240541458, | |
| "learning_rate": 0.0015, | |
| "loss": 2.455397367477417, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 0.1696508432128279, | |
| "grad_norm": 0.10982918739318848, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4648571014404297, | |
| "step": 1304 | |
| }, | |
| { | |
| "epoch": 0.16991104389260217, | |
| "grad_norm": 0.18002374470233917, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3659491539001465, | |
| "step": 1306 | |
| }, | |
| { | |
| "epoch": 0.17017124457237645, | |
| "grad_norm": 0.11057405173778534, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4196794033050537, | |
| "step": 1308 | |
| }, | |
| { | |
| "epoch": 0.17043144525215073, | |
| "grad_norm": 0.11353861540555954, | |
| "learning_rate": 0.0015, | |
| "loss": 2.393937587738037, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.17069164593192498, | |
| "grad_norm": 0.11239606887102127, | |
| "learning_rate": 0.0015, | |
| "loss": 2.359034538269043, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 0.17095184661169927, | |
| "grad_norm": 0.14231309294700623, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4108057022094727, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 0.17121204729147355, | |
| "grad_norm": 0.19448791444301605, | |
| "learning_rate": 0.0015, | |
| "loss": 2.477170944213867, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 0.17147224797124783, | |
| "grad_norm": 0.1748061627149582, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4192404747009277, | |
| "step": 1318 | |
| }, | |
| { | |
| "epoch": 0.1717324486510221, | |
| "grad_norm": 0.13385999202728271, | |
| "learning_rate": 0.0015, | |
| "loss": 2.45928692817688, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.1719926493307964, | |
| "grad_norm": 0.09599027782678604, | |
| "learning_rate": 0.0015, | |
| "loss": 2.411952018737793, | |
| "step": 1322 | |
| }, | |
| { | |
| "epoch": 0.17225285001057064, | |
| "grad_norm": 0.19161750376224518, | |
| "learning_rate": 0.0015, | |
| "loss": 2.405963182449341, | |
| "step": 1324 | |
| }, | |
| { | |
| "epoch": 0.17251305069034492, | |
| "grad_norm": 0.13632002472877502, | |
| "learning_rate": 0.0015, | |
| "loss": 2.405630588531494, | |
| "step": 1326 | |
| }, | |
| { | |
| "epoch": 0.1727732513701192, | |
| "grad_norm": 0.10875320434570312, | |
| "learning_rate": 0.0015, | |
| "loss": 2.400637626647949, | |
| "step": 1328 | |
| }, | |
| { | |
| "epoch": 0.17303345204989348, | |
| "grad_norm": 0.1277407705783844, | |
| "learning_rate": 0.0015, | |
| "loss": 2.497649908065796, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.17329365272966776, | |
| "grad_norm": 0.11995089799165726, | |
| "learning_rate": 0.0015, | |
| "loss": 2.36509108543396, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 0.17355385340944204, | |
| "grad_norm": 0.1417117416858673, | |
| "learning_rate": 0.0015, | |
| "loss": 2.41786527633667, | |
| "step": 1334 | |
| }, | |
| { | |
| "epoch": 0.1738140540892163, | |
| "grad_norm": 0.12198492139577866, | |
| "learning_rate": 0.0015, | |
| "loss": 2.42653226852417, | |
| "step": 1336 | |
| }, | |
| { | |
| "epoch": 0.17407425476899058, | |
| "grad_norm": 0.16528841853141785, | |
| "learning_rate": 0.0015, | |
| "loss": 2.440850257873535, | |
| "step": 1338 | |
| }, | |
| { | |
| "epoch": 0.17433445544876486, | |
| "grad_norm": 0.10439668595790863, | |
| "learning_rate": 0.0015, | |
| "loss": 2.2864136695861816, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.17459465612853914, | |
| "grad_norm": 0.10300511121749878, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3731436729431152, | |
| "step": 1342 | |
| }, | |
| { | |
| "epoch": 0.17485485680831342, | |
| "grad_norm": 0.18186108767986298, | |
| "learning_rate": 0.0015, | |
