Add files using upload-large-folder tool

Math_QA/group_06/checkpoints/checkpoint-1200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/不冻结Qwen训练/models/Qwen2.5-1.5B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

Math_QA/group_06/checkpoints/checkpoint-1500/trainer_state.json

@@ -0,0 +1,2141 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 375.0,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "grad_norm": 11.104532241821289,
+      "learning_rate": 0.0,
+      "loss": 1.8881,
+      "step": 1
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 7.216622829437256,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.8059,
+      "step": 5
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 3.460949182510376,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.5521,
+      "step": 10
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 1.9872286319732666,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 1.1534,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.5143823623657227,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.8946,
+      "step": 20
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.6239762306213379,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.7338,
+      "step": 25
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.6216806173324585,
+      "learning_rate": 5.370370370370371e-05,
+      "loss": 0.6218,
+      "step": 30
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.5028809905052185,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.5368,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.2165335416793823,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.4395,
+      "step": 40
+    },
+    {
+      "epoch": 11.32,
+      "grad_norm": 0.7524298429489136,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.3374,
+      "step": 45
+    },
+    {
+      "epoch": 12.64,
+      "grad_norm": 1.2006490230560303,
+      "learning_rate": 9.074074074074075e-05,
+      "loss": 0.2433,
+      "step": 50
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 1.0558921098709106,
+      "learning_rate": 0.0001,
+      "loss": 0.219,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 4.885622501373291,
+      "learning_rate": 9.971363115693013e-05,
+      "loss": 0.1595,
+      "step": 60
+    },
+    {
+      "epoch": 16.32,
+      "grad_norm": 0.6441199779510498,
+      "learning_rate": 9.942726231386026e-05,
+      "loss": 0.0905,
+      "step": 65
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 0.8051611185073853,
+      "learning_rate": 9.914089347079038e-05,
+      "loss": 0.0634,
+      "step": 70
+    },
+    {
+      "epoch": 18.96,
+      "grad_norm": 0.5070267915725708,
+      "learning_rate": 9.885452462772051e-05,
+      "loss": 0.0473,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.7553927898406982,
+      "learning_rate": 9.856815578465064e-05,
+      "loss": 0.041,
+      "step": 80
+    },
+    {
+      "epoch": 21.32,
+      "grad_norm": 0.3303334712982178,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 0.0315,
+      "step": 85
+    },
+    {
+      "epoch": 22.64,
+      "grad_norm": 1.3955363035202026,
+      "learning_rate": 9.799541809851088e-05,
+      "loss": 0.0438,
+      "step": 90
+    },
+    {
+      "epoch": 23.96,
+      "grad_norm": 0.6044227480888367,
+      "learning_rate": 9.7709049255441e-05,
+      "loss": 0.0335,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.37705135345458984,
+      "learning_rate": 9.742268041237114e-05,
+      "loss": 0.0305,
+      "step": 100
+    },
+    {
+      "epoch": 26.32,
+      "grad_norm": 0.14478059113025665,
+      "learning_rate": 9.713631156930127e-05,
+      "loss": 0.0304,
+      "step": 105
+    },
+    {
+      "epoch": 27.64,
+      "grad_norm": 0.3496911823749542,
+      "learning_rate": 9.68499427262314e-05,
+      "loss": 0.0334,
+      "step": 110
+    },
+    {
+      "epoch": 28.96,
+      "grad_norm": 0.36351385712623596,
+      "learning_rate": 9.656357388316152e-05,
+      "loss": 0.0338,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.2110755294561386,
+      "learning_rate": 9.627720504009165e-05,
+      "loss": 0.0318,
+      "step": 120
+    },
+    {
+      "epoch": 31.32,
+      "grad_norm": 0.08316600322723389,
+      "learning_rate": 9.599083619702178e-05,
+      "loss": 0.027,
+      "step": 125
+    },
+    {
+      "epoch": 32.64,
+      "grad_norm": 0.07070767879486084,
+      "learning_rate": 9.57044673539519e-05,
+      "loss": 0.0284,
+      "step": 130
+    },
+    {
+      "epoch": 33.96,
+      "grad_norm": 0.06981239467859268,
+      "learning_rate": 9.541809851088203e-05,
+      "loss": 0.0274,
+      "step": 135
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.15813617408275604,
+      "learning_rate": 9.513172966781214e-05,
+      "loss": 0.025,
+      "step": 140
+    },
+    {
+      "epoch": 36.32,
+      "grad_norm": 0.06278073787689209,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.0256,
+      "step": 145
+    },
+    {
+      "epoch": 37.64,
+      "grad_norm": 0.07232863456010818,
+      "learning_rate": 9.45589919816724e-05,
+      "loss": 0.0259,
+      "step": 150
+    },
+    {
+      "epoch": 38.96,
+      "grad_norm": 0.05737334489822388,
+      "learning_rate": 9.427262313860252e-05,
+      "loss": 0.0263,
+      "step": 155
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.19587241113185883,
+      "learning_rate": 9.398625429553265e-05,
+      "loss": 0.0276,
+      "step": 160
+    },
+    {
+      "epoch": 41.32,
+      "grad_norm": 0.05878272280097008,
+      "learning_rate": 9.369988545246277e-05,
+      "loss": 0.0271,
+      "step": 165
+    },
+    {
+      "epoch": 42.64,
+      "grad_norm": 0.06356244534254074,
+      "learning_rate": 9.34135166093929e-05,
+      "loss": 0.0264,
+      "step": 170
+    },
+    {
+      "epoch": 43.96,
+      "grad_norm": 0.05739160627126694,
+      "learning_rate": 9.312714776632303e-05,
+      "loss": 0.0269,
+      "step": 175
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 0.18483243882656097,
+      "learning_rate": 9.284077892325315e-05,
+      "loss": 0.0277,
+      "step": 180
+    },
+    {
+      "epoch": 46.32,
+      "grad_norm": 0.05537231266498566,
+      "learning_rate": 9.255441008018328e-05,
+      "loss": 0.0255,
+      "step": 185
+    },
+    {
+      "epoch": 47.64,
+      "grad_norm": 0.06456373631954193,
+      "learning_rate": 9.22680412371134e-05,
+      "loss": 0.0268,
+      "step": 190
+    },
+    {
+      "epoch": 48.96,
+      "grad_norm": 0.053096506744623184,
+      "learning_rate": 9.198167239404353e-05,
+      "loss": 0.0244,
+      "step": 195
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.17689672112464905,
+      "learning_rate": 9.169530355097366e-05,
+      "loss": 0.0258,
+      "step": 200
+    },
+    {
+      "epoch": 51.32,
+      "grad_norm": 0.06029054522514343,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.0277,
+      "step": 205
+    },
+    {
+      "epoch": 52.64,
+      "grad_norm": 0.0548815056681633,
+      "learning_rate": 9.112256586483391e-05,
+      "loss": 0.028,
+      "step": 210
+    },
+    {
+      "epoch": 53.96,
+      "grad_norm": 0.05216140300035477,
+      "learning_rate": 9.083619702176404e-05,
+      "loss": 0.0243,
+      "step": 215
+    },
+    {
+      "epoch": 55.0,
+      "grad_norm": 0.1264064759016037,
+      "learning_rate": 9.054982817869416e-05,
+      "loss": 0.0284,
+      "step": 220
+    },
+    {
+      "epoch": 56.32,
+      "grad_norm": 0.0550195574760437,
+      "learning_rate": 9.026345933562429e-05,
+      "loss": 0.0267,
+      "step": 225
+    },
+    {
+      "epoch": 57.64,
+      "grad_norm": 0.04373545199632645,
+      "learning_rate": 8.997709049255442e-05,
+      "loss": 0.0261,
+      "step": 230
+    },
+    {
+      "epoch": 58.96,
+      "grad_norm": 0.06298700720071793,
+      "learning_rate": 8.969072164948454e-05,
+      "loss": 0.0262,
+      "step": 235
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.10524652153253555,
+      "learning_rate": 8.940435280641467e-05,
+      "loss": 0.0238,
+      "step": 240
+    },
+    {
+      "epoch": 61.32,
+      "grad_norm": 0.05074843764305115,
+      "learning_rate": 8.91179839633448e-05,
+      "loss": 0.0246,
+      "step": 245
+    },
+    {
+      "epoch": 62.64,
+      "grad_norm": 0.04865209385752678,
+      "learning_rate": 8.883161512027491e-05,
+      "loss": 0.0256,
+      "step": 250
+    },
+    {
+      "epoch": 63.96,
+      "grad_norm": 0.04322940111160278,
+      "learning_rate": 8.854524627720504e-05,
+      "loss": 0.0256,
+      "step": 255
+    },
+    {
+      "epoch": 65.0,
+      "grad_norm": 0.11021823436021805,
+      "learning_rate": 8.825887743413516e-05,
+      "loss": 0.0238,
+      "step": 260
+    },
+    {
+      "epoch": 66.32,
+      "grad_norm": 0.04945431277155876,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 0.0251,
+      "step": 265
+    },
+    {
+      "epoch": 67.64,
+      "grad_norm": 0.05235425382852554,
+      "learning_rate": 8.768613974799542e-05,
+      "loss": 0.0246,
+      "step": 270
+    },
+    {
+      "epoch": 68.96,
+      "grad_norm": 0.04749702662229538,
+      "learning_rate": 8.739977090492554e-05,
+      "loss": 0.0247,
+      "step": 275
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.09817614406347275,
+      "learning_rate": 8.711340206185567e-05,
+      "loss": 0.0254,
+      "step": 280
+    },
+    {
+      "epoch": 71.32,
+      "grad_norm": 0.054523907601833344,
+      "learning_rate": 8.682703321878581e-05,
+      "loss": 0.025,
+      "step": 285
+    },
+    {
+      "epoch": 72.64,
+      "grad_norm": 0.053732652217149734,
+      "learning_rate": 8.654066437571594e-05,
+      "loss": 0.026,
+      "step": 290
+    },
+    {
+      "epoch": 73.96,
+      "grad_norm": 0.050208788365125656,
+      "learning_rate": 8.625429553264606e-05,
+      "loss": 0.0248,
+      "step": 295
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.11127286404371262,
+      "learning_rate": 8.596792668957619e-05,
+      "loss": 0.0235,
+      "step": 300
+    },
+    {
+      "epoch": 76.32,
+      "grad_norm": 0.047599948942661285,
+      "learning_rate": 8.56815578465063e-05,
+      "loss": 0.0249,
+      "step": 305
+    },
+    {
+      "epoch": 77.64,
+      "grad_norm": 0.0452277734875679,
+      "learning_rate": 8.539518900343643e-05,
+      "loss": 0.0249,
+      "step": 310
+    },
+    {
+      "epoch": 78.96,
+      "grad_norm": 0.049311988055706024,
+      "learning_rate": 8.510882016036655e-05,
+      "loss": 0.0247,
+      "step": 315
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 0.13898910582065582,
+      "learning_rate": 8.482245131729668e-05,
+      "loss": 0.0251,
+      "step": 320
+    },
+    {
+      "epoch": 81.32,
+      "grad_norm": 0.040757764130830765,
+      "learning_rate": 8.453608247422681e-05,
+      "loss": 0.0249,
+      "step": 325
+    },
+    {
+      "epoch": 82.64,
+      "grad_norm": 0.04465162381529808,
+      "learning_rate": 8.424971363115693e-05,
+      "loss": 0.025,
+      "step": 330
+    },
+    {
+      "epoch": 83.96,
+      "grad_norm": 0.04066985845565796,
+      "learning_rate": 8.396334478808706e-05,
+      "loss": 0.0225,
+      "step": 335
+    },
+    {
+      "epoch": 85.0,
+      "grad_norm": 0.16414588689804077,
+      "learning_rate": 8.367697594501719e-05,
+      "loss": 0.0246,
+      "step": 340
+    },
+    {
+      "epoch": 86.32,
+      "grad_norm": 0.0515274740755558,
+      "learning_rate": 8.339060710194731e-05,
+      "loss": 0.0239,
+      "step": 345
+    },
+    {
+      "epoch": 87.64,
+      "grad_norm": 0.0446721687912941,
+      "learning_rate": 8.310423825887744e-05,
+      "loss": 0.0245,
+      "step": 350
+    },
+    {
+      "epoch": 88.96,
+      "grad_norm": 0.043738313019275665,
+      "learning_rate": 8.281786941580757e-05,
+      "loss": 0.0254,
+      "step": 355
+    },
+    {
+      "epoch": 90.0,
+      "grad_norm": 0.1853068321943283,
+      "learning_rate": 8.253150057273768e-05,
+      "loss": 0.026,
+      "step": 360
+    },
+    {
+      "epoch": 91.32,
+      "grad_norm": 0.04070025309920311,
+      "learning_rate": 8.224513172966782e-05,
+      "loss": 0.0264,
+      "step": 365
+    },
+    {
+      "epoch": 92.64,
+      "grad_norm": 0.04621007665991783,
+      "learning_rate": 8.195876288659795e-05,
+      "loss": 0.0239,
+      "step": 370
+    },
+    {
+      "epoch": 93.96,
+      "grad_norm": 0.0490901954472065,
+      "learning_rate": 8.167239404352807e-05,
+      "loss": 0.0259,
+      "step": 375
+    },
+    {
+      "epoch": 95.0,
+      "grad_norm": 0.11828532069921494,
+      "learning_rate": 8.13860252004582e-05,
+      "loss": 0.0231,
+      "step": 380
+    },
+    {
+      "epoch": 96.32,
+      "grad_norm": 0.046177372336387634,
+      "learning_rate": 8.109965635738833e-05,
+      "loss": 0.0248,
+      "step": 385
+    },
+    {
+      "epoch": 97.64,
+      "grad_norm": 0.042552754282951355,
+      "learning_rate": 8.081328751431845e-05,
+      "loss": 0.0234,
+      "step": 390
+    },
+    {
+      "epoch": 98.96,
+      "grad_norm": 0.04748699814081192,
+      "learning_rate": 8.052691867124858e-05,
+      "loss": 0.0261,
+      "step": 395
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.1385429948568344,
+      "learning_rate": 8.02405498281787e-05,
+      "loss": 0.025,
+      "step": 400
+    },
+    {
+      "epoch": 101.32,
+      "grad_norm": 0.04103074222803116,
+      "learning_rate": 7.995418098510883e-05,
+      "loss": 0.0269,
+      "step": 405
+    },
+    {
+      "epoch": 102.64,
+      "grad_norm": 0.03280722349882126,
+      "learning_rate": 7.966781214203894e-05,
+      "loss": 0.0241,
+      "step": 410
+    },
+    {
+      "epoch": 103.96,
+      "grad_norm": 0.04333680495619774,
+      "learning_rate": 7.938144329896907e-05,
+      "loss": 0.0245,
+      "step": 415
+    },
+    {
+      "epoch": 105.0,
+      "grad_norm": 0.08673492819070816,
+      "learning_rate": 7.90950744558992e-05,
+      "loss": 0.0253,
+      "step": 420
+    },
+    {
+      "epoch": 106.32,
+      "grad_norm": 0.04038430377840996,
+      "learning_rate": 7.880870561282932e-05,
+      "loss": 0.0259,
+      "step": 425
+    },
+    {
+      "epoch": 107.64,
+      "grad_norm": 0.03518936410546303,
+      "learning_rate": 7.852233676975945e-05,
+      "loss": 0.0233,
+      "step": 430
+    },
+    {
+      "epoch": 108.96,
+      "grad_norm": 0.042619626969099045,
+      "learning_rate": 7.823596792668958e-05,
+      "loss": 0.0248,
+      "step": 435
+    },
+    {
+      "epoch": 110.0,
+      "grad_norm": 0.14510254561901093,
+      "learning_rate": 7.79495990836197e-05,
+      "loss": 0.0243,
+      "step": 440
+    },
+    {
+      "epoch": 111.32,
+      "grad_norm": 0.04383605346083641,
+      "learning_rate": 7.766323024054983e-05,
+      "loss": 0.0247,
+      "step": 445
+    },
+    {
+      "epoch": 112.64,
+      "grad_norm": 0.04186142981052399,
+      "learning_rate": 7.737686139747996e-05,
+      "loss": 0.0246,
+      "step": 450
+    },
+    {
+      "epoch": 113.96,
+      "grad_norm": 0.03870782628655434,
+      "learning_rate": 7.709049255441008e-05,
+      "loss": 0.0246,
+      "step": 455
+    },
+    {
+      "epoch": 115.0,
+      "grad_norm": 0.10923579335212708,
+      "learning_rate": 7.680412371134021e-05,
+      "loss": 0.0245,
+      "step": 460
+    },
+    {
+      "epoch": 116.32,
+      "grad_norm": 0.03715936094522476,
+      "learning_rate": 7.651775486827034e-05,
+      "loss": 0.0243,
+      "step": 465
+    },
+    {
+      "epoch": 117.64,
+      "grad_norm": 0.03120102733373642,
+      "learning_rate": 7.623138602520046e-05,
+      "loss": 0.0234,
+      "step": 470
+    },
+    {
+      "epoch": 118.96,
+      "grad_norm": 0.03617759793996811,
+      "learning_rate": 7.594501718213059e-05,
+      "loss": 0.0265,
+      "step": 475
+    },
+    {
+      "epoch": 120.0,
+      "grad_norm": 0.12326925247907639,
+      "learning_rate": 7.565864833906071e-05,
+      "loss": 0.0244,
+      "step": 480
+    },
+    {
+      "epoch": 121.32,
+      "grad_norm": 0.03131456300616264,
+      "learning_rate": 7.537227949599084e-05,
+      "loss": 0.0237,
+      "step": 485
+    },
+    {
+      "epoch": 122.64,
+      "grad_norm": 0.03460497781634331,
+      "learning_rate": 7.508591065292097e-05,
+      "loss": 0.0244,
+      "step": 490
+    },
+    {
+      "epoch": 123.96,
+      "grad_norm": 0.0392792634665966,
+      "learning_rate": 7.47995418098511e-05,
+      "loss": 0.0259,
+      "step": 495
+    },
+    {
+      "epoch": 125.0,
+      "grad_norm": 0.11717823147773743,
+      "learning_rate": 7.451317296678122e-05,
+      "loss": 0.0253,
+      "step": 500
+    },
+    {
+      "epoch": 126.32,
+      "grad_norm": 0.03736049681901932,
+      "learning_rate": 7.422680412371135e-05,
+      "loss": 0.024,
+      "step": 505
+    },
+    {
+      "epoch": 127.64,
+      "grad_norm": 0.04238331690430641,
+      "learning_rate": 7.394043528064147e-05,
+      "loss": 0.0254,
+      "step": 510
+    },
+    {
+      "epoch": 128.96,
+      "grad_norm": 0.036686044186353683,
+      "learning_rate": 7.36540664375716e-05,
+      "loss": 0.0249,
+      "step": 515
+    },
+    {
+      "epoch": 130.0,
+      "grad_norm": 0.11898811906576157,
+      "learning_rate": 7.336769759450171e-05,
+      "loss": 0.0245,
+      "step": 520
+    },
+    {
+      "epoch": 131.32,
+      "grad_norm": 0.03935862332582474,
+      "learning_rate": 7.308132875143184e-05,
+      "loss": 0.0248,
+      "step": 525
+    },
+    {
+      "epoch": 132.64,
+      "grad_norm": 0.035374052822589874,
+      "learning_rate": 7.279495990836197e-05,
+      "loss": 0.0244,
+      "step": 530
+    },
+    {
+      "epoch": 133.96,
+      "grad_norm": 0.03667380288243294,
+      "learning_rate": 7.250859106529209e-05,
+      "loss": 0.0246,
+      "step": 535
+    },
+    {
+      "epoch": 135.0,
+      "grad_norm": 0.1304934173822403,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.0249,
+      "step": 540
+    },
+    {
+      "epoch": 136.32,
+      "grad_norm": 0.03300497308373451,
+      "learning_rate": 7.193585337915235e-05,
+      "loss": 0.0266,
+      "step": 545
+    },
+    {
+      "epoch": 137.64,
+      "grad_norm": 0.03661350905895233,
+      "learning_rate": 7.164948453608247e-05,
+      "loss": 0.0247,
+      "step": 550
+    },
+    {
+      "epoch": 138.96,
+      "grad_norm": 0.04630376026034355,
+      "learning_rate": 7.136311569301261e-05,
+      "loss": 0.0271,
+      "step": 555
+    },
+    {
+      "epoch": 140.0,
+      "grad_norm": 0.10119768232107162,
+      "learning_rate": 7.107674684994274e-05,
+      "loss": 0.0252,
+      "step": 560
+    },
+    {
+      "epoch": 141.32,
+      "grad_norm": 0.030455591157078743,
+      "learning_rate": 7.079037800687286e-05,
+      "loss": 0.0255,
+      "step": 565
+    },
+    {
+      "epoch": 142.64,
+      "grad_norm": 0.036023061722517014,
+      "learning_rate": 7.050400916380299e-05,
+      "loss": 0.0255,
+      "step": 570
+    },
+    {
+      "epoch": 143.96,
+      "grad_norm": 0.03697853162884712,
+      "learning_rate": 7.02176403207331e-05,
+      "loss": 0.023,
+      "step": 575
+    },
+    {
+      "epoch": 145.0,
+      "grad_norm": 0.10646484047174454,
+      "learning_rate": 6.993127147766323e-05,
+      "loss": 0.0246,
+      "step": 580
+    },
+    {
+      "epoch": 146.32,
+      "grad_norm": 0.03505175933241844,
+      "learning_rate": 6.964490263459336e-05,
+      "loss": 0.0246,
+      "step": 585
+    },
+    {
+      "epoch": 147.64,
+      "grad_norm": 0.03091881051659584,
+      "learning_rate": 6.935853379152348e-05,
+      "loss": 0.0236,
+      "step": 590
+    },
+    {
+      "epoch": 148.96,
+      "grad_norm": 0.03566066175699234,
+      "learning_rate": 6.907216494845361e-05,
+      "loss": 0.0257,
+      "step": 595
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 0.13368169963359833,
+      "learning_rate": 6.878579610538374e-05,
+      "loss": 0.0246,
+      "step": 600
+    },
+    {
+      "epoch": 151.32,
+      "grad_norm": 0.03456564620137215,
+      "learning_rate": 6.849942726231386e-05,
+      "loss": 0.0249,
+      "step": 605
+    },
+    {
+      "epoch": 152.64,
+      "grad_norm": 0.037680983543395996,
+      "learning_rate": 6.821305841924399e-05,
+      "loss": 0.0236,
+      "step": 610
+    },
+    {
+      "epoch": 153.96,
+      "grad_norm": 0.02970520406961441,
+      "learning_rate": 6.792668957617412e-05,
+      "loss": 0.0235,
+      "step": 615
+    },
+    {
+      "epoch": 155.0,
+      "grad_norm": 0.12523308396339417,
+      "learning_rate": 6.764032073310424e-05,
+      "loss": 0.0237,
+      "step": 620
+    },
+    {
+      "epoch": 156.32,
+      "grad_norm": 0.03233841061592102,
+      "learning_rate": 6.735395189003437e-05,
+      "loss": 0.0234,
+      "step": 625
+    },
+    {
+      "epoch": 157.64,
+      "grad_norm": 0.03602683171629906,
+      "learning_rate": 6.706758304696448e-05,
+      "loss": 0.0241,
+      "step": 630
+    },
+    {
+      "epoch": 158.96,
+      "grad_norm": 0.03763331472873688,
+      "learning_rate": 6.678121420389462e-05,
+      "loss": 0.0238,
+      "step": 635
+    },
+    {
+      "epoch": 160.0,
+      "grad_norm": 0.122522734105587,
+      "learning_rate": 6.649484536082475e-05,
+      "loss": 0.0252,
+      "step": 640
+    },
+    {
+      "epoch": 161.32,
+      "grad_norm": 0.033675480633974075,
+      "learning_rate": 6.620847651775487e-05,
+      "loss": 0.0241,
+      "step": 645
+    },
+    {
+      "epoch": 162.64,
+      "grad_norm": 0.03151499852538109,
+      "learning_rate": 6.5922107674685e-05,
+      "loss": 0.0248,
+      "step": 650
+    },
+    {
+      "epoch": 163.96,
+      "grad_norm": 0.03151350095868111,
+      "learning_rate": 6.563573883161513e-05,
+      "loss": 0.0245,
+      "step": 655
+    },
+    {
+      "epoch": 165.0,
+      "grad_norm": 0.11250028759241104,
+      "learning_rate": 6.534936998854525e-05,
+      "loss": 0.0252,
+      "step": 660
+    },
+    {
+      "epoch": 166.32,
+      "grad_norm": 0.033449526876211166,
+      "learning_rate": 6.506300114547538e-05,
+      "loss": 0.025,
+      "step": 665
+    },
+    {
+      "epoch": 167.64,
+      "grad_norm": 0.030957462266087532,
+      "learning_rate": 6.477663230240551e-05,
+      "loss": 0.0257,
+      "step": 670
+    },
+    {
+      "epoch": 168.96,
+      "grad_norm": 0.03218599036335945,
+      "learning_rate": 6.449026345933563e-05,
+      "loss": 0.0257,
+      "step": 675
+    },
+    {
+      "epoch": 170.0,
+      "grad_norm": 0.09439749270677567,
+      "learning_rate": 6.420389461626576e-05,
+      "loss": 0.0246,
+      "step": 680
+    },
+    {
+      "epoch": 171.32,
+      "grad_norm": 0.029240014031529427,
+      "learning_rate": 6.391752577319587e-05,
+      "loss": 0.0236,
+      "step": 685
+    },
+    {
+      "epoch": 172.64,
+      "grad_norm": 0.034742940217256546,
+      "learning_rate": 6.3631156930126e-05,
+      "loss": 0.0236,
+      "step": 690
+    },
+    {
+      "epoch": 173.96,
+      "grad_norm": 0.030582355335354805,
+      "learning_rate": 6.334478808705613e-05,
+      "loss": 0.0236,
+      "step": 695
+    },
+    {
+      "epoch": 175.0,
+      "grad_norm": 0.08759982883930206,
+      "learning_rate": 6.305841924398625e-05,
+      "loss": 0.0265,
+      "step": 700
+    },
+    {
+      "epoch": 176.32,
+      "grad_norm": 0.029291506856679916,
+      "learning_rate": 6.277205040091638e-05,
+      "loss": 0.024,
+      "step": 705
+    },
+    {
+      "epoch": 177.64,
+      "grad_norm": 0.031786780804395676,
+      "learning_rate": 6.24856815578465e-05,
+      "loss": 0.0263,
+      "step": 710
+    },
+    {
+      "epoch": 178.96,
+      "grad_norm": 0.035743582993745804,
+      "learning_rate": 6.219931271477663e-05,
+      "loss": 0.0261,
+      "step": 715
+    },
+    {
+      "epoch": 180.0,
+      "grad_norm": 0.1054234430193901,
+      "learning_rate": 6.191294387170676e-05,
+      "loss": 0.0253,
+      "step": 720
+    },
+    {
+      "epoch": 181.32,
+      "grad_norm": 0.03243524953722954,
+      "learning_rate": 6.162657502863689e-05,
+      "loss": 0.0251,
+      "step": 725
+    },
+    {
+      "epoch": 182.64,
+      "grad_norm": 0.03032608889043331,
+      "learning_rate": 6.134020618556701e-05,
+      "loss": 0.0251,
+      "step": 730
+    },
+    {
+      "epoch": 183.96,
+      "grad_norm": 0.03101290389895439,
+      "learning_rate": 6.105383734249714e-05,
+      "loss": 0.0241,
+      "step": 735
+    },
+    {
+      "epoch": 185.0,
+      "grad_norm": 0.07965508848428726,
+      "learning_rate": 6.076746849942726e-05,
+      "loss": 0.0229,
+      "step": 740
+    },
+    {
+      "epoch": 186.32,
+      "grad_norm": 0.03219285607337952,
+      "learning_rate": 6.0481099656357384e-05,
+      "loss": 0.0239,
+      "step": 745
+    },
+    {
+      "epoch": 187.64,
+      "grad_norm": 0.032278887927532196,
+      "learning_rate": 6.019473081328752e-05,
+      "loss": 0.0246,
+      "step": 750
+    },
+    {
+      "epoch": 188.96,
+      "grad_norm": 0.03127485513687134,
+      "learning_rate": 5.9908361970217644e-05,
+      "loss": 0.0248,
+      "step": 755
+    },
+    {
+      "epoch": 190.0,
+      "grad_norm": 0.09103897213935852,
+      "learning_rate": 5.962199312714777e-05,
+      "loss": 0.0262,
+      "step": 760
+    },
+    {
+      "epoch": 191.32,
+      "grad_norm": 0.032904159277677536,
+      "learning_rate": 5.93356242840779e-05,
+      "loss": 0.0247,
+      "step": 765
+    },
+    {
+      "epoch": 192.64,
+      "grad_norm": 0.034943412989377975,
+      "learning_rate": 5.904925544100802e-05,
+      "loss": 0.0245,
+      "step": 770
+    },
+    {
+      "epoch": 193.96,
+      "grad_norm": 0.029192674905061722,
+      "learning_rate": 5.876288659793815e-05,
+      "loss": 0.0248,
+      "step": 775
+    },
+    {
+      "epoch": 195.0,
+      "grad_norm": 0.13117201626300812,
+      "learning_rate": 5.8476517754868276e-05,
+      "loss": 0.0257,
+      "step": 780
+    },
+    {
+      "epoch": 196.32,
+      "grad_norm": 0.030321085825562477,
+      "learning_rate": 5.81901489117984e-05,
+      "loss": 0.0244,
+      "step": 785
+    },
+    {
+      "epoch": 197.64,
+      "grad_norm": 0.03632837533950806,
+      "learning_rate": 5.790378006872853e-05,
+      "loss": 0.0247,
+      "step": 790
+    },
+    {
+      "epoch": 198.96,
+      "grad_norm": 0.029967786744236946,
+      "learning_rate": 5.761741122565865e-05,
+      "loss": 0.0252,
+      "step": 795
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 0.07372202724218369,
+      "learning_rate": 5.7331042382588775e-05,
+      "loss": 0.024,
+      "step": 800
+    },
+    {
+      "epoch": 201.32,
+      "grad_norm": 0.033607207238674164,
+      "learning_rate": 5.70446735395189e-05,
+      "loss": 0.0242,
+      "step": 805
+    },
+    {
+      "epoch": 202.64,
+      "grad_norm": 0.0330338180065155,
+      "learning_rate": 5.675830469644903e-05,
+      "loss": 0.0244,
+      "step": 810
+    },
+    {
+      "epoch": 203.96,
+      "grad_norm": 0.034020259976387024,
+      "learning_rate": 5.6471935853379155e-05,
+      "loss": 0.0227,
+      "step": 815
+    },
+    {
+      "epoch": 205.0,
+      "grad_norm": 0.18551097810268402,
+      "learning_rate": 5.618556701030928e-05,
+      "loss": 0.0265,
+      "step": 820
+    },
+    {
+      "epoch": 206.32,
+      "grad_norm": 0.033085715025663376,
+      "learning_rate": 5.589919816723941e-05,
+      "loss": 0.0247,
+      "step": 825
+    },
+    {
+      "epoch": 207.64,
+      "grad_norm": 0.03386640176177025,
+      "learning_rate": 5.5612829324169534e-05,
+      "loss": 0.0238,
+      "step": 830
+    },
+    {
+      "epoch": 208.96,
+      "grad_norm": 0.035608984529972076,
+      "learning_rate": 5.532646048109966e-05,
+      "loss": 0.0247,
+      "step": 835
+    },
+    {
+      "epoch": 210.0,
+      "grad_norm": 0.10785692930221558,
+      "learning_rate": 5.504009163802979e-05,
+      "loss": 0.0247,
+      "step": 840
+    },
+    {
+      "epoch": 211.32,
+      "grad_norm": 0.03013814426958561,
+      "learning_rate": 5.4753722794959914e-05,
+      "loss": 0.0251,
+      "step": 845
+    },
+    {
+      "epoch": 212.64,
+      "grad_norm": 0.02756708860397339,
+      "learning_rate": 5.4467353951890033e-05,
+      "loss": 0.0257,
+      "step": 850
+    },
+    {
+      "epoch": 213.96,
+      "grad_norm": 0.030665891245007515,
+      "learning_rate": 5.418098510882016e-05,
+      "loss": 0.0243,
+      "step": 855
+    },
+    {
+      "epoch": 215.0,
+      "grad_norm": 0.0745956227183342,
+      "learning_rate": 5.3894616265750286e-05,
+      "loss": 0.0234,
+      "step": 860
+    },
+    {
+      "epoch": 216.32,
+      "grad_norm": 0.028612101450562477,
+      "learning_rate": 5.360824742268041e-05,
+      "loss": 0.0233,
+      "step": 865
+    },
+    {
+      "epoch": 217.64,
+      "grad_norm": 0.03162551298737526,
+      "learning_rate": 5.332187857961054e-05,
+      "loss": 0.0251,
+      "step": 870
+    },
+    {
+      "epoch": 218.96,
+      "grad_norm": 0.031918879598379135,
+      "learning_rate": 5.3035509736540666e-05,
+      "loss": 0.0236,
+      "step": 875
+    },
+    {
+      "epoch": 220.0,
+      "grad_norm": 0.10774800181388855,
+      "learning_rate": 5.274914089347079e-05,
+      "loss": 0.0239,
+      "step": 880
+    },
+    {
+      "epoch": 221.32,
+      "grad_norm": 0.03076888434588909,
+      "learning_rate": 5.246277205040092e-05,
+      "loss": 0.0264,
+      "step": 885
+    },
+    {
+      "epoch": 222.64,
+      "grad_norm": 0.028414763510227203,
+      "learning_rate": 5.2176403207331045e-05,
+      "loss": 0.024,
+      "step": 890
+    },
+    {
+      "epoch": 223.96,
+      "grad_norm": 0.030206475406885147,
+      "learning_rate": 5.189003436426118e-05,
+      "loss": 0.024,
+      "step": 895
+    },
+    {
+      "epoch": 225.0,
+      "grad_norm": 0.08630042523145676,
+      "learning_rate": 5.1603665521191305e-05,
+      "loss": 0.0239,
+      "step": 900
+    },
+    {
+      "epoch": 226.32,
+      "grad_norm": 0.028488921001553535,
+      "learning_rate": 5.131729667812142e-05,
+      "loss": 0.023,
+      "step": 905
+    },
+    {
+      "epoch": 227.64,
+      "grad_norm": 0.030469467863440514,
+      "learning_rate": 5.1030927835051544e-05,
+      "loss": 0.0241,
+      "step": 910
+    },
+    {
+      "epoch": 228.96,
+      "grad_norm": 0.03881875425577164,
+      "learning_rate": 5.074455899198167e-05,
+      "loss": 0.0246,
+      "step": 915
+    },
+    {
+      "epoch": 230.0,
+      "grad_norm": 0.12875375151634216,
+      "learning_rate": 5.04581901489118e-05,
+      "loss": 0.0251,
+      "step": 920
+    },
+    {
+      "epoch": 231.32,
+      "grad_norm": 0.032451994717121124,
+      "learning_rate": 5.0171821305841924e-05,
+      "loss": 0.0241,
+      "step": 925
+    },
+    {
+      "epoch": 232.64,
+      "grad_norm": 0.027808066457509995,
+      "learning_rate": 4.988545246277205e-05,
+      "loss": 0.0235,
+      "step": 930
+    },
+    {
+      "epoch": 233.96,
+      "grad_norm": 0.029480665922164917,
+      "learning_rate": 4.9599083619702184e-05,
+      "loss": 0.0244,
+      "step": 935
+    },
+    {
+      "epoch": 235.0,
+      "grad_norm": 0.10908841341733932,
+      "learning_rate": 4.931271477663231e-05,
+      "loss": 0.0244,
+      "step": 940
+    },
+    {
+      "epoch": 236.32,
+      "grad_norm": 0.030934063717722893,
+      "learning_rate": 4.902634593356243e-05,
+      "loss": 0.0233,
+      "step": 945
+    },
+    {
+      "epoch": 237.64,
+      "grad_norm": 0.03168102353811264,
+      "learning_rate": 4.8739977090492556e-05,
+      "loss": 0.025,
+      "step": 950
+    },
+    {
+      "epoch": 238.96,
+      "grad_norm": 0.03343883156776428,
+      "learning_rate": 4.845360824742268e-05,
+      "loss": 0.0247,
+      "step": 955
+    },
+    {
+      "epoch": 240.0,
+      "grad_norm": 0.09705886244773865,
+      "learning_rate": 4.816723940435281e-05,
+      "loss": 0.0241,
+      "step": 960
+    },
+    {
+      "epoch": 241.32,
+      "grad_norm": 0.030061587691307068,
+      "learning_rate": 4.7880870561282936e-05,
+      "loss": 0.0245,
+      "step": 965
+    },
+    {
+      "epoch": 242.64,
+      "grad_norm": 0.03334140032529831,
+      "learning_rate": 4.7594501718213055e-05,
+      "loss": 0.0235,
+      "step": 970
+    },
+    {
+      "epoch": 243.96,
+      "grad_norm": 0.029101941734552383,
+      "learning_rate": 4.730813287514318e-05,
+      "loss": 0.0245,
+      "step": 975
+    },
+    {
+      "epoch": 245.0,
+      "grad_norm": 0.0960671678185463,
+      "learning_rate": 4.7021764032073315e-05,
+      "loss": 0.0234,
+      "step": 980
+    },
+    {
+      "epoch": 246.32,
+      "grad_norm": 0.02781585231423378,
+      "learning_rate": 4.673539518900344e-05,
+      "loss": 0.0245,
+      "step": 985
+    },
+    {
+      "epoch": 247.64,
+      "grad_norm": 0.028559748083353043,
+      "learning_rate": 4.644902634593357e-05,
+      "loss": 0.0238,
+      "step": 990
+    },
+    {
+      "epoch": 248.96,
+      "grad_norm": 0.033065810799598694,
+      "learning_rate": 4.6162657502863694e-05,
+      "loss": 0.0248,
+      "step": 995
+    },
+    {
+      "epoch": 250.0,
+      "grad_norm": 0.09891372174024582,
+      "learning_rate": 4.5876288659793814e-05,
+      "loss": 0.0246,
+      "step": 1000
+    },
+    {
+      "epoch": 251.32,
+      "grad_norm": 0.034241512417793274,
+      "learning_rate": 4.558991981672394e-05,
+      "loss": 0.0238,
+      "step": 1005
+    },
+    {
+      "epoch": 252.64,
+      "grad_norm": 0.029995698481798172,
+      "learning_rate": 4.530355097365407e-05,
+      "loss": 0.0234,
+      "step": 1010
+    },
+    {
+      "epoch": 253.96,
+      "grad_norm": 0.02568650431931019,
+      "learning_rate": 4.5017182130584194e-05,
+      "loss": 0.0252,
+      "step": 1015
+    },
+    {
+      "epoch": 255.0,
+      "grad_norm": 0.10262944549322128,
+      "learning_rate": 4.473081328751432e-05,
+      "loss": 0.0254,
+      "step": 1020
+    },
+    {
+      "epoch": 256.32,
+      "grad_norm": 0.030975807458162308,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.024,
+      "step": 1025
+    },
+    {
+      "epoch": 257.64,
+      "grad_norm": 0.03410029411315918,
+      "learning_rate": 4.415807560137457e-05,
+      "loss": 0.0235,
+      "step": 1030
+    },
+    {
+      "epoch": 258.96,
+      "grad_norm": 0.035321272909641266,
+      "learning_rate": 4.38717067583047e-05,
+      "loss": 0.0247,
+      "step": 1035
+    },
+    {
+      "epoch": 260.0,
+      "grad_norm": 0.11808375269174576,
+      "learning_rate": 4.3585337915234826e-05,
+      "loss": 0.0253,
+      "step": 1040
+    },
+    {
+      "epoch": 261.32,
+      "grad_norm": 0.031260352581739426,
+      "learning_rate": 4.329896907216495e-05,
+      "loss": 0.0247,
+      "step": 1045
+    },
+    {
+      "epoch": 262.64,
+      "grad_norm": 0.02619328908622265,
+      "learning_rate": 4.301260022909508e-05,
+      "loss": 0.0236,
+      "step": 1050
+    },
+    {
+      "epoch": 263.96,
+      "grad_norm": 0.029771093279123306,
+      "learning_rate": 4.27262313860252e-05,
+      "loss": 0.026,
+      "step": 1055
+    },
+    {
+      "epoch": 265.0,
+      "grad_norm": 0.06893468648195267,
+      "learning_rate": 4.2439862542955325e-05,
+      "loss": 0.0239,
+      "step": 1060
+    },
+    {
+      "epoch": 266.32,
+      "grad_norm": 0.033501140773296356,
+      "learning_rate": 4.215349369988545e-05,
+      "loss": 0.0241,
+      "step": 1065
+    },
+    {
+      "epoch": 267.64,
+      "grad_norm": 0.024325627833604813,
+      "learning_rate": 4.1867124856815585e-05,
+      "loss": 0.0245,
+      "step": 1070
+    },
+    {
+      "epoch": 268.96,
+      "grad_norm": 0.02805325947701931,
+      "learning_rate": 4.158075601374571e-05,
+      "loss": 0.0239,
+      "step": 1075
+    },
+    {
+      "epoch": 270.0,
+      "grad_norm": 0.06762038171291351,
+      "learning_rate": 4.129438717067583e-05,
+      "loss": 0.0221,
+      "step": 1080
+    },
+    {
+      "epoch": 271.32,
+      "grad_norm": 0.029501326382160187,
+      "learning_rate": 4.100801832760596e-05,
+      "loss": 0.0245,
+      "step": 1085
+    },
+    {
+      "epoch": 272.64,
+      "grad_norm": 0.029515661299228668,
+      "learning_rate": 4.0721649484536084e-05,
+      "loss": 0.0238,
+      "step": 1090
+    },
+    {
+      "epoch": 273.96,
+      "grad_norm": 0.027613315731287003,
+      "learning_rate": 4.043528064146621e-05,
+      "loss": 0.0224,
+      "step": 1095
+    },
+    {
+      "epoch": 275.0,
+      "grad_norm": 0.09525981545448303,
+      "learning_rate": 4.014891179839634e-05,
+      "loss": 0.0253,
+      "step": 1100
+    },
+    {
+      "epoch": 276.32,
+      "grad_norm": 0.03334690257906914,
+      "learning_rate": 3.9862542955326463e-05,
+      "loss": 0.0237,
+      "step": 1105
+    },
+    {
+      "epoch": 277.64,
+      "grad_norm": 0.029919110238552094,
+      "learning_rate": 3.957617411225659e-05,
+      "loss": 0.0245,
+      "step": 1110
+    },
+    {
+      "epoch": 278.96,
+      "grad_norm": 0.030859502032399178,
+      "learning_rate": 3.9289805269186716e-05,
+      "loss": 0.025,
+      "step": 1115
+    },
+    {
+      "epoch": 280.0,
+      "grad_norm": 0.10942446440458298,
+      "learning_rate": 3.900343642611684e-05,
+      "loss": 0.025,
+      "step": 1120
+    },
+    {
+      "epoch": 281.32,
+      "grad_norm": 0.03168985992670059,
+      "learning_rate": 3.871706758304697e-05,
+      "loss": 0.0235,
+      "step": 1125
+    },
+    {
+      "epoch": 282.64,
+      "grad_norm": 0.026724940165877342,
+      "learning_rate": 3.8430698739977096e-05,
+      "loss": 0.0241,
+      "step": 1130
+    },
+    {
+      "epoch": 283.96,
+      "grad_norm": 0.031092727556824684,
+      "learning_rate": 3.8144329896907216e-05,
+      "loss": 0.0255,
+      "step": 1135
+    },
+    {
+      "epoch": 285.0,
+      "grad_norm": 0.09548906981945038,
+      "learning_rate": 3.785796105383734e-05,
+      "loss": 0.0227,
+      "step": 1140
+    },
+    {
+      "epoch": 286.32,
+      "grad_norm": 0.02706352062523365,
+      "learning_rate": 3.757159221076747e-05,
+      "loss": 0.0234,
+      "step": 1145
+    },
+    {
+      "epoch": 287.64,
+      "grad_norm": 0.02627880498766899,
+      "learning_rate": 3.7285223367697595e-05,
+      "loss": 0.0237,
+      "step": 1150
+    },
+    {
+      "epoch": 288.96,
+      "grad_norm": 0.027149919420480728,
+      "learning_rate": 3.699885452462772e-05,
+      "loss": 0.0238,
+      "step": 1155
+    },
+    {
+      "epoch": 290.0,
+      "grad_norm": 0.08567748218774796,
+      "learning_rate": 3.671248568155785e-05,
+      "loss": 0.025,
+      "step": 1160
+    },
+    {
+      "epoch": 291.32,
+      "grad_norm": 0.030523810535669327,
+      "learning_rate": 3.6426116838487974e-05,
+      "loss": 0.0243,
+      "step": 1165
+    },
+    {
+      "epoch": 292.64,
+      "grad_norm": 0.026270387694239616,
+      "learning_rate": 3.61397479954181e-05,
+      "loss": 0.0235,
+      "step": 1170
+    },
+    {
+      "epoch": 293.96,
+      "grad_norm": 0.03181422874331474,
+      "learning_rate": 3.585337915234823e-05,
+      "loss": 0.0246,
+      "step": 1175
+    },
+    {
+      "epoch": 295.0,
+      "grad_norm": 0.10440130531787872,
+      "learning_rate": 3.5567010309278354e-05,
+      "loss": 0.0248,
+      "step": 1180
+    },
+    {
+      "epoch": 296.32,
+      "grad_norm": 0.02957691065967083,
+      "learning_rate": 3.528064146620848e-05,
+      "loss": 0.0249,
+      "step": 1185
+    },
+    {
+      "epoch": 297.64,
+      "grad_norm": 0.03012160025537014,
+      "learning_rate": 3.49942726231386e-05,
+      "loss": 0.0236,
+      "step": 1190
+    },
+    {
+      "epoch": 298.96,
+      "grad_norm": 0.03137727081775665,
+      "learning_rate": 3.4707903780068726e-05,
+      "loss": 0.0231,
+      "step": 1195
+    },
+    {
+      "epoch": 300.0,
+      "grad_norm": 0.08718854933977127,
+      "learning_rate": 3.442153493699885e-05,
+      "loss": 0.0236,
+      "step": 1200
+    },
+    {
+      "epoch": 301.32,
+      "grad_norm": 0.029862714931368828,
+      "learning_rate": 3.4135166093928986e-05,
+      "loss": 0.025,
+      "step": 1205
+    },
+    {
+      "epoch": 302.64,
+      "grad_norm": 0.02560766227543354,
+      "learning_rate": 3.384879725085911e-05,
+      "loss": 0.0231,
+      "step": 1210
+    },
+    {
+      "epoch": 303.96,
+      "grad_norm": 0.028654081746935844,
+      "learning_rate": 3.356242840778923e-05,
+      "loss": 0.0234,
+      "step": 1215
+    },
+    {
+      "epoch": 305.0,
+      "grad_norm": 0.0949280634522438,
+      "learning_rate": 3.327605956471936e-05,
+      "loss": 0.025,
+      "step": 1220
+    },
+    {
+      "epoch": 306.32,
+      "grad_norm": 0.026477837935090065,
+      "learning_rate": 3.2989690721649485e-05,
+      "loss": 0.0234,
+      "step": 1225
+    },
+    {
+      "epoch": 307.64,
+      "grad_norm": 0.026831798255443573,
+      "learning_rate": 3.270332187857961e-05,
+      "loss": 0.0248,
+      "step": 1230
+    },
+    {
+      "epoch": 308.96,
+      "grad_norm": 0.028621774166822433,
+      "learning_rate": 3.241695303550974e-05,
+      "loss": 0.0249,
+      "step": 1235
+    },
+    {
+      "epoch": 310.0,
+      "grad_norm": 0.09070394188165665,
+      "learning_rate": 3.2130584192439865e-05,
+      "loss": 0.0226,
+      "step": 1240
+    },
+    {
+      "epoch": 311.32,
+      "grad_norm": 0.026786576956510544,
+      "learning_rate": 3.184421534936999e-05,
+      "loss": 0.0221,
+      "step": 1245
+    },
+    {
+      "epoch": 312.64,
+      "grad_norm": 0.02507033571600914,
+      "learning_rate": 3.155784650630012e-05,
+      "loss": 0.0238,
+      "step": 1250
+    },
+    {
+      "epoch": 313.96,
+      "grad_norm": 0.028852174058556557,
+      "learning_rate": 3.1271477663230244e-05,
+      "loss": 0.0247,
+      "step": 1255
+    },
+    {
+      "epoch": 315.0,
+      "grad_norm": 0.08960720151662827,
+      "learning_rate": 3.098510882016037e-05,
+      "loss": 0.0245,
+      "step": 1260
+    },
+    {
+      "epoch": 316.32,
+      "grad_norm": 0.02706362120807171,
+      "learning_rate": 3.06987399770905e-05,
+      "loss": 0.0232,
+      "step": 1265
+    },
+    {
+      "epoch": 317.64,
+      "grad_norm": 0.034065067768096924,
+      "learning_rate": 3.0412371134020617e-05,
+      "loss": 0.0243,
+      "step": 1270
+    },
+    {
+      "epoch": 318.96,
+      "grad_norm": 0.03338128700852394,
+      "learning_rate": 3.0126002290950743e-05,
+      "loss": 0.0232,
+      "step": 1275
+    },
+    {
+      "epoch": 320.0,
+      "grad_norm": 0.07813101261854172,
+      "learning_rate": 2.983963344788087e-05,
+      "loss": 0.0237,
+      "step": 1280
+    },
+    {
+      "epoch": 321.32,
+      "grad_norm": 0.024868899956345558,
+      "learning_rate": 2.9553264604811e-05,
+      "loss": 0.0243,
+      "step": 1285
+    },
+    {
+      "epoch": 322.64,
+      "grad_norm": 0.0315781868994236,
+      "learning_rate": 2.9266895761741126e-05,
+      "loss": 0.0246,
+      "step": 1290
+    },
+    {
+      "epoch": 323.96,
+      "grad_norm": 0.02967393584549427,
+      "learning_rate": 2.8980526918671253e-05,
+      "loss": 0.0232,
+      "step": 1295
+    },
+    {
+      "epoch": 325.0,
+      "grad_norm": 0.09609349817037582,
+      "learning_rate": 2.8694158075601372e-05,
+      "loss": 0.0244,
+      "step": 1300
+    },
+    {
+      "epoch": 326.32,
+      "grad_norm": 0.029491806402802467,
+      "learning_rate": 2.8407789232531502e-05,
+      "loss": 0.0239,
+      "step": 1305
+    },
+    {
+      "epoch": 327.64,
+      "grad_norm": 0.029985398054122925,
+      "learning_rate": 2.812142038946163e-05,
+      "loss": 0.0256,
+      "step": 1310
+    },
+    {
+      "epoch": 328.96,
+      "grad_norm": 0.0266531091183424,
+      "learning_rate": 2.7835051546391755e-05,
+      "loss": 0.0235,
+      "step": 1315
+    },
+    {
+      "epoch": 330.0,
+      "grad_norm": 0.10653591901063919,
+      "learning_rate": 2.754868270332188e-05,
+      "loss": 0.0245,
+      "step": 1320
+    },
+    {
+      "epoch": 331.32,
+      "grad_norm": 0.026373600587248802,
+      "learning_rate": 2.7262313860252005e-05,
+      "loss": 0.023,
+      "step": 1325
+    },
+    {
+      "epoch": 332.64,
+      "grad_norm": 0.02818775363266468,
+      "learning_rate": 2.697594501718213e-05,
+      "loss": 0.0239,
+      "step": 1330
+    },
+    {
+      "epoch": 333.96,
+      "grad_norm": 0.031018992885947227,
+      "learning_rate": 2.6689576174112258e-05,
+      "loss": 0.025,
+      "step": 1335
+    },
+    {
+      "epoch": 335.0,
+      "grad_norm": 0.08792488276958466,
+      "learning_rate": 2.6403207331042384e-05,
+      "loss": 0.0238,
+      "step": 1340
+    },
+    {
+      "epoch": 336.32,
+      "grad_norm": 0.028193149715662003,
+      "learning_rate": 2.611683848797251e-05,
+      "loss": 0.0236,
+      "step": 1345
+    },
+    {
+      "epoch": 337.64,
+      "grad_norm": 0.028593050315976143,
+      "learning_rate": 2.5830469644902637e-05,
+      "loss": 0.0244,
+      "step": 1350
+    },
+    {
+      "epoch": 338.96,
+      "grad_norm": 0.030603837221860886,
+      "learning_rate": 2.554410080183276e-05,
+      "loss": 0.0235,
+      "step": 1355
+    },
+    {
+      "epoch": 340.0,
+      "grad_norm": 0.08820123970508575,
+      "learning_rate": 2.5257731958762887e-05,
+      "loss": 0.0243,
+      "step": 1360
+    },
+    {
+      "epoch": 341.32,
+      "grad_norm": 0.025534510612487793,
+      "learning_rate": 2.4971363115693013e-05,
+      "loss": 0.0239,
+      "step": 1365
+    },
+    {
+      "epoch": 342.64,
+      "grad_norm": 0.02913915552198887,
+      "learning_rate": 2.468499427262314e-05,
+      "loss": 0.025,
+      "step": 1370
+    },
+    {
+      "epoch": 343.96,
+      "grad_norm": 0.027463385835289955,
+      "learning_rate": 2.4398625429553266e-05,
+      "loss": 0.0239,
+      "step": 1375
+    },
+    {
+      "epoch": 345.0,
+      "grad_norm": 0.1210053488612175,
+      "learning_rate": 2.4112256586483393e-05,
+      "loss": 0.0238,
+      "step": 1380
+    },
+    {
+      "epoch": 346.32,
+      "grad_norm": 0.027720389887690544,
+      "learning_rate": 2.3825887743413516e-05,
+      "loss": 0.0242,
+      "step": 1385
+    },
+    {
+      "epoch": 347.64,
+      "grad_norm": 0.027453245595097542,
+      "learning_rate": 2.3539518900343642e-05,
+      "loss": 0.0242,
+      "step": 1390
+    },
+    {
+      "epoch": 348.96,
+      "grad_norm": 0.02763674035668373,
+      "learning_rate": 2.3253150057273772e-05,
+      "loss": 0.0234,
+      "step": 1395
+    },
+    {
+      "epoch": 350.0,
+      "grad_norm": 0.08798635005950928,
+      "learning_rate": 2.2966781214203895e-05,
+      "loss": 0.0237,
+      "step": 1400
+    },
+    {
+      "epoch": 351.32,
+      "grad_norm": 0.0286979041993618,
+      "learning_rate": 2.268041237113402e-05,
+      "loss": 0.0238,
+      "step": 1405
+    },
+    {
+      "epoch": 352.64,
+      "grad_norm": 0.03111179918050766,
+      "learning_rate": 2.2394043528064148e-05,
+      "loss": 0.0235,
+      "step": 1410
+    },
+    {
+      "epoch": 353.96,
+      "grad_norm": 0.030224261805415154,
+      "learning_rate": 2.210767468499427e-05,
+      "loss": 0.024,
+      "step": 1415
+    },
+    {
+      "epoch": 355.0,
+      "grad_norm": 0.09825381636619568,
+      "learning_rate": 2.18213058419244e-05,
+      "loss": 0.0232,
+      "step": 1420
+    },
+    {
+      "epoch": 356.32,
+      "grad_norm": 0.029364706948399544,
+      "learning_rate": 2.1534936998854528e-05,
+      "loss": 0.024,
+      "step": 1425
+    },
+    {
+      "epoch": 357.64,
+      "grad_norm": 0.02721550688147545,
+      "learning_rate": 2.124856815578465e-05,
+      "loss": 0.0238,
+      "step": 1430
+    },
+    {
+      "epoch": 358.96,
+      "grad_norm": 0.027872690930962563,
+      "learning_rate": 2.0962199312714777e-05,
+      "loss": 0.0247,
+      "step": 1435
+    },
+    {
+      "epoch": 360.0,
+      "grad_norm": 0.11348076164722443,
+      "learning_rate": 2.0675830469644904e-05,
+      "loss": 0.0247,
+      "step": 1440
+    },
+    {
+      "epoch": 361.32,
+      "grad_norm": 0.02704751119017601,
+      "learning_rate": 2.038946162657503e-05,
+      "loss": 0.0247,
+      "step": 1445
+    },
+    {
+      "epoch": 362.64,
+      "grad_norm": 0.027226556092500687,
+      "learning_rate": 2.0103092783505157e-05,
+      "loss": 0.0245,
+      "step": 1450
+    },
+    {
+      "epoch": 363.96,
+      "grad_norm": 0.02961592935025692,
+      "learning_rate": 1.981672394043528e-05,
+      "loss": 0.0251,
+      "step": 1455
+    },
+    {
+      "epoch": 365.0,
+      "grad_norm": 0.09505930542945862,
+      "learning_rate": 1.9530355097365406e-05,
+      "loss": 0.0225,
+      "step": 1460
+    },
+    {
+      "epoch": 366.32,
+      "grad_norm": 0.029282381758093834,
+      "learning_rate": 1.9243986254295536e-05,
+      "loss": 0.023,
+      "step": 1465
+    },
+    {
+      "epoch": 367.64,
+      "grad_norm": 0.028713850304484367,
+      "learning_rate": 1.895761741122566e-05,
+      "loss": 0.0242,
+      "step": 1470
+    },
+    {
+      "epoch": 368.96,
+      "grad_norm": 0.028631310909986496,
+      "learning_rate": 1.8671248568155786e-05,
+      "loss": 0.0226,
+      "step": 1475
+    },
+    {
+      "epoch": 370.0,
+      "grad_norm": 0.0981796383857727,
+      "learning_rate": 1.8384879725085912e-05,
+      "loss": 0.0244,
+      "step": 1480
+    },
+    {
+      "epoch": 371.32,
+      "grad_norm": 0.027549922466278076,
+      "learning_rate": 1.809851088201604e-05,
+      "loss": 0.0237,
+      "step": 1485
+    },
+    {
+      "epoch": 372.64,
+      "grad_norm": 0.02814653515815735,
+      "learning_rate": 1.7812142038946165e-05,
+      "loss": 0.0235,
+      "step": 1490
+    },
+    {
+      "epoch": 373.96,
+      "grad_norm": 0.028644410893321037,
+      "learning_rate": 1.7525773195876288e-05,
+      "loss": 0.024,
+      "step": 1495
+    },
+    {
+      "epoch": 375.0,
+      "grad_norm": 0.09073706716299057,
+      "learning_rate": 1.7239404352806415e-05,
+      "loss": 0.0238,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 450,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.275678425088e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

Math_QA/group_06/checkpoints/checkpoint-900/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/不冻结Qwen训练/models/Qwen2.5-1.5B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

Math_QA/group_06/checkpoints/checkpoint-900/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/\u4e0d\u51bb\u7ed3Qwen\u8bad\u7ec3/models/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Math_QA/group_06/checkpoints/checkpoint-900/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

Math_QA/group_06/checkpoints/checkpoint-900/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

Math_QA/group_06/checkpoints/checkpoint-900/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Math_QA/group_06/checkpoints/checkpoint-900/trainer_state.json

@@ -0,0 +1,1301 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 225.0,
+  "eval_steps": 500,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "grad_norm": 11.104532241821289,
+      "learning_rate": 0.0,
+      "loss": 1.8881,
+      "step": 1
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 7.216622829437256,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.8059,
+      "step": 5
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 3.460949182510376,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.5521,
+      "step": 10
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 1.9872286319732666,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 1.1534,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.5143823623657227,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.8946,
+      "step": 20
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.6239762306213379,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.7338,
+      "step": 25
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.6216806173324585,
+      "learning_rate": 5.370370370370371e-05,
+      "loss": 0.6218,
+      "step": 30
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.5028809905052185,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.5368,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.2165335416793823,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.4395,
+      "step": 40
+    },
+    {
+      "epoch": 11.32,
+      "grad_norm": 0.7524298429489136,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.3374,
+      "step": 45
+    },
+    {
+      "epoch": 12.64,
+      "grad_norm": 1.2006490230560303,
+      "learning_rate": 9.074074074074075e-05,
+      "loss": 0.2433,
+      "step": 50
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 1.0558921098709106,
+      "learning_rate": 0.0001,
+      "loss": 0.219,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 4.885622501373291,
+      "learning_rate": 9.971363115693013e-05,
+      "loss": 0.1595,
+      "step": 60
+    },
+    {
+      "epoch": 16.32,
+      "grad_norm": 0.6441199779510498,
+      "learning_rate": 9.942726231386026e-05,
+      "loss": 0.0905,
+      "step": 65
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 0.8051611185073853,
+      "learning_rate": 9.914089347079038e-05,
+      "loss": 0.0634,
+      "step": 70
+    },
+    {
+      "epoch": 18.96,
+      "grad_norm": 0.5070267915725708,
+      "learning_rate": 9.885452462772051e-05,
+      "loss": 0.0473,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.7553927898406982,
+      "learning_rate": 9.856815578465064e-05,
+      "loss": 0.041,
+      "step": 80
+    },
+    {
+      "epoch": 21.32,
+      "grad_norm": 0.3303334712982178,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 0.0315,
+      "step": 85
+    },
+    {
+      "epoch": 22.64,
+      "grad_norm": 1.3955363035202026,
+      "learning_rate": 9.799541809851088e-05,
+      "loss": 0.0438,
+      "step": 90
+    },
+    {
+      "epoch": 23.96,
+      "grad_norm": 0.6044227480888367,
+      "learning_rate": 9.7709049255441e-05,
+      "loss": 0.0335,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.37705135345458984,
+      "learning_rate": 9.742268041237114e-05,
+      "loss": 0.0305,
+      "step": 100
+    },
+    {
+      "epoch": 26.32,
+      "grad_norm": 0.14478059113025665,
+      "learning_rate": 9.713631156930127e-05,
+      "loss": 0.0304,
+      "step": 105
+    },
+    {
+      "epoch": 27.64,
+      "grad_norm": 0.3496911823749542,
+      "learning_rate": 9.68499427262314e-05,
+      "loss": 0.0334,
+      "step": 110
+    },
+    {
+      "epoch": 28.96,
+      "grad_norm": 0.36351385712623596,
+      "learning_rate": 9.656357388316152e-05,
+      "loss": 0.0338,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.2110755294561386,
+      "learning_rate": 9.627720504009165e-05,
+      "loss": 0.0318,
+      "step": 120
+    },
+    {
+      "epoch": 31.32,
+      "grad_norm": 0.08316600322723389,
+      "learning_rate": 9.599083619702178e-05,
+      "loss": 0.027,
+      "step": 125
+    },
+    {
+      "epoch": 32.64,
+      "grad_norm": 0.07070767879486084,
+      "learning_rate": 9.57044673539519e-05,
+      "loss": 0.0284,
+      "step": 130
+    },
+    {
+      "epoch": 33.96,
+      "grad_norm": 0.06981239467859268,
+      "learning_rate": 9.541809851088203e-05,
+      "loss": 0.0274,
+      "step": 135
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.15813617408275604,
+      "learning_rate": 9.513172966781214e-05,
+      "loss": 0.025,
+      "step": 140
+    },
+    {
+      "epoch": 36.32,
+      "grad_norm": 0.06278073787689209,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.0256,
+      "step": 145
+    },
+    {
+      "epoch": 37.64,
+      "grad_norm": 0.07232863456010818,
+      "learning_rate": 9.45589919816724e-05,
+      "loss": 0.0259,
+      "step": 150
+    },
+    {
+      "epoch": 38.96,
+      "grad_norm": 0.05737334489822388,
+      "learning_rate": 9.427262313860252e-05,
+      "loss": 0.0263,
+      "step": 155
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.19587241113185883,
+      "learning_rate": 9.398625429553265e-05,
+      "loss": 0.0276,
+      "step": 160
+    },
+    {
+      "epoch": 41.32,
+      "grad_norm": 0.05878272280097008,
+      "learning_rate": 9.369988545246277e-05,
+      "loss": 0.0271,
+      "step": 165
+    },
+    {
+      "epoch": 42.64,
+      "grad_norm": 0.06356244534254074,
+      "learning_rate": 9.34135166093929e-05,
+      "loss": 0.0264,
+      "step": 170
+    },
+    {
+      "epoch": 43.96,
+      "grad_norm": 0.05739160627126694,
+      "learning_rate": 9.312714776632303e-05,
+      "loss": 0.0269,
+      "step": 175
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 0.18483243882656097,
+      "learning_rate": 9.284077892325315e-05,
+      "loss": 0.0277,
+      "step": 180
+    },
+    {
+      "epoch": 46.32,
+      "grad_norm": 0.05537231266498566,
+      "learning_rate": 9.255441008018328e-05,
+      "loss": 0.0255,
+      "step": 185
+    },
+    {
+      "epoch": 47.64,
+      "grad_norm": 0.06456373631954193,
+      "learning_rate": 9.22680412371134e-05,
+      "loss": 0.0268,
+      "step": 190
+    },
+    {
+      "epoch": 48.96,
+      "grad_norm": 0.053096506744623184,
+      "learning_rate": 9.198167239404353e-05,
+      "loss": 0.0244,
+      "step": 195
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.17689672112464905,
+      "learning_rate": 9.169530355097366e-05,
+      "loss": 0.0258,
+      "step": 200
+    },
+    {
+      "epoch": 51.32,
+      "grad_norm": 0.06029054522514343,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.0277,
+      "step": 205
+    },
+    {
+      "epoch": 52.64,
+      "grad_norm": 0.0548815056681633,
+      "learning_rate": 9.112256586483391e-05,
+      "loss": 0.028,
+      "step": 210
+    },
+    {
+      "epoch": 53.96,
+      "grad_norm": 0.05216140300035477,
+      "learning_rate": 9.083619702176404e-05,
+      "loss": 0.0243,
+      "step": 215
+    },
+    {
+      "epoch": 55.0,
+      "grad_norm": 0.1264064759016037,
+      "learning_rate": 9.054982817869416e-05,
+      "loss": 0.0284,
+      "step": 220
+    },
+    {
+      "epoch": 56.32,
+      "grad_norm": 0.0550195574760437,
+      "learning_rate": 9.026345933562429e-05,
+      "loss": 0.0267,
+      "step": 225
+    },
+    {
+      "epoch": 57.64,
+      "grad_norm": 0.04373545199632645,
+      "learning_rate": 8.997709049255442e-05,
+      "loss": 0.0261,
+      "step": 230
+    },
+    {
+      "epoch": 58.96,
+      "grad_norm": 0.06298700720071793,
+      "learning_rate": 8.969072164948454e-05,
+      "loss": 0.0262,
+      "step": 235
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.10524652153253555,
+      "learning_rate": 8.940435280641467e-05,
+      "loss": 0.0238,
+      "step": 240
+    },
+    {
+      "epoch": 61.32,
+      "grad_norm": 0.05074843764305115,
+      "learning_rate": 8.91179839633448e-05,
+      "loss": 0.0246,
+      "step": 245
+    },
+    {
+      "epoch": 62.64,
+      "grad_norm": 0.04865209385752678,
+      "learning_rate": 8.883161512027491e-05,
+      "loss": 0.0256,
+      "step": 250
+    },
+    {
+      "epoch": 63.96,
+      "grad_norm": 0.04322940111160278,
+      "learning_rate": 8.854524627720504e-05,
+      "loss": 0.0256,
+      "step": 255
+    },
+    {
+      "epoch": 65.0,
+      "grad_norm": 0.11021823436021805,
+      "learning_rate": 8.825887743413516e-05,
+      "loss": 0.0238,
+      "step": 260
+    },
+    {
+      "epoch": 66.32,
+      "grad_norm": 0.04945431277155876,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 0.0251,
+      "step": 265
+    },
+    {
+      "epoch": 67.64,
+      "grad_norm": 0.05235425382852554,
+      "learning_rate": 8.768613974799542e-05,
+      "loss": 0.0246,
+      "step": 270
+    },
+    {
+      "epoch": 68.96,
+      "grad_norm": 0.04749702662229538,
+      "learning_rate": 8.739977090492554e-05,
+      "loss": 0.0247,
+      "step": 275
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.09817614406347275,
+      "learning_rate": 8.711340206185567e-05,
+      "loss": 0.0254,
+      "step": 280
+    },
+    {
+      "epoch": 71.32,
+      "grad_norm": 0.054523907601833344,
+      "learning_rate": 8.682703321878581e-05,
+      "loss": 0.025,
+      "step": 285
+    },
+    {
+      "epoch": 72.64,
+      "grad_norm": 0.053732652217149734,
+      "learning_rate": 8.654066437571594e-05,
+      "loss": 0.026,
+      "step": 290
+    },
+    {
+      "epoch": 73.96,
+      "grad_norm": 0.050208788365125656,
+      "learning_rate": 8.625429553264606e-05,
+      "loss": 0.0248,
+      "step": 295
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.11127286404371262,
+      "learning_rate": 8.596792668957619e-05,
+      "loss": 0.0235,
+      "step": 300
+    },
+    {
+      "epoch": 76.32,
+      "grad_norm": 0.047599948942661285,
+      "learning_rate": 8.56815578465063e-05,
+      "loss": 0.0249,
+      "step": 305
+    },
+    {
+      "epoch": 77.64,
+      "grad_norm": 0.0452277734875679,
+      "learning_rate": 8.539518900343643e-05,
+      "loss": 0.0249,
+      "step": 310
+    },
+    {
+      "epoch": 78.96,
+      "grad_norm": 0.049311988055706024,
+      "learning_rate": 8.510882016036655e-05,
+      "loss": 0.0247,
+      "step": 315
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 0.13898910582065582,
+      "learning_rate": 8.482245131729668e-05,
+      "loss": 0.0251,
+      "step": 320
+    },
+    {
+      "epoch": 81.32,
+      "grad_norm": 0.040757764130830765,
+      "learning_rate": 8.453608247422681e-05,
+      "loss": 0.0249,
+      "step": 325
+    },
+    {
+      "epoch": 82.64,
+      "grad_norm": 0.04465162381529808,
+      "learning_rate": 8.424971363115693e-05,
+      "loss": 0.025,
+      "step": 330
+    },
+    {
+      "epoch": 83.96,
+      "grad_norm": 0.04066985845565796,
+      "learning_rate": 8.396334478808706e-05,
+      "loss": 0.0225,
+      "step": 335
+    },
+    {
+      "epoch": 85.0,
+      "grad_norm": 0.16414588689804077,
+      "learning_rate": 8.367697594501719e-05,
+      "loss": 0.0246,
+      "step": 340
+    },
+    {
+      "epoch": 86.32,
+      "grad_norm": 0.0515274740755558,
+      "learning_rate": 8.339060710194731e-05,
+      "loss": 0.0239,
+      "step": 345
+    },
+    {
+      "epoch": 87.64,
+      "grad_norm": 0.0446721687912941,
+      "learning_rate": 8.310423825887744e-05,
+      "loss": 0.0245,
+      "step": 350
+    },
+    {
+      "epoch": 88.96,
+      "grad_norm": 0.043738313019275665,
+      "learning_rate": 8.281786941580757e-05,
+      "loss": 0.0254,
+      "step": 355
+    },
+    {
+      "epoch": 90.0,
+      "grad_norm": 0.1853068321943283,
+      "learning_rate": 8.253150057273768e-05,
+      "loss": 0.026,
+      "step": 360
+    },
+    {
+      "epoch": 91.32,
+      "grad_norm": 0.04070025309920311,
+      "learning_rate": 8.224513172966782e-05,
+      "loss": 0.0264,
+      "step": 365
+    },
+    {
+      "epoch": 92.64,
+      "grad_norm": 0.04621007665991783,
+      "learning_rate": 8.195876288659795e-05,
+      "loss": 0.0239,
+      "step": 370
+    },
+    {
+      "epoch": 93.96,
+      "grad_norm": 0.0490901954472065,
+      "learning_rate": 8.167239404352807e-05,
+      "loss": 0.0259,
+      "step": 375
+    },
+    {
+      "epoch": 95.0,
+      "grad_norm": 0.11828532069921494,
+      "learning_rate": 8.13860252004582e-05,
+      "loss": 0.0231,
+      "step": 380
+    },
+    {
+      "epoch": 96.32,
+      "grad_norm": 0.046177372336387634,
+      "learning_rate": 8.109965635738833e-05,
+      "loss": 0.0248,
+      "step": 385
+    },
+    {
+      "epoch": 97.64,
+      "grad_norm": 0.042552754282951355,
+      "learning_rate": 8.081328751431845e-05,
+      "loss": 0.0234,
+      "step": 390
+    },
+    {
+      "epoch": 98.96,
+      "grad_norm": 0.04748699814081192,
+      "learning_rate": 8.052691867124858e-05,
+      "loss": 0.0261,
+      "step": 395
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.1385429948568344,
+      "learning_rate": 8.02405498281787e-05,
+      "loss": 0.025,
+      "step": 400
+    },
+    {
+      "epoch": 101.32,
+      "grad_norm": 0.04103074222803116,
+      "learning_rate": 7.995418098510883e-05,
+      "loss": 0.0269,
+      "step": 405
+    },
+    {
+      "epoch": 102.64,
+      "grad_norm": 0.03280722349882126,
+      "learning_rate": 7.966781214203894e-05,
+      "loss": 0.0241,
+      "step": 410
+    },
+    {
+      "epoch": 103.96,
+      "grad_norm": 0.04333680495619774,
+      "learning_rate": 7.938144329896907e-05,
+      "loss": 0.0245,
+      "step": 415
+    },
+    {
+      "epoch": 105.0,
+      "grad_norm": 0.08673492819070816,
+      "learning_rate": 7.90950744558992e-05,
+      "loss": 0.0253,
+      "step": 420
+    },
+    {
+      "epoch": 106.32,
+      "grad_norm": 0.04038430377840996,
+      "learning_rate": 7.880870561282932e-05,
+      "loss": 0.0259,
+      "step": 425
+    },
+    {
+      "epoch": 107.64,
+      "grad_norm": 0.03518936410546303,
+      "learning_rate": 7.852233676975945e-05,
+      "loss": 0.0233,
+      "step": 430
+    },
+    {
+      "epoch": 108.96,
+      "grad_norm": 0.042619626969099045,
+      "learning_rate": 7.823596792668958e-05,
+      "loss": 0.0248,
+      "step": 435
+    },
+    {
+      "epoch": 110.0,
+      "grad_norm": 0.14510254561901093,
+      "learning_rate": 7.79495990836197e-05,
+      "loss": 0.0243,
+      "step": 440
+    },
+    {
+      "epoch": 111.32,
+      "grad_norm": 0.04383605346083641,
+      "learning_rate": 7.766323024054983e-05,
+      "loss": 0.0247,
+      "step": 445
+    },
+    {
+      "epoch": 112.64,
+      "grad_norm": 0.04186142981052399,
+      "learning_rate": 7.737686139747996e-05,
+      "loss": 0.0246,
+      "step": 450
+    },
+    {
+      "epoch": 113.96,
+      "grad_norm": 0.03870782628655434,
+      "learning_rate": 7.709049255441008e-05,
+      "loss": 0.0246,
+      "step": 455
+    },
+    {
+      "epoch": 115.0,
+      "grad_norm": 0.10923579335212708,
+      "learning_rate": 7.680412371134021e-05,
+      "loss": 0.0245,
+      "step": 460
+    },
+    {
+      "epoch": 116.32,
+      "grad_norm": 0.03715936094522476,
+      "learning_rate": 7.651775486827034e-05,
+      "loss": 0.0243,
+      "step": 465
+    },
+    {
+      "epoch": 117.64,
+      "grad_norm": 0.03120102733373642,
+      "learning_rate": 7.623138602520046e-05,
+      "loss": 0.0234,
+      "step": 470
+    },
+    {
+      "epoch": 118.96,
+      "grad_norm": 0.03617759793996811,
+      "learning_rate": 7.594501718213059e-05,
+      "loss": 0.0265,
+      "step": 475
+    },
+    {
+      "epoch": 120.0,
+      "grad_norm": 0.12326925247907639,
+      "learning_rate": 7.565864833906071e-05,
+      "loss": 0.0244,
+      "step": 480
+    },
+    {
+      "epoch": 121.32,
+      "grad_norm": 0.03131456300616264,
+      "learning_rate": 7.537227949599084e-05,
+      "loss": 0.0237,
+      "step": 485
+    },
+    {
+      "epoch": 122.64,
+      "grad_norm": 0.03460497781634331,
+      "learning_rate": 7.508591065292097e-05,
+      "loss": 0.0244,
+      "step": 490
+    },
+    {
+      "epoch": 123.96,
+      "grad_norm": 0.0392792634665966,
+      "learning_rate": 7.47995418098511e-05,
+      "loss": 0.0259,
+      "step": 495
+    },
+    {
+      "epoch": 125.0,
+      "grad_norm": 0.11717823147773743,
+      "learning_rate": 7.451317296678122e-05,
+      "loss": 0.0253,
+      "step": 500
+    },
+    {
+      "epoch": 126.32,
+      "grad_norm": 0.03736049681901932,
+      "learning_rate": 7.422680412371135e-05,
+      "loss": 0.024,
+      "step": 505
+    },
+    {
+      "epoch": 127.64,
+      "grad_norm": 0.04238331690430641,
+      "learning_rate": 7.394043528064147e-05,
+      "loss": 0.0254,
+      "step": 510
+    },
+    {
+      "epoch": 128.96,
+      "grad_norm": 0.036686044186353683,
+      "learning_rate": 7.36540664375716e-05,
+      "loss": 0.0249,
+      "step": 515
+    },
+    {
+      "epoch": 130.0,
+      "grad_norm": 0.11898811906576157,
+      "learning_rate": 7.336769759450171e-05,
+      "loss": 0.0245,
+      "step": 520
+    },
+    {
+      "epoch": 131.32,
+      "grad_norm": 0.03935862332582474,
+      "learning_rate": 7.308132875143184e-05,
+      "loss": 0.0248,
+      "step": 525
+    },
+    {
+      "epoch": 132.64,
+      "grad_norm": 0.035374052822589874,
+      "learning_rate": 7.279495990836197e-05,
+      "loss": 0.0244,
+      "step": 530
+    },
+    {
+      "epoch": 133.96,
+      "grad_norm": 0.03667380288243294,
+      "learning_rate": 7.250859106529209e-05,
+      "loss": 0.0246,
+      "step": 535
+    },
+    {
+      "epoch": 135.0,
+      "grad_norm": 0.1304934173822403,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.0249,
+      "step": 540
+    },
+    {
+      "epoch": 136.32,
+      "grad_norm": 0.03300497308373451,
+      "learning_rate": 7.193585337915235e-05,
+      "loss": 0.0266,
+      "step": 545
+    },
+    {
+      "epoch": 137.64,
+      "grad_norm": 0.03661350905895233,
+      "learning_rate": 7.164948453608247e-05,
+      "loss": 0.0247,
+      "step": 550
+    },
+    {
+      "epoch": 138.96,
+      "grad_norm": 0.04630376026034355,
+      "learning_rate": 7.136311569301261e-05,
+      "loss": 0.0271,
+      "step": 555
+    },
+    {
+      "epoch": 140.0,
+      "grad_norm": 0.10119768232107162,
+      "learning_rate": 7.107674684994274e-05,
+      "loss": 0.0252,
+      "step": 560
+    },
+    {
+      "epoch": 141.32,
+      "grad_norm": 0.030455591157078743,
+      "learning_rate": 7.079037800687286e-05,
+      "loss": 0.0255,
+      "step": 565
+    },
+    {
+      "epoch": 142.64,
+      "grad_norm": 0.036023061722517014,
+      "learning_rate": 7.050400916380299e-05,
+      "loss": 0.0255,
+      "step": 570
+    },
+    {
+      "epoch": 143.96,
+      "grad_norm": 0.03697853162884712,
+      "learning_rate": 7.02176403207331e-05,
+      "loss": 0.023,
+      "step": 575
+    },
+    {
+      "epoch": 145.0,
+      "grad_norm": 0.10646484047174454,
+      "learning_rate": 6.993127147766323e-05,
+      "loss": 0.0246,
+      "step": 580
+    },
+    {
+      "epoch": 146.32,
+      "grad_norm": 0.03505175933241844,
+      "learning_rate": 6.964490263459336e-05,
+      "loss": 0.0246,
+      "step": 585
+    },
+    {
+      "epoch": 147.64,
+      "grad_norm": 0.03091881051659584,
+      "learning_rate": 6.935853379152348e-05,
+      "loss": 0.0236,
+      "step": 590
+    },
+    {
+      "epoch": 148.96,
+      "grad_norm": 0.03566066175699234,
+      "learning_rate": 6.907216494845361e-05,
+      "loss": 0.0257,
+      "step": 595
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 0.13368169963359833,
+      "learning_rate": 6.878579610538374e-05,
+      "loss": 0.0246,
+      "step": 600
+    },
+    {
+      "epoch": 151.32,
+      "grad_norm": 0.03456564620137215,
+      "learning_rate": 6.849942726231386e-05,
+      "loss": 0.0249,
+      "step": 605
+    },
+    {
+      "epoch": 152.64,
+      "grad_norm": 0.037680983543395996,
+      "learning_rate": 6.821305841924399e-05,
+      "loss": 0.0236,
+      "step": 610
+    },
+    {
+      "epoch": 153.96,
+      "grad_norm": 0.02970520406961441,
+      "learning_rate": 6.792668957617412e-05,
+      "loss": 0.0235,
+      "step": 615
+    },
+    {
+      "epoch": 155.0,
+      "grad_norm": 0.12523308396339417,
+      "learning_rate": 6.764032073310424e-05,
+      "loss": 0.0237,
+      "step": 620
+    },
+    {
+      "epoch": 156.32,
+      "grad_norm": 0.03233841061592102,
+      "learning_rate": 6.735395189003437e-05,
+      "loss": 0.0234,
+      "step": 625
+    },
+    {
+      "epoch": 157.64,
+      "grad_norm": 0.03602683171629906,
+      "learning_rate": 6.706758304696448e-05,
+      "loss": 0.0241,
+      "step": 630
+    },
+    {
+      "epoch": 158.96,
+      "grad_norm": 0.03763331472873688,
+      "learning_rate": 6.678121420389462e-05,
+      "loss": 0.0238,
+      "step": 635
+    },
+    {
+      "epoch": 160.0,
+      "grad_norm": 0.122522734105587,
+      "learning_rate": 6.649484536082475e-05,
+      "loss": 0.0252,
+      "step": 640
+    },
+    {
+      "epoch": 161.32,
+      "grad_norm": 0.033675480633974075,
+      "learning_rate": 6.620847651775487e-05,
+      "loss": 0.0241,
+      "step": 645
+    },
+    {
+      "epoch": 162.64,
+      "grad_norm": 0.03151499852538109,
+      "learning_rate": 6.5922107674685e-05,
+      "loss": 0.0248,
+      "step": 650
+    },
+    {
+      "epoch": 163.96,
+      "grad_norm": 0.03151350095868111,
+      "learning_rate": 6.563573883161513e-05,
+      "loss": 0.0245,
+      "step": 655
+    },
+    {
+      "epoch": 165.0,
+      "grad_norm": 0.11250028759241104,
+      "learning_rate": 6.534936998854525e-05,
+      "loss": 0.0252,
+      "step": 660
+    },
+    {
+      "epoch": 166.32,
+      "grad_norm": 0.033449526876211166,
+      "learning_rate": 6.506300114547538e-05,
+      "loss": 0.025,
+      "step": 665
+    },
+    {
+      "epoch": 167.64,
+      "grad_norm": 0.030957462266087532,
+      "learning_rate": 6.477663230240551e-05,
+      "loss": 0.0257,
+      "step": 670
+    },
+    {
+      "epoch": 168.96,
+      "grad_norm": 0.03218599036335945,
+      "learning_rate": 6.449026345933563e-05,
+      "loss": 0.0257,
+      "step": 675
+    },
+    {
+      "epoch": 170.0,
+      "grad_norm": 0.09439749270677567,
+      "learning_rate": 6.420389461626576e-05,
+      "loss": 0.0246,
+      "step": 680
+    },
+    {
+      "epoch": 171.32,
+      "grad_norm": 0.029240014031529427,
+      "learning_rate": 6.391752577319587e-05,
+      "loss": 0.0236,
+      "step": 685
+    },
+    {
+      "epoch": 172.64,
+      "grad_norm": 0.034742940217256546,
+      "learning_rate": 6.3631156930126e-05,
+      "loss": 0.0236,
+      "step": 690
+    },
+    {
+      "epoch": 173.96,
+      "grad_norm": 0.030582355335354805,
+      "learning_rate": 6.334478808705613e-05,
+      "loss": 0.0236,
+      "step": 695
+    },
+    {
+      "epoch": 175.0,
+      "grad_norm": 0.08759982883930206,
+      "learning_rate": 6.305841924398625e-05,
+      "loss": 0.0265,
+      "step": 700
+    },
+    {
+      "epoch": 176.32,
+      "grad_norm": 0.029291506856679916,
+      "learning_rate": 6.277205040091638e-05,
+      "loss": 0.024,
+      "step": 705
+    },
+    {
+      "epoch": 177.64,
+      "grad_norm": 0.031786780804395676,
+      "learning_rate": 6.24856815578465e-05,
+      "loss": 0.0263,
+      "step": 710
+    },
+    {
+      "epoch": 178.96,
+      "grad_norm": 0.035743582993745804,
+      "learning_rate": 6.219931271477663e-05,
+      "loss": 0.0261,
+      "step": 715
+    },
+    {
+      "epoch": 180.0,
+      "grad_norm": 0.1054234430193901,
+      "learning_rate": 6.191294387170676e-05,
+      "loss": 0.0253,
+      "step": 720
+    },
+    {
+      "epoch": 181.32,
+      "grad_norm": 0.03243524953722954,
+      "learning_rate": 6.162657502863689e-05,
+      "loss": 0.0251,
+      "step": 725
+    },
+    {
+      "epoch": 182.64,
+      "grad_norm": 0.03032608889043331,
+      "learning_rate": 6.134020618556701e-05,
+      "loss": 0.0251,
+      "step": 730
+    },
+    {
+      "epoch": 183.96,
+      "grad_norm": 0.03101290389895439,
+      "learning_rate": 6.105383734249714e-05,
+      "loss": 0.0241,
+      "step": 735
+    },
+    {
+      "epoch": 185.0,
+      "grad_norm": 0.07965508848428726,
+      "learning_rate": 6.076746849942726e-05,
+      "loss": 0.0229,
+      "step": 740
+    },
+    {
+      "epoch": 186.32,
+      "grad_norm": 0.03219285607337952,
+      "learning_rate": 6.0481099656357384e-05,
+      "loss": 0.0239,
+      "step": 745
+    },
+    {
+      "epoch": 187.64,
+      "grad_norm": 0.032278887927532196,
+      "learning_rate": 6.019473081328752e-05,
+      "loss": 0.0246,
+      "step": 750
+    },
+    {
+      "epoch": 188.96,
+      "grad_norm": 0.03127485513687134,
+      "learning_rate": 5.9908361970217644e-05,
+      "loss": 0.0248,
+      "step": 755
+    },
+    {
+      "epoch": 190.0,
+      "grad_norm": 0.09103897213935852,
+      "learning_rate": 5.962199312714777e-05,
+      "loss": 0.0262,
+      "step": 760
+    },
+    {
+      "epoch": 191.32,
+      "grad_norm": 0.032904159277677536,
+      "learning_rate": 5.93356242840779e-05,
+      "loss": 0.0247,
+      "step": 765
+    },
+    {
+      "epoch": 192.64,
+      "grad_norm": 0.034943412989377975,
+      "learning_rate": 5.904925544100802e-05,
+      "loss": 0.0245,
+      "step": 770
+    },
+    {
+      "epoch": 193.96,
+      "grad_norm": 0.029192674905061722,
+      "learning_rate": 5.876288659793815e-05,
+      "loss": 0.0248,
+      "step": 775
+    },
+    {
+      "epoch": 195.0,
+      "grad_norm": 0.13117201626300812,
+      "learning_rate": 5.8476517754868276e-05,
+      "loss": 0.0257,
+      "step": 780
+    },
+    {
+      "epoch": 196.32,
+      "grad_norm": 0.030321085825562477,
+      "learning_rate": 5.81901489117984e-05,
+      "loss": 0.0244,
+      "step": 785
+    },
+    {
+      "epoch": 197.64,
+      "grad_norm": 0.03632837533950806,
+      "learning_rate": 5.790378006872853e-05,
+      "loss": 0.0247,
+      "step": 790
+    },
+    {
+      "epoch": 198.96,
+      "grad_norm": 0.029967786744236946,
+      "learning_rate": 5.761741122565865e-05,
+      "loss": 0.0252,
+      "step": 795
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 0.07372202724218369,
+      "learning_rate": 5.7331042382588775e-05,
+      "loss": 0.024,
+      "step": 800
+    },
+    {
+      "epoch": 201.32,
+      "grad_norm": 0.033607207238674164,
+      "learning_rate": 5.70446735395189e-05,
+      "loss": 0.0242,
+      "step": 805
+    },
+    {
+      "epoch": 202.64,
+      "grad_norm": 0.0330338180065155,
+      "learning_rate": 5.675830469644903e-05,
+      "loss": 0.0244,
+      "step": 810
+    },
+    {
+      "epoch": 203.96,
+      "grad_norm": 0.034020259976387024,
+      "learning_rate": 5.6471935853379155e-05,
+      "loss": 0.0227,
+      "step": 815
+    },
+    {
+      "epoch": 205.0,
+      "grad_norm": 0.18551097810268402,
+      "learning_rate": 5.618556701030928e-05,
+      "loss": 0.0265,
+      "step": 820
+    },
+    {
+      "epoch": 206.32,
+      "grad_norm": 0.033085715025663376,
+      "learning_rate": 5.589919816723941e-05,
+      "loss": 0.0247,
+      "step": 825
+    },
+    {
+      "epoch": 207.64,
+      "grad_norm": 0.03386640176177025,
+      "learning_rate": 5.5612829324169534e-05,
+      "loss": 0.0238,
+      "step": 830
+    },
+    {
+      "epoch": 208.96,
+      "grad_norm": 0.035608984529972076,
+      "learning_rate": 5.532646048109966e-05,
+      "loss": 0.0247,
+      "step": 835
+    },
+    {
+      "epoch": 210.0,
+      "grad_norm": 0.10785692930221558,
+      "learning_rate": 5.504009163802979e-05,
+      "loss": 0.0247,
+      "step": 840
+    },
+    {
+      "epoch": 211.32,
+      "grad_norm": 0.03013814426958561,
+      "learning_rate": 5.4753722794959914e-05,
+      "loss": 0.0251,
+      "step": 845
+    },
+    {
+      "epoch": 212.64,
+      "grad_norm": 0.02756708860397339,
+      "learning_rate": 5.4467353951890033e-05,
+      "loss": 0.0257,
+      "step": 850
+    },
+    {
+      "epoch": 213.96,
+      "grad_norm": 0.030665891245007515,
+      "learning_rate": 5.418098510882016e-05,
+      "loss": 0.0243,
+      "step": 855
+    },
+    {
+      "epoch": 215.0,
+      "grad_norm": 0.0745956227183342,
+      "learning_rate": 5.3894616265750286e-05,
+      "loss": 0.0234,
+      "step": 860
+    },
+    {
+      "epoch": 216.32,
+      "grad_norm": 0.028612101450562477,
+      "learning_rate": 5.360824742268041e-05,
+      "loss": 0.0233,
+      "step": 865
+    },
+    {
+      "epoch": 217.64,
+      "grad_norm": 0.03162551298737526,
+      "learning_rate": 5.332187857961054e-05,
+      "loss": 0.0251,
+      "step": 870
+    },
+    {
+      "epoch": 218.96,
+      "grad_norm": 0.031918879598379135,
+      "learning_rate": 5.3035509736540666e-05,
+      "loss": 0.0236,
+      "step": 875
+    },
+    {
+      "epoch": 220.0,
+      "grad_norm": 0.10774800181388855,
+      "learning_rate": 5.274914089347079e-05,
+      "loss": 0.0239,
+      "step": 880
+    },
+    {
+      "epoch": 221.32,
+      "grad_norm": 0.03076888434588909,
+      "learning_rate": 5.246277205040092e-05,
+      "loss": 0.0264,
+      "step": 885
+    },
+    {
+      "epoch": 222.64,
+      "grad_norm": 0.028414763510227203,
+      "learning_rate": 5.2176403207331045e-05,
+      "loss": 0.024,
+      "step": 890
+    },
+    {
+      "epoch": 223.96,
+      "grad_norm": 0.030206475406885147,
+      "learning_rate": 5.189003436426118e-05,
+      "loss": 0.024,
+      "step": 895
+    },
+    {
+      "epoch": 225.0,
+      "grad_norm": 0.08630042523145676,
+      "learning_rate": 5.1603665521191305e-05,
+      "loss": 0.0239,
+      "step": 900
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 450,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.654070550528e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

Math_QA/group_08/adapter/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/不冻结Qwen训练/models/Qwen2.5-1.5B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

Math_QA/group_08/adapter/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

Math_QA/group_08/adapter/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

Math_QA/group_08/adapter/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Math_QA/group_08/adapter/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

Math_QA/group_08/checkpoints/checkpoint-1200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/不冻结Qwen训练/models/Qwen2.5-1.5B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

Math_QA/group_08/checkpoints/checkpoint-1200/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/\u4e0d\u51bb\u7ed3Qwen\u8bad\u7ec3/models/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Math_QA/group_08/checkpoints/checkpoint-1200/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

Math_QA/group_08/checkpoints/checkpoint-1200/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

Math_QA/group_08/checkpoints/checkpoint-1200/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Math_QA/group_08/checkpoints/checkpoint-1200/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

Math_QA/group_08/checkpoints/checkpoint-1200/trainer_state.json

@@ -0,0 +1,1721 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 300.0,
+  "eval_steps": 500,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "grad_norm": 10.268527030944824,
+      "learning_rate": 0.0,
+      "loss": 1.8412,
+      "step": 1
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 7.169743537902832,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.7908,
+      "step": 5
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 3.2965712547302246,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.541,
+      "step": 10
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 1.9259239435195923,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 1.195,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.5386537313461304,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.8407,
+      "step": 20
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.7439631223678589,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.7134,
+      "step": 25
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.5669045448303223,
+      "learning_rate": 5.370370370370371e-05,
+      "loss": 0.6253,
+      "step": 30
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.5955387353897095,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.5425,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.794498324394226,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.4517,
+      "step": 40
+    },
+    {
+      "epoch": 11.32,
+      "grad_norm": 0.6224164366722107,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.3649,
+      "step": 45
+    },
+    {
+      "epoch": 12.64,
+      "grad_norm": 0.7097190022468567,
+      "learning_rate": 9.074074074074075e-05,
+      "loss": 0.2806,
+      "step": 50
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 0.8385046124458313,
+      "learning_rate": 0.0001,
+      "loss": 0.2055,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 2.7302768230438232,
+      "learning_rate": 9.971363115693013e-05,
+      "loss": 0.1593,
+      "step": 60
+    },
+    {
+      "epoch": 16.32,
+      "grad_norm": 0.573469877243042,
+      "learning_rate": 9.942726231386026e-05,
+      "loss": 0.1173,
+      "step": 65
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 1.059529423713684,
+      "learning_rate": 9.914089347079038e-05,
+      "loss": 0.0856,
+      "step": 70
+    },
+    {
+      "epoch": 18.96,
+      "grad_norm": 0.6318557858467102,
+      "learning_rate": 9.885452462772051e-05,
+      "loss": 0.0783,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.4067771434783936,
+      "learning_rate": 9.856815578465064e-05,
+      "loss": 0.0684,
+      "step": 80
+    },
+    {
+      "epoch": 21.32,
+      "grad_norm": 0.3381839096546173,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 0.0351,
+      "step": 85
+    },
+    {
+      "epoch": 22.64,
+      "grad_norm": 0.3768102824687958,
+      "learning_rate": 9.799541809851088e-05,
+      "loss": 0.0296,
+      "step": 90
+    },
+    {
+      "epoch": 23.96,
+      "grad_norm": 0.21533846855163574,
+      "learning_rate": 9.7709049255441e-05,
+      "loss": 0.0296,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.729438841342926,
+      "learning_rate": 9.742268041237114e-05,
+      "loss": 0.0327,
+      "step": 100
+    },
+    {
+      "epoch": 26.32,
+      "grad_norm": 0.15956193208694458,
+      "learning_rate": 9.713631156930127e-05,
+      "loss": 0.0335,
+      "step": 105
+    },
+    {
+      "epoch": 27.64,
+      "grad_norm": 0.3089437186717987,
+      "learning_rate": 9.68499427262314e-05,
+      "loss": 0.0373,
+      "step": 110
+    },
+    {
+      "epoch": 28.96,
+      "grad_norm": 0.2873784303665161,
+      "learning_rate": 9.656357388316152e-05,
+      "loss": 0.028,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.3081432282924652,
+      "learning_rate": 9.627720504009165e-05,
+      "loss": 0.0288,
+      "step": 120
+    },
+    {
+      "epoch": 31.32,
+      "grad_norm": 0.15154343843460083,
+      "learning_rate": 9.599083619702178e-05,
+      "loss": 0.0258,
+      "step": 125
+    },
+    {
+      "epoch": 32.64,
+      "grad_norm": 0.21917082369327545,
+      "learning_rate": 9.57044673539519e-05,
+      "loss": 0.0276,
+      "step": 130
+    },
+    {
+      "epoch": 33.96,
+      "grad_norm": 0.4817427396774292,
+      "learning_rate": 9.541809851088203e-05,
+      "loss": 0.028,
+      "step": 135
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.9411588311195374,
+      "learning_rate": 9.513172966781214e-05,
+      "loss": 0.0301,
+      "step": 140
+    },
+    {
+      "epoch": 36.32,
+      "grad_norm": 0.12594084441661835,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.0278,
+      "step": 145
+    },
+    {
+      "epoch": 37.64,
+      "grad_norm": 0.09696595370769501,
+      "learning_rate": 9.45589919816724e-05,
+      "loss": 0.0254,
+      "step": 150
+    },
+    {
+      "epoch": 38.96,
+      "grad_norm": 0.07912517338991165,
+      "learning_rate": 9.427262313860252e-05,
+      "loss": 0.0253,
+      "step": 155
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.16622836887836456,
+      "learning_rate": 9.398625429553265e-05,
+      "loss": 0.0244,
+      "step": 160
+    },
+    {
+      "epoch": 41.32,
+      "grad_norm": 0.0670735314488411,
+      "learning_rate": 9.369988545246277e-05,
+      "loss": 0.0246,
+      "step": 165
+    },
+    {
+      "epoch": 42.64,
+      "grad_norm": 0.06884271651506424,
+      "learning_rate": 9.34135166093929e-05,
+      "loss": 0.0228,
+      "step": 170
+    },
+    {
+      "epoch": 43.96,
+      "grad_norm": 0.1034952700138092,
+      "learning_rate": 9.312714776632303e-05,
+      "loss": 0.0242,
+      "step": 175
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 0.1411074995994568,
+      "learning_rate": 9.284077892325315e-05,
+      "loss": 0.0237,
+      "step": 180
+    },
+    {
+      "epoch": 46.32,
+      "grad_norm": 0.06430694460868835,
+      "learning_rate": 9.255441008018328e-05,
+      "loss": 0.0244,
+      "step": 185
+    },
+    {
+      "epoch": 47.64,
+      "grad_norm": 0.06416841596364975,
+      "learning_rate": 9.22680412371134e-05,
+      "loss": 0.0253,
+      "step": 190
+    },
+    {
+      "epoch": 48.96,
+      "grad_norm": 0.05058900639414787,
+      "learning_rate": 9.198167239404353e-05,
+      "loss": 0.0234,
+      "step": 195
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.17872126400470734,
+      "learning_rate": 9.169530355097366e-05,
+      "loss": 0.0247,
+      "step": 200
+    },
+    {
+      "epoch": 51.32,
+      "grad_norm": 0.05059915408492088,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.0248,
+      "step": 205
+    },
+    {
+      "epoch": 52.64,
+      "grad_norm": 0.05440365895628929,
+      "learning_rate": 9.112256586483391e-05,
+      "loss": 0.0254,
+      "step": 210
+    },
+    {
+      "epoch": 53.96,
+      "grad_norm": 0.05572507157921791,
+      "learning_rate": 9.083619702176404e-05,
+      "loss": 0.0245,
+      "step": 215
+    },
+    {
+      "epoch": 55.0,
+      "grad_norm": 0.13678045570850372,
+      "learning_rate": 9.054982817869416e-05,
+      "loss": 0.0226,
+      "step": 220
+    },
+    {
+      "epoch": 56.32,
+      "grad_norm": 0.05588487163186073,
+      "learning_rate": 9.026345933562429e-05,
+      "loss": 0.0243,
+      "step": 225
+    },
+    {
+      "epoch": 57.64,
+      "grad_norm": 0.052309829741716385,
+      "learning_rate": 8.997709049255442e-05,
+      "loss": 0.0236,
+      "step": 230
+    },
+    {
+      "epoch": 58.96,
+      "grad_norm": 0.056767936795949936,
+      "learning_rate": 8.969072164948454e-05,
+      "loss": 0.0226,
+      "step": 235
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.24060668051242828,
+      "learning_rate": 8.940435280641467e-05,
+      "loss": 0.0232,
+      "step": 240
+    },
+    {
+      "epoch": 61.32,
+      "grad_norm": 0.05159705877304077,
+      "learning_rate": 8.91179839633448e-05,
+      "loss": 0.0231,
+      "step": 245
+    },
+    {
+      "epoch": 62.64,
+      "grad_norm": 0.053261805325746536,
+      "learning_rate": 8.883161512027491e-05,
+      "loss": 0.0231,
+      "step": 250
+    },
+    {
+      "epoch": 63.96,
+      "grad_norm": 0.05033772811293602,
+      "learning_rate": 8.854524627720504e-05,
+      "loss": 0.0243,
+      "step": 255
+    },
+    {
+      "epoch": 65.0,
+      "grad_norm": 0.1512952744960785,
+      "learning_rate": 8.825887743413516e-05,
+      "loss": 0.0245,
+      "step": 260
+    },
+    {
+      "epoch": 66.32,
+      "grad_norm": 0.057306934148073196,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 0.0232,
+      "step": 265
+    },
+    {
+      "epoch": 67.64,
+      "grad_norm": 0.04558086022734642,
+      "learning_rate": 8.768613974799542e-05,
+      "loss": 0.0223,
+      "step": 270
+    },
+    {
+      "epoch": 68.96,
+      "grad_norm": 0.04183197394013405,
+      "learning_rate": 8.739977090492554e-05,
+      "loss": 0.0259,
+      "step": 275
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.15279851853847504,
+      "learning_rate": 8.711340206185567e-05,
+      "loss": 0.0231,
+      "step": 280
+    },
+    {
+      "epoch": 71.32,
+      "grad_norm": 0.04648765176534653,
+      "learning_rate": 8.682703321878581e-05,
+      "loss": 0.0247,
+      "step": 285
+    },
+    {
+      "epoch": 72.64,
+      "grad_norm": 0.05621657893061638,
+      "learning_rate": 8.654066437571594e-05,
+      "loss": 0.0241,
+      "step": 290
+    },
+    {
+      "epoch": 73.96,
+      "grad_norm": 0.05430695042014122,
+      "learning_rate": 8.625429553264606e-05,
+      "loss": 0.0224,
+      "step": 295
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.13658379018306732,
+      "learning_rate": 8.596792668957619e-05,
+      "loss": 0.0244,
+      "step": 300
+    },
+    {
+      "epoch": 76.32,
+      "grad_norm": 0.04552018269896507,
+      "learning_rate": 8.56815578465063e-05,
+      "loss": 0.023,
+      "step": 305
+    },
+    {
+      "epoch": 77.64,
+      "grad_norm": 0.061252057552337646,
+      "learning_rate": 8.539518900343643e-05,
+      "loss": 0.0232,
+      "step": 310
+    },
+    {
+      "epoch": 78.96,
+      "grad_norm": 0.06784722954034805,
+      "learning_rate": 8.510882016036655e-05,
+      "loss": 0.0225,
+      "step": 315
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 0.12553691864013672,
+      "learning_rate": 8.482245131729668e-05,
+      "loss": 0.0232,
+      "step": 320
+    },
+    {
+      "epoch": 81.32,
+      "grad_norm": 0.043866027146577835,
+      "learning_rate": 8.453608247422681e-05,
+      "loss": 0.0219,
+      "step": 325
+    },
+    {
+      "epoch": 82.64,
+      "grad_norm": 0.042383234947919846,
+      "learning_rate": 8.424971363115693e-05,
+      "loss": 0.0232,
+      "step": 330
+    },
+    {
+      "epoch": 83.96,
+      "grad_norm": 0.058206457644701004,
+      "learning_rate": 8.396334478808706e-05,
+      "loss": 0.0222,
+      "step": 335
+    },
+    {
+      "epoch": 85.0,
+      "grad_norm": 0.13048116862773895,
+      "learning_rate": 8.367697594501719e-05,
+      "loss": 0.0235,
+      "step": 340
+    },
+    {
+      "epoch": 86.32,
+      "grad_norm": 0.03514638915657997,
+      "learning_rate": 8.339060710194731e-05,
+      "loss": 0.0231,
+      "step": 345
+    },
+    {
+      "epoch": 87.64,
+      "grad_norm": 0.04375334829092026,
+      "learning_rate": 8.310423825887744e-05,
+      "loss": 0.0231,
+      "step": 350
+    },
+    {
+      "epoch": 88.96,
+      "grad_norm": 0.04651033505797386,
+      "learning_rate": 8.281786941580757e-05,
+      "loss": 0.0241,
+      "step": 355
+    },
+    {
+      "epoch": 90.0,
+      "grad_norm": 0.15422558784484863,
+      "learning_rate": 8.253150057273768e-05,
+      "loss": 0.0225,
+      "step": 360
+    },
+    {
+      "epoch": 91.32,
+      "grad_norm": 0.05017378553748131,
+      "learning_rate": 8.224513172966782e-05,
+      "loss": 0.0226,
+      "step": 365
+    },
+    {
+      "epoch": 92.64,
+      "grad_norm": 0.04900256544351578,
+      "learning_rate": 8.195876288659795e-05,
+      "loss": 0.0214,
+      "step": 370
+    },
+    {
+      "epoch": 93.96,
+      "grad_norm": 0.039168599992990494,
+      "learning_rate": 8.167239404352807e-05,
+      "loss": 0.0235,
+      "step": 375
+    },
+    {
+      "epoch": 95.0,
+      "grad_norm": 0.16431346535682678,
+      "learning_rate": 8.13860252004582e-05,
+      "loss": 0.0234,
+      "step": 380
+    },
+    {
+      "epoch": 96.32,
+      "grad_norm": 0.047646068036556244,
+      "learning_rate": 8.109965635738833e-05,
+      "loss": 0.0233,
+      "step": 385
+    },
+    {
+      "epoch": 97.64,
+      "grad_norm": 0.04928329959511757,
+      "learning_rate": 8.081328751431845e-05,
+      "loss": 0.0224,
+      "step": 390
+    },
+    {
+      "epoch": 98.96,
+      "grad_norm": 0.042253389954566956,
+      "learning_rate": 8.052691867124858e-05,
+      "loss": 0.0231,
+      "step": 395
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.13217468559741974,
+      "learning_rate": 8.02405498281787e-05,
+      "loss": 0.0232,
+      "step": 400
+    },
+    {
+      "epoch": 101.32,
+      "grad_norm": 0.03638666123151779,
+      "learning_rate": 7.995418098510883e-05,
+      "loss": 0.0224,
+      "step": 405
+    },
+    {
+      "epoch": 102.64,
+      "grad_norm": 0.04150665923953056,
+      "learning_rate": 7.966781214203894e-05,
+      "loss": 0.0234,
+      "step": 410
+    },
+    {
+      "epoch": 103.96,
+      "grad_norm": 0.035543572157621384,
+      "learning_rate": 7.938144329896907e-05,
+      "loss": 0.0221,
+      "step": 415
+    },
+    {
+      "epoch": 105.0,
+      "grad_norm": 0.12740617990493774,
+      "learning_rate": 7.90950744558992e-05,
+      "loss": 0.0222,
+      "step": 420
+    },
+    {
+      "epoch": 106.32,
+      "grad_norm": 0.040774207562208176,
+      "learning_rate": 7.880870561282932e-05,
+      "loss": 0.0224,
+      "step": 425
+    },
+    {
+      "epoch": 107.64,
+      "grad_norm": 0.040325164794921875,
+      "learning_rate": 7.852233676975945e-05,
+      "loss": 0.0235,
+      "step": 430
+    },
+    {
+      "epoch": 108.96,
+      "grad_norm": 0.04361337795853615,
+      "learning_rate": 7.823596792668958e-05,
+      "loss": 0.0236,
+      "step": 435
+    },
+    {
+      "epoch": 110.0,
+      "grad_norm": 0.11627431213855743,
+      "learning_rate": 7.79495990836197e-05,
+      "loss": 0.0238,
+      "step": 440
+    },
+    {
+      "epoch": 111.32,
+      "grad_norm": 0.04112754762172699,
+      "learning_rate": 7.766323024054983e-05,
+      "loss": 0.0232,
+      "step": 445
+    },
+    {
+      "epoch": 112.64,
+      "grad_norm": 0.04499945417046547,
+      "learning_rate": 7.737686139747996e-05,
+      "loss": 0.0241,
+      "step": 450
+    },
+    {
+      "epoch": 113.96,
+      "grad_norm": 0.04413345456123352,
+      "learning_rate": 7.709049255441008e-05,
+      "loss": 0.0237,
+      "step": 455
+    },
+    {
+      "epoch": 115.0,
+      "grad_norm": 0.12778876721858978,
+      "learning_rate": 7.680412371134021e-05,
+      "loss": 0.023,
+      "step": 460
+    },
+    {
+      "epoch": 116.32,
+      "grad_norm": 0.039127930998802185,
+      "learning_rate": 7.651775486827034e-05,
+      "loss": 0.0226,
+      "step": 465
+    },
+    {
+      "epoch": 117.64,
+      "grad_norm": 0.04621637240052223,
+      "learning_rate": 7.623138602520046e-05,
+      "loss": 0.0228,
+      "step": 470
+    },
+    {
+      "epoch": 118.96,
+      "grad_norm": 0.0423317514359951,
+      "learning_rate": 7.594501718213059e-05,
+      "loss": 0.0236,
+      "step": 475
+    },
+    {
+      "epoch": 120.0,
+      "grad_norm": 0.13693822920322418,
+      "learning_rate": 7.565864833906071e-05,
+      "loss": 0.0229,
+      "step": 480
+    },
+    {
+      "epoch": 121.32,
+      "grad_norm": 0.03447780758142471,
+      "learning_rate": 7.537227949599084e-05,
+      "loss": 0.0223,
+      "step": 485
+    },
+    {
+      "epoch": 122.64,
+      "grad_norm": 0.03120778128504753,
+      "learning_rate": 7.508591065292097e-05,
+      "loss": 0.0232,
+      "step": 490
+    },
+    {
+      "epoch": 123.96,
+      "grad_norm": 0.03796784579753876,
+      "learning_rate": 7.47995418098511e-05,
+      "loss": 0.0226,
+      "step": 495
+    },
+    {
+      "epoch": 125.0,
+      "grad_norm": 0.11713339388370514,
+      "learning_rate": 7.451317296678122e-05,
+      "loss": 0.0227,
+      "step": 500
+    },
+    {
+      "epoch": 126.32,
+      "grad_norm": 0.03978479281067848,
+      "learning_rate": 7.422680412371135e-05,
+      "loss": 0.0225,
+      "step": 505
+    },
+    {
+      "epoch": 127.64,
+      "grad_norm": 0.03598278388381004,
+      "learning_rate": 7.394043528064147e-05,
+      "loss": 0.022,
+      "step": 510
+    },
+    {
+      "epoch": 128.96,
+      "grad_norm": 0.039090823382139206,
+      "learning_rate": 7.36540664375716e-05,
+      "loss": 0.0233,
+      "step": 515
+    },
+    {
+      "epoch": 130.0,
+      "grad_norm": 0.15534059703350067,
+      "learning_rate": 7.336769759450171e-05,
+      "loss": 0.0226,
+      "step": 520
+    },
+    {
+      "epoch": 131.32,
+      "grad_norm": 0.029727406799793243,
+      "learning_rate": 7.308132875143184e-05,
+      "loss": 0.0219,
+      "step": 525
+    },
+    {
+      "epoch": 132.64,
+      "grad_norm": 0.04031675308942795,
+      "learning_rate": 7.279495990836197e-05,
+      "loss": 0.0238,
+      "step": 530
+    },
+    {
+      "epoch": 133.96,
+      "grad_norm": 0.03739027678966522,
+      "learning_rate": 7.250859106529209e-05,
+      "loss": 0.0226,
+      "step": 535
+    },
+    {
+      "epoch": 135.0,
+      "grad_norm": 0.11986713111400604,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.0236,
+      "step": 540
+    },
+    {
+      "epoch": 136.32,
+      "grad_norm": 0.03799319267272949,
+      "learning_rate": 7.193585337915235e-05,
+      "loss": 0.0239,
+      "step": 545
+    },
+    {
+      "epoch": 137.64,
+      "grad_norm": 0.033889301121234894,
+      "learning_rate": 7.164948453608247e-05,
+      "loss": 0.0212,
+      "step": 550
+    },
+    {
+      "epoch": 138.96,
+      "grad_norm": 0.03568562492728233,
+      "learning_rate": 7.136311569301261e-05,
+      "loss": 0.0232,
+      "step": 555
+    },
+    {
+      "epoch": 140.0,
+      "grad_norm": 0.09219885617494583,
+      "learning_rate": 7.107674684994274e-05,
+      "loss": 0.0209,
+      "step": 560
+    },
+    {
+      "epoch": 141.32,
+      "grad_norm": 0.030130775645375252,
+      "learning_rate": 7.079037800687286e-05,
+      "loss": 0.0218,
+      "step": 565
+    },
+    {
+      "epoch": 142.64,
+      "grad_norm": 0.04322782903909683,
+      "learning_rate": 7.050400916380299e-05,
+      "loss": 0.024,
+      "step": 570
+    },
+    {
+      "epoch": 143.96,
+      "grad_norm": 0.04596129059791565,
+      "learning_rate": 7.02176403207331e-05,
+      "loss": 0.0223,
+      "step": 575
+    },
+    {
+      "epoch": 145.0,
+      "grad_norm": 0.13223205506801605,
+      "learning_rate": 6.993127147766323e-05,
+      "loss": 0.0228,
+      "step": 580
+    },
+    {
+      "epoch": 146.32,
+      "grad_norm": 0.033803775906562805,
+      "learning_rate": 6.964490263459336e-05,
+      "loss": 0.0221,
+      "step": 585
+    },
+    {
+      "epoch": 147.64,
+      "grad_norm": 0.03498265892267227,
+      "learning_rate": 6.935853379152348e-05,
+      "loss": 0.0223,
+      "step": 590
+    },
+    {
+      "epoch": 148.96,
+      "grad_norm": 0.03388480842113495,
+      "learning_rate": 6.907216494845361e-05,
+      "loss": 0.0228,
+      "step": 595
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 0.07770175486803055,
+      "learning_rate": 6.878579610538374e-05,
+      "loss": 0.0226,
+      "step": 600
+    },
+    {
+      "epoch": 151.32,
+      "grad_norm": 0.035058703273534775,
+      "learning_rate": 6.849942726231386e-05,
+      "loss": 0.0222,
+      "step": 605
+    },
+    {
+      "epoch": 152.64,
+      "grad_norm": 0.03751351311802864,
+      "learning_rate": 6.821305841924399e-05,
+      "loss": 0.0226,
+      "step": 610
+    },
+    {
+      "epoch": 153.96,
+      "grad_norm": 0.03246760368347168,
+      "learning_rate": 6.792668957617412e-05,
+      "loss": 0.0214,
+      "step": 615
+    },
+    {
+      "epoch": 155.0,
+      "grad_norm": 0.13589045405387878,
+      "learning_rate": 6.764032073310424e-05,
+      "loss": 0.0237,
+      "step": 620
+    },
+    {
+      "epoch": 156.32,
+      "grad_norm": 0.031439099460840225,
+      "learning_rate": 6.735395189003437e-05,
+      "loss": 0.0217,
+      "step": 625
+    },
+    {
+      "epoch": 157.64,
+      "grad_norm": 0.03206655755639076,
+      "learning_rate": 6.706758304696448e-05,
+      "loss": 0.0232,
+      "step": 630
+    },
+    {
+      "epoch": 158.96,
+      "grad_norm": 0.037526197731494904,
+      "learning_rate": 6.678121420389462e-05,
+      "loss": 0.0218,
+      "step": 635
+    },
+    {
+      "epoch": 160.0,
+      "grad_norm": 0.09874481707811356,
+      "learning_rate": 6.649484536082475e-05,
+      "loss": 0.0228,
+      "step": 640
+    },
+    {
+      "epoch": 161.32,
+      "grad_norm": 0.03909553959965706,
+      "learning_rate": 6.620847651775487e-05,
+      "loss": 0.0225,
+      "step": 645
+    },
+    {
+      "epoch": 162.64,
+      "grad_norm": 0.034332025796175,
+      "learning_rate": 6.5922107674685e-05,
+      "loss": 0.0222,
+      "step": 650
+    },
+    {
+      "epoch": 163.96,
+      "grad_norm": 0.033894602209329605,
+      "learning_rate": 6.563573883161513e-05,
+      "loss": 0.0219,
+      "step": 655
+    },
+    {
+      "epoch": 165.0,
+      "grad_norm": 0.09040471911430359,
+      "learning_rate": 6.534936998854525e-05,
+      "loss": 0.0219,
+      "step": 660
+    },
+    {
+      "epoch": 166.32,
+      "grad_norm": 0.03086320124566555,
+      "learning_rate": 6.506300114547538e-05,
+      "loss": 0.0241,
+      "step": 665
+    },
+    {
+      "epoch": 167.64,
+      "grad_norm": 0.030052335932850838,
+      "learning_rate": 6.477663230240551e-05,
+      "loss": 0.0223,
+      "step": 670
+    },
+    {
+      "epoch": 168.96,
+      "grad_norm": 0.028752340003848076,
+      "learning_rate": 6.449026345933563e-05,
+      "loss": 0.0226,
+      "step": 675
+    },
+    {
+      "epoch": 170.0,
+      "grad_norm": 0.09044802188873291,
+      "learning_rate": 6.420389461626576e-05,
+      "loss": 0.0245,
+      "step": 680
+    },
+    {
+      "epoch": 171.32,
+      "grad_norm": 0.031187741085886955,
+      "learning_rate": 6.391752577319587e-05,
+      "loss": 0.0234,
+      "step": 685
+    },
+    {
+      "epoch": 172.64,
+      "grad_norm": 0.032953280955553055,
+      "learning_rate": 6.3631156930126e-05,
+      "loss": 0.0231,
+      "step": 690
+    },
+    {
+      "epoch": 173.96,
+      "grad_norm": 0.035380713641643524,
+      "learning_rate": 6.334478808705613e-05,
+      "loss": 0.0231,
+      "step": 695
+    },
+    {
+      "epoch": 175.0,
+      "grad_norm": 0.10263343155384064,
+      "learning_rate": 6.305841924398625e-05,
+      "loss": 0.0226,
+      "step": 700
+    },
+    {
+      "epoch": 176.32,
+      "grad_norm": 0.03277510777115822,
+      "learning_rate": 6.277205040091638e-05,
+      "loss": 0.0222,
+      "step": 705
+    },
+    {
+      "epoch": 177.64,
+      "grad_norm": 0.034485459327697754,
+      "learning_rate": 6.24856815578465e-05,
+      "loss": 0.0227,
+      "step": 710
+    },
+    {
+      "epoch": 178.96,
+      "grad_norm": 0.03501957654953003,
+      "learning_rate": 6.219931271477663e-05,
+      "loss": 0.0223,
+      "step": 715
+    },
+    {
+      "epoch": 180.0,
+      "grad_norm": 0.11059446632862091,
+      "learning_rate": 6.191294387170676e-05,
+      "loss": 0.0219,
+      "step": 720
+    },
+    {
+      "epoch": 181.32,
+      "grad_norm": 0.03453643247485161,
+      "learning_rate": 6.162657502863689e-05,
+      "loss": 0.0223,
+      "step": 725
+    },
+    {
+      "epoch": 182.64,
+      "grad_norm": 0.031747136265039444,
+      "learning_rate": 6.134020618556701e-05,
+      "loss": 0.0211,
+      "step": 730
+    },
+    {
+      "epoch": 183.96,
+      "grad_norm": 0.03772411495447159,
+      "learning_rate": 6.105383734249714e-05,
+      "loss": 0.0213,
+      "step": 735
+    },
+    {
+      "epoch": 185.0,
+      "grad_norm": 0.08717264235019684,
+      "learning_rate": 6.076746849942726e-05,
+      "loss": 0.0232,
+      "step": 740
+    },
+    {
+      "epoch": 186.32,
+      "grad_norm": 0.030604945495724678,
+      "learning_rate": 6.0481099656357384e-05,
+      "loss": 0.023,
+      "step": 745
+    },
+    {
+      "epoch": 187.64,
+      "grad_norm": 0.027379345148801804,
+      "learning_rate": 6.019473081328752e-05,
+      "loss": 0.0217,
+      "step": 750
+    },
+    {
+      "epoch": 188.96,
+      "grad_norm": 0.032438065856695175,
+      "learning_rate": 5.9908361970217644e-05,
+      "loss": 0.0252,
+      "step": 755
+    },
+    {
+      "epoch": 190.0,
+      "grad_norm": 0.08274230360984802,
+      "learning_rate": 5.962199312714777e-05,
+      "loss": 0.0212,
+      "step": 760
+    },
+    {
+      "epoch": 191.32,
+      "grad_norm": 0.02920094132423401,
+      "learning_rate": 5.93356242840779e-05,
+      "loss": 0.0224,
+      "step": 765
+    },
+    {
+      "epoch": 192.64,
+      "grad_norm": 0.03730329871177673,
+      "learning_rate": 5.904925544100802e-05,
+      "loss": 0.0228,
+      "step": 770
+    },
+    {
+      "epoch": 193.96,
+      "grad_norm": 0.040118809789419174,
+      "learning_rate": 5.876288659793815e-05,
+      "loss": 0.0226,
+      "step": 775
+    },
+    {
+      "epoch": 195.0,
+      "grad_norm": 0.08151891827583313,
+      "learning_rate": 5.8476517754868276e-05,
+      "loss": 0.022,
+      "step": 780
+    },
+    {
+      "epoch": 196.32,
+      "grad_norm": 0.0327572226524353,
+      "learning_rate": 5.81901489117984e-05,
+      "loss": 0.0219,
+      "step": 785
+    },
+    {
+      "epoch": 197.64,
+      "grad_norm": 0.027864839881658554,
+      "learning_rate": 5.790378006872853e-05,
+      "loss": 0.0235,
+      "step": 790
+    },
+    {
+      "epoch": 198.96,
+      "grad_norm": 0.033668313175439835,
+      "learning_rate": 5.761741122565865e-05,
+      "loss": 0.0229,
+      "step": 795
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 0.07690460234880447,
+      "learning_rate": 5.7331042382588775e-05,
+      "loss": 0.0225,
+      "step": 800
+    },
+    {
+      "epoch": 201.32,
+      "grad_norm": 0.030898429453372955,
+      "learning_rate": 5.70446735395189e-05,
+      "loss": 0.022,
+      "step": 805
+    },
+    {
+      "epoch": 202.64,
+      "grad_norm": 0.02849520556628704,
+      "learning_rate": 5.675830469644903e-05,
+      "loss": 0.023,
+      "step": 810
+    },
+    {
+      "epoch": 203.96,
+      "grad_norm": 0.031954504549503326,
+      "learning_rate": 5.6471935853379155e-05,
+      "loss": 0.0225,
+      "step": 815
+    },
+    {
+      "epoch": 205.0,
+      "grad_norm": 0.09324806183576584,
+      "learning_rate": 5.618556701030928e-05,
+      "loss": 0.0233,
+      "step": 820
+    },
+    {
+      "epoch": 206.32,
+      "grad_norm": 0.0302401315420866,
+      "learning_rate": 5.589919816723941e-05,
+      "loss": 0.0215,
+      "step": 825
+    },
+    {
+      "epoch": 207.64,
+      "grad_norm": 0.029426347464323044,
+      "learning_rate": 5.5612829324169534e-05,
+      "loss": 0.0215,
+      "step": 830
+    },
+    {
+      "epoch": 208.96,
+      "grad_norm": 0.031664323061704636,
+      "learning_rate": 5.532646048109966e-05,
+      "loss": 0.0218,
+      "step": 835
+    },
+    {
+      "epoch": 210.0,
+      "grad_norm": 0.09568897634744644,
+      "learning_rate": 5.504009163802979e-05,
+      "loss": 0.0208,
+      "step": 840
+    },
+    {
+      "epoch": 211.32,
+      "grad_norm": 0.029477190226316452,
+      "learning_rate": 5.4753722794959914e-05,
+      "loss": 0.0214,
+      "step": 845
+    },
+    {
+      "epoch": 212.64,
+      "grad_norm": 0.030615277588367462,
+      "learning_rate": 5.4467353951890033e-05,
+      "loss": 0.0227,
+      "step": 850
+    },
+    {
+      "epoch": 213.96,
+      "grad_norm": 0.03466692939400673,
+      "learning_rate": 5.418098510882016e-05,
+      "loss": 0.0212,
+      "step": 855
+    },
+    {
+      "epoch": 215.0,
+      "grad_norm": 0.1077422946691513,
+      "learning_rate": 5.3894616265750286e-05,
+      "loss": 0.022,
+      "step": 860
+    },
+    {
+      "epoch": 216.32,
+      "grad_norm": 0.030155370011925697,
+      "learning_rate": 5.360824742268041e-05,
+      "loss": 0.0227,
+      "step": 865
+    },
+    {
+      "epoch": 217.64,
+      "grad_norm": 0.02762630768120289,
+      "learning_rate": 5.332187857961054e-05,
+      "loss": 0.0219,
+      "step": 870
+    },
+    {
+      "epoch": 218.96,
+      "grad_norm": 0.027750438079237938,
+      "learning_rate": 5.3035509736540666e-05,
+      "loss": 0.0225,
+      "step": 875
+    },
+    {
+      "epoch": 220.0,
+      "grad_norm": 0.1480046659708023,
+      "learning_rate": 5.274914089347079e-05,
+      "loss": 0.024,
+      "step": 880
+    },
+    {
+      "epoch": 221.32,
+      "grad_norm": 0.027756843715906143,
+      "learning_rate": 5.246277205040092e-05,
+      "loss": 0.0232,
+      "step": 885
+    },
+    {
+      "epoch": 222.64,
+      "grad_norm": 0.025351909920573235,
+      "learning_rate": 5.2176403207331045e-05,
+      "loss": 0.0224,
+      "step": 890
+    },
+    {
+      "epoch": 223.96,
+      "grad_norm": 0.03722308948636055,
+      "learning_rate": 5.189003436426118e-05,
+      "loss": 0.0224,
+      "step": 895
+    },
+    {
+      "epoch": 225.0,
+      "grad_norm": 0.09891820698976517,
+      "learning_rate": 5.1603665521191305e-05,
+      "loss": 0.0223,
+      "step": 900
+    },
+    {
+      "epoch": 226.32,
+      "grad_norm": 0.031157376244664192,
+      "learning_rate": 5.131729667812142e-05,
+      "loss": 0.0228,
+      "step": 905
+    },
+    {
+      "epoch": 227.64,
+      "grad_norm": 0.026530060917139053,
+      "learning_rate": 5.1030927835051544e-05,
+      "loss": 0.0227,
+      "step": 910
+    },
+    {
+      "epoch": 228.96,
+      "grad_norm": 0.028711870312690735,
+      "learning_rate": 5.074455899198167e-05,
+      "loss": 0.0229,
+      "step": 915
+    },
+    {
+      "epoch": 230.0,
+      "grad_norm": 0.10996802896261215,
+      "learning_rate": 5.04581901489118e-05,
+      "loss": 0.0236,
+      "step": 920
+    },
+    {
+      "epoch": 231.32,
+      "grad_norm": 0.026562057435512543,
+      "learning_rate": 5.0171821305841924e-05,
+      "loss": 0.0221,
+      "step": 925
+    },
+    {
+      "epoch": 232.64,
+      "grad_norm": 0.029791025444865227,
+      "learning_rate": 4.988545246277205e-05,
+      "loss": 0.0237,
+      "step": 930
+    },
+    {
+      "epoch": 233.96,
+      "grad_norm": 0.030204325914382935,
+      "learning_rate": 4.9599083619702184e-05,
+      "loss": 0.0222,
+      "step": 935
+    },
+    {
+      "epoch": 235.0,
+      "grad_norm": 0.06489063054323196,
+      "learning_rate": 4.931271477663231e-05,
+      "loss": 0.0212,
+      "step": 940
+    },
+    {
+      "epoch": 236.32,
+      "grad_norm": 0.033282287418842316,
+      "learning_rate": 4.902634593356243e-05,
+      "loss": 0.0224,
+      "step": 945
+    },
+    {
+      "epoch": 237.64,
+      "grad_norm": 0.030851591378450394,
+      "learning_rate": 4.8739977090492556e-05,
+      "loss": 0.0216,
+      "step": 950
+    },
+    {
+      "epoch": 238.96,
+      "grad_norm": 0.029777253046631813,
+      "learning_rate": 4.845360824742268e-05,
+      "loss": 0.0222,
+      "step": 955
+    },
+    {
+      "epoch": 240.0,
+      "grad_norm": 0.06517614424228668,
+      "learning_rate": 4.816723940435281e-05,
+      "loss": 0.0197,
+      "step": 960
+    },
+    {
+      "epoch": 241.32,
+      "grad_norm": 0.027710000053048134,
+      "learning_rate": 4.7880870561282936e-05,
+      "loss": 0.0231,
+      "step": 965
+    },
+    {
+      "epoch": 242.64,
+      "grad_norm": 0.027534285560250282,
+      "learning_rate": 4.7594501718213055e-05,
+      "loss": 0.0229,
+      "step": 970
+    },
+    {
+      "epoch": 243.96,
+      "grad_norm": 0.029630396515130997,
+      "learning_rate": 4.730813287514318e-05,
+      "loss": 0.0219,
+      "step": 975
+    },
+    {
+      "epoch": 245.0,
+      "grad_norm": 0.09967376291751862,
+      "learning_rate": 4.7021764032073315e-05,
+      "loss": 0.0211,
+      "step": 980
+    },
+    {
+      "epoch": 246.32,
+      "grad_norm": 0.026448087766766548,
+      "learning_rate": 4.673539518900344e-05,
+      "loss": 0.0219,
+      "step": 985
+    },
+    {
+      "epoch": 247.64,
+      "grad_norm": 0.030766399577260017,
+      "learning_rate": 4.644902634593357e-05,
+      "loss": 0.0218,
+      "step": 990
+    },
+    {
+      "epoch": 248.96,
+      "grad_norm": 0.03127891570329666,
+      "learning_rate": 4.6162657502863694e-05,
+      "loss": 0.0222,
+      "step": 995
+    },
+    {
+      "epoch": 250.0,
+      "grad_norm": 0.07358253002166748,
+      "learning_rate": 4.5876288659793814e-05,
+      "loss": 0.022,
+      "step": 1000
+    },
+    {
+      "epoch": 251.32,
+      "grad_norm": 0.030259255319833755,
+      "learning_rate": 4.558991981672394e-05,
+      "loss": 0.0215,
+      "step": 1005
+    },
+    {
+      "epoch": 252.64,
+      "grad_norm": 0.031163489446043968,
+      "learning_rate": 4.530355097365407e-05,
+      "loss": 0.0218,
+      "step": 1010
+    },
+    {
+      "epoch": 253.96,
+      "grad_norm": 0.025623638182878494,
+      "learning_rate": 4.5017182130584194e-05,
+      "loss": 0.0225,
+      "step": 1015
+    },
+    {
+      "epoch": 255.0,
+      "grad_norm": 0.10825876146554947,
+      "learning_rate": 4.473081328751432e-05,
+      "loss": 0.0228,
+      "step": 1020
+    },
+    {
+      "epoch": 256.32,
+      "grad_norm": 0.029599890112876892,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.0218,
+      "step": 1025
+    },
+    {
+      "epoch": 257.64,
+      "grad_norm": 0.027761822566390038,
+      "learning_rate": 4.415807560137457e-05,
+      "loss": 0.0226,
+      "step": 1030
+    },
+    {
+      "epoch": 258.96,
+      "grad_norm": 0.03065340407192707,
+      "learning_rate": 4.38717067583047e-05,
+      "loss": 0.0235,
+      "step": 1035
+    },
+    {
+      "epoch": 260.0,
+      "grad_norm": 0.08595085889101028,
+      "learning_rate": 4.3585337915234826e-05,
+      "loss": 0.0225,
+      "step": 1040
+    },
+    {
+      "epoch": 261.32,
+      "grad_norm": 0.031066762283444405,
+      "learning_rate": 4.329896907216495e-05,
+      "loss": 0.0236,
+      "step": 1045
+    },
+    {
+      "epoch": 262.64,
+      "grad_norm": 0.028579367324709892,
+      "learning_rate": 4.301260022909508e-05,
+      "loss": 0.0214,
+      "step": 1050
+    },
+    {
+      "epoch": 263.96,
+      "grad_norm": 0.028484277427196503,
+      "learning_rate": 4.27262313860252e-05,
+      "loss": 0.0223,
+      "step": 1055
+    },
+    {
+      "epoch": 265.0,
+      "grad_norm": 0.08596421033143997,
+      "learning_rate": 4.2439862542955325e-05,
+      "loss": 0.0215,
+      "step": 1060
+    },
+    {
+      "epoch": 266.32,
+      "grad_norm": 0.02508409693837166,
+      "learning_rate": 4.215349369988545e-05,
+      "loss": 0.0214,
+      "step": 1065
+    },
+    {
+      "epoch": 267.64,
+      "grad_norm": 0.02804061770439148,
+      "learning_rate": 4.1867124856815585e-05,
+      "loss": 0.0236,
+      "step": 1070
+    },
+    {
+      "epoch": 268.96,
+      "grad_norm": 0.030820870772004128,
+      "learning_rate": 4.158075601374571e-05,
+      "loss": 0.0222,
+      "step": 1075
+    },
+    {
+      "epoch": 270.0,
+      "grad_norm": 0.09306512773036957,
+      "learning_rate": 4.129438717067583e-05,
+      "loss": 0.0211,
+      "step": 1080
+    },
+    {
+      "epoch": 271.32,
+      "grad_norm": 0.030462536960840225,
+      "learning_rate": 4.100801832760596e-05,
+      "loss": 0.0222,
+      "step": 1085
+    },
+    {
+      "epoch": 272.64,
+      "grad_norm": 0.029752682894468307,
+      "learning_rate": 4.0721649484536084e-05,
+      "loss": 0.0219,
+      "step": 1090
+    },
+    {
+      "epoch": 273.96,
+      "grad_norm": 0.02907637320458889,
+      "learning_rate": 4.043528064146621e-05,
+      "loss": 0.0224,
+      "step": 1095
+    },
+    {
+      "epoch": 275.0,
+      "grad_norm": 0.11900507658720016,
+      "learning_rate": 4.014891179839634e-05,
+      "loss": 0.0224,
+      "step": 1100
+    },
+    {
+      "epoch": 276.32,
+      "grad_norm": 0.029513241723179817,
+      "learning_rate": 3.9862542955326463e-05,
+      "loss": 0.0223,
+      "step": 1105
+    },
+    {
+      "epoch": 277.64,
+      "grad_norm": 0.02655150555074215,
+      "learning_rate": 3.957617411225659e-05,
+      "loss": 0.0215,
+      "step": 1110
+    },
+    {
+      "epoch": 278.96,
+      "grad_norm": 0.031090132892131805,
+      "learning_rate": 3.9289805269186716e-05,
+      "loss": 0.0229,
+      "step": 1115
+    },
+    {
+      "epoch": 280.0,
+      "grad_norm": 0.10574332624673843,
+      "learning_rate": 3.900343642611684e-05,
+      "loss": 0.0226,
+      "step": 1120
+    },
+    {
+      "epoch": 281.32,
+      "grad_norm": 0.025768013671040535,
+      "learning_rate": 3.871706758304697e-05,
+      "loss": 0.022,
+      "step": 1125
+    },
+    {
+      "epoch": 282.64,
+      "grad_norm": 0.02915865182876587,
+      "learning_rate": 3.8430698739977096e-05,
+      "loss": 0.0226,
+      "step": 1130
+    },
+    {
+      "epoch": 283.96,
+      "grad_norm": 0.028867091983556747,
+      "learning_rate": 3.8144329896907216e-05,
+      "loss": 0.0223,
+      "step": 1135
+    },
+    {
+      "epoch": 285.0,
+      "grad_norm": 0.06698961555957794,
+      "learning_rate": 3.785796105383734e-05,
+      "loss": 0.0209,
+      "step": 1140
+    },
+    {
+      "epoch": 286.32,
+      "grad_norm": 0.029880354180932045,
+      "learning_rate": 3.757159221076747e-05,
+      "loss": 0.0226,
+      "step": 1145
+    },
+    {
+      "epoch": 287.64,
+      "grad_norm": 0.027591262012720108,
+      "learning_rate": 3.7285223367697595e-05,
+      "loss": 0.0213,
+      "step": 1150
+    },
+    {
+      "epoch": 288.96,
+      "grad_norm": 0.029396766796708107,
+      "learning_rate": 3.699885452462772e-05,
+      "loss": 0.023,
+      "step": 1155
+    },
+    {
+      "epoch": 290.0,
+      "grad_norm": 0.10461018979549408,
+      "learning_rate": 3.671248568155785e-05,
+      "loss": 0.0218,
+      "step": 1160
+    },
+    {
+      "epoch": 291.32,
+      "grad_norm": 0.029114672914147377,
+      "learning_rate": 3.6426116838487974e-05,
+      "loss": 0.0222,
+      "step": 1165
+    },
+    {
+      "epoch": 292.64,
+      "grad_norm": 0.027854561805725098,
+      "learning_rate": 3.61397479954181e-05,
+      "loss": 0.0229,
+      "step": 1170
+    },
+    {
+      "epoch": 293.96,
+      "grad_norm": 0.0312589667737484,
+      "learning_rate": 3.585337915234823e-05,
+      "loss": 0.0222,
+      "step": 1175
+    },
+    {
+      "epoch": 295.0,
+      "grad_norm": 0.10697894543409348,
+      "learning_rate": 3.5567010309278354e-05,
+      "loss": 0.0209,
+      "step": 1180
+    },
+    {
+      "epoch": 296.32,
+      "grad_norm": 0.029923448339104652,
+      "learning_rate": 3.528064146620848e-05,
+      "loss": 0.0224,
+      "step": 1185
+    },
+    {
+      "epoch": 297.64,
+      "grad_norm": 0.02807888388633728,
+      "learning_rate": 3.49942726231386e-05,
+      "loss": 0.0225,
+      "step": 1190
+    },
+    {
+      "epoch": 298.96,
+      "grad_norm": 0.028458457440137863,
+      "learning_rate": 3.4707903780068726e-05,
+      "loss": 0.023,
+      "step": 1195
+    },
+    {
+      "epoch": 300.0,
+      "grad_norm": 0.09004534780979156,
+      "learning_rate": 3.442153493699885e-05,
+      "loss": 0.0216,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 450,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0205427400704e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

Math_QA/group_08/checkpoints/checkpoint-1500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/不冻结Qwen训练/models/Qwen2.5-1.5B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

Math_QA/group_08/checkpoints/checkpoint-1500/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

Math_QA/group_08/checkpoints/checkpoint-1500/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

Math_QA/group_08/checkpoints/checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Math_QA/group_08/checkpoints/checkpoint-1500/trainer_state.json

@@ -0,0 +1,2141 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 375.0,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "grad_norm": 10.268527030944824,
+      "learning_rate": 0.0,
+      "loss": 1.8412,
+      "step": 1
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 7.169743537902832,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.7908,
+      "step": 5
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 3.2965712547302246,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.541,
+      "step": 10
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 1.9259239435195923,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 1.195,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.5386537313461304,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.8407,
+      "step": 20
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.7439631223678589,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.7134,
+      "step": 25
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.5669045448303223,
+      "learning_rate": 5.370370370370371e-05,
+      "loss": 0.6253,
+      "step": 30
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.5955387353897095,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.5425,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.794498324394226,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.4517,
+      "step": 40
+    },
+    {
+      "epoch": 11.32,
+      "grad_norm": 0.6224164366722107,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.3649,
+      "step": 45
+    },
+    {
+      "epoch": 12.64,
+      "grad_norm": 0.7097190022468567,
+      "learning_rate": 9.074074074074075e-05,
+      "loss": 0.2806,
+      "step": 50
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 0.8385046124458313,
+      "learning_rate": 0.0001,
+      "loss": 0.2055,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 2.7302768230438232,
+      "learning_rate": 9.971363115693013e-05,
+      "loss": 0.1593,
+      "step": 60
+    },
+    {
+      "epoch": 16.32,
+      "grad_norm": 0.573469877243042,
+      "learning_rate": 9.942726231386026e-05,
+      "loss": 0.1173,
+      "step": 65
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 1.059529423713684,
+      "learning_rate": 9.914089347079038e-05,
+      "loss": 0.0856,
+      "step": 70
+    },
+    {
+      "epoch": 18.96,
+      "grad_norm": 0.6318557858467102,
+      "learning_rate": 9.885452462772051e-05,
+      "loss": 0.0783,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.4067771434783936,
+      "learning_rate": 9.856815578465064e-05,
+      "loss": 0.0684,
+      "step": 80
+    },
+    {
+      "epoch": 21.32,
+      "grad_norm": 0.3381839096546173,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 0.0351,
+      "step": 85
+    },
+    {
+      "epoch": 22.64,
+      "grad_norm": 0.3768102824687958,
+      "learning_rate": 9.799541809851088e-05,
+      "loss": 0.0296,
+      "step": 90
+    },
+    {
+      "epoch": 23.96,
+      "grad_norm": 0.21533846855163574,
+      "learning_rate": 9.7709049255441e-05,
+      "loss": 0.0296,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.729438841342926,
+      "learning_rate": 9.742268041237114e-05,
+      "loss": 0.0327,
+      "step": 100
+    },
+    {
+      "epoch": 26.32,
+      "grad_norm": 0.15956193208694458,
+      "learning_rate": 9.713631156930127e-05,
+      "loss": 0.0335,
+      "step": 105
+    },
+    {
+      "epoch": 27.64,
+      "grad_norm": 0.3089437186717987,
+      "learning_rate": 9.68499427262314e-05,
+      "loss": 0.0373,
+      "step": 110
+    },
+    {
+      "epoch": 28.96,
+      "grad_norm": 0.2873784303665161,
+      "learning_rate": 9.656357388316152e-05,
+      "loss": 0.028,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.3081432282924652,
+      "learning_rate": 9.627720504009165e-05,
+      "loss": 0.0288,
+      "step": 120
+    },
+    {
+      "epoch": 31.32,
+      "grad_norm": 0.15154343843460083,
+      "learning_rate": 9.599083619702178e-05,
+      "loss": 0.0258,
+      "step": 125
+    },
+    {
+      "epoch": 32.64,
+      "grad_norm": 0.21917082369327545,
+      "learning_rate": 9.57044673539519e-05,
+      "loss": 0.0276,
+      "step": 130
+    },
+    {
+      "epoch": 33.96,
+      "grad_norm": 0.4817427396774292,
+      "learning_rate": 9.541809851088203e-05,
+      "loss": 0.028,
+      "step": 135
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.9411588311195374,
+      "learning_rate": 9.513172966781214e-05,
+      "loss": 0.0301,
+      "step": 140
+    },
+    {
+      "epoch": 36.32,
+      "grad_norm": 0.12594084441661835,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.0278,
+      "step": 145
+    },
+    {
+      "epoch": 37.64,
+      "grad_norm": 0.09696595370769501,
+      "learning_rate": 9.45589919816724e-05,
+      "loss": 0.0254,
+      "step": 150
+    },
+    {
+      "epoch": 38.96,
+      "grad_norm": 0.07912517338991165,
+      "learning_rate": 9.427262313860252e-05,
+      "loss": 0.0253,
+      "step": 155
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.16622836887836456,
+      "learning_rate": 9.398625429553265e-05,
+      "loss": 0.0244,
+      "step": 160
+    },
+    {
+      "epoch": 41.32,
+      "grad_norm": 0.0670735314488411,
+      "learning_rate": 9.369988545246277e-05,
+      "loss": 0.0246,
+      "step": 165
+    },
+    {
+      "epoch": 42.64,
+      "grad_norm": 0.06884271651506424,
+      "learning_rate": 9.34135166093929e-05,
+      "loss": 0.0228,
+      "step": 170
+    },
+    {
+      "epoch": 43.96,
+      "grad_norm": 0.1034952700138092,
+      "learning_rate": 9.312714776632303e-05,
+      "loss": 0.0242,
+      "step": 175
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 0.1411074995994568,
+      "learning_rate": 9.284077892325315e-05,
+      "loss": 0.0237,
+      "step": 180
+    },
+    {
+      "epoch": 46.32,
+      "grad_norm": 0.06430694460868835,
+      "learning_rate": 9.255441008018328e-05,
+      "loss": 0.0244,
+      "step": 185
+    },
+    {
+      "epoch": 47.64,
+      "grad_norm": 0.06416841596364975,
+      "learning_rate": 9.22680412371134e-05,
+      "loss": 0.0253,
+      "step": 190
+    },
+    {
+      "epoch": 48.96,
+      "grad_norm": 0.05058900639414787,
+      "learning_rate": 9.198167239404353e-05,
+      "loss": 0.0234,
+      "step": 195
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.17872126400470734,
+      "learning_rate": 9.169530355097366e-05,
+      "loss": 0.0247,
+      "step": 200
+    },
+    {
+      "epoch": 51.32,
+      "grad_norm": 0.05059915408492088,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.0248,
+      "step": 205
+    },
+    {
+      "epoch": 52.64,
+      "grad_norm": 0.05440365895628929,
+      "learning_rate": 9.112256586483391e-05,
+      "loss": 0.0254,
+      "step": 210
+    },
+    {
+      "epoch": 53.96,
+      "grad_norm": 0.05572507157921791,
+      "learning_rate": 9.083619702176404e-05,
+      "loss": 0.0245,
+      "step": 215
+    },
+    {
+      "epoch": 55.0,
+      "grad_norm": 0.13678045570850372,
+      "learning_rate": 9.054982817869416e-05,
+      "loss": 0.0226,
+      "step": 220
+    },
+    {
+      "epoch": 56.32,
+      "grad_norm": 0.05588487163186073,
+      "learning_rate": 9.026345933562429e-05,
+      "loss": 0.0243,
+      "step": 225
+    },
+    {
+      "epoch": 57.64,
+      "grad_norm": 0.052309829741716385,
+      "learning_rate": 8.997709049255442e-05,
+      "loss": 0.0236,
+      "step": 230
+    },
+    {
+      "epoch": 58.96,
+      "grad_norm": 0.056767936795949936,
+      "learning_rate": 8.969072164948454e-05,
+      "loss": 0.0226,
+      "step": 235
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.24060668051242828,
+      "learning_rate": 8.940435280641467e-05,
+      "loss": 0.0232,
+      "step": 240
+    },
+    {
+      "epoch": 61.32,
+      "grad_norm": 0.05159705877304077,
+      "learning_rate": 8.91179839633448e-05,
+      "loss": 0.0231,
+      "step": 245
+    },
+    {
+      "epoch": 62.64,
+      "grad_norm": 0.053261805325746536,
+      "learning_rate": 8.883161512027491e-05,
+      "loss": 0.0231,
+      "step": 250
+    },
+    {
+      "epoch": 63.96,
+      "grad_norm": 0.05033772811293602,
+      "learning_rate": 8.854524627720504e-05,
+      "loss": 0.0243,
+      "step": 255
+    },
+    {
+      "epoch": 65.0,
+      "grad_norm": 0.1512952744960785,
+      "learning_rate": 8.825887743413516e-05,
+      "loss": 0.0245,
+      "step": 260
+    },
+    {
+      "epoch": 66.32,
+      "grad_norm": 0.057306934148073196,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 0.0232,
+      "step": 265
+    },
+    {
+      "epoch": 67.64,
+      "grad_norm": 0.04558086022734642,
+      "learning_rate": 8.768613974799542e-05,
+      "loss": 0.0223,
+      "step": 270
+    },
+    {
+      "epoch": 68.96,
+      "grad_norm": 0.04183197394013405,
+      "learning_rate": 8.739977090492554e-05,
+      "loss": 0.0259,
+      "step": 275
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.15279851853847504,
+      "learning_rate": 8.711340206185567e-05,
+      "loss": 0.0231,
+      "step": 280
+    },
+    {
+      "epoch": 71.32,
+      "grad_norm": 0.04648765176534653,
+      "learning_rate": 8.682703321878581e-05,
+      "loss": 0.0247,
+      "step": 285
+    },
+    {
+      "epoch": 72.64,
+      "grad_norm": 0.05621657893061638,
+      "learning_rate": 8.654066437571594e-05,
+      "loss": 0.0241,
+      "step": 290
+    },
+    {
+      "epoch": 73.96,
+      "grad_norm": 0.05430695042014122,
+      "learning_rate": 8.625429553264606e-05,
+      "loss": 0.0224,
+      "step": 295
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.13658379018306732,
+      "learning_rate": 8.596792668957619e-05,
+      "loss": 0.0244,
+      "step": 300
+    },
+    {
+      "epoch": 76.32,
+      "grad_norm": 0.04552018269896507,
+      "learning_rate": 8.56815578465063e-05,
+      "loss": 0.023,
+      "step": 305
+    },
+    {
+      "epoch": 77.64,
+      "grad_norm": 0.061252057552337646,
+      "learning_rate": 8.539518900343643e-05,
+      "loss": 0.0232,
+      "step": 310
+    },
+    {
+      "epoch": 78.96,
+      "grad_norm": 0.06784722954034805,
+      "learning_rate": 8.510882016036655e-05,
+      "loss": 0.0225,
+      "step": 315
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 0.12553691864013672,
+      "learning_rate": 8.482245131729668e-05,
+      "loss": 0.0232,
+      "step": 320
+    },
+    {
+      "epoch": 81.32,
+      "grad_norm": 0.043866027146577835,
+      "learning_rate": 8.453608247422681e-05,
+      "loss": 0.0219,
+      "step": 325
+    },
+    {
+      "epoch": 82.64,
+      "grad_norm": 0.042383234947919846,
+      "learning_rate": 8.424971363115693e-05,
+      "loss": 0.0232,
+      "step": 330
+    },
+    {
+      "epoch": 83.96,
+      "grad_norm": 0.058206457644701004,
+      "learning_rate": 8.396334478808706e-05,
+      "loss": 0.0222,
+      "step": 335
+    },
+    {
+      "epoch": 85.0,
+      "grad_norm": 0.13048116862773895,
+      "learning_rate": 8.367697594501719e-05,
+      "loss": 0.0235,
+      "step": 340
+    },
+    {
+      "epoch": 86.32,
+      "grad_norm": 0.03514638915657997,
+      "learning_rate": 8.339060710194731e-05,
+      "loss": 0.0231,
+      "step": 345
+    },
+    {
+      "epoch": 87.64,
+      "grad_norm": 0.04375334829092026,
+      "learning_rate": 8.310423825887744e-05,
+      "loss": 0.0231,
+      "step": 350
+    },
+    {
+      "epoch": 88.96,
+      "grad_norm": 0.04651033505797386,
+      "learning_rate": 8.281786941580757e-05,
+      "loss": 0.0241,
+      "step": 355
+    },
+    {
+      "epoch": 90.0,
+      "grad_norm": 0.15422558784484863,
+      "learning_rate": 8.253150057273768e-05,
+      "loss": 0.0225,
+      "step": 360
+    },
+    {
+      "epoch": 91.32,
+      "grad_norm": 0.05017378553748131,
+      "learning_rate": 8.224513172966782e-05,
+      "loss": 0.0226,
+      "step": 365
+    },
+    {
+      "epoch": 92.64,
+      "grad_norm": 0.04900256544351578,
+      "learning_rate": 8.195876288659795e-05,
+      "loss": 0.0214,
+      "step": 370
+    },
+    {
+      "epoch": 93.96,
+      "grad_norm": 0.039168599992990494,
+      "learning_rate": 8.167239404352807e-05,
+      "loss": 0.0235,
+      "step": 375
+    },
+    {
+      "epoch": 95.0,
+      "grad_norm": 0.16431346535682678,
+      "learning_rate": 8.13860252004582e-05,
+      "loss": 0.0234,
+      "step": 380
+    },
+    {
+      "epoch": 96.32,
+      "grad_norm": 0.047646068036556244,
+      "learning_rate": 8.109965635738833e-05,
+      "loss": 0.0233,
+      "step": 385
+    },
+    {
+      "epoch": 97.64,
+      "grad_norm": 0.04928329959511757,
+      "learning_rate": 8.081328751431845e-05,
+      "loss": 0.0224,
+      "step": 390
+    },
+    {
+      "epoch": 98.96,
+      "grad_norm": 0.042253389954566956,
+      "learning_rate": 8.052691867124858e-05,
+      "loss": 0.0231,
+      "step": 395
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.13217468559741974,
+      "learning_rate": 8.02405498281787e-05,
+      "loss": 0.0232,
+      "step": 400
+    },
+    {
+      "epoch": 101.32,
+      "grad_norm": 0.03638666123151779,
+      "learning_rate": 7.995418098510883e-05,
+      "loss": 0.0224,
+      "step": 405
+    },
+    {
+      "epoch": 102.64,
+      "grad_norm": 0.04150665923953056,
+      "learning_rate": 7.966781214203894e-05,
+      "loss": 0.0234,
+      "step": 410
+    },
+    {
+      "epoch": 103.96,
+      "grad_norm": 0.035543572157621384,
+      "learning_rate": 7.938144329896907e-05,
+      "loss": 0.0221,
+      "step": 415
+    },
+    {
+      "epoch": 105.0,
+      "grad_norm": 0.12740617990493774,
+      "learning_rate": 7.90950744558992e-05,
+      "loss": 0.0222,
+      "step": 420
+    },
+    {
+      "epoch": 106.32,
+      "grad_norm": 0.040774207562208176,
+      "learning_rate": 7.880870561282932e-05,
+      "loss": 0.0224,
+      "step": 425
+    },
+    {
+      "epoch": 107.64,
+      "grad_norm": 0.040325164794921875,
+      "learning_rate": 7.852233676975945e-05,
+      "loss": 0.0235,
+      "step": 430
+    },
+    {
+      "epoch": 108.96,
+      "grad_norm": 0.04361337795853615,
+      "learning_rate": 7.823596792668958e-05,
+      "loss": 0.0236,
+      "step": 435
+    },
+    {
+      "epoch": 110.0,
+      "grad_norm": 0.11627431213855743,
+      "learning_rate": 7.79495990836197e-05,
+      "loss": 0.0238,
+      "step": 440
+    },
+    {
+      "epoch": 111.32,
+      "grad_norm": 0.04112754762172699,
+      "learning_rate": 7.766323024054983e-05,
+      "loss": 0.0232,
+      "step": 445
+    },
+    {
+      "epoch": 112.64,
+      "grad_norm": 0.04499945417046547,
+      "learning_rate": 7.737686139747996e-05,
+      "loss": 0.0241,
+      "step": 450
+    },
+    {
+      "epoch": 113.96,
+      "grad_norm": 0.04413345456123352,
+      "learning_rate": 7.709049255441008e-05,
+      "loss": 0.0237,
+      "step": 455
+    },
+    {
+      "epoch": 115.0,
+      "grad_norm": 0.12778876721858978,
+      "learning_rate": 7.680412371134021e-05,
+      "loss": 0.023,
+      "step": 460
+    },
+    {
+      "epoch": 116.32,
+      "grad_norm": 0.039127930998802185,
+      "learning_rate": 7.651775486827034e-05,
+      "loss": 0.0226,
+      "step": 465
+    },
+    {
+      "epoch": 117.64,
+      "grad_norm": 0.04621637240052223,
+      "learning_rate": 7.623138602520046e-05,
+      "loss": 0.0228,
+      "step": 470
+    },
+    {
+      "epoch": 118.96,
+      "grad_norm": 0.0423317514359951,
+      "learning_rate": 7.594501718213059e-05,
+      "loss": 0.0236,
+      "step": 475
+    },
+    {
+      "epoch": 120.0,
+      "grad_norm": 0.13693822920322418,
+      "learning_rate": 7.565864833906071e-05,
+      "loss": 0.0229,
+      "step": 480
+    },
+    {
+      "epoch": 121.32,
+      "grad_norm": 0.03447780758142471,
+      "learning_rate": 7.537227949599084e-05,
+      "loss": 0.0223,
+      "step": 485
+    },
+    {
+      "epoch": 122.64,
+      "grad_norm": 0.03120778128504753,
+      "learning_rate": 7.508591065292097e-05,
+      "loss": 0.0232,
+      "step": 490
+    },
+    {
+      "epoch": 123.96,
+      "grad_norm": 0.03796784579753876,
+      "learning_rate": 7.47995418098511e-05,
+      "loss": 0.0226,
+      "step": 495
+    },
+    {
+      "epoch": 125.0,
+      "grad_norm": 0.11713339388370514,
+      "learning_rate": 7.451317296678122e-05,
+      "loss": 0.0227,
+      "step": 500
+    },
+    {
+      "epoch": 126.32,
+      "grad_norm": 0.03978479281067848,
+      "learning_rate": 7.422680412371135e-05,
+      "loss": 0.0225,
+      "step": 505
+    },
+    {
+      "epoch": 127.64,
+      "grad_norm": 0.03598278388381004,
+      "learning_rate": 7.394043528064147e-05,
+      "loss": 0.022,
+      "step": 510
+    },
+    {
+      "epoch": 128.96,
+      "grad_norm": 0.039090823382139206,
+      "learning_rate": 7.36540664375716e-05,
+      "loss": 0.0233,
+      "step": 515
+    },
+    {
+      "epoch": 130.0,
+      "grad_norm": 0.15534059703350067,
+      "learning_rate": 7.336769759450171e-05,
+      "loss": 0.0226,
+      "step": 520
+    },
+    {
+      "epoch": 131.32,
+      "grad_norm": 0.029727406799793243,
+      "learning_rate": 7.308132875143184e-05,
+      "loss": 0.0219,
+      "step": 525
+    },
+    {
+      "epoch": 132.64,
+      "grad_norm": 0.04031675308942795,
+      "learning_rate": 7.279495990836197e-05,
+      "loss": 0.0238,
+      "step": 530
+    },
+    {
+      "epoch": 133.96,
+      "grad_norm": 0.03739027678966522,
+      "learning_rate": 7.250859106529209e-05,
+      "loss": 0.0226,
+      "step": 535
+    },
+    {
+      "epoch": 135.0,
+      "grad_norm": 0.11986713111400604,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.0236,
+      "step": 540
+    },
+    {
+      "epoch": 136.32,
+      "grad_norm": 0.03799319267272949,
+      "learning_rate": 7.193585337915235e-05,
+      "loss": 0.0239,
+      "step": 545
+    },
+    {
+      "epoch": 137.64,
+      "grad_norm": 0.033889301121234894,
+      "learning_rate": 7.164948453608247e-05,
+      "loss": 0.0212,
+      "step": 550
+    },
+    {
+      "epoch": 138.96,
+      "grad_norm": 0.03568562492728233,
+      "learning_rate": 7.136311569301261e-05,
+      "loss": 0.0232,
+      "step": 555
+    },
+    {
+      "epoch": 140.0,
+      "grad_norm": 0.09219885617494583,
+      "learning_rate": 7.107674684994274e-05,
+      "loss": 0.0209,
+      "step": 560
+    },
+    {
+      "epoch": 141.32,
+      "grad_norm": 0.030130775645375252,
+      "learning_rate": 7.079037800687286e-05,
+      "loss": 0.0218,
+      "step": 565
+    },
+    {
+      "epoch": 142.64,
+      "grad_norm": 0.04322782903909683,
+      "learning_rate": 7.050400916380299e-05,
+      "loss": 0.024,
+      "step": 570
+    },
+    {
+      "epoch": 143.96,
+      "grad_norm": 0.04596129059791565,
+      "learning_rate": 7.02176403207331e-05,
+      "loss": 0.0223,
+      "step": 575
+    },
+    {
+      "epoch": 145.0,
+      "grad_norm": 0.13223205506801605,
+      "learning_rate": 6.993127147766323e-05,
+      "loss": 0.0228,
+      "step": 580
+    },
+    {
+      "epoch": 146.32,
+      "grad_norm": 0.033803775906562805,
+      "learning_rate": 6.964490263459336e-05,
+      "loss": 0.0221,
+      "step": 585
+    },
+    {
+      "epoch": 147.64,
+      "grad_norm": 0.03498265892267227,
+      "learning_rate": 6.935853379152348e-05,
+      "loss": 0.0223,
+      "step": 590
+    },
+    {
+      "epoch": 148.96,
+      "grad_norm": 0.03388480842113495,
+      "learning_rate": 6.907216494845361e-05,
+      "loss": 0.0228,
+      "step": 595
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 0.07770175486803055,
+      "learning_rate": 6.878579610538374e-05,
+      "loss": 0.0226,
+      "step": 600
+    },
+    {
+      "epoch": 151.32,
+      "grad_norm": 0.035058703273534775,
+      "learning_rate": 6.849942726231386e-05,
+      "loss": 0.0222,
+      "step": 605
+    },
+    {
+      "epoch": 152.64,
+      "grad_norm": 0.03751351311802864,
+      "learning_rate": 6.821305841924399e-05,
+      "loss": 0.0226,
+      "step": 610
+    },
+    {
+      "epoch": 153.96,
+      "grad_norm": 0.03246760368347168,
+      "learning_rate": 6.792668957617412e-05,
+      "loss": 0.0214,
+      "step": 615
+    },
+    {
+      "epoch": 155.0,
+      "grad_norm": 0.13589045405387878,
+      "learning_rate": 6.764032073310424e-05,
+      "loss": 0.0237,
+      "step": 620
+    },
+    {
+      "epoch": 156.32,
+      "grad_norm": 0.031439099460840225,
+      "learning_rate": 6.735395189003437e-05,
+      "loss": 0.0217,
+      "step": 625
+    },
+    {
+      "epoch": 157.64,
+      "grad_norm": 0.03206655755639076,
+      "learning_rate": 6.706758304696448e-05,
+      "loss": 0.0232,
+      "step": 630
+    },
+    {
+      "epoch": 158.96,
+      "grad_norm": 0.037526197731494904,
+      "learning_rate": 6.678121420389462e-05,
+      "loss": 0.0218,
+      "step": 635
+    },
+    {
+      "epoch": 160.0,
+      "grad_norm": 0.09874481707811356,
+      "learning_rate": 6.649484536082475e-05,
+      "loss": 0.0228,
+      "step": 640
+    },
+    {
+      "epoch": 161.32,
+      "grad_norm": 0.03909553959965706,
+      "learning_rate": 6.620847651775487e-05,
+      "loss": 0.0225,
+      "step": 645
+    },
+    {
+      "epoch": 162.64,
+      "grad_norm": 0.034332025796175,
+      "learning_rate": 6.5922107674685e-05,
+      "loss": 0.0222,
+      "step": 650
+    },
+    {
+      "epoch": 163.96,
+      "grad_norm": 0.033894602209329605,
+      "learning_rate": 6.563573883161513e-05,
+      "loss": 0.0219,
+      "step": 655
+    },
+    {
+      "epoch": 165.0,
+      "grad_norm": 0.09040471911430359,
+      "learning_rate": 6.534936998854525e-05,
+      "loss": 0.0219,
+      "step": 660
+    },
+    {
+      "epoch": 166.32,
+      "grad_norm": 0.03086320124566555,
+      "learning_rate": 6.506300114547538e-05,
+      "loss": 0.0241,
+      "step": 665
+    },
+    {
+      "epoch": 167.64,
+      "grad_norm": 0.030052335932850838,
+      "learning_rate": 6.477663230240551e-05,
+      "loss": 0.0223,
+      "step": 670
+    },
+    {
+      "epoch": 168.96,
+      "grad_norm": 0.028752340003848076,
+      "learning_rate": 6.449026345933563e-05,
+      "loss": 0.0226,
+      "step": 675
+    },
+    {
+      "epoch": 170.0,
+      "grad_norm": 0.09044802188873291,
+      "learning_rate": 6.420389461626576e-05,
+      "loss": 0.0245,
+      "step": 680
+    },
+    {
+      "epoch": 171.32,
+      "grad_norm": 0.031187741085886955,
+      "learning_rate": 6.391752577319587e-05,
+      "loss": 0.0234,
+      "step": 685
+    },
+    {
+      "epoch": 172.64,
+      "grad_norm": 0.032953280955553055,
+      "learning_rate": 6.3631156930126e-05,
+      "loss": 0.0231,
+      "step": 690
+    },
+    {
+      "epoch": 173.96,
+      "grad_norm": 0.035380713641643524,
+      "learning_rate": 6.334478808705613e-05,
+      "loss": 0.0231,
+      "step": 695
+    },
+    {
+      "epoch": 175.0,
+      "grad_norm": 0.10263343155384064,
+      "learning_rate": 6.305841924398625e-05,
+      "loss": 0.0226,
+      "step": 700
+    },
+    {
+      "epoch": 176.32,
+      "grad_norm": 0.03277510777115822,
+      "learning_rate": 6.277205040091638e-05,
+      "loss": 0.0222,
+      "step": 705
+    },
+    {
+      "epoch": 177.64,
+      "grad_norm": 0.034485459327697754,
+      "learning_rate": 6.24856815578465e-05,
+      "loss": 0.0227,
+      "step": 710
+    },
+    {
+      "epoch": 178.96,
+      "grad_norm": 0.03501957654953003,
+      "learning_rate": 6.219931271477663e-05,
+      "loss": 0.0223,
+      "step": 715
+    },
+    {
+      "epoch": 180.0,
+      "grad_norm": 0.11059446632862091,
+      "learning_rate": 6.191294387170676e-05,
+      "loss": 0.0219,
+      "step": 720
+    },
+    {
+      "epoch": 181.32,
+      "grad_norm": 0.03453643247485161,
+      "learning_rate": 6.162657502863689e-05,
+      "loss": 0.0223,
+      "step": 725
+    },
+    {
+      "epoch": 182.64,
+      "grad_norm": 0.031747136265039444,
+      "learning_rate": 6.134020618556701e-05,
+      "loss": 0.0211,
+      "step": 730
+    },
+    {
+      "epoch": 183.96,
+      "grad_norm": 0.03772411495447159,
+      "learning_rate": 6.105383734249714e-05,
+      "loss": 0.0213,
+      "step": 735
+    },
+    {
+      "epoch": 185.0,
+      "grad_norm": 0.08717264235019684,
+      "learning_rate": 6.076746849942726e-05,
+      "loss": 0.0232,
+      "step": 740
+    },
+    {
+      "epoch": 186.32,
+      "grad_norm": 0.030604945495724678,
+      "learning_rate": 6.0481099656357384e-05,
+      "loss": 0.023,
+      "step": 745
+    },
+    {
+      "epoch": 187.64,
+      "grad_norm": 0.027379345148801804,
+      "learning_rate": 6.019473081328752e-05,
+      "loss": 0.0217,
+      "step": 750
+    },
+    {
+      "epoch": 188.96,
+      "grad_norm": 0.032438065856695175,
+      "learning_rate": 5.9908361970217644e-05,
+      "loss": 0.0252,
+      "step": 755
+    },
+    {
+      "epoch": 190.0,
+      "grad_norm": 0.08274230360984802,
+      "learning_rate": 5.962199312714777e-05,
+      "loss": 0.0212,
+      "step": 760
+    },
+    {
+      "epoch": 191.32,
+      "grad_norm": 0.02920094132423401,
+      "learning_rate": 5.93356242840779e-05,
+      "loss": 0.0224,
+      "step": 765
+    },
+    {
+      "epoch": 192.64,
+      "grad_norm": 0.03730329871177673,
+      "learning_rate": 5.904925544100802e-05,
+      "loss": 0.0228,
+      "step": 770
+    },
+    {
+      "epoch": 193.96,
+      "grad_norm": 0.040118809789419174,
+      "learning_rate": 5.876288659793815e-05,
+      "loss": 0.0226,
+      "step": 775
+    },
+    {
+      "epoch": 195.0,
+      "grad_norm": 0.08151891827583313,
+      "learning_rate": 5.8476517754868276e-05,
+      "loss": 0.022,
+      "step": 780
+    },
+    {
+      "epoch": 196.32,
+      "grad_norm": 0.0327572226524353,
+      "learning_rate": 5.81901489117984e-05,
+      "loss": 0.0219,
+      "step": 785
+    },
+    {
+      "epoch": 197.64,
+      "grad_norm": 0.027864839881658554,
+      "learning_rate": 5.790378006872853e-05,
+      "loss": 0.0235,
+      "step": 790
+    },
+    {
+      "epoch": 198.96,
+      "grad_norm": 0.033668313175439835,
+      "learning_rate": 5.761741122565865e-05,
+      "loss": 0.0229,
+      "step": 795
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 0.07690460234880447,
+      "learning_rate": 5.7331042382588775e-05,
+      "loss": 0.0225,
+      "step": 800
+    },
+    {
+      "epoch": 201.32,
+      "grad_norm": 0.030898429453372955,
+      "learning_rate": 5.70446735395189e-05,
+      "loss": 0.022,
+      "step": 805
+    },
+    {
+      "epoch": 202.64,
+      "grad_norm": 0.02849520556628704,
+      "learning_rate": 5.675830469644903e-05,
+      "loss": 0.023,
+      "step": 810
+    },
+    {
+      "epoch": 203.96,
+      "grad_norm": 0.031954504549503326,
+      "learning_rate": 5.6471935853379155e-05,
+      "loss": 0.0225,
+      "step": 815
+    },
+    {
+      "epoch": 205.0,
+      "grad_norm": 0.09324806183576584,
+      "learning_rate": 5.618556701030928e-05,
+      "loss": 0.0233,
+      "step": 820
+    },
+    {
+      "epoch": 206.32,
+      "grad_norm": 0.0302401315420866,
+      "learning_rate": 5.589919816723941e-05,
+      "loss": 0.0215,
+      "step": 825
+    },
+    {
+      "epoch": 207.64,
+      "grad_norm": 0.029426347464323044,
+      "learning_rate": 5.5612829324169534e-05,
+      "loss": 0.0215,
+      "step": 830
+    },
+    {
+      "epoch": 208.96,
+      "grad_norm": 0.031664323061704636,
+      "learning_rate": 5.532646048109966e-05,
+      "loss": 0.0218,
+      "step": 835
+    },
+    {
+      "epoch": 210.0,
+      "grad_norm": 0.09568897634744644,
+      "learning_rate": 5.504009163802979e-05,
+      "loss": 0.0208,
+      "step": 840
+    },
+    {
+      "epoch": 211.32,
+      "grad_norm": 0.029477190226316452,
+      "learning_rate": 5.4753722794959914e-05,
+      "loss": 0.0214,
+      "step": 845
+    },
+    {
+      "epoch": 212.64,
+      "grad_norm": 0.030615277588367462,
+      "learning_rate": 5.4467353951890033e-05,
+      "loss": 0.0227,
+      "step": 850
+    },
+    {
+      "epoch": 213.96,
+      "grad_norm": 0.03466692939400673,
+      "learning_rate": 5.418098510882016e-05,
+      "loss": 0.0212,
+      "step": 855
+    },
+    {
+      "epoch": 215.0,
+      "grad_norm": 0.1077422946691513,
+      "learning_rate": 5.3894616265750286e-05,
+      "loss": 0.022,
+      "step": 860
+    },
+    {
+      "epoch": 216.32,
+      "grad_norm": 0.030155370011925697,
+      "learning_rate": 5.360824742268041e-05,
+      "loss": 0.0227,
+      "step": 865
+    },
+    {
+      "epoch": 217.64,
+      "grad_norm": 0.02762630768120289,
+      "learning_rate": 5.332187857961054e-05,
+      "loss": 0.0219,
+      "step": 870
+    },
+    {
+      "epoch": 218.96,
+      "grad_norm": 0.027750438079237938,
+      "learning_rate": 5.3035509736540666e-05,
+      "loss": 0.0225,
+      "step": 875
+    },
+    {
+      "epoch": 220.0,
+      "grad_norm": 0.1480046659708023,
+      "learning_rate": 5.274914089347079e-05,
+      "loss": 0.024,
+      "step": 880
+    },
+    {
+      "epoch": 221.32,
+      "grad_norm": 0.027756843715906143,
+      "learning_rate": 5.246277205040092e-05,
+      "loss": 0.0232,
+      "step": 885
+    },
+    {
+      "epoch": 222.64,
+      "grad_norm": 0.025351909920573235,
+      "learning_rate": 5.2176403207331045e-05,
+      "loss": 0.0224,
+      "step": 890
+    },
+    {
+      "epoch": 223.96,
+      "grad_norm": 0.03722308948636055,
+      "learning_rate": 5.189003436426118e-05,
+      "loss": 0.0224,
+      "step": 895
+    },
+    {
+      "epoch": 225.0,
+      "grad_norm": 0.09891820698976517,
+      "learning_rate": 5.1603665521191305e-05,
+      "loss": 0.0223,
+      "step": 900
+    },
+    {
+      "epoch": 226.32,
+      "grad_norm": 0.031157376244664192,
+      "learning_rate": 5.131729667812142e-05,
+      "loss": 0.0228,
+      "step": 905
+    },
+    {
+      "epoch": 227.64,
+      "grad_norm": 0.026530060917139053,
+      "learning_rate": 5.1030927835051544e-05,
+      "loss": 0.0227,
+      "step": 910
+    },
+    {
+      "epoch": 228.96,
+      "grad_norm": 0.028711870312690735,
+      "learning_rate": 5.074455899198167e-05,
+      "loss": 0.0229,
+      "step": 915
+    },
+    {
+      "epoch": 230.0,
+      "grad_norm": 0.10996802896261215,
+      "learning_rate": 5.04581901489118e-05,
+      "loss": 0.0236,
+      "step": 920
+    },
+    {
+      "epoch": 231.32,
+      "grad_norm": 0.026562057435512543,
+      "learning_rate": 5.0171821305841924e-05,
+      "loss": 0.0221,
+      "step": 925
+    },
+    {
+      "epoch": 232.64,
+      "grad_norm": 0.029791025444865227,
+      "learning_rate": 4.988545246277205e-05,
+      "loss": 0.0237,
+      "step": 930
+    },
+    {
+      "epoch": 233.96,
+      "grad_norm": 0.030204325914382935,
+      "learning_rate": 4.9599083619702184e-05,
+      "loss": 0.0222,
+      "step": 935
+    },
+    {
+      "epoch": 235.0,
+      "grad_norm": 0.06489063054323196,
+      "learning_rate": 4.931271477663231e-05,
+      "loss": 0.0212,
+      "step": 940
+    },
+    {
+      "epoch": 236.32,
+      "grad_norm": 0.033282287418842316,
+      "learning_rate": 4.902634593356243e-05,
+      "loss": 0.0224,
+      "step": 945
+    },
+    {
+      "epoch": 237.64,
+      "grad_norm": 0.030851591378450394,
+      "learning_rate": 4.8739977090492556e-05,
+      "loss": 0.0216,
+      "step": 950
+    },
+    {
+      "epoch": 238.96,
+      "grad_norm": 0.029777253046631813,
+      "learning_rate": 4.845360824742268e-05,
+      "loss": 0.0222,
+      "step": 955
+    },
+    {
+      "epoch": 240.0,
+      "grad_norm": 0.06517614424228668,
+      "learning_rate": 4.816723940435281e-05,
+      "loss": 0.0197,
+      "step": 960
+    },
+    {
+      "epoch": 241.32,
+      "grad_norm": 0.027710000053048134,
+      "learning_rate": 4.7880870561282936e-05,
+      "loss": 0.0231,
+      "step": 965
+    },
+    {
+      "epoch": 242.64,
+      "grad_norm": 0.027534285560250282,
+      "learning_rate": 4.7594501718213055e-05,
+      "loss": 0.0229,
+      "step": 970
+    },
+    {
+      "epoch": 243.96,
+      "grad_norm": 0.029630396515130997,
+      "learning_rate": 4.730813287514318e-05,
+      "loss": 0.0219,
+      "step": 975
+    },
+    {
+      "epoch": 245.0,
+      "grad_norm": 0.09967376291751862,
+      "learning_rate": 4.7021764032073315e-05,
+      "loss": 0.0211,
+      "step": 980
+    },
+    {
+      "epoch": 246.32,
+      "grad_norm": 0.026448087766766548,
+      "learning_rate": 4.673539518900344e-05,
+      "loss": 0.0219,
+      "step": 985
+    },
+    {
+      "epoch": 247.64,
+      "grad_norm": 0.030766399577260017,
+      "learning_rate": 4.644902634593357e-05,
+      "loss": 0.0218,
+      "step": 990
+    },
+    {
+      "epoch": 248.96,
+      "grad_norm": 0.03127891570329666,
+      "learning_rate": 4.6162657502863694e-05,
+      "loss": 0.0222,
+      "step": 995
+    },
+    {
+      "epoch": 250.0,
+      "grad_norm": 0.07358253002166748,
+      "learning_rate": 4.5876288659793814e-05,
+      "loss": 0.022,
+      "step": 1000
+    },
+    {
+      "epoch": 251.32,
+      "grad_norm": 0.030259255319833755,
+      "learning_rate": 4.558991981672394e-05,
+      "loss": 0.0215,
+      "step": 1005
+    },
+    {
+      "epoch": 252.64,
+      "grad_norm": 0.031163489446043968,
+      "learning_rate": 4.530355097365407e-05,
+      "loss": 0.0218,
+      "step": 1010
+    },
+    {
+      "epoch": 253.96,
+      "grad_norm": 0.025623638182878494,
+      "learning_rate": 4.5017182130584194e-05,
+      "loss": 0.0225,
+      "step": 1015
+    },
+    {
+      "epoch": 255.0,
+      "grad_norm": 0.10825876146554947,
+      "learning_rate": 4.473081328751432e-05,
+      "loss": 0.0228,
+      "step": 1020
+    },
+    {
+      "epoch": 256.32,
+      "grad_norm": 0.029599890112876892,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.0218,
+      "step": 1025
+    },
+    {
+      "epoch": 257.64,
+      "grad_norm": 0.027761822566390038,
+      "learning_rate": 4.415807560137457e-05,
+      "loss": 0.0226,
+      "step": 1030
+    },
+    {
+      "epoch": 258.96,
+      "grad_norm": 0.03065340407192707,
+      "learning_rate": 4.38717067583047e-05,
+      "loss": 0.0235,
+      "step": 1035
+    },
+    {
+      "epoch": 260.0,
+      "grad_norm": 0.08595085889101028,
+      "learning_rate": 4.3585337915234826e-05,
+      "loss": 0.0225,
+      "step": 1040
+    },
+    {
+      "epoch": 261.32,
+      "grad_norm": 0.031066762283444405,
+      "learning_rate": 4.329896907216495e-05,
+      "loss": 0.0236,
+      "step": 1045
+    },
+    {
+      "epoch": 262.64,
+      "grad_norm": 0.028579367324709892,
+      "learning_rate": 4.301260022909508e-05,
+      "loss": 0.0214,
+      "step": 1050
+    },
+    {
+      "epoch": 263.96,
+      "grad_norm": 0.028484277427196503,
+      "learning_rate": 4.27262313860252e-05,
+      "loss": 0.0223,
+      "step": 1055
+    },
+    {
+      "epoch": 265.0,
+      "grad_norm": 0.08596421033143997,
+      "learning_rate": 4.2439862542955325e-05,
+      "loss": 0.0215,
+      "step": 1060
+    },
+    {
+      "epoch": 266.32,
+      "grad_norm": 0.02508409693837166,
+      "learning_rate": 4.215349369988545e-05,
+      "loss": 0.0214,
+      "step": 1065
+    },
+    {
+      "epoch": 267.64,
+      "grad_norm": 0.02804061770439148,
+      "learning_rate": 4.1867124856815585e-05,
+      "loss": 0.0236,
+      "step": 1070
+    },
+    {
+      "epoch": 268.96,
+      "grad_norm": 0.030820870772004128,
+      "learning_rate": 4.158075601374571e-05,
+      "loss": 0.0222,
+      "step": 1075
+    },
+    {
+      "epoch": 270.0,
+      "grad_norm": 0.09306512773036957,
+      "learning_rate": 4.129438717067583e-05,
+      "loss": 0.0211,
+      "step": 1080
+    },
+    {
+      "epoch": 271.32,
+      "grad_norm": 0.030462536960840225,
+      "learning_rate": 4.100801832760596e-05,
+      "loss": 0.0222,
+      "step": 1085
+    },
+    {
+      "epoch": 272.64,
+      "grad_norm": 0.029752682894468307,
+      "learning_rate": 4.0721649484536084e-05,
+      "loss": 0.0219,
+      "step": 1090
+    },
+    {
+      "epoch": 273.96,
+      "grad_norm": 0.02907637320458889,
+      "learning_rate": 4.043528064146621e-05,
+      "loss": 0.0224,
+      "step": 1095
+    },
+    {
+      "epoch": 275.0,
+      "grad_norm": 0.11900507658720016,
+      "learning_rate": 4.014891179839634e-05,
+      "loss": 0.0224,
+      "step": 1100
+    },
+    {
+      "epoch": 276.32,
+      "grad_norm": 0.029513241723179817,
+      "learning_rate": 3.9862542955326463e-05,
+      "loss": 0.0223,
+      "step": 1105
+    },
+    {
+      "epoch": 277.64,
+      "grad_norm": 0.02655150555074215,
+      "learning_rate": 3.957617411225659e-05,
+      "loss": 0.0215,
+      "step": 1110
+    },
+    {
+      "epoch": 278.96,
+      "grad_norm": 0.031090132892131805,
+      "learning_rate": 3.9289805269186716e-05,
+      "loss": 0.0229,
+      "step": 1115
+    },
+    {
+      "epoch": 280.0,
+      "grad_norm": 0.10574332624673843,
+      "learning_rate": 3.900343642611684e-05,
+      "loss": 0.0226,
+      "step": 1120
+    },
+    {
+      "epoch": 281.32,
+      "grad_norm": 0.025768013671040535,
+      "learning_rate": 3.871706758304697e-05,
+      "loss": 0.022,
+      "step": 1125
+    },
+    {
+      "epoch": 282.64,
+      "grad_norm": 0.02915865182876587,
+      "learning_rate": 3.8430698739977096e-05,
+      "loss": 0.0226,
+      "step": 1130
+    },
+    {
+      "epoch": 283.96,
+      "grad_norm": 0.028867091983556747,
+      "learning_rate": 3.8144329896907216e-05,
+      "loss": 0.0223,
+      "step": 1135
+    },
+    {
+      "epoch": 285.0,
+      "grad_norm": 0.06698961555957794,
+      "learning_rate": 3.785796105383734e-05,
+      "loss": 0.0209,
+      "step": 1140
+    },
+    {
+      "epoch": 286.32,
+      "grad_norm": 0.029880354180932045,
+      "learning_rate": 3.757159221076747e-05,
+      "loss": 0.0226,
+      "step": 1145
+    },
+    {
+      "epoch": 287.64,
+      "grad_norm": 0.027591262012720108,
+      "learning_rate": 3.7285223367697595e-05,
+      "loss": 0.0213,
+      "step": 1150
+    },
+    {
+      "epoch": 288.96,
+      "grad_norm": 0.029396766796708107,
+      "learning_rate": 3.699885452462772e-05,
+      "loss": 0.023,
+      "step": 1155
+    },
+    {
+      "epoch": 290.0,
+      "grad_norm": 0.10461018979549408,
+      "learning_rate": 3.671248568155785e-05,
+      "loss": 0.0218,
+      "step": 1160
+    },
+    {
+      "epoch": 291.32,
+      "grad_norm": 0.029114672914147377,
+      "learning_rate": 3.6426116838487974e-05,
+      "loss": 0.0222,
+      "step": 1165
+    },
+    {
+      "epoch": 292.64,
+      "grad_norm": 0.027854561805725098,
+      "learning_rate": 3.61397479954181e-05,
+      "loss": 0.0229,
+      "step": 1170
+    },
+    {
+      "epoch": 293.96,
+      "grad_norm": 0.0312589667737484,
+      "learning_rate": 3.585337915234823e-05,
+      "loss": 0.0222,
+      "step": 1175
+    },
+    {
+      "epoch": 295.0,
+      "grad_norm": 0.10697894543409348,
+      "learning_rate": 3.5567010309278354e-05,
+      "loss": 0.0209,
+      "step": 1180
+    },
+    {
+      "epoch": 296.32,
+      "grad_norm": 0.029923448339104652,
+      "learning_rate": 3.528064146620848e-05,
+      "loss": 0.0224,
+      "step": 1185
+    },
+    {
+      "epoch": 297.64,
+      "grad_norm": 0.02807888388633728,
+      "learning_rate": 3.49942726231386e-05,
+      "loss": 0.0225,
+      "step": 1190
+    },
+    {
+      "epoch": 298.96,
+      "grad_norm": 0.028458457440137863,
+      "learning_rate": 3.4707903780068726e-05,
+      "loss": 0.023,
+      "step": 1195
+    },
+    {
+      "epoch": 300.0,
+      "grad_norm": 0.09004534780979156,
+      "learning_rate": 3.442153493699885e-05,
+      "loss": 0.0216,
+      "step": 1200
+    },
+    {
+      "epoch": 301.32,
+      "grad_norm": 0.02781865932047367,
+      "learning_rate": 3.4135166093928986e-05,
+      "loss": 0.0221,
+      "step": 1205
+    },
+    {
+      "epoch": 302.64,
+      "grad_norm": 0.028483230620622635,
+      "learning_rate": 3.384879725085911e-05,
+      "loss": 0.0218,
+      "step": 1210
+    },
+    {
+      "epoch": 303.96,
+      "grad_norm": 0.029581783339381218,
+      "learning_rate": 3.356242840778923e-05,
+      "loss": 0.0227,
+      "step": 1215
+    },
+    {
+      "epoch": 305.0,
+      "grad_norm": 0.11656039208173752,
+      "learning_rate": 3.327605956471936e-05,
+      "loss": 0.0234,
+      "step": 1220
+    },
+    {
+      "epoch": 306.32,
+      "grad_norm": 0.026737062260508537,
+      "learning_rate": 3.2989690721649485e-05,
+      "loss": 0.0221,
+      "step": 1225
+    },
+    {
+      "epoch": 307.64,
+      "grad_norm": 0.030143236741423607,
+      "learning_rate": 3.270332187857961e-05,
+      "loss": 0.0223,
+      "step": 1230
+    },
+    {
+      "epoch": 308.96,
+      "grad_norm": 0.027385924011468887,
+      "learning_rate": 3.241695303550974e-05,
+      "loss": 0.0224,
+      "step": 1235
+    },
+    {
+      "epoch": 310.0,
+      "grad_norm": 0.09042290598154068,
+      "learning_rate": 3.2130584192439865e-05,
+      "loss": 0.0223,
+      "step": 1240
+    },
+    {
+      "epoch": 311.32,
+      "grad_norm": 0.02867588959634304,
+      "learning_rate": 3.184421534936999e-05,
+      "loss": 0.0224,
+      "step": 1245
+    },
+    {
+      "epoch": 312.64,
+      "grad_norm": 0.026082267984747887,
+      "learning_rate": 3.155784650630012e-05,
+      "loss": 0.0222,
+      "step": 1250
+    },
+    {
+      "epoch": 313.96,
+      "grad_norm": 0.030696265399456024,
+      "learning_rate": 3.1271477663230244e-05,
+      "loss": 0.0218,
+      "step": 1255
+    },
+    {
+      "epoch": 315.0,
+      "grad_norm": 0.06664582341909409,
+      "learning_rate": 3.098510882016037e-05,
+      "loss": 0.0205,
+      "step": 1260
+    },
+    {
+      "epoch": 316.32,
+      "grad_norm": 0.02528396248817444,
+      "learning_rate": 3.06987399770905e-05,
+      "loss": 0.0212,
+      "step": 1265
+    },
+    {
+      "epoch": 317.64,
+      "grad_norm": 0.028939127922058105,
+      "learning_rate": 3.0412371134020617e-05,
+      "loss": 0.0225,
+      "step": 1270
+    },
+    {
+      "epoch": 318.96,
+      "grad_norm": 0.026384050026535988,
+      "learning_rate": 3.0126002290950743e-05,
+      "loss": 0.0223,
+      "step": 1275
+    },
+    {
+      "epoch": 320.0,
+      "grad_norm": 0.08773248642683029,
+      "learning_rate": 2.983963344788087e-05,
+      "loss": 0.022,
+      "step": 1280
+    },
+    {
+      "epoch": 321.32,
+      "grad_norm": 0.029451629146933556,
+      "learning_rate": 2.9553264604811e-05,
+      "loss": 0.0213,
+      "step": 1285
+    },
+    {
+      "epoch": 322.64,
+      "grad_norm": 0.029388943687081337,
+      "learning_rate": 2.9266895761741126e-05,
+      "loss": 0.0226,
+      "step": 1290
+    },
+    {
+      "epoch": 323.96,
+      "grad_norm": 0.02841971069574356,
+      "learning_rate": 2.8980526918671253e-05,
+      "loss": 0.021,
+      "step": 1295
+    },
+    {
+      "epoch": 325.0,
+      "grad_norm": 0.08616754412651062,
+      "learning_rate": 2.8694158075601372e-05,
+      "loss": 0.0218,
+      "step": 1300
+    },
+    {
+      "epoch": 326.32,
+      "grad_norm": 0.03196750581264496,
+      "learning_rate": 2.8407789232531502e-05,
+      "loss": 0.0226,
+      "step": 1305
+    },
+    {
+      "epoch": 327.64,
+      "grad_norm": 0.02681926265358925,
+      "learning_rate": 2.812142038946163e-05,
+      "loss": 0.0207,
+      "step": 1310
+    },
+    {
+      "epoch": 328.96,
+      "grad_norm": 0.029461359605193138,
+      "learning_rate": 2.7835051546391755e-05,
+      "loss": 0.0216,
+      "step": 1315
+    },
+    {
+      "epoch": 330.0,
+      "grad_norm": 0.10138925909996033,
+      "learning_rate": 2.754868270332188e-05,
+      "loss": 0.022,
+      "step": 1320
+    },
+    {
+      "epoch": 331.32,
+      "grad_norm": 0.02837948128581047,
+      "learning_rate": 2.7262313860252005e-05,
+      "loss": 0.0223,
+      "step": 1325
+    },
+    {
+      "epoch": 332.64,
+      "grad_norm": 0.02668078988790512,
+      "learning_rate": 2.697594501718213e-05,
+      "loss": 0.0226,
+      "step": 1330
+    },
+    {
+      "epoch": 333.96,
+      "grad_norm": 0.028131477534770966,
+      "learning_rate": 2.6689576174112258e-05,
+      "loss": 0.0223,
+      "step": 1335
+    },
+    {
+      "epoch": 335.0,
+      "grad_norm": 0.08429412543773651,
+      "learning_rate": 2.6403207331042384e-05,
+      "loss": 0.0228,
+      "step": 1340
+    },
+    {
+      "epoch": 336.32,
+      "grad_norm": 0.026646487414836884,
+      "learning_rate": 2.611683848797251e-05,
+      "loss": 0.0223,
+      "step": 1345
+    },
+    {
+      "epoch": 337.64,
+      "grad_norm": 0.027175936847925186,
+      "learning_rate": 2.5830469644902637e-05,
+      "loss": 0.0227,
+      "step": 1350
+    },
+    {
+      "epoch": 338.96,
+      "grad_norm": 0.030607223510742188,
+      "learning_rate": 2.554410080183276e-05,
+      "loss": 0.0236,
+      "step": 1355
+    },
+    {
+      "epoch": 340.0,
+      "grad_norm": 0.07383383065462112,
+      "learning_rate": 2.5257731958762887e-05,
+      "loss": 0.022,
+      "step": 1360
+    },
+    {
+      "epoch": 341.32,
+      "grad_norm": 0.028488941490650177,
+      "learning_rate": 2.4971363115693013e-05,
+      "loss": 0.0221,
+      "step": 1365
+    },
+    {
+      "epoch": 342.64,
+      "grad_norm": 0.033083755522966385,
+      "learning_rate": 2.468499427262314e-05,
+      "loss": 0.0215,
+      "step": 1370
+    },
+    {
+      "epoch": 343.96,
+      "grad_norm": 0.029608990997076035,
+      "learning_rate": 2.4398625429553266e-05,
+      "loss": 0.0217,
+      "step": 1375
+    },
+    {
+      "epoch": 345.0,
+      "grad_norm": 0.10344070196151733,
+      "learning_rate": 2.4112256586483393e-05,
+      "loss": 0.0236,
+      "step": 1380
+    },
+    {
+      "epoch": 346.32,
+      "grad_norm": 0.033095359802246094,
+      "learning_rate": 2.3825887743413516e-05,
+      "loss": 0.0234,
+      "step": 1385
+    },
+    {
+      "epoch": 347.64,
+      "grad_norm": 0.029788870364427567,
+      "learning_rate": 2.3539518900343642e-05,
+      "loss": 0.0224,
+      "step": 1390
+    },
+    {
+      "epoch": 348.96,
+      "grad_norm": 0.030327215790748596,
+      "learning_rate": 2.3253150057273772e-05,
+      "loss": 0.022,
+      "step": 1395
+    },
+    {
+      "epoch": 350.0,
+      "grad_norm": 0.11181904375553131,
+      "learning_rate": 2.2966781214203895e-05,
+      "loss": 0.0226,
+      "step": 1400
+    },
+    {
+      "epoch": 351.32,
+      "grad_norm": 0.03141086548566818,
+      "learning_rate": 2.268041237113402e-05,
+      "loss": 0.0233,
+      "step": 1405
+    },
+    {
+      "epoch": 352.64,
+      "grad_norm": 0.02836909517645836,
+      "learning_rate": 2.2394043528064148e-05,
+      "loss": 0.0235,
+      "step": 1410
+    },
+    {
+      "epoch": 353.96,
+      "grad_norm": 0.026505406945943832,
+      "learning_rate": 2.210767468499427e-05,
+      "loss": 0.0221,
+      "step": 1415
+    },
+    {
+      "epoch": 355.0,
+      "grad_norm": 0.05104130879044533,
+      "learning_rate": 2.18213058419244e-05,
+      "loss": 0.0207,
+      "step": 1420
+    },
+    {
+      "epoch": 356.32,
+      "grad_norm": 0.027829525992274284,
+      "learning_rate": 2.1534936998854528e-05,
+      "loss": 0.0219,
+      "step": 1425
+    },
+    {
+      "epoch": 357.64,
+      "grad_norm": 0.03288746252655983,
+      "learning_rate": 2.124856815578465e-05,
+      "loss": 0.0223,
+      "step": 1430
+    },
+    {
+      "epoch": 358.96,
+      "grad_norm": 0.027919428423047066,
+      "learning_rate": 2.0962199312714777e-05,
+      "loss": 0.0204,
+      "step": 1435
+    },
+    {
+      "epoch": 360.0,
+      "grad_norm": 0.07339093089103699,
+      "learning_rate": 2.0675830469644904e-05,
+      "loss": 0.0212,
+      "step": 1440
+    },
+    {
+      "epoch": 361.32,
+      "grad_norm": 0.02630612812936306,
+      "learning_rate": 2.038946162657503e-05,
+      "loss": 0.0222,
+      "step": 1445
+    },
+    {
+      "epoch": 362.64,
+      "grad_norm": 0.026910657063126564,
+      "learning_rate": 2.0103092783505157e-05,
+      "loss": 0.023,
+      "step": 1450
+    },
+    {
+      "epoch": 363.96,
+      "grad_norm": 0.02552923373878002,
+      "learning_rate": 1.981672394043528e-05,
+      "loss": 0.0202,
+      "step": 1455
+    },
+    {
+      "epoch": 365.0,
+      "grad_norm": 0.08786323666572571,
+      "learning_rate": 1.9530355097365406e-05,
+      "loss": 0.0218,
+      "step": 1460
+    },
+    {
+      "epoch": 366.32,
+      "grad_norm": 0.023231837898492813,
+      "learning_rate": 1.9243986254295536e-05,
+      "loss": 0.022,
+      "step": 1465
+    },
+    {
+      "epoch": 367.64,
+      "grad_norm": 0.024473244324326515,
+      "learning_rate": 1.895761741122566e-05,
+      "loss": 0.0234,
+      "step": 1470
+    },
+    {
+      "epoch": 368.96,
+      "grad_norm": 0.027507726103067398,
+      "learning_rate": 1.8671248568155786e-05,
+      "loss": 0.0229,
+      "step": 1475
+    },
+    {
+      "epoch": 370.0,
+      "grad_norm": 0.08709301054477692,
+      "learning_rate": 1.8384879725085912e-05,
+      "loss": 0.022,
+      "step": 1480
+    },
+    {
+      "epoch": 371.32,
+      "grad_norm": 0.02902478352189064,
+      "learning_rate": 1.809851088201604e-05,
+      "loss": 0.0225,
+      "step": 1485
+    },
+    {
+      "epoch": 372.64,
+      "grad_norm": 0.026616817340254784,
+      "learning_rate": 1.7812142038946165e-05,
+      "loss": 0.0222,
+      "step": 1490
+    },
+    {
+      "epoch": 373.96,
+      "grad_norm": 0.02648814581334591,
+      "learning_rate": 1.7525773195876288e-05,
+      "loss": 0.0218,
+      "step": 1495
+    },
+    {
+      "epoch": 375.0,
+      "grad_norm": 0.09145989269018173,
+      "learning_rate": 1.7239404352806415e-05,
+      "loss": 0.0219,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 450,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.275678425088e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

Math_QA/group_08/checkpoints/checkpoint-1800/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/不冻结Qwen训练/models/Qwen2.5-1.5B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

Math_QA/group_08/checkpoints/checkpoint-1800/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/\u4e0d\u51bb\u7ed3Qwen\u8bad\u7ec3/models/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Math_QA/group_08/checkpoints/checkpoint-1800/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

Math_QA/group_08/checkpoints/checkpoint-1800/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

Math_QA/group_08/checkpoints/checkpoint-1800/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Math_QA/group_08/checkpoints/checkpoint-1800/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

Math_QA/group_08/checkpoints/checkpoint-1800/trainer_state.json

@@ -0,0 +1,2561 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 450.0,
+  "eval_steps": 500,
+  "global_step": 1800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "grad_norm": 10.268527030944824,
+      "learning_rate": 0.0,
+      "loss": 1.8412,
+      "step": 1
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 7.169743537902832,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.7908,
+      "step": 5
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 3.2965712547302246,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.541,
+      "step": 10
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 1.9259239435195923,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 1.195,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.5386537313461304,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.8407,
+      "step": 20
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.7439631223678589,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.7134,
+      "step": 25
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.5669045448303223,
+      "learning_rate": 5.370370370370371e-05,
+      "loss": 0.6253,
+      "step": 30
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.5955387353897095,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.5425,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.794498324394226,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.4517,
+      "step": 40
+    },
+    {
+      "epoch": 11.32,
+      "grad_norm": 0.6224164366722107,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.3649,
+      "step": 45
+    },
+    {
+      "epoch": 12.64,
+      "grad_norm": 0.7097190022468567,
+      "learning_rate": 9.074074074074075e-05,
+      "loss": 0.2806,
+      "step": 50
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 0.8385046124458313,
+      "learning_rate": 0.0001,
+      "loss": 0.2055,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 2.7302768230438232,
+      "learning_rate": 9.971363115693013e-05,
+      "loss": 0.1593,
+      "step": 60
+    },
+    {
+      "epoch": 16.32,
+      "grad_norm": 0.573469877243042,
+      "learning_rate": 9.942726231386026e-05,
+      "loss": 0.1173,
+      "step": 65
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 1.059529423713684,
+      "learning_rate": 9.914089347079038e-05,
+      "loss": 0.0856,
+      "step": 70
+    },
+    {
+      "epoch": 18.96,
+      "grad_norm": 0.6318557858467102,
+      "learning_rate": 9.885452462772051e-05,
+      "loss": 0.0783,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.4067771434783936,
+      "learning_rate": 9.856815578465064e-05,
+      "loss": 0.0684,
+      "step": 80
+    },
+    {
+      "epoch": 21.32,
+      "grad_norm": 0.3381839096546173,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 0.0351,
+      "step": 85
+    },
+    {
+      "epoch": 22.64,
+      "grad_norm": 0.3768102824687958,
+      "learning_rate": 9.799541809851088e-05,
+      "loss": 0.0296,
+      "step": 90
+    },
+    {
+      "epoch": 23.96,
+      "grad_norm": 0.21533846855163574,
+      "learning_rate": 9.7709049255441e-05,
+      "loss": 0.0296,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.729438841342926,
+      "learning_rate": 9.742268041237114e-05,
+      "loss": 0.0327,
+      "step": 100
+    },
+    {
+      "epoch": 26.32,
+      "grad_norm": 0.15956193208694458,
+      "learning_rate": 9.713631156930127e-05,
+      "loss": 0.0335,
+      "step": 105
+    },
+    {
+      "epoch": 27.64,
+      "grad_norm": 0.3089437186717987,
+      "learning_rate": 9.68499427262314e-05,
+      "loss": 0.0373,
+      "step": 110
+    },
+    {
+      "epoch": 28.96,
+      "grad_norm": 0.2873784303665161,
+      "learning_rate": 9.656357388316152e-05,
+      "loss": 0.028,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.3081432282924652,
+      "learning_rate": 9.627720504009165e-05,
+      "loss": 0.0288,
+      "step": 120
+    },
+    {
+      "epoch": 31.32,
+      "grad_norm": 0.15154343843460083,
+      "learning_rate": 9.599083619702178e-05,
+      "loss": 0.0258,
+      "step": 125
+    },
+    {
+      "epoch": 32.64,
+      "grad_norm": 0.21917082369327545,
+      "learning_rate": 9.57044673539519e-05,
+      "loss": 0.0276,
+      "step": 130
+    },
+    {
+      "epoch": 33.96,
+      "grad_norm": 0.4817427396774292,
+      "learning_rate": 9.541809851088203e-05,
+      "loss": 0.028,
+      "step": 135
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.9411588311195374,
+      "learning_rate": 9.513172966781214e-05,
+      "loss": 0.0301,
+      "step": 140
+    },
+    {
+      "epoch": 36.32,
+      "grad_norm": 0.12594084441661835,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.0278,
+      "step": 145
+    },
+    {
+      "epoch": 37.64,
+      "grad_norm": 0.09696595370769501,
+      "learning_rate": 9.45589919816724e-05,
+      "loss": 0.0254,
+      "step": 150
+    },
+    {
+      "epoch": 38.96,
+      "grad_norm": 0.07912517338991165,
+      "learning_rate": 9.427262313860252e-05,
+      "loss": 0.0253,
+      "step": 155
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.16622836887836456,
+      "learning_rate": 9.398625429553265e-05,
+      "loss": 0.0244,
+      "step": 160
+    },
+    {
+      "epoch": 41.32,
+      "grad_norm": 0.0670735314488411,
+      "learning_rate": 9.369988545246277e-05,
+      "loss": 0.0246,
+      "step": 165
+    },
+    {
+      "epoch": 42.64,
+      "grad_norm": 0.06884271651506424,
+      "learning_rate": 9.34135166093929e-05,
+      "loss": 0.0228,
+      "step": 170
+    },
+    {
+      "epoch": 43.96,
+      "grad_norm": 0.1034952700138092,
+      "learning_rate": 9.312714776632303e-05,
+      "loss": 0.0242,
+      "step": 175
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 0.1411074995994568,
+      "learning_rate": 9.284077892325315e-05,
+      "loss": 0.0237,
+      "step": 180
+    },
+    {
+      "epoch": 46.32,
+      "grad_norm": 0.06430694460868835,
+      "learning_rate": 9.255441008018328e-05,
+      "loss": 0.0244,
+      "step": 185
+    },
+    {
+      "epoch": 47.64,
+      "grad_norm": 0.06416841596364975,
+      "learning_rate": 9.22680412371134e-05,
+      "loss": 0.0253,
+      "step": 190
+    },
+    {
+      "epoch": 48.96,
+      "grad_norm": 0.05058900639414787,
+      "learning_rate": 9.198167239404353e-05,
+      "loss": 0.0234,
+      "step": 195
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.17872126400470734,
+      "learning_rate": 9.169530355097366e-05,
+      "loss": 0.0247,
+      "step": 200
+    },
+    {
+      "epoch": 51.32,
+      "grad_norm": 0.05059915408492088,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.0248,
+      "step": 205
+    },
+    {
+      "epoch": 52.64,
+      "grad_norm": 0.05440365895628929,
+      "learning_rate": 9.112256586483391e-05,
+      "loss": 0.0254,
+      "step": 210
+    },
+    {
+      "epoch": 53.96,
+      "grad_norm": 0.05572507157921791,
+      "learning_rate": 9.083619702176404e-05,
+      "loss": 0.0245,
+      "step": 215
+    },
+    {
+      "epoch": 55.0,
+      "grad_norm": 0.13678045570850372,
+      "learning_rate": 9.054982817869416e-05,
+      "loss": 0.0226,
+      "step": 220
+    },
+    {
+      "epoch": 56.32,
+      "grad_norm": 0.05588487163186073,
+      "learning_rate": 9.026345933562429e-05,
+      "loss": 0.0243,
+      "step": 225
+    },
+    {
+      "epoch": 57.64,
+      "grad_norm": 0.052309829741716385,
+      "learning_rate": 8.997709049255442e-05,
+      "loss": 0.0236,
+      "step": 230
+    },
+    {
+      "epoch": 58.96,
+      "grad_norm": 0.056767936795949936,
+      "learning_rate": 8.969072164948454e-05,
+      "loss": 0.0226,
+      "step": 235
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.24060668051242828,
+      "learning_rate": 8.940435280641467e-05,
+      "loss": 0.0232,
+      "step": 240
+    },
+    {
+      "epoch": 61.32,
+      "grad_norm": 0.05159705877304077,
+      "learning_rate": 8.91179839633448e-05,
+      "loss": 0.0231,
+      "step": 245
+    },
+    {
+      "epoch": 62.64,
+      "grad_norm": 0.053261805325746536,
+      "learning_rate": 8.883161512027491e-05,
+      "loss": 0.0231,
+      "step": 250
+    },
+    {
+      "epoch": 63.96,
+      "grad_norm": 0.05033772811293602,
+      "learning_rate": 8.854524627720504e-05,
+      "loss": 0.0243,
+      "step": 255
+    },
+    {
+      "epoch": 65.0,
+      "grad_norm": 0.1512952744960785,
+      "learning_rate": 8.825887743413516e-05,
+      "loss": 0.0245,
+      "step": 260
+    },
+    {
+      "epoch": 66.32,
+      "grad_norm": 0.057306934148073196,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 0.0232,
+      "step": 265
+    },
+    {
+      "epoch": 67.64,
+      "grad_norm": 0.04558086022734642,
+      "learning_rate": 8.768613974799542e-05,
+      "loss": 0.0223,
+      "step": 270
+    },
+    {
+      "epoch": 68.96,
+      "grad_norm": 0.04183197394013405,
+      "learning_rate": 8.739977090492554e-05,
+      "loss": 0.0259,
+      "step": 275
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.15279851853847504,
+      "learning_rate": 8.711340206185567e-05,
+      "loss": 0.0231,
+      "step": 280
+    },
+    {
+      "epoch": 71.32,
+      "grad_norm": 0.04648765176534653,
+      "learning_rate": 8.682703321878581e-05,
+      "loss": 0.0247,
+      "step": 285
+    },
+    {
+      "epoch": 72.64,
+      "grad_norm": 0.05621657893061638,
+      "learning_rate": 8.654066437571594e-05,
+      "loss": 0.0241,
+      "step": 290
+    },
+    {
+      "epoch": 73.96,
+      "grad_norm": 0.05430695042014122,
+      "learning_rate": 8.625429553264606e-05,
+      "loss": 0.0224,
+      "step": 295
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.13658379018306732,
+      "learning_rate": 8.596792668957619e-05,
+      "loss": 0.0244,
+      "step": 300
+    },
+    {
+      "epoch": 76.32,
+      "grad_norm": 0.04552018269896507,
+      "learning_rate": 8.56815578465063e-05,
+      "loss": 0.023,
+      "step": 305
+    },
+    {
+      "epoch": 77.64,
+      "grad_norm": 0.061252057552337646,
+      "learning_rate": 8.539518900343643e-05,
+      "loss": 0.0232,
+      "step": 310
+    },
+    {
+      "epoch": 78.96,
+      "grad_norm": 0.06784722954034805,
+      "learning_rate": 8.510882016036655e-05,
+      "loss": 0.0225,
+      "step": 315
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 0.12553691864013672,
+      "learning_rate": 8.482245131729668e-05,
+      "loss": 0.0232,
+      "step": 320
+    },
+    {
+      "epoch": 81.32,
+      "grad_norm": 0.043866027146577835,
+      "learning_rate": 8.453608247422681e-05,
+      "loss": 0.0219,
+      "step": 325
+    },
+    {
+      "epoch": 82.64,
+      "grad_norm": 0.042383234947919846,
+      "learning_rate": 8.424971363115693e-05,
+      "loss": 0.0232,
+      "step": 330
+    },
+    {
+      "epoch": 83.96,
+      "grad_norm": 0.058206457644701004,
+      "learning_rate": 8.396334478808706e-05,
+      "loss": 0.0222,
+      "step": 335
+    },
+    {
+      "epoch": 85.0,
+      "grad_norm": 0.13048116862773895,
+      "learning_rate": 8.367697594501719e-05,
+      "loss": 0.0235,
+      "step": 340
+    },
+    {
+      "epoch": 86.32,
+      "grad_norm": 0.03514638915657997,
+      "learning_rate": 8.339060710194731e-05,
+      "loss": 0.0231,
+      "step": 345
+    },
+    {
+      "epoch": 87.64,
+      "grad_norm": 0.04375334829092026,
+      "learning_rate": 8.310423825887744e-05,
+      "loss": 0.0231,
+      "step": 350
+    },
+    {
+      "epoch": 88.96,
+      "grad_norm": 0.04651033505797386,
+      "learning_rate": 8.281786941580757e-05,
+      "loss": 0.0241,
+      "step": 355
+    },
+    {
+      "epoch": 90.0,
+      "grad_norm": 0.15422558784484863,
+      "learning_rate": 8.253150057273768e-05,
+      "loss": 0.0225,
+      "step": 360
+    },
+    {
+      "epoch": 91.32,
+      "grad_norm": 0.05017378553748131,
+      "learning_rate": 8.224513172966782e-05,
+      "loss": 0.0226,
+      "step": 365
+    },
+    {
+      "epoch": 92.64,
+      "grad_norm": 0.04900256544351578,
+      "learning_rate": 8.195876288659795e-05,
+      "loss": 0.0214,
+      "step": 370
+    },
+    {
+      "epoch": 93.96,
+      "grad_norm": 0.039168599992990494,
+      "learning_rate": 8.167239404352807e-05,
+      "loss": 0.0235,
+      "step": 375
+    },
+    {
+      "epoch": 95.0,
+      "grad_norm": 0.16431346535682678,
+      "learning_rate": 8.13860252004582e-05,
+      "loss": 0.0234,
+      "step": 380
+    },
+    {
+      "epoch": 96.32,
+      "grad_norm": 0.047646068036556244,
+      "learning_rate": 8.109965635738833e-05,
+      "loss": 0.0233,
+      "step": 385
+    },
+    {
+      "epoch": 97.64,
+      "grad_norm": 0.04928329959511757,
+      "learning_rate": 8.081328751431845e-05,
+      "loss": 0.0224,
+      "step": 390
+    },
+    {
+      "epoch": 98.96,
+      "grad_norm": 0.042253389954566956,
+      "learning_rate": 8.052691867124858e-05,
+      "loss": 0.0231,
+      "step": 395
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.13217468559741974,
+      "learning_rate": 8.02405498281787e-05,
+      "loss": 0.0232,
+      "step": 400
+    },
+    {
+      "epoch": 101.32,
+      "grad_norm": 0.03638666123151779,
+      "learning_rate": 7.995418098510883e-05,
+      "loss": 0.0224,
+      "step": 405
+    },
+    {
+      "epoch": 102.64,
+      "grad_norm": 0.04150665923953056,
+      "learning_rate": 7.966781214203894e-05,
+      "loss": 0.0234,
+      "step": 410
+    },
+    {
+      "epoch": 103.96,
+      "grad_norm": 0.035543572157621384,
+      "learning_rate": 7.938144329896907e-05,
+      "loss": 0.0221,
+      "step": 415
+    },
+    {
+      "epoch": 105.0,
+      "grad_norm": 0.12740617990493774,
+      "learning_rate": 7.90950744558992e-05,
+      "loss": 0.0222,
+      "step": 420
+    },
+    {
+      "epoch": 106.32,
+      "grad_norm": 0.040774207562208176,
+      "learning_rate": 7.880870561282932e-05,
+      "loss": 0.0224,
+      "step": 425
+    },
+    {
+      "epoch": 107.64,
+      "grad_norm": 0.040325164794921875,
+      "learning_rate": 7.852233676975945e-05,
+      "loss": 0.0235,
+      "step": 430
+    },
+    {
+      "epoch": 108.96,
+      "grad_norm": 0.04361337795853615,
+      "learning_rate": 7.823596792668958e-05,
+      "loss": 0.0236,
+      "step": 435
+    },
+    {
+      "epoch": 110.0,
+      "grad_norm": 0.11627431213855743,
+      "learning_rate": 7.79495990836197e-05,
+      "loss": 0.0238,
+      "step": 440
+    },
+    {
+      "epoch": 111.32,
+      "grad_norm": 0.04112754762172699,
+      "learning_rate": 7.766323024054983e-05,
+      "loss": 0.0232,
+      "step": 445
+    },
+    {
+      "epoch": 112.64,
+      "grad_norm": 0.04499945417046547,
+      "learning_rate": 7.737686139747996e-05,
+      "loss": 0.0241,
+      "step": 450
+    },
+    {
+      "epoch": 113.96,
+      "grad_norm": 0.04413345456123352,
+      "learning_rate": 7.709049255441008e-05,
+      "loss": 0.0237,
+      "step": 455
+    },
+    {
+      "epoch": 115.0,
+      "grad_norm": 0.12778876721858978,
+      "learning_rate": 7.680412371134021e-05,
+      "loss": 0.023,
+      "step": 460
+    },
+    {
+      "epoch": 116.32,
+      "grad_norm": 0.039127930998802185,
+      "learning_rate": 7.651775486827034e-05,
+      "loss": 0.0226,
+      "step": 465
+    },
+    {
+      "epoch": 117.64,
+      "grad_norm": 0.04621637240052223,
+      "learning_rate": 7.623138602520046e-05,
+      "loss": 0.0228,
+      "step": 470
+    },
+    {
+      "epoch": 118.96,
+      "grad_norm": 0.0423317514359951,
+      "learning_rate": 7.594501718213059e-05,
+      "loss": 0.0236,
+      "step": 475
+    },
+    {
+      "epoch": 120.0,
+      "grad_norm": 0.13693822920322418,
+      "learning_rate": 7.565864833906071e-05,
+      "loss": 0.0229,
+      "step": 480
+    },
+    {
+      "epoch": 121.32,
+      "grad_norm": 0.03447780758142471,
+      "learning_rate": 7.537227949599084e-05,
+      "loss": 0.0223,
+      "step": 485
+    },
+    {
+      "epoch": 122.64,
+      "grad_norm": 0.03120778128504753,
+      "learning_rate": 7.508591065292097e-05,
+      "loss": 0.0232,
+      "step": 490
+    },
+    {
+      "epoch": 123.96,
+      "grad_norm": 0.03796784579753876,
+      "learning_rate": 7.47995418098511e-05,
+      "loss": 0.0226,
+      "step": 495
+    },
+    {
+      "epoch": 125.0,
+      "grad_norm": 0.11713339388370514,
+      "learning_rate": 7.451317296678122e-05,
+      "loss": 0.0227,
+      "step": 500
+    },
+    {
+      "epoch": 126.32,
+      "grad_norm": 0.03978479281067848,
+      "learning_rate": 7.422680412371135e-05,
+      "loss": 0.0225,
+      "step": 505
+    },
+    {
+      "epoch": 127.64,
+      "grad_norm": 0.03598278388381004,
+      "learning_rate": 7.394043528064147e-05,
+      "loss": 0.022,
+      "step": 510
+    },
+    {
+      "epoch": 128.96,
+      "grad_norm": 0.039090823382139206,
+      "learning_rate": 7.36540664375716e-05,
+      "loss": 0.0233,
+      "step": 515
+    },
+    {
+      "epoch": 130.0,
+      "grad_norm": 0.15534059703350067,
+      "learning_rate": 7.336769759450171e-05,
+      "loss": 0.0226,
+      "step": 520
+    },
+    {
+      "epoch": 131.32,
+      "grad_norm": 0.029727406799793243,
+      "learning_rate": 7.308132875143184e-05,
+      "loss": 0.0219,
+      "step": 525
+    },
+    {
+      "epoch": 132.64,
+      "grad_norm": 0.04031675308942795,
+      "learning_rate": 7.279495990836197e-05,
+      "loss": 0.0238,
+      "step": 530
+    },
+    {
+      "epoch": 133.96,
+      "grad_norm": 0.03739027678966522,
+      "learning_rate": 7.250859106529209e-05,
+      "loss": 0.0226,
+      "step": 535
+    },
+    {
+      "epoch": 135.0,
+      "grad_norm": 0.11986713111400604,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.0236,
+      "step": 540
+    },
+    {
+      "epoch": 136.32,
+      "grad_norm": 0.03799319267272949,
+      "learning_rate": 7.193585337915235e-05,
+      "loss": 0.0239,
+      "step": 545
+    },
+    {
+      "epoch": 137.64,
+      "grad_norm": 0.033889301121234894,
+      "learning_rate": 7.164948453608247e-05,
+      "loss": 0.0212,
+      "step": 550
+    },
+    {
+      "epoch": 138.96,
+      "grad_norm": 0.03568562492728233,
+      "learning_rate": 7.136311569301261e-05,
+      "loss": 0.0232,
+      "step": 555
+    },
+    {
+      "epoch": 140.0,
+      "grad_norm": 0.09219885617494583,
+      "learning_rate": 7.107674684994274e-05,
+      "loss": 0.0209,
+      "step": 560
+    },
+    {
+      "epoch": 141.32,
+      "grad_norm": 0.030130775645375252,
+      "learning_rate": 7.079037800687286e-05,
+      "loss": 0.0218,
+      "step": 565
+    },
+    {
+      "epoch": 142.64,
+      "grad_norm": 0.04322782903909683,
+      "learning_rate": 7.050400916380299e-05,
+      "loss": 0.024,
+      "step": 570
+    },
+    {
+      "epoch": 143.96,
+      "grad_norm": 0.04596129059791565,
+      "learning_rate": 7.02176403207331e-05,
+      "loss": 0.0223,
+      "step": 575
+    },
+    {
+      "epoch": 145.0,
+      "grad_norm": 0.13223205506801605,
+      "learning_rate": 6.993127147766323e-05,
+      "loss": 0.0228,
+      "step": 580
+    },
+    {
+      "epoch": 146.32,
+      "grad_norm": 0.033803775906562805,
+      "learning_rate": 6.964490263459336e-05,
+      "loss": 0.0221,
+      "step": 585
+    },
+    {
+      "epoch": 147.64,
+      "grad_norm": 0.03498265892267227,
+      "learning_rate": 6.935853379152348e-05,
+      "loss": 0.0223,
+      "step": 590
+    },
+    {
+      "epoch": 148.96,
+      "grad_norm": 0.03388480842113495,
+      "learning_rate": 6.907216494845361e-05,
+      "loss": 0.0228,
+      "step": 595
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 0.07770175486803055,
+      "learning_rate": 6.878579610538374e-05,
+      "loss": 0.0226,
+      "step": 600
+    },
+    {
+      "epoch": 151.32,
+      "grad_norm": 0.035058703273534775,
+      "learning_rate": 6.849942726231386e-05,
+      "loss": 0.0222,
+      "step": 605
+    },
+    {
+      "epoch": 152.64,
+      "grad_norm": 0.03751351311802864,
+      "learning_rate": 6.821305841924399e-05,
+      "loss": 0.0226,
+      "step": 610
+    },
+    {
+      "epoch": 153.96,
+      "grad_norm": 0.03246760368347168,
+      "learning_rate": 6.792668957617412e-05,
+      "loss": 0.0214,
+      "step": 615
+    },
+    {
+      "epoch": 155.0,
+      "grad_norm": 0.13589045405387878,
+      "learning_rate": 6.764032073310424e-05,
+      "loss": 0.0237,
+      "step": 620
+    },
+    {
+      "epoch": 156.32,
+      "grad_norm": 0.031439099460840225,
+      "learning_rate": 6.735395189003437e-05,
+      "loss": 0.0217,
+      "step": 625
+    },
+    {
+      "epoch": 157.64,
+      "grad_norm": 0.03206655755639076,
+      "learning_rate": 6.706758304696448e-05,
+      "loss": 0.0232,
+      "step": 630
+    },
+    {
+      "epoch": 158.96,
+      "grad_norm": 0.037526197731494904,
+      "learning_rate": 6.678121420389462e-05,
+      "loss": 0.0218,
+      "step": 635
+    },
+    {
+      "epoch": 160.0,
+      "grad_norm": 0.09874481707811356,
+      "learning_rate": 6.649484536082475e-05,
+      "loss": 0.0228,
+      "step": 640
+    },
+    {
+      "epoch": 161.32,
+      "grad_norm": 0.03909553959965706,
+      "learning_rate": 6.620847651775487e-05,
+      "loss": 0.0225,
+      "step": 645
+    },
+    {
+      "epoch": 162.64,
+      "grad_norm": 0.034332025796175,
+      "learning_rate": 6.5922107674685e-05,
+      "loss": 0.0222,
+      "step": 650
+    },
+    {
+      "epoch": 163.96,
+      "grad_norm": 0.033894602209329605,
+      "learning_rate": 6.563573883161513e-05,
+      "loss": 0.0219,
+      "step": 655
+    },
+    {
+      "epoch": 165.0,
+      "grad_norm": 0.09040471911430359,
+      "learning_rate": 6.534936998854525e-05,
+      "loss": 0.0219,
+      "step": 660
+    },
+    {
+      "epoch": 166.32,
+      "grad_norm": 0.03086320124566555,
+      "learning_rate": 6.506300114547538e-05,
+      "loss": 0.0241,
+      "step": 665
+    },
+    {
+      "epoch": 167.64,
+      "grad_norm": 0.030052335932850838,
+      "learning_rate": 6.477663230240551e-05,
+      "loss": 0.0223,
+      "step": 670
+    },
+    {
+      "epoch": 168.96,
+      "grad_norm": 0.028752340003848076,
+      "learning_rate": 6.449026345933563e-05,
+      "loss": 0.0226,
+      "step": 675
+    },
+    {
+      "epoch": 170.0,
+      "grad_norm": 0.09044802188873291,
+      "learning_rate": 6.420389461626576e-05,
+      "loss": 0.0245,
+      "step": 680
+    },
+    {
+      "epoch": 171.32,
+      "grad_norm": 0.031187741085886955,
+      "learning_rate": 6.391752577319587e-05,
+      "loss": 0.0234,
+      "step": 685
+    },
+    {
+      "epoch": 172.64,
+      "grad_norm": 0.032953280955553055,
+      "learning_rate": 6.3631156930126e-05,
+      "loss": 0.0231,
+      "step": 690
+    },
+    {
+      "epoch": 173.96,
+      "grad_norm": 0.035380713641643524,
+      "learning_rate": 6.334478808705613e-05,
+      "loss": 0.0231,
+      "step": 695
+    },
+    {
+      "epoch": 175.0,
+      "grad_norm": 0.10263343155384064,
+      "learning_rate": 6.305841924398625e-05,
+      "loss": 0.0226,
+      "step": 700
+    },
+    {
+      "epoch": 176.32,
+      "grad_norm": 0.03277510777115822,
+      "learning_rate": 6.277205040091638e-05,
+      "loss": 0.0222,
+      "step": 705
+    },
+    {
+      "epoch": 177.64,
+      "grad_norm": 0.034485459327697754,
+      "learning_rate": 6.24856815578465e-05,
+      "loss": 0.0227,
+      "step": 710
+    },
+    {
+      "epoch": 178.96,
+      "grad_norm": 0.03501957654953003,
+      "learning_rate": 6.219931271477663e-05,
+      "loss": 0.0223,
+      "step": 715
+    },
+    {
+      "epoch": 180.0,
+      "grad_norm": 0.11059446632862091,
+      "learning_rate": 6.191294387170676e-05,
+      "loss": 0.0219,
+      "step": 720
+    },
+    {
+      "epoch": 181.32,
+      "grad_norm": 0.03453643247485161,
+      "learning_rate": 6.162657502863689e-05,
+      "loss": 0.0223,
+      "step": 725
+    },
+    {
+      "epoch": 182.64,
+      "grad_norm": 0.031747136265039444,
+      "learning_rate": 6.134020618556701e-05,
+      "loss": 0.0211,
+      "step": 730
+    },
+    {
+      "epoch": 183.96,
+      "grad_norm": 0.03772411495447159,
+      "learning_rate": 6.105383734249714e-05,
+      "loss": 0.0213,
+      "step": 735
+    },
+    {
+      "epoch": 185.0,
+      "grad_norm": 0.08717264235019684,
+      "learning_rate": 6.076746849942726e-05,
+      "loss": 0.0232,
+      "step": 740
+    },
+    {
+      "epoch": 186.32,
+      "grad_norm": 0.030604945495724678,
+      "learning_rate": 6.0481099656357384e-05,
+      "loss": 0.023,
+      "step": 745
+    },
+    {
+      "epoch": 187.64,
+      "grad_norm": 0.027379345148801804,
+      "learning_rate": 6.019473081328752e-05,
+      "loss": 0.0217,
+      "step": 750
+    },
+    {
+      "epoch": 188.96,
+      "grad_norm": 0.032438065856695175,
+      "learning_rate": 5.9908361970217644e-05,
+      "loss": 0.0252,
+      "step": 755
+    },
+    {
+      "epoch": 190.0,
+      "grad_norm": 0.08274230360984802,
+      "learning_rate": 5.962199312714777e-05,
+      "loss": 0.0212,
+      "step": 760
+    },
+    {
+      "epoch": 191.32,
+      "grad_norm": 0.02920094132423401,
+      "learning_rate": 5.93356242840779e-05,
+      "loss": 0.0224,
+      "step": 765
+    },
+    {
+      "epoch": 192.64,
+      "grad_norm": 0.03730329871177673,
+      "learning_rate": 5.904925544100802e-05,
+      "loss": 0.0228,
+      "step": 770
+    },
+    {
+      "epoch": 193.96,
+      "grad_norm": 0.040118809789419174,
+      "learning_rate": 5.876288659793815e-05,
+      "loss": 0.0226,
+      "step": 775
+    },
+    {
+      "epoch": 195.0,
+      "grad_norm": 0.08151891827583313,
+      "learning_rate": 5.8476517754868276e-05,
+      "loss": 0.022,
+      "step": 780
+    },
+    {
+      "epoch": 196.32,
+      "grad_norm": 0.0327572226524353,
+      "learning_rate": 5.81901489117984e-05,
+      "loss": 0.0219,
+      "step": 785
+    },
+    {
+      "epoch": 197.64,
+      "grad_norm": 0.027864839881658554,
+      "learning_rate": 5.790378006872853e-05,
+      "loss": 0.0235,
+      "step": 790
+    },
+    {
+      "epoch": 198.96,
+      "grad_norm": 0.033668313175439835,
+      "learning_rate": 5.761741122565865e-05,
+      "loss": 0.0229,
+      "step": 795
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 0.07690460234880447,
+      "learning_rate": 5.7331042382588775e-05,
+      "loss": 0.0225,
+      "step": 800
+    },
+    {
+      "epoch": 201.32,
+      "grad_norm": 0.030898429453372955,
+      "learning_rate": 5.70446735395189e-05,
+      "loss": 0.022,
+      "step": 805
+    },
+    {
+      "epoch": 202.64,
+      "grad_norm": 0.02849520556628704,
+      "learning_rate": 5.675830469644903e-05,
+      "loss": 0.023,
+      "step": 810
+    },
+    {
+      "epoch": 203.96,
+      "grad_norm": 0.031954504549503326,
+      "learning_rate": 5.6471935853379155e-05,
+      "loss": 0.0225,
+      "step": 815
+    },
+    {
+      "epoch": 205.0,
+      "grad_norm": 0.09324806183576584,
+      "learning_rate": 5.618556701030928e-05,
+      "loss": 0.0233,
+      "step": 820
+    },
+    {
+      "epoch": 206.32,
+      "grad_norm": 0.0302401315420866,
+      "learning_rate": 5.589919816723941e-05,
+      "loss": 0.0215,
+      "step": 825
+    },
+    {
+      "epoch": 207.64,
+      "grad_norm": 0.029426347464323044,
+      "learning_rate": 5.5612829324169534e-05,
+      "loss": 0.0215,
+      "step": 830
+    },
+    {
+      "epoch": 208.96,
+      "grad_norm": 0.031664323061704636,
+      "learning_rate": 5.532646048109966e-05,
+      "loss": 0.0218,
+      "step": 835
+    },
+    {
+      "epoch": 210.0,
+      "grad_norm": 0.09568897634744644,
+      "learning_rate": 5.504009163802979e-05,
+      "loss": 0.0208,
+      "step": 840
+    },
+    {
+      "epoch": 211.32,
+      "grad_norm": 0.029477190226316452,
+      "learning_rate": 5.4753722794959914e-05,
+      "loss": 0.0214,
+      "step": 845
+    },
+    {
+      "epoch": 212.64,
+      "grad_norm": 0.030615277588367462,
+      "learning_rate": 5.4467353951890033e-05,
+      "loss": 0.0227,
+      "step": 850
+    },
+    {
+      "epoch": 213.96,
+      "grad_norm": 0.03466692939400673,
+      "learning_rate": 5.418098510882016e-05,
+      "loss": 0.0212,
+      "step": 855
+    },
+    {
+      "epoch": 215.0,
+      "grad_norm": 0.1077422946691513,
+      "learning_rate": 5.3894616265750286e-05,
+      "loss": 0.022,
+      "step": 860
+    },
+    {
+      "epoch": 216.32,
+      "grad_norm": 0.030155370011925697,
+      "learning_rate": 5.360824742268041e-05,
+      "loss": 0.0227,
+      "step": 865
+    },
+    {
+      "epoch": 217.64,
+      "grad_norm": 0.02762630768120289,
+      "learning_rate": 5.332187857961054e-05,
+      "loss": 0.0219,
+      "step": 870
+    },
+    {
+      "epoch": 218.96,
+      "grad_norm": 0.027750438079237938,
+      "learning_rate": 5.3035509736540666e-05,
+      "loss": 0.0225,
+      "step": 875
+    },
+    {
+      "epoch": 220.0,
+      "grad_norm": 0.1480046659708023,
+      "learning_rate": 5.274914089347079e-05,
+      "loss": 0.024,
+      "step": 880
+    },
+    {
+      "epoch": 221.32,
+      "grad_norm": 0.027756843715906143,
+      "learning_rate": 5.246277205040092e-05,
+      "loss": 0.0232,
+      "step": 885
+    },
+    {
+      "epoch": 222.64,
+      "grad_norm": 0.025351909920573235,
+      "learning_rate": 5.2176403207331045e-05,
+      "loss": 0.0224,
+      "step": 890
+    },
+    {
+      "epoch": 223.96,
+      "grad_norm": 0.03722308948636055,
+      "learning_rate": 5.189003436426118e-05,
+      "loss": 0.0224,
+      "step": 895
+    },
+    {
+      "epoch": 225.0,
+      "grad_norm": 0.09891820698976517,
+      "learning_rate": 5.1603665521191305e-05,
+      "loss": 0.0223,
+      "step": 900
+    },
+    {
+      "epoch": 226.32,
+      "grad_norm": 0.031157376244664192,
+      "learning_rate": 5.131729667812142e-05,
+      "loss": 0.0228,
+      "step": 905
+    },
+    {
+      "epoch": 227.64,
+      "grad_norm": 0.026530060917139053,
+      "learning_rate": 5.1030927835051544e-05,
+      "loss": 0.0227,
+      "step": 910
+    },
+    {
+      "epoch": 228.96,
+      "grad_norm": 0.028711870312690735,
+      "learning_rate": 5.074455899198167e-05,
+      "loss": 0.0229,
+      "step": 915
+    },
+    {
+      "epoch": 230.0,
+      "grad_norm": 0.10996802896261215,
+      "learning_rate": 5.04581901489118e-05,
+      "loss": 0.0236,
+      "step": 920
+    },
+    {
+      "epoch": 231.32,
+      "grad_norm": 0.026562057435512543,
+      "learning_rate": 5.0171821305841924e-05,
+      "loss": 0.0221,
+      "step": 925
+    },
+    {
+      "epoch": 232.64,
+      "grad_norm": 0.029791025444865227,
+      "learning_rate": 4.988545246277205e-05,
+      "loss": 0.0237,
+      "step": 930
+    },
+    {
+      "epoch": 233.96,
+      "grad_norm": 0.030204325914382935,
+      "learning_rate": 4.9599083619702184e-05,
+      "loss": 0.0222,
+      "step": 935
+    },
+    {
+      "epoch": 235.0,
+      "grad_norm": 0.06489063054323196,
+      "learning_rate": 4.931271477663231e-05,
+      "loss": 0.0212,
+      "step": 940
+    },
+    {
+      "epoch": 236.32,
+      "grad_norm": 0.033282287418842316,
+      "learning_rate": 4.902634593356243e-05,
+      "loss": 0.0224,
+      "step": 945
+    },
+    {
+      "epoch": 237.64,
+      "grad_norm": 0.030851591378450394,
+      "learning_rate": 4.8739977090492556e-05,
+      "loss": 0.0216,
+      "step": 950
+    },
+    {
+      "epoch": 238.96,
+      "grad_norm": 0.029777253046631813,
+      "learning_rate": 4.845360824742268e-05,
+      "loss": 0.0222,
+      "step": 955
+    },
+    {
+      "epoch": 240.0,
+      "grad_norm": 0.06517614424228668,
+      "learning_rate": 4.816723940435281e-05,
+      "loss": 0.0197,
+      "step": 960
+    },
+    {
+      "epoch": 241.32,
+      "grad_norm": 0.027710000053048134,
+      "learning_rate": 4.7880870561282936e-05,
+      "loss": 0.0231,
+      "step": 965
+    },
+    {
+      "epoch": 242.64,
+      "grad_norm": 0.027534285560250282,
+      "learning_rate": 4.7594501718213055e-05,
+      "loss": 0.0229,
+      "step": 970
+    },
+    {
+      "epoch": 243.96,
+      "grad_norm": 0.029630396515130997,
+      "learning_rate": 4.730813287514318e-05,
+      "loss": 0.0219,
+      "step": 975
+    },
+    {
+      "epoch": 245.0,
+      "grad_norm": 0.09967376291751862,
+      "learning_rate": 4.7021764032073315e-05,
+      "loss": 0.0211,
+      "step": 980
+    },
+    {
+      "epoch": 246.32,
+      "grad_norm": 0.026448087766766548,
+      "learning_rate": 4.673539518900344e-05,
+      "loss": 0.0219,
+      "step": 985
+    },
+    {
+      "epoch": 247.64,
+      "grad_norm": 0.030766399577260017,
+      "learning_rate": 4.644902634593357e-05,
+      "loss": 0.0218,
+      "step": 990
+    },
+    {
+      "epoch": 248.96,
+      "grad_norm": 0.03127891570329666,
+      "learning_rate": 4.6162657502863694e-05,
+      "loss": 0.0222,
+      "step": 995
+    },
+    {
+      "epoch": 250.0,
+      "grad_norm": 0.07358253002166748,
+      "learning_rate": 4.5876288659793814e-05,
+      "loss": 0.022,
+      "step": 1000
+    },
+    {
+      "epoch": 251.32,
+      "grad_norm": 0.030259255319833755,
+      "learning_rate": 4.558991981672394e-05,
+      "loss": 0.0215,
+      "step": 1005
+    },
+    {
+      "epoch": 252.64,
+      "grad_norm": 0.031163489446043968,
+      "learning_rate": 4.530355097365407e-05,
+      "loss": 0.0218,
+      "step": 1010
+    },
+    {
+      "epoch": 253.96,
+      "grad_norm": 0.025623638182878494,
+      "learning_rate": 4.5017182130584194e-05,
+      "loss": 0.0225,
+      "step": 1015
+    },
+    {
+      "epoch": 255.0,
+      "grad_norm": 0.10825876146554947,
+      "learning_rate": 4.473081328751432e-05,
+      "loss": 0.0228,
+      "step": 1020
+    },
+    {
+      "epoch": 256.32,
+      "grad_norm": 0.029599890112876892,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.0218,
+      "step": 1025
+    },
+    {
+      "epoch": 257.64,
+      "grad_norm": 0.027761822566390038,
+      "learning_rate": 4.415807560137457e-05,
+      "loss": 0.0226,
+      "step": 1030
+    },
+    {
+      "epoch": 258.96,
+      "grad_norm": 0.03065340407192707,
+      "learning_rate": 4.38717067583047e-05,
+      "loss": 0.0235,
+      "step": 1035
+    },
+    {
+      "epoch": 260.0,
+      "grad_norm": 0.08595085889101028,
+      "learning_rate": 4.3585337915234826e-05,
+      "loss": 0.0225,
+      "step": 1040
+    },
+    {
+      "epoch": 261.32,
+      "grad_norm": 0.031066762283444405,
+      "learning_rate": 4.329896907216495e-05,
+      "loss": 0.0236,
+      "step": 1045
+    },
+    {
+      "epoch": 262.64,
+      "grad_norm": 0.028579367324709892,
+      "learning_rate": 4.301260022909508e-05,
+      "loss": 0.0214,
+      "step": 1050
+    },
+    {
+      "epoch": 263.96,
+      "grad_norm": 0.028484277427196503,
+      "learning_rate": 4.27262313860252e-05,
+      "loss": 0.0223,
+      "step": 1055
+    },
+    {
+      "epoch": 265.0,
+      "grad_norm": 0.08596421033143997,
+      "learning_rate": 4.2439862542955325e-05,
+      "loss": 0.0215,
+      "step": 1060
+    },
+    {
+      "epoch": 266.32,
+      "grad_norm": 0.02508409693837166,
+      "learning_rate": 4.215349369988545e-05,
+      "loss": 0.0214,
+      "step": 1065
+    },
+    {
+      "epoch": 267.64,
+      "grad_norm": 0.02804061770439148,
+      "learning_rate": 4.1867124856815585e-05,
+      "loss": 0.0236,
+      "step": 1070
+    },
+    {
+      "epoch": 268.96,
+      "grad_norm": 0.030820870772004128,
+      "learning_rate": 4.158075601374571e-05,
+      "loss": 0.0222,
+      "step": 1075
+    },
+    {
+      "epoch": 270.0,
+      "grad_norm": 0.09306512773036957,
+      "learning_rate": 4.129438717067583e-05,
+      "loss": 0.0211,
+      "step": 1080
+    },
+    {
+      "epoch": 271.32,
+      "grad_norm": 0.030462536960840225,
+      "learning_rate": 4.100801832760596e-05,
+      "loss": 0.0222,
+      "step": 1085
+    },
+    {
+      "epoch": 272.64,
+      "grad_norm": 0.029752682894468307,
+      "learning_rate": 4.0721649484536084e-05,
+      "loss": 0.0219,
+      "step": 1090
+    },
+    {
+      "epoch": 273.96,
+      "grad_norm": 0.02907637320458889,
+      "learning_rate": 4.043528064146621e-05,
+      "loss": 0.0224,
+      "step": 1095
+    },
+    {
+      "epoch": 275.0,
+      "grad_norm": 0.11900507658720016,
+      "learning_rate": 4.014891179839634e-05,
+      "loss": 0.0224,
+      "step": 1100
+    },
+    {
+      "epoch": 276.32,
+      "grad_norm": 0.029513241723179817,
+      "learning_rate": 3.9862542955326463e-05,
+      "loss": 0.0223,
+      "step": 1105
+    },
+    {
+      "epoch": 277.64,
+      "grad_norm": 0.02655150555074215,
+      "learning_rate": 3.957617411225659e-05,
+      "loss": 0.0215,
+      "step": 1110
+    },
+    {
+      "epoch": 278.96,
+      "grad_norm": 0.031090132892131805,
+      "learning_rate": 3.9289805269186716e-05,
+      "loss": 0.0229,
+      "step": 1115
+    },
+    {
+      "epoch": 280.0,
+      "grad_norm": 0.10574332624673843,
+      "learning_rate": 3.900343642611684e-05,
+      "loss": 0.0226,
+      "step": 1120
+    },
+    {
+      "epoch": 281.32,
+      "grad_norm": 0.025768013671040535,
+      "learning_rate": 3.871706758304697e-05,
+      "loss": 0.022,
+      "step": 1125
+    },
+    {
+      "epoch": 282.64,
+      "grad_norm": 0.02915865182876587,
+      "learning_rate": 3.8430698739977096e-05,
+      "loss": 0.0226,
+      "step": 1130
+    },
+    {
+      "epoch": 283.96,
+      "grad_norm": 0.028867091983556747,
+      "learning_rate": 3.8144329896907216e-05,
+      "loss": 0.0223,
+      "step": 1135
+    },
+    {
+      "epoch": 285.0,
+      "grad_norm": 0.06698961555957794,
+      "learning_rate": 3.785796105383734e-05,
+      "loss": 0.0209,
+      "step": 1140
+    },
+    {
+      "epoch": 286.32,
+      "grad_norm": 0.029880354180932045,
+      "learning_rate": 3.757159221076747e-05,
+      "loss": 0.0226,
+      "step": 1145
+    },
+    {
+      "epoch": 287.64,
+      "grad_norm": 0.027591262012720108,
+      "learning_rate": 3.7285223367697595e-05,
+      "loss": 0.0213,
+      "step": 1150
+    },
+    {
+      "epoch": 288.96,
+      "grad_norm": 0.029396766796708107,
+      "learning_rate": 3.699885452462772e-05,
+      "loss": 0.023,
+      "step": 1155
+    },
+    {
+      "epoch": 290.0,
+      "grad_norm": 0.10461018979549408,
+      "learning_rate": 3.671248568155785e-05,
+      "loss": 0.0218,
+      "step": 1160
+    },
+    {
+      "epoch": 291.32,
+      "grad_norm": 0.029114672914147377,
+      "learning_rate": 3.6426116838487974e-05,
+      "loss": 0.0222,
+      "step": 1165
+    },
+    {
+      "epoch": 292.64,
+      "grad_norm": 0.027854561805725098,
+      "learning_rate": 3.61397479954181e-05,
+      "loss": 0.0229,
+      "step": 1170
+    },
+    {
+      "epoch": 293.96,
+      "grad_norm": 0.0312589667737484,
+      "learning_rate": 3.585337915234823e-05,
+      "loss": 0.0222,
+      "step": 1175
+    },
+    {
+      "epoch": 295.0,
+      "grad_norm": 0.10697894543409348,
+      "learning_rate": 3.5567010309278354e-05,
+      "loss": 0.0209,
+      "step": 1180
+    },
+    {
+      "epoch": 296.32,
+      "grad_norm": 0.029923448339104652,
+      "learning_rate": 3.528064146620848e-05,
+      "loss": 0.0224,
+      "step": 1185
+    },
+    {
+      "epoch": 297.64,
+      "grad_norm": 0.02807888388633728,
+      "learning_rate": 3.49942726231386e-05,
+      "loss": 0.0225,
+      "step": 1190
+    },
+    {
+      "epoch": 298.96,
+      "grad_norm": 0.028458457440137863,
+      "learning_rate": 3.4707903780068726e-05,
+      "loss": 0.023,
+      "step": 1195
+    },
+    {
+      "epoch": 300.0,
+      "grad_norm": 0.09004534780979156,
+      "learning_rate": 3.442153493699885e-05,
+      "loss": 0.0216,
+      "step": 1200
+    },
+    {
+      "epoch": 301.32,
+      "grad_norm": 0.02781865932047367,
+      "learning_rate": 3.4135166093928986e-05,
+      "loss": 0.0221,
+      "step": 1205
+    },
+    {
+      "epoch": 302.64,
+      "grad_norm": 0.028483230620622635,
+      "learning_rate": 3.384879725085911e-05,
+      "loss": 0.0218,
+      "step": 1210
+    },
+    {
+      "epoch": 303.96,
+      "grad_norm": 0.029581783339381218,
+      "learning_rate": 3.356242840778923e-05,
+      "loss": 0.0227,
+      "step": 1215
+    },
+    {
+      "epoch": 305.0,
+      "grad_norm": 0.11656039208173752,
+      "learning_rate": 3.327605956471936e-05,
+      "loss": 0.0234,
+      "step": 1220
+    },
+    {
+      "epoch": 306.32,
+      "grad_norm": 0.026737062260508537,
+      "learning_rate": 3.2989690721649485e-05,
+      "loss": 0.0221,
+      "step": 1225
+    },
+    {
+      "epoch": 307.64,
+      "grad_norm": 0.030143236741423607,
+      "learning_rate": 3.270332187857961e-05,
+      "loss": 0.0223,
+      "step": 1230
+    },
+    {
+      "epoch": 308.96,
+      "grad_norm": 0.027385924011468887,
+      "learning_rate": 3.241695303550974e-05,
+      "loss": 0.0224,
+      "step": 1235
+    },
+    {
+      "epoch": 310.0,
+      "grad_norm": 0.09042290598154068,
+      "learning_rate": 3.2130584192439865e-05,
+      "loss": 0.0223,
+      "step": 1240
+    },
+    {
+      "epoch": 311.32,
+      "grad_norm": 0.02867588959634304,
+      "learning_rate": 3.184421534936999e-05,
+      "loss": 0.0224,
+      "step": 1245
+    },
+    {
+      "epoch": 312.64,
+      "grad_norm": 0.026082267984747887,
+      "learning_rate": 3.155784650630012e-05,
+      "loss": 0.0222,
+      "step": 1250
+    },
+    {
+      "epoch": 313.96,
+      "grad_norm": 0.030696265399456024,
+      "learning_rate": 3.1271477663230244e-05,
+      "loss": 0.0218,
+      "step": 1255
+    },
+    {
+      "epoch": 315.0,
+      "grad_norm": 0.06664582341909409,
+      "learning_rate": 3.098510882016037e-05,
+      "loss": 0.0205,
+      "step": 1260
+    },
+    {
+      "epoch": 316.32,
+      "grad_norm": 0.02528396248817444,
+      "learning_rate": 3.06987399770905e-05,
+      "loss": 0.0212,
+      "step": 1265
+    },
+    {
+      "epoch": 317.64,
+      "grad_norm": 0.028939127922058105,
+      "learning_rate": 3.0412371134020617e-05,
+      "loss": 0.0225,
+      "step": 1270
+    },
+    {
+      "epoch": 318.96,
+      "grad_norm": 0.026384050026535988,
+      "learning_rate": 3.0126002290950743e-05,
+      "loss": 0.0223,
+      "step": 1275
+    },
+    {
+      "epoch": 320.0,
+      "grad_norm": 0.08773248642683029,
+      "learning_rate": 2.983963344788087e-05,
+      "loss": 0.022,
+      "step": 1280
+    },
+    {
+      "epoch": 321.32,
+      "grad_norm": 0.029451629146933556,
+      "learning_rate": 2.9553264604811e-05,
+      "loss": 0.0213,
+      "step": 1285
+    },
+    {
+      "epoch": 322.64,
+      "grad_norm": 0.029388943687081337,
+      "learning_rate": 2.9266895761741126e-05,
+      "loss": 0.0226,
+      "step": 1290
+    },
+    {
+      "epoch": 323.96,
+      "grad_norm": 0.02841971069574356,
+      "learning_rate": 2.8980526918671253e-05,
+      "loss": 0.021,
+      "step": 1295
+    },
+    {
+      "epoch": 325.0,
+      "grad_norm": 0.08616754412651062,
+      "learning_rate": 2.8694158075601372e-05,
+      "loss": 0.0218,
+      "step": 1300
+    },
+    {
+      "epoch": 326.32,
+      "grad_norm": 0.03196750581264496,
+      "learning_rate": 2.8407789232531502e-05,
+      "loss": 0.0226,
+      "step": 1305
+    },
+    {
+      "epoch": 327.64,
+      "grad_norm": 0.02681926265358925,
+      "learning_rate": 2.812142038946163e-05,
+      "loss": 0.0207,
+      "step": 1310
+    },
+    {
+      "epoch": 328.96,
+      "grad_norm": 0.029461359605193138,
+      "learning_rate": 2.7835051546391755e-05,
+      "loss": 0.0216,
+      "step": 1315
+    },
+    {
+      "epoch": 330.0,
+      "grad_norm": 0.10138925909996033,
+      "learning_rate": 2.754868270332188e-05,
+      "loss": 0.022,
+      "step": 1320
+    },
+    {
+      "epoch": 331.32,
+      "grad_norm": 0.02837948128581047,
+      "learning_rate": 2.7262313860252005e-05,
+      "loss": 0.0223,
+      "step": 1325
+    },
+    {
+      "epoch": 332.64,
+      "grad_norm": 0.02668078988790512,
+      "learning_rate": 2.697594501718213e-05,
+      "loss": 0.0226,
+      "step": 1330
+    },
+    {
+      "epoch": 333.96,
+      "grad_norm": 0.028131477534770966,
+      "learning_rate": 2.6689576174112258e-05,
+      "loss": 0.0223,
+      "step": 1335
+    },
+    {
+      "epoch": 335.0,
+      "grad_norm": 0.08429412543773651,
+      "learning_rate": 2.6403207331042384e-05,
+      "loss": 0.0228,
+      "step": 1340
+    },
+    {
+      "epoch": 336.32,
+      "grad_norm": 0.026646487414836884,
+      "learning_rate": 2.611683848797251e-05,
+      "loss": 0.0223,
+      "step": 1345
+    },
+    {
+      "epoch": 337.64,
+      "grad_norm": 0.027175936847925186,
+      "learning_rate": 2.5830469644902637e-05,
+      "loss": 0.0227,
+      "step": 1350
+    },
+    {
+      "epoch": 338.96,
+      "grad_norm": 0.030607223510742188,
+      "learning_rate": 2.554410080183276e-05,
+      "loss": 0.0236,
+      "step": 1355
+    },
+    {
+      "epoch": 340.0,
+      "grad_norm": 0.07383383065462112,
+      "learning_rate": 2.5257731958762887e-05,
+      "loss": 0.022,
+      "step": 1360
+    },
+    {
+      "epoch": 341.32,
+      "grad_norm": 0.028488941490650177,
+      "learning_rate": 2.4971363115693013e-05,
+      "loss": 0.0221,
+      "step": 1365
+    },
+    {
+      "epoch": 342.64,
+      "grad_norm": 0.033083755522966385,
+      "learning_rate": 2.468499427262314e-05,
+      "loss": 0.0215,
+      "step": 1370
+    },
+    {
+      "epoch": 343.96,
+      "grad_norm": 0.029608990997076035,
+      "learning_rate": 2.4398625429553266e-05,
+      "loss": 0.0217,
+      "step": 1375
+    },
+    {
+      "epoch": 345.0,
+      "grad_norm": 0.10344070196151733,
+      "learning_rate": 2.4112256586483393e-05,
+      "loss": 0.0236,
+      "step": 1380
+    },
+    {
+      "epoch": 346.32,
+      "grad_norm": 0.033095359802246094,
+      "learning_rate": 2.3825887743413516e-05,
+      "loss": 0.0234,
+      "step": 1385
+    },
+    {
+      "epoch": 347.64,
+      "grad_norm": 0.029788870364427567,
+      "learning_rate": 2.3539518900343642e-05,
+      "loss": 0.0224,
+      "step": 1390
+    },
+    {
+      "epoch": 348.96,
+      "grad_norm": 0.030327215790748596,
+      "learning_rate": 2.3253150057273772e-05,
+      "loss": 0.022,
+      "step": 1395
+    },
+    {
+      "epoch": 350.0,
+      "grad_norm": 0.11181904375553131,
+      "learning_rate": 2.2966781214203895e-05,
+      "loss": 0.0226,
+      "step": 1400
+    },
+    {
+      "epoch": 351.32,
+      "grad_norm": 0.03141086548566818,
+      "learning_rate": 2.268041237113402e-05,
+      "loss": 0.0233,
+      "step": 1405
+    },
+    {
+      "epoch": 352.64,
+      "grad_norm": 0.02836909517645836,
+      "learning_rate": 2.2394043528064148e-05,
+      "loss": 0.0235,
+      "step": 1410
+    },
+    {
+      "epoch": 353.96,
+      "grad_norm": 0.026505406945943832,
+      "learning_rate": 2.210767468499427e-05,
+      "loss": 0.0221,
+      "step": 1415
+    },
+    {
+      "epoch": 355.0,
+      "grad_norm": 0.05104130879044533,
+      "learning_rate": 2.18213058419244e-05,
+      "loss": 0.0207,
+      "step": 1420
+    },
+    {
+      "epoch": 356.32,
+      "grad_norm": 0.027829525992274284,
+      "learning_rate": 2.1534936998854528e-05,
+      "loss": 0.0219,
+      "step": 1425
+    },
+    {
+      "epoch": 357.64,
+      "grad_norm": 0.03288746252655983,
+      "learning_rate": 2.124856815578465e-05,
+      "loss": 0.0223,
+      "step": 1430
+    },
+    {
+      "epoch": 358.96,
+      "grad_norm": 0.027919428423047066,
+      "learning_rate": 2.0962199312714777e-05,
+      "loss": 0.0204,
+      "step": 1435
+    },
+    {
+      "epoch": 360.0,
+      "grad_norm": 0.07339093089103699,
+      "learning_rate": 2.0675830469644904e-05,
+      "loss": 0.0212,
+      "step": 1440
+    },
+    {
+      "epoch": 361.32,
+      "grad_norm": 0.02630612812936306,
+      "learning_rate": 2.038946162657503e-05,
+      "loss": 0.0222,
+      "step": 1445
+    },
+    {
+      "epoch": 362.64,
+      "grad_norm": 0.026910657063126564,
+      "learning_rate": 2.0103092783505157e-05,
+      "loss": 0.023,
+      "step": 1450
+    },
+    {
+      "epoch": 363.96,
+      "grad_norm": 0.02552923373878002,
+      "learning_rate": 1.981672394043528e-05,
+      "loss": 0.0202,
+      "step": 1455
+    },
+    {
+      "epoch": 365.0,
+      "grad_norm": 0.08786323666572571,
+      "learning_rate": 1.9530355097365406e-05,
+      "loss": 0.0218,
+      "step": 1460
+    },
+    {
+      "epoch": 366.32,
+      "grad_norm": 0.023231837898492813,
+      "learning_rate": 1.9243986254295536e-05,
+      "loss": 0.022,
+      "step": 1465
+    },
+    {
+      "epoch": 367.64,
+      "grad_norm": 0.024473244324326515,
+      "learning_rate": 1.895761741122566e-05,
+      "loss": 0.0234,
+      "step": 1470
+    },
+    {
+      "epoch": 368.96,
+      "grad_norm": 0.027507726103067398,
+      "learning_rate": 1.8671248568155786e-05,
+      "loss": 0.0229,
+      "step": 1475
+    },
+    {
+      "epoch": 370.0,
+      "grad_norm": 0.08709301054477692,
+      "learning_rate": 1.8384879725085912e-05,
+      "loss": 0.022,
+      "step": 1480
+    },
+    {
+      "epoch": 371.32,
+      "grad_norm": 0.02902478352189064,
+      "learning_rate": 1.809851088201604e-05,
+      "loss": 0.0225,
+      "step": 1485
+    },
+    {
+      "epoch": 372.64,
+      "grad_norm": 0.026616817340254784,
+      "learning_rate": 1.7812142038946165e-05,
+      "loss": 0.0222,
+      "step": 1490
+    },
+    {
+      "epoch": 373.96,
+      "grad_norm": 0.02648814581334591,
+      "learning_rate": 1.7525773195876288e-05,
+      "loss": 0.0218,
+      "step": 1495
+    },
+    {
+      "epoch": 375.0,
+      "grad_norm": 0.09145989269018173,
+      "learning_rate": 1.7239404352806415e-05,
+      "loss": 0.0219,
+      "step": 1500
+    },
+    {
+      "epoch": 376.32,
+      "grad_norm": 0.02692406438291073,
+      "learning_rate": 1.695303550973654e-05,
+      "loss": 0.0211,
+      "step": 1505
+    },
+    {
+      "epoch": 377.64,
+      "grad_norm": 0.03306850790977478,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.0229,
+      "step": 1510
+    },
+    {
+      "epoch": 378.96,
+      "grad_norm": 0.027390655130147934,
+      "learning_rate": 1.6380297823596794e-05,
+      "loss": 0.022,
+      "step": 1515
+    },
+    {
+      "epoch": 380.0,
+      "grad_norm": 0.07528829574584961,
+      "learning_rate": 1.609392898052692e-05,
+      "loss": 0.0215,
+      "step": 1520
+    },
+    {
+      "epoch": 381.32,
+      "grad_norm": 0.02776075154542923,
+      "learning_rate": 1.5807560137457044e-05,
+      "loss": 0.0219,
+      "step": 1525
+    },
+    {
+      "epoch": 382.64,
+      "grad_norm": 0.02962840534746647,
+      "learning_rate": 1.5521191294387173e-05,
+      "loss": 0.0234,
+      "step": 1530
+    },
+    {
+      "epoch": 383.96,
+      "grad_norm": 0.028057308867573738,
+      "learning_rate": 1.5234822451317298e-05,
+      "loss": 0.0214,
+      "step": 1535
+    },
+    {
+      "epoch": 385.0,
+      "grad_norm": 0.09331432729959488,
+      "learning_rate": 1.4948453608247423e-05,
+      "loss": 0.0229,
+      "step": 1540
+    },
+    {
+      "epoch": 386.32,
+      "grad_norm": 0.0273224338889122,
+      "learning_rate": 1.466208476517755e-05,
+      "loss": 0.0213,
+      "step": 1545
+    },
+    {
+      "epoch": 387.64,
+      "grad_norm": 0.02868926338851452,
+      "learning_rate": 1.4375715922107674e-05,
+      "loss": 0.022,
+      "step": 1550
+    },
+    {
+      "epoch": 388.96,
+      "grad_norm": 0.03012736141681671,
+      "learning_rate": 1.40893470790378e-05,
+      "loss": 0.022,
+      "step": 1555
+    },
+    {
+      "epoch": 390.0,
+      "grad_norm": 0.0737493485212326,
+      "learning_rate": 1.3802978235967929e-05,
+      "loss": 0.021,
+      "step": 1560
+    },
+    {
+      "epoch": 391.32,
+      "grad_norm": 0.024876805022358894,
+      "learning_rate": 1.3516609392898052e-05,
+      "loss": 0.0223,
+      "step": 1565
+    },
+    {
+      "epoch": 392.64,
+      "grad_norm": 0.03155525028705597,
+      "learning_rate": 1.323024054982818e-05,
+      "loss": 0.0233,
+      "step": 1570
+    },
+    {
+      "epoch": 393.96,
+      "grad_norm": 0.024891577661037445,
+      "learning_rate": 1.2943871706758307e-05,
+      "loss": 0.0217,
+      "step": 1575
+    },
+    {
+      "epoch": 395.0,
+      "grad_norm": 0.08001179993152618,
+      "learning_rate": 1.2657502863688431e-05,
+      "loss": 0.0208,
+      "step": 1580
+    },
+    {
+      "epoch": 396.32,
+      "grad_norm": 0.027790989726781845,
+      "learning_rate": 1.2371134020618558e-05,
+      "loss": 0.0225,
+      "step": 1585
+    },
+    {
+      "epoch": 397.64,
+      "grad_norm": 0.025982750579714775,
+      "learning_rate": 1.2084765177548683e-05,
+      "loss": 0.0214,
+      "step": 1590
+    },
+    {
+      "epoch": 398.96,
+      "grad_norm": 0.030336298048496246,
+      "learning_rate": 1.1798396334478809e-05,
+      "loss": 0.0213,
+      "step": 1595
+    },
+    {
+      "epoch": 400.0,
+      "grad_norm": 0.08807449787855148,
+      "learning_rate": 1.1512027491408934e-05,
+      "loss": 0.0203,
+      "step": 1600
+    },
+    {
+      "epoch": 401.32,
+      "grad_norm": 0.029395850375294685,
+      "learning_rate": 1.1225658648339062e-05,
+      "loss": 0.0216,
+      "step": 1605
+    },
+    {
+      "epoch": 402.64,
+      "grad_norm": 0.026089362800121307,
+      "learning_rate": 1.0939289805269187e-05,
+      "loss": 0.0218,
+      "step": 1610
+    },
+    {
+      "epoch": 403.96,
+      "grad_norm": 0.026861408725380898,
+      "learning_rate": 1.0652920962199313e-05,
+      "loss": 0.0219,
+      "step": 1615
+    },
+    {
+      "epoch": 405.0,
+      "grad_norm": 0.10676798969507217,
+      "learning_rate": 1.036655211912944e-05,
+      "loss": 0.0223,
+      "step": 1620
+    },
+    {
+      "epoch": 406.32,
+      "grad_norm": 0.02716854028403759,
+      "learning_rate": 1.0080183276059566e-05,
+      "loss": 0.0215,
+      "step": 1625
+    },
+    {
+      "epoch": 407.64,
+      "grad_norm": 0.029034120962023735,
+      "learning_rate": 9.793814432989691e-06,
+      "loss": 0.0224,
+      "step": 1630
+    },
+    {
+      "epoch": 408.96,
+      "grad_norm": 0.027368783950805664,
+      "learning_rate": 9.507445589919818e-06,
+      "loss": 0.021,
+      "step": 1635
+    },
+    {
+      "epoch": 410.0,
+      "grad_norm": 0.10494464635848999,
+      "learning_rate": 9.221076746849944e-06,
+      "loss": 0.0217,
+      "step": 1640
+    },
+    {
+      "epoch": 411.32,
+      "grad_norm": 0.02767275646328926,
+      "learning_rate": 8.934707903780069e-06,
+      "loss": 0.0216,
+      "step": 1645
+    },
+    {
+      "epoch": 412.64,
+      "grad_norm": 0.02528652921319008,
+      "learning_rate": 8.648339060710195e-06,
+      "loss": 0.0213,
+      "step": 1650
+    },
+    {
+      "epoch": 413.96,
+      "grad_norm": 0.029360255226492882,
+      "learning_rate": 8.36197021764032e-06,
+      "loss": 0.0219,
+      "step": 1655
+    },
+    {
+      "epoch": 415.0,
+      "grad_norm": 0.09360278397798538,
+      "learning_rate": 8.075601374570448e-06,
+      "loss": 0.0217,
+      "step": 1660
+    },
+    {
+      "epoch": 416.32,
+      "grad_norm": 0.025939369574189186,
+      "learning_rate": 7.789232531500573e-06,
+      "loss": 0.0211,
+      "step": 1665
+    },
+    {
+      "epoch": 417.64,
+      "grad_norm": 0.030566802248358727,
+      "learning_rate": 7.502863688430699e-06,
+      "loss": 0.0221,
+      "step": 1670
+    },
+    {
+      "epoch": 418.96,
+      "grad_norm": 0.03019922599196434,
+      "learning_rate": 7.216494845360824e-06,
+      "loss": 0.0214,
+      "step": 1675
+    },
+    {
+      "epoch": 420.0,
+      "grad_norm": 0.08565034717321396,
+      "learning_rate": 6.930126002290952e-06,
+      "loss": 0.0221,
+      "step": 1680
+    },
+    {
+      "epoch": 421.32,
+      "grad_norm": 0.02598632499575615,
+      "learning_rate": 6.643757159221077e-06,
+      "loss": 0.022,
+      "step": 1685
+    },
+    {
+      "epoch": 422.64,
+      "grad_norm": 0.029259851202368736,
+      "learning_rate": 6.357388316151203e-06,
+      "loss": 0.022,
+      "step": 1690
+    },
+    {
+      "epoch": 423.96,
+      "grad_norm": 0.02969968505203724,
+      "learning_rate": 6.071019473081329e-06,
+      "loss": 0.0207,
+      "step": 1695
+    },
+    {
+      "epoch": 425.0,
+      "grad_norm": 0.1266016662120819,
+      "learning_rate": 5.784650630011455e-06,
+      "loss": 0.0234,
+      "step": 1700
+    },
+    {
+      "epoch": 426.32,
+      "grad_norm": 0.028426626697182655,
+      "learning_rate": 5.498281786941581e-06,
+      "loss": 0.0234,
+      "step": 1705
+    },
+    {
+      "epoch": 427.64,
+      "grad_norm": 0.025310739874839783,
+      "learning_rate": 5.211912943871707e-06,
+      "loss": 0.0216,
+      "step": 1710
+    },
+    {
+      "epoch": 428.96,
+      "grad_norm": 0.026703959330916405,
+      "learning_rate": 4.925544100801833e-06,
+      "loss": 0.022,
+      "step": 1715
+    },
+    {
+      "epoch": 430.0,
+      "grad_norm": 0.08460796624422073,
+      "learning_rate": 4.639175257731959e-06,
+      "loss": 0.0216,
+      "step": 1720
+    },
+    {
+      "epoch": 431.32,
+      "grad_norm": 0.029488299041986465,
+      "learning_rate": 4.352806414662085e-06,
+      "loss": 0.0214,
+      "step": 1725
+    },
+    {
+      "epoch": 432.64,
+      "grad_norm": 0.025535397231578827,
+      "learning_rate": 4.066437571592211e-06,
+      "loss": 0.0229,
+      "step": 1730
+    },
+    {
+      "epoch": 433.96,
+      "grad_norm": 0.02838149107992649,
+      "learning_rate": 3.7800687285223365e-06,
+      "loss": 0.0218,
+      "step": 1735
+    },
+    {
+      "epoch": 435.0,
+      "grad_norm": 0.09865429252386093,
+      "learning_rate": 3.493699885452463e-06,
+      "loss": 0.0212,
+      "step": 1740
+    },
+    {
+      "epoch": 436.32,
+      "grad_norm": 0.029500354081392288,
+      "learning_rate": 3.2073310423825886e-06,
+      "loss": 0.0214,
+      "step": 1745
+    },
+    {
+      "epoch": 437.64,
+      "grad_norm": 0.02420145459473133,
+      "learning_rate": 2.920962199312715e-06,
+      "loss": 0.0218,
+      "step": 1750
+    },
+    {
+      "epoch": 438.96,
+      "grad_norm": 0.027570409700274467,
+      "learning_rate": 2.6345933562428407e-06,
+      "loss": 0.0215,
+      "step": 1755
+    },
+    {
+      "epoch": 440.0,
+      "grad_norm": 0.08870929479598999,
+      "learning_rate": 2.3482245131729668e-06,
+      "loss": 0.022,
+      "step": 1760
+    },
+    {
+      "epoch": 441.32,
+      "grad_norm": 0.027623537927865982,
+      "learning_rate": 2.061855670103093e-06,
+      "loss": 0.0219,
+      "step": 1765
+    },
+    {
+      "epoch": 442.64,
+      "grad_norm": 0.027542902156710625,
+      "learning_rate": 1.7754868270332189e-06,
+      "loss": 0.0219,
+      "step": 1770
+    },
+    {
+      "epoch": 443.96,
+      "grad_norm": 0.029447708278894424,
+      "learning_rate": 1.4891179839633447e-06,
+      "loss": 0.0222,
+      "step": 1775
+    },
+    {
+      "epoch": 445.0,
+      "grad_norm": 0.07486788183450699,
+      "learning_rate": 1.202749140893471e-06,
+      "loss": 0.02,
+      "step": 1780
+    },
+    {
+      "epoch": 446.32,
+      "grad_norm": 0.02825229801237583,
+      "learning_rate": 9.163802978235968e-07,
+      "loss": 0.0211,
+      "step": 1785
+    },
+    {
+      "epoch": 447.64,
+      "grad_norm": 0.02755124121904373,
+      "learning_rate": 6.300114547537229e-07,
+      "loss": 0.0212,
+      "step": 1790
+    },
+    {
+      "epoch": 448.96,
+      "grad_norm": 0.02858681231737137,
+      "learning_rate": 3.436426116838488e-07,
+      "loss": 0.0224,
+      "step": 1795
+    },
+    {
+      "epoch": 450.0,
+      "grad_norm": 0.09043806791305542,
+      "learning_rate": 5.72737686139748e-08,
+      "loss": 0.021,
+      "step": 1800
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 450,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5308141101056e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

Math_QA/group_08/checkpoints/checkpoint-300/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/\u4e0d\u51bb\u7ed3Qwen\u8bad\u7ec3/models/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Math_QA/group_08/checkpoints/checkpoint-300/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

Math_QA/group_08/checkpoints/checkpoint-300/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

Math_QA/group_08/checkpoints/checkpoint-300/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Math_QA/group_08/checkpoints/checkpoint-300/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

Math_QA/group_08/checkpoints/checkpoint-300/trainer_state.json

@@ -0,0 +1,461 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 75.0,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "grad_norm": 10.268527030944824,
+      "learning_rate": 0.0,
+      "loss": 1.8412,
+      "step": 1
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 7.169743537902832,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.7908,
+      "step": 5
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 3.2965712547302246,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.541,
+      "step": 10
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 1.9259239435195923,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 1.195,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.5386537313461304,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.8407,
+      "step": 20
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.7439631223678589,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.7134,
+      "step": 25
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.5669045448303223,
+      "learning_rate": 5.370370370370371e-05,
+      "loss": 0.6253,
+      "step": 30
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.5955387353897095,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.5425,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.794498324394226,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.4517,
+      "step": 40
+    },
+    {
+      "epoch": 11.32,
+      "grad_norm": 0.6224164366722107,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.3649,
+      "step": 45
+    },
+    {
+      "epoch": 12.64,
+      "grad_norm": 0.7097190022468567,
+      "learning_rate": 9.074074074074075e-05,
+      "loss": 0.2806,
+      "step": 50
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 0.8385046124458313,
+      "learning_rate": 0.0001,
+      "loss": 0.2055,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 2.7302768230438232,
+      "learning_rate": 9.971363115693013e-05,
+      "loss": 0.1593,
+      "step": 60
+    },
+    {
+      "epoch": 16.32,
+      "grad_norm": 0.573469877243042,
+      "learning_rate": 9.942726231386026e-05,
+      "loss": 0.1173,
+      "step": 65
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 1.059529423713684,
+      "learning_rate": 9.914089347079038e-05,
+      "loss": 0.0856,
+      "step": 70
+    },
+    {
+      "epoch": 18.96,
+      "grad_norm": 0.6318557858467102,
+      "learning_rate": 9.885452462772051e-05,
+      "loss": 0.0783,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.4067771434783936,
+      "learning_rate": 9.856815578465064e-05,
+      "loss": 0.0684,
+      "step": 80
+    },
+    {
+      "epoch": 21.32,
+      "grad_norm": 0.3381839096546173,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 0.0351,
+      "step": 85
+    },
+    {
+      "epoch": 22.64,
+      "grad_norm": 0.3768102824687958,
+      "learning_rate": 9.799541809851088e-05,
+      "loss": 0.0296,
+      "step": 90
+    },
+    {
+      "epoch": 23.96,
+      "grad_norm": 0.21533846855163574,
+      "learning_rate": 9.7709049255441e-05,
+      "loss": 0.0296,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.729438841342926,
+      "learning_rate": 9.742268041237114e-05,
+      "loss": 0.0327,
+      "step": 100
+    },
+    {
+      "epoch": 26.32,
+      "grad_norm": 0.15956193208694458,
+      "learning_rate": 9.713631156930127e-05,
+      "loss": 0.0335,
+      "step": 105
+    },
+    {
+      "epoch": 27.64,
+      "grad_norm": 0.3089437186717987,
+      "learning_rate": 9.68499427262314e-05,
+      "loss": 0.0373,
+      "step": 110
+    },
+    {
+      "epoch": 28.96,
+      "grad_norm": 0.2873784303665161,
+      "learning_rate": 9.656357388316152e-05,
+      "loss": 0.028,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.3081432282924652,
+      "learning_rate": 9.627720504009165e-05,
+      "loss": 0.0288,
+      "step": 120
+    },
+    {
+      "epoch": 31.32,
+      "grad_norm": 0.15154343843460083,
+      "learning_rate": 9.599083619702178e-05,
+      "loss": 0.0258,
+      "step": 125
+    },
+    {
+      "epoch": 32.64,
+      "grad_norm": 0.21917082369327545,
+      "learning_rate": 9.57044673539519e-05,
+      "loss": 0.0276,
+      "step": 130
+    },
+    {
+      "epoch": 33.96,
+      "grad_norm": 0.4817427396774292,
+      "learning_rate": 9.541809851088203e-05,
+      "loss": 0.028,
+      "step": 135
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.9411588311195374,
+      "learning_rate": 9.513172966781214e-05,
+      "loss": 0.0301,
+      "step": 140
+    },
+    {
+      "epoch": 36.32,
+      "grad_norm": 0.12594084441661835,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.0278,
+      "step": 145
+    },
+    {
+      "epoch": 37.64,
+      "grad_norm": 0.09696595370769501,
+      "learning_rate": 9.45589919816724e-05,
+      "loss": 0.0254,
+      "step": 150
+    },
+    {
+      "epoch": 38.96,
+      "grad_norm": 0.07912517338991165,
+      "learning_rate": 9.427262313860252e-05,
+      "loss": 0.0253,
+      "step": 155
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.16622836887836456,
+      "learning_rate": 9.398625429553265e-05,
+      "loss": 0.0244,
+      "step": 160
+    },
+    {
+      "epoch": 41.32,
+      "grad_norm": 0.0670735314488411,
+      "learning_rate": 9.369988545246277e-05,
+      "loss": 0.0246,
+      "step": 165
+    },
+    {
+      "epoch": 42.64,
+      "grad_norm": 0.06884271651506424,
+      "learning_rate": 9.34135166093929e-05,
+      "loss": 0.0228,
+      "step": 170
+    },
+    {
+      "epoch": 43.96,
+      "grad_norm": 0.1034952700138092,
+      "learning_rate": 9.312714776632303e-05,
+      "loss": 0.0242,
+      "step": 175
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 0.1411074995994568,
+      "learning_rate": 9.284077892325315e-05,
+      "loss": 0.0237,
+      "step": 180
+    },
+    {
+      "epoch": 46.32,
+      "grad_norm": 0.06430694460868835,
+      "learning_rate": 9.255441008018328e-05,
+      "loss": 0.0244,
+      "step": 185
+    },
+    {
+      "epoch": 47.64,
+      "grad_norm": 0.06416841596364975,
+      "learning_rate": 9.22680412371134e-05,
+      "loss": 0.0253,
+      "step": 190
+    },
+    {
+      "epoch": 48.96,
+      "grad_norm": 0.05058900639414787,
+      "learning_rate": 9.198167239404353e-05,
+      "loss": 0.0234,
+      "step": 195
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.17872126400470734,
+      "learning_rate": 9.169530355097366e-05,
+      "loss": 0.0247,
+      "step": 200
+    },
+    {
+      "epoch": 51.32,
+      "grad_norm": 0.05059915408492088,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.0248,
+      "step": 205
+    },
+    {
+      "epoch": 52.64,
+      "grad_norm": 0.05440365895628929,
+      "learning_rate": 9.112256586483391e-05,
+      "loss": 0.0254,
+      "step": 210
+    },
+    {
+      "epoch": 53.96,
+      "grad_norm": 0.05572507157921791,
+      "learning_rate": 9.083619702176404e-05,
+      "loss": 0.0245,
+      "step": 215
+    },
+    {
+      "epoch": 55.0,
+      "grad_norm": 0.13678045570850372,
+      "learning_rate": 9.054982817869416e-05,
+      "loss": 0.0226,
+      "step": 220
+    },
+    {
+      "epoch": 56.32,
+      "grad_norm": 0.05588487163186073,
+      "learning_rate": 9.026345933562429e-05,
+      "loss": 0.0243,
+      "step": 225
+    },
+    {
+      "epoch": 57.64,
+      "grad_norm": 0.052309829741716385,
+      "learning_rate": 8.997709049255442e-05,
+      "loss": 0.0236,
+      "step": 230
+    },
+    {
+      "epoch": 58.96,
+      "grad_norm": 0.056767936795949936,
+      "learning_rate": 8.969072164948454e-05,
+      "loss": 0.0226,
+      "step": 235
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.24060668051242828,
+      "learning_rate": 8.940435280641467e-05,
+      "loss": 0.0232,
+      "step": 240
+    },
+    {
+      "epoch": 61.32,
+      "grad_norm": 0.05159705877304077,
+      "learning_rate": 8.91179839633448e-05,
+      "loss": 0.0231,
+      "step": 245
+    },
+    {
+      "epoch": 62.64,
+      "grad_norm": 0.053261805325746536,
+      "learning_rate": 8.883161512027491e-05,
+      "loss": 0.0231,
+      "step": 250
+    },
+    {
+      "epoch": 63.96,
+      "grad_norm": 0.05033772811293602,
+      "learning_rate": 8.854524627720504e-05,
+      "loss": 0.0243,
+      "step": 255
+    },
+    {
+      "epoch": 65.0,
+      "grad_norm": 0.1512952744960785,
+      "learning_rate": 8.825887743413516e-05,
+      "loss": 0.0245,
+      "step": 260
+    },
+    {
+      "epoch": 66.32,
+      "grad_norm": 0.057306934148073196,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 0.0232,
+      "step": 265
+    },
+    {
+      "epoch": 67.64,
+      "grad_norm": 0.04558086022734642,
+      "learning_rate": 8.768613974799542e-05,
+      "loss": 0.0223,
+      "step": 270
+    },
+    {
+      "epoch": 68.96,
+      "grad_norm": 0.04183197394013405,
+      "learning_rate": 8.739977090492554e-05,
+      "loss": 0.0259,
+      "step": 275
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.15279851853847504,
+      "learning_rate": 8.711340206185567e-05,
+      "loss": 0.0231,
+      "step": 280
+    },
+    {
+      "epoch": 71.32,
+      "grad_norm": 0.04648765176534653,
+      "learning_rate": 8.682703321878581e-05,
+      "loss": 0.0247,
+      "step": 285
+    },
+    {
+      "epoch": 72.64,
+      "grad_norm": 0.05621657893061638,
+      "learning_rate": 8.654066437571594e-05,
+      "loss": 0.0241,
+      "step": 290
+    },
+    {
+      "epoch": 73.96,
+      "grad_norm": 0.05430695042014122,
+      "learning_rate": 8.625429553264606e-05,
+      "loss": 0.0224,
+      "step": 295
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.13658379018306732,
+      "learning_rate": 8.596792668957619e-05,
+      "loss": 0.0244,
+      "step": 300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 450,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.551356850176e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

Math_QA/group_08/checkpoints/checkpoint-600/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/不冻结Qwen训练/models/Qwen2.5-1.5B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

Math_QA/group_08/checkpoints/checkpoint-600/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/\u4e0d\u51bb\u7ed3Qwen\u8bad\u7ec3/models/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}