| "loss": 2.388641357421875, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 0.1751150574880877, | |
| "grad_norm": 0.10545193403959274, | |
| "learning_rate": 0.0015, | |
| "loss": 2.323863983154297, | |
| "step": 1346 | |
| }, | |
| { | |
| "epoch": 0.17537525816786195, | |
| "grad_norm": 0.10705488920211792, | |
| "learning_rate": 0.0015, | |
| "loss": 2.488503932952881, | |
| "step": 1348 | |
| }, | |
| { | |
| "epoch": 0.17563545884763623, | |
| "grad_norm": 0.11458684504032135, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4604709148406982, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.17589565952741051, | |
| "grad_norm": 0.11846322566270828, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4203875064849854, | |
| "step": 1352 | |
| }, | |
| { | |
| "epoch": 0.1761558602071848, | |
| "grad_norm": 0.10294774919748306, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4126439094543457, | |
| "step": 1354 | |
| }, | |
| { | |
| "epoch": 0.17641606088695908, | |
| "grad_norm": 0.11134915053844452, | |
| "learning_rate": 0.0015, | |
| "loss": 2.372790813446045, | |
| "step": 1356 | |
| }, | |
| { | |
| "epoch": 0.17667626156673336, | |
| "grad_norm": 0.15922658145427704, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4994258880615234, | |
| "step": 1358 | |
| }, | |
| { | |
| "epoch": 0.1769364622465076, | |
| "grad_norm": 0.10634514689445496, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4253621101379395, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.1771966629262819, | |
| "grad_norm": 0.19085898995399475, | |
| "learning_rate": 0.0015, | |
| "loss": 2.5060479640960693, | |
| "step": 1362 | |
| }, | |
| { | |
| "epoch": 0.17745686360605617, | |
| "grad_norm": 0.1864626705646515, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4373955726623535, | |
| "step": 1364 | |
| }, | |
| { | |
| "epoch": 0.17771706428583045, | |
| "grad_norm": 0.12415165454149246, | |
| "learning_rate": 0.0015, | |
| "loss": 2.433816909790039, | |
| "step": 1366 | |
| }, | |
| { | |
| "epoch": 0.17797726496560473, | |
| "grad_norm": 0.1111738458275795, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4260969161987305, | |
| "step": 1368 | |
| }, | |
| { | |
| "epoch": 0.178237465645379, | |
| "grad_norm": 0.13230733573436737, | |
| "learning_rate": 0.0015, | |
| "loss": 2.432861804962158, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.17849766632515326, | |
| "grad_norm": 0.13344313204288483, | |
| "learning_rate": 0.0015, | |
| "loss": 2.3097424507141113, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 0.17875786700492755, | |
| "grad_norm": 0.11272049695253372, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4169774055480957, | |
| "step": 1374 | |
| }, | |
| { | |
| "epoch": 0.17901806768470183, | |
| "grad_norm": 0.14284023642539978, | |
| "learning_rate": 0.0015, | |
| "loss": 2.421970844268799, | |
| "step": 1376 | |
| }, | |
| { | |
| "epoch": 0.1792782683644761, | |
| "grad_norm": 0.13425251841545105, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4190189838409424, | |
| "step": 1378 | |
| }, | |
| { | |
| "epoch": 0.1795384690442504, | |
| "grad_norm": 0.10962817072868347, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4182591438293457, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.17979866972402467, | |
| "grad_norm": 0.12920773029327393, | |
| "learning_rate": 0.0015, | |
| "loss": 2.424931526184082, | |
| "step": 1382 | |
| }, | |
| { | |
| "epoch": 0.18005887040379892, | |
| "grad_norm": 0.15149635076522827, | |
| "learning_rate": 0.0015, | |
| "loss": 2.4042811393737793, | |
| "step": 1384 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 6919, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1384, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.971626564799693e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |