Upload folder using huggingface_hub

checkpoint-5200/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Qwen/Qwen-VL-Chat
+---
+
+# 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 0.10.0

checkpoint-5200/adapter_config.json

@@ -0,0 +1,380 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen-VL-Chat",
+  "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": 16,
+  "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": [
+    "transformer.h.16.mlp.w1",
+    "transformer.visual.transformer.resblocks.13.attn.out_proj",
+    "transformer.h.28.mlp.w1",
+    "transformer.h.16.attn.c_attn",
+    "transformer.h.3.mlp.w1",
+    "transformer.visual.transformer.resblocks.29.attn.in_proj",
+    "transformer.visual.transformer.resblocks.19.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.47.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.34.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.4.attn.out_proj",
+    "transformer.h.31.attn.c_attn",
+    "transformer.h.16.mlp.w2",
+    "transformer.visual.transformer.resblocks.5.attn.out_proj",
+    "transformer.h.2.mlp.w1",
+    "transformer.visual.transformer.resblocks.7.attn.in_proj",
+    "transformer.h.20.mlp.w2",
+    "transformer.h.19.mlp.w1",
+    "transformer.visual.transformer.resblocks.18.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.27.attn.out_proj",
+    "transformer.visual.transformer.resblocks.10.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.43.mlp.c_fc",
+    "transformer.h.5.mlp.w1",
+    "transformer.visual.transformer.resblocks.15.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.25.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.10.attn.out_proj",
+    "transformer.visual.transformer.resblocks.4.mlp.c_fc",
+    "transformer.h.31.mlp.w2",
+    "transformer.visual.transformer.resblocks.37.attn.out_proj",
+    "transformer.h.8.attn.c_proj",
+    "transformer.h.29.attn.c_attn",
+    "transformer.visual.transformer.resblocks.24.mlp.c_proj",
+    "transformer.h.19.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.11.attn.out_proj",
+    "transformer.h.13.mlp.c_proj",
+    "transformer.h.27.mlp.c_proj",
+    "transformer.h.31.mlp.w1",
+    "transformer.visual.transformer.resblocks.7.mlp.c_proj",
+    "transformer.h.28.mlp.w2",
+    "transformer.visual.transformer.resblocks.3.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.13.attn.in_proj",
+    "transformer.h.21.attn.c_attn",
+    "transformer.visual.transformer.resblocks.23.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.33.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.42.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.3.attn.in_proj",
+    "transformer.h.13.mlp.w1",
+    "transformer.visual.transformer.resblocks.22.attn.out_proj",
+    "transformer.visual.transformer.resblocks.20.mlp.c_fc",
+    "transformer.h.26.mlp.w2",
+    "transformer.h.14.attn.c_attn",
+    "transformer.h.16.attn.c_proj",
+    "transformer.h.1.mlp.w1",
+    "transformer.visual.transformer.resblocks.21.attn.out_proj",
+    "transformer.visual.transformer.resblocks.39.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.4.attn.in_proj",
+    "transformer.h.29.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.12.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.14.attn.in_proj",
+    "transformer.h.28.attn.c_proj",
+    "transformer.h.18.mlp.w1",
+    "transformer.h.27.mlp.w2",
+    "transformer.h.18.attn.c_attn",
+    "transformer.visual.transformer.resblocks.33.attn.out_proj",
+    "transformer.h.5.mlp.w2",
+    "transformer.visual.transformer.resblocks.37.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.2.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.42.attn.out_proj",
+    "transformer.visual.transformer.resblocks.15.attn.in_proj",
+    "transformer.visual.transformer.resblocks.6.mlp.c_fc",
+    "transformer.h.13.mlp.w2",
+    "transformer.h.23.attn.c_proj",
+    "transformer.h.20.mlp.c_proj",
+    "transformer.h.14.mlp.w2",
+    "transformer.visual.transformer.resblocks.9.attn.in_proj",
+    "transformer.visual.transformer.resblocks.46.attn.in_proj",
+    "transformer.h.9.attn.c_attn",
+    "transformer.visual.transformer.resblocks.36.mlp.c_proj",
+    "transformer.h.31.attn.c_proj",
+    "transformer.visual.transformer.resblocks.19.mlp.c_fc",
+    "transformer.h.17.mlp.w1",
+    "transformer.h.2.attn.c_proj",
+    "transformer.visual.transformer.resblocks.47.attn.in_proj",
+    "transformer.visual.transformer.resblocks.45.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.46.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.27.attn.in_proj",
+    "transformer.visual.transformer.resblocks.26.attn.out_proj",
+    "transformer.h.22.attn.c_proj",
+    "transformer.visual.transformer.resblocks.40.attn.out_proj",
+    "transformer.visual.transformer.resblocks.46.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.18.attn.out_proj",
+    "transformer.h.27.attn.c_proj",
+    "transformer.visual.transformer.resblocks.26.attn.in_proj",
+    "transformer.h.4.mlp.w1",
+    "transformer.h.10.attn.c_proj",
+    "transformer.h.6.attn.c_attn",
+    "transformer.h.2.attn.c_attn",
+    "transformer.h.22.mlp.w1",
+    "transformer.visual.transformer.resblocks.39.mlp.c_fc",
+    "transformer.h.8.mlp.w2",
+    "transformer.h.4.attn.c_attn",
+    "transformer.h.26.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.29.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.5.mlp.c_proj",
+    "transformer.h.11.mlp.c_proj",
+    "transformer.h.0.mlp.w2",
+    "transformer.visual.transformer.resblocks.36.attn.out_proj",
+    "transformer.h.29.mlp.w1",
+    "transformer.h.12.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.2.attn.in_proj",
+    "transformer.visual.transformer.resblocks.2.mlp.c_fc",
+    "transformer.h.25.attn.c_attn",
+    "transformer.visual.transformer.resblocks.19.attn.in_proj",
+    "transformer.visual.transformer.resblocks.43.attn.out_proj",
+    "transformer.visual.transformer.resblocks.35.attn.out_proj",
+    "transformer.h.22.attn.c_attn",
+    "transformer.h.0.mlp.w1",
+    "transformer.h.3.attn.c_attn",
+    "transformer.h.28.attn.c_attn",
+    "transformer.visual.transformer.resblocks.25.attn.in_proj",
+    "transformer.visual.transformer.resblocks.34.attn.out_proj",
+    "transformer.h.21.attn.c_proj",
+    "transformer.h.6.attn.c_proj",
+    "transformer.visual.transformer.resblocks.11.mlp.c_proj",
+    "transformer.h.13.attn.c_attn",
+    "transformer.visual.transformer.resblocks.38.attn.out_proj",
+    "transformer.h.3.attn.c_proj",
+    "transformer.visual.transformer.resblocks.17.mlp.c_fc",
+    "transformer.h.26.mlp.w1",
+    "transformer.visual.transformer.resblocks.36.mlp.c_fc",
+    "transformer.h.26.attn.c_attn",
+    "transformer.visual.transformer.resblocks.29.attn.out_proj",
+    "transformer.h.7.mlp.w1",
+    "transformer.visual.transformer.resblocks.40.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.9.attn.out_proj",
+    "transformer.h.3.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.26.mlp.c_fc",
+    "transformer.h.11.mlp.w2",
+    "transformer.visual.transformer.resblocks.33.attn.in_proj",
+    "transformer.visual.transformer.resblocks.42.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.32.attn.out_proj",
+    "transformer.h.4.attn.c_proj",
+    "transformer.visual.transformer.resblocks.27.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.11.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.25.attn.out_proj",
+    "transformer.visual.transformer.resblocks.23.attn.in_proj",
+    "transformer.h.5.attn.c_attn",
+    "transformer.h.16.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.14.mlp.c_proj",
+    "transformer.h.22.mlp.w2",
+    "transformer.h.25.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.10.mlp.c_fc",
+    "transformer.h.24.mlp.c_proj",
+    "transformer.h.19.mlp.w2",
+    "transformer.h.14.mlp.w1",
+    "transformer.visual.transformer.resblocks.40.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.28.attn.out_proj",
+    "transformer.visual.transformer.resblocks.24.mlp.c_fc",
+    "transformer.h.8.attn.c_attn",
+    "transformer.h.9.mlp.w1",
+    "transformer.h.6.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.19.attn.out_proj",
+    "transformer.visual.transformer.resblocks.32.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.7.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.44.attn.in_proj",
+    "transformer.visual.transformer.resblocks.34.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.9.mlp.c_fc",
+    "transformer.visual.conv1",
+    "transformer.visual.transformer.resblocks.8.attn.out_proj",
+    "transformer.h.23.mlp.w2",
+    "transformer.h.7.mlp.w2",
+    "transformer.h.24.attn.c_proj",
+    "transformer.h.30.attn.c_proj",
+    "transformer.h.29.attn.c_proj",
+    "transformer.visual.transformer.resblocks.9.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.35.attn.in_proj",
+    "transformer.visual.transformer.resblocks.21.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.41.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.38.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.13.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.41.attn.out_proj",
+    "transformer.visual.transformer.resblocks.16.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.45.attn.out_proj",
+    "transformer.h.11.mlp.w1",
+    "transformer.visual.transformer.resblocks.16.attn.in_proj",
+    "transformer.visual.transformer.resblocks.47.attn.out_proj",
+    "transformer.h.9.attn.c_proj",
+    "transformer.h.31.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.12.attn.in_proj",
+    "transformer.visual.transformer.resblocks.28.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.20.attn.out_proj",
+    "transformer.h.12.attn.c_attn",
+    "transformer.h.24.mlp.w1",
+    "transformer.visual.transformer.resblocks.21.attn.in_proj",
+    "transformer.visual.transformer.resblocks.41.attn.in_proj",
+    "transformer.h.10.mlp.w1",
+    "transformer.h.1.mlp.w2",
+    "transformer.h.0.mlp.c_proj",
+    "transformer.h.22.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.18.attn.in_proj",
+    "transformer.visual.transformer.resblocks.38.mlp.c_proj",
+    "transformer.h.12.mlp.w1",
+    "transformer.h.1.attn.c_attn",
+    "transformer.visual.transformer.resblocks.31.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.44.mlp.c_proj",
+    "transformer.h.15.mlp.c_proj",
+    "transformer.h.6.mlp.w1",
+    "transformer.visual.transformer.resblocks.16.mlp.c_proj",
+    "transformer.h.13.attn.c_proj",
+    "transformer.h.15.attn.c_attn",
+    "transformer.h.15.mlp.w1",
+    "transformer.h.17.mlp.w2",
+    "transformer.visual.transformer.resblocks.10.attn.in_proj",
+    "transformer.h.26.attn.c_proj",
+    "transformer.visual.transformer.resblocks.20.attn.in_proj",
+    "transformer.h.10.mlp.w2",
+    "transformer.h.24.attn.c_attn",
+    "transformer.h.8.mlp.w1",
+    "transformer.h.23.mlp.w1",
+    "transformer.visual.transformer.resblocks.1.mlp.c_proj",
+    "transformer.h.4.mlp.w2",
+    "transformer.visual.transformer.resblocks.38.attn.in_proj",
+    "transformer.h.12.mlp.w2",
+    "transformer.h.7.attn.c_proj",
+    "transformer.h.4.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.31.attn.out_proj",
+    "transformer.visual.transformer.resblocks.17.mlp.c_proj",
+    "transformer.h.21.mlp.w2",
+    "transformer.visual.transformer.resblocks.5.attn.in_proj",
+    "transformer.h.18.attn.c_proj",
+    "transformer.visual.transformer.resblocks.31.mlp.c_fc",
+    "transformer.h.18.mlp.w2",
+    "transformer.visual.transformer.resblocks.6.attn.out_proj",
+    "transformer.visual.transformer.resblocks.8.attn.in_proj",
+    "transformer.visual.transformer.resblocks.30.mlp.c_proj",
+    "transformer.h.30.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.30.attn.out_proj",
+    "transformer.visual.transformer.resblocks.16.attn.out_proj",
+    "transformer.visual.transformer.resblocks.14.attn.out_proj",
+    "transformer.h.25.mlp.w1",
+    "transformer.visual.transformer.resblocks.45.attn.in_proj",
+    "transformer.h.11.attn.c_proj",
+    "transformer.visual.transformer.resblocks.30.attn.in_proj",
+    "transformer.visual.transformer.resblocks.43.mlp.c_proj",
+    "transformer.h.10.mlp.c_proj",
+    "transformer.h.21.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.43.attn.in_proj",
+    "transformer.visual.transformer.resblocks.3.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.44.attn.out_proj",
+    "transformer.h.23.attn.c_attn",
+    "transformer.visual.transformer.resblocks.22.attn.in_proj",
+    "transformer.visual.transformer.resblocks.6.attn.in_proj",
+    "transformer.visual.transformer.resblocks.44.mlp.c_fc",
+    "transformer.h.17.attn.c_attn",
+    "transformer.h.7.attn.c_attn",
+    "transformer.visual.transformer.resblocks.42.attn.in_proj",
+    "transformer.visual.transformer.resblocks.20.mlp.c_proj",
+    "transformer.h.8.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.17.attn.out_proj",
+    "transformer.h.14.attn.c_proj",
+    "transformer.visual.transformer.resblocks.40.attn.in_proj",
+    "transformer.h.25.attn.c_proj",
+    "transformer.h.28.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.35.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.36.attn.in_proj",
+    "transformer.visual.transformer.resblocks.41.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.14.mlp.c_fc",
+    "transformer.h.30.mlp.w2",
+    "transformer.h.20.mlp.w1",
+    "transformer.visual.transformer.resblocks.33.mlp.c_fc",
+    "transformer.h.29.mlp.w2",
+    "transformer.visual.transformer.resblocks.47.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.30.mlp.c_fc",
+    "transformer.h.10.attn.c_attn",
+    "transformer.visual.transformer.resblocks.1.attn.in_proj",
+    "transformer.h.1.attn.c_proj",
+    "transformer.visual.transformer.resblocks.8.mlp.c_proj",
+    "transformer.h.19.attn.c_proj",
+    "transformer.visual.transformer.resblocks.37.attn.in_proj",
+    "transformer.h.15.attn.c_proj",
+    "transformer.h.5.attn.c_proj",
+    "transformer.visual.transformer.resblocks.32.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.3.attn.out_proj",
+    "transformer.visual.transformer.resblocks.32.attn.in_proj",
+    "transformer.h.21.mlp.w1",
+    "transformer.h.23.mlp.c_proj",
+    "transformer.h.30.mlp.w1",
+    "transformer.h.0.attn.c_attn",
+    "transformer.visual.transformer.resblocks.24.attn.out_proj",
+    "transformer.visual.transformer.resblocks.31.attn.in_proj",
+    "transformer.h.18.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.25.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.22.mlp.c_fc",
+    "transformer.h.30.attn.c_attn",
+    "transformer.visual.transformer.resblocks.13.mlp.c_fc",
+    "transformer.h.17.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.24.attn.in_proj",
+    "transformer.h.11.attn.c_attn",
+    "transformer.h.2.mlp.w2",
+    "transformer.visual.transformer.resblocks.8.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.0.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.2.attn.out_proj",
+    "transformer.visual.transformer.resblocks.35.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.39.attn.out_proj",
+    "transformer.h.12.attn.c_proj",
+    "transformer.visual.transformer.resblocks.28.attn.in_proj",
+    "transformer.visual.transformer.resblocks.29.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.0.attn.out_proj",
+    "transformer.visual.transformer.resblocks.23.mlp.c_proj",
+    "transformer.h.20.attn.c_attn",
+    "transformer.visual.transformer.resblocks.7.attn.out_proj",
+    "transformer.visual.transformer.resblocks.15.attn.out_proj",
+    "transformer.h.7.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.1.attn.out_proj",
+    "transformer.h.3.mlp.w2",
+    "transformer.h.9.mlp.w2",
+    "transformer.visual.transformer.resblocks.34.attn.in_proj",
+    "transformer.h.27.attn.c_attn",
+    "transformer.visual.transformer.resblocks.12.mlp.c_fc",
+    "transformer.h.6.mlp.w2",
+    "transformer.visual.transformer.resblocks.39.attn.in_proj",
+    "transformer.h.15.mlp.w2",
+    "transformer.visual.transformer.resblocks.18.mlp.c_proj",
+    "transformer.h.0.attn.c_proj",
+    "transformer.h.19.attn.c_attn",
+    "transformer.visual.transformer.resblocks.27.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.23.attn.out_proj",
+    "transformer.h.14.mlp.c_proj",
+    "transformer.h.9.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.12.attn.out_proj",
+    "transformer.visual.transformer.resblocks.0.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.5.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.28.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.6.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.22.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.37.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.17.attn.in_proj",
+    "transformer.visual.transformer.resblocks.46.attn.out_proj",
+    "transformer.h.24.mlp.w2",
+    "transformer.h.27.mlp.w1",
+    "transformer.visual.transformer.resblocks.11.attn.in_proj",
+    "transformer.visual.transformer.resblocks.4.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.21.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.26.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.15.mlp.c_fc",
+    "transformer.h.2.mlp.c_proj",
+    "transformer.h.1.mlp.c_proj",
+    "transformer.h.5.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.45.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.0.attn.in_proj",
+    "transformer.h.25.mlp.w2",
+    "transformer.h.20.attn.c_proj",
+    "transformer.h.17.attn.c_proj",
+    "transformer.visual.transformer.resblocks.1.mlp.c_fc"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-5200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b5ef3d5719113913692eeaa39ff4098b0ceeca314ccc84b6f04866cf6f4bf84
+size 469105640

checkpoint-5200/global_step5200/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a36c8f8e91a6bfe4799f43c7f8064ecbbe95908178c32e3e1ed88f350f75baf
+size 351761648

checkpoint-5200/global_step5200/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9338755c4a34fb5d9ed728f74c4be62bcecfdaa267dc244f91db4b18617370e
+size 351761776

checkpoint-5200/global_step5200/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d00898834b2f07b5e883b85c7ded4172d494edc03bcacb73ab507e5119b0f2f4
+size 351761776

checkpoint-5200/global_step5200/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a3e9f1e769c038f236cc51b66e0399264b05edda3ef0c50173a69c58ba65aa
+size 351761584

checkpoint-5200/global_step5200/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57846740e6e233c0a7c6df1c9af368d8bf525ff0b963a4a02233e904356bcdd2
+size 351763184

checkpoint-5200/global_step5200/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e6012072237cdcbcff539dcb5b9972fda4ba155b9e6c80dc9dea7b77f77c271
+size 351771440

checkpoint-5200/global_step5200/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d689c96bd309c72b6541317f37bb6905bacdec457610954646818ca2c5deb4ea
+size 351771632

checkpoint-5200/global_step5200/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:415bb6e9d58bca21160e721e81f707a09332b4f19646c9e950ee45eb6e609f69
+size 351771312

checkpoint-5200/global_step5200/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23c87fee1cad5b7e0e00e3e810b397f362a830c3b3fe62d1529e97e856b7eddd
+size 469584556

checkpoint-5200/latest

@@ -0,0 +1 @@
+global_step5200

checkpoint-5200/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e934de68459f0fc23e96e0ac510efe6f61c68d638e71ef316f857ba59de66289
+size 15920

checkpoint-5200/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9db7709767592d9eeaed9c579550e0424175e4d8a3f205ec83524eb2c69b5c60
+size 15920

checkpoint-5200/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5c7b815b768d669cc970352d0c2bf61c905dcc23ae46efb0d3797444c368124
+size 15920

checkpoint-5200/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b95ffedd1d351c277ed06becb1d243c8b61e6ddc55eab23d02bb5ac65fb136f6
+size 15920

checkpoint-5200/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ebe43a0375e33568487bb2a1effa1d2ece7954bdaa4da4cfa6bf7bf7643d5e8
+size 15920

checkpoint-5200/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:815cc6c68d60fda371c499224bbaf36c22763c1fefa24ebb2e006c41f09e9266
+size 15920

checkpoint-5200/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce78992c6a2a427ab1b8f086ecfb531b3e90a0578817c096b9fdcc696cdec2d1
+size 15920

checkpoint-5200/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:854cf6b32562e4235b76c377b821d14174ff9d710e00399c2ca8a60a5aede63f
+size 15920

checkpoint-5200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbace2fb3eb63840abd6b9d3fe5a52009d4d02f90fb4dc45f21ea2c505f2d544
+size 1064

checkpoint-5200/special_tokens_map.json

@@ -0,0 +1,3 @@
+{
+  "pad_token": "<|endoftext|>"
+}

checkpoint-5200/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "added_tokens_decoder": {},
+  "auto_map": {
+    "AutoTokenizer": [
+      "Qwen/Qwen-VL-Chat--tokenization_qwen.QWenTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "QWenTokenizer"
+}

checkpoint-5200/trainer_state.json

@@ -0,0 +1,3673 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3393591333289826,
+  "eval_steps": 500,
+  "global_step": 5200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0006526137179403511,
+      "grad_norm": 17.690582114691438,
+      "learning_rate": 1.948051948051948e-06,
+      "loss": 1.3559,
+      "step": 10
+    },
+    {
+      "epoch": 0.0013052274358807021,
+      "grad_norm": 7.768088366444893,
+      "learning_rate": 3.896103896103896e-06,
+      "loss": 1.2706,
+      "step": 20
+    },
+    {
+      "epoch": 0.001957841153821053,
+      "grad_norm": 7.705313536090087,
+      "learning_rate": 5.844155844155845e-06,
+      "loss": 1.3781,
+      "step": 30
+    },
+    {
+      "epoch": 0.0026104548717614043,
+      "grad_norm": 34.39078827766783,
+      "learning_rate": 7.792207792207792e-06,
+      "loss": 1.2749,
+      "step": 40
+    },
+    {
+      "epoch": 0.0032630685897017554,
+      "grad_norm": 68.28824334896528,
+      "learning_rate": 9.74025974025974e-06,
+      "loss": 1.2955,
+      "step": 50
+    },
+    {
+      "epoch": 0.003915682307642106,
+      "grad_norm": 14.220322607917241,
+      "learning_rate": 1.168831168831169e-05,
+      "loss": 1.2315,
+      "step": 60
+    },
+    {
+      "epoch": 0.0045682960255824575,
+      "grad_norm": 12.611848231734811,
+      "learning_rate": 1.3636363636363637e-05,
+      "loss": 1.0953,
+      "step": 70
+    },
+    {
+      "epoch": 0.0052209097435228086,
+      "grad_norm": 6.055664298727015,
+      "learning_rate": 1.5584415584415583e-05,
+      "loss": 1.105,
+      "step": 80
+    },
+    {
+      "epoch": 0.00587352346146316,
+      "grad_norm": 3.52269227801977,
+      "learning_rate": 1.753246753246753e-05,
+      "loss": 0.9563,
+      "step": 90
+    },
+    {
+      "epoch": 0.006526137179403511,
+      "grad_norm": 10.771884023354394,
+      "learning_rate": 1.948051948051948e-05,
+      "loss": 0.9523,
+      "step": 100
+    },
+    {
+      "epoch": 0.007178750897343862,
+      "grad_norm": 33.41476483216757,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.832,
+      "step": 110
+    },
+    {
+      "epoch": 0.007831364615284213,
+      "grad_norm": 31.120240364617406,
+      "learning_rate": 2.337662337662338e-05,
+      "loss": 0.8376,
+      "step": 120
+    },
+    {
+      "epoch": 0.008483978333224564,
+      "grad_norm": 5.517231564060886,
+      "learning_rate": 2.5324675324675325e-05,
+      "loss": 0.8293,
+      "step": 130
+    },
+    {
+      "epoch": 0.009136592051164915,
+      "grad_norm": 4.311605388342058,
+      "learning_rate": 2.7272727272727273e-05,
+      "loss": 0.8295,
+      "step": 140
+    },
+    {
+      "epoch": 0.009789205769105266,
+      "grad_norm": 6.997724163121519,
+      "learning_rate": 2.922077922077922e-05,
+      "loss": 0.7662,
+      "step": 150
+    },
+    {
+      "epoch": 0.010441819487045617,
+      "grad_norm": 6.517836234400708,
+      "learning_rate": 2.999998841890695e-05,
+      "loss": 0.8158,
+      "step": 160
+    },
+    {
+      "epoch": 0.011094433204985968,
+      "grad_norm": 4.186989141019666,
+      "learning_rate": 2.99999176456253e-05,
+      "loss": 0.8037,
+      "step": 170
+    },
+    {
+      "epoch": 0.01174704692292632,
+      "grad_norm": 5.181546943355458,
+      "learning_rate": 2.9999782533305785e-05,
+      "loss": 0.7274,
+      "step": 180
+    },
+    {
+      "epoch": 0.01239966064086667,
+      "grad_norm": 3.767076521211455,
+      "learning_rate": 2.9999583082527935e-05,
+      "loss": 0.7474,
+      "step": 190
+    },
+    {
+      "epoch": 0.013052274358807021,
+      "grad_norm": 18.84416377940188,
+      "learning_rate": 2.999931929414726e-05,
+      "loss": 0.7708,
+      "step": 200
+    },
+    {
+      "epoch": 0.013704888076747372,
+      "grad_norm": 3.169160630444992,
+      "learning_rate": 2.999899116929522e-05,
+      "loss": 0.8279,
+      "step": 210
+    },
+    {
+      "epoch": 0.014357501794687724,
+      "grad_norm": 1.912782077307437,
+      "learning_rate": 2.999859870937924e-05,
+      "loss": 0.7407,
+      "step": 220
+    },
+    {
+      "epoch": 0.015010115512628075,
+      "grad_norm": 3.3906505952914974,
+      "learning_rate": 2.9998141916082696e-05,
+      "loss": 0.7732,
+      "step": 230
+    },
+    {
+      "epoch": 0.015662729230568426,
+      "grad_norm": 2.7144492322383584,
+      "learning_rate": 2.999762079136491e-05,
+      "loss": 0.7272,
+      "step": 240
+    },
+    {
+      "epoch": 0.01631534294850878,
+      "grad_norm": 7.109330196029837,
+      "learning_rate": 2.9997035337461135e-05,
+      "loss": 0.7748,
+      "step": 250
+    },
+    {
+      "epoch": 0.016967956666449128,
+      "grad_norm": 1.6054280593801813,
+      "learning_rate": 2.9996385556882555e-05,
+      "loss": 0.7676,
+      "step": 260
+    },
+    {
+      "epoch": 0.01762057038438948,
+      "grad_norm": 10.883212441614672,
+      "learning_rate": 2.9995671452416274e-05,
+      "loss": 0.735,
+      "step": 270
+    },
+    {
+      "epoch": 0.01827318410232983,
+      "grad_norm": 3.511064886507805,
+      "learning_rate": 2.999489302712529e-05,
+      "loss": 0.7741,
+      "step": 280
+    },
+    {
+      "epoch": 0.018925797820270183,
+      "grad_norm": 3.618603818375307,
+      "learning_rate": 2.9994050284348497e-05,
+      "loss": 0.749,
+      "step": 290
+    },
+    {
+      "epoch": 0.019578411538210532,
+      "grad_norm": 6.012944880342178,
+      "learning_rate": 2.9993143227700668e-05,
+      "loss": 0.7411,
+      "step": 300
+    },
+    {
+      "epoch": 0.020231025256150885,
+      "grad_norm": 2.348670372295822,
+      "learning_rate": 2.9992171861072428e-05,
+      "loss": 0.7394,
+      "step": 310
+    },
+    {
+      "epoch": 0.020883638974091234,
+      "grad_norm": 4.728309497649916,
+      "learning_rate": 2.9991136188630263e-05,
+      "loss": 0.8077,
+      "step": 320
+    },
+    {
+      "epoch": 0.021536252692031587,
+      "grad_norm": 15.611917863290122,
+      "learning_rate": 2.9990036214816467e-05,
+      "loss": 0.7209,
+      "step": 330
+    },
+    {
+      "epoch": 0.022188866409971936,
+      "grad_norm": 3.7315277354070817,
+      "learning_rate": 2.998887194434916e-05,
+      "loss": 0.7101,
+      "step": 340
+    },
+    {
+      "epoch": 0.02284148012791229,
+      "grad_norm": 6.618759094750745,
+      "learning_rate": 2.998764338222222e-05,
+      "loss": 0.7759,
+      "step": 350
+    },
+    {
+      "epoch": 0.02349409384585264,
+      "grad_norm": 6.770044306239603,
+      "learning_rate": 2.998635053370533e-05,
+      "loss": 0.7398,
+      "step": 360
+    },
+    {
+      "epoch": 0.02414670756379299,
+      "grad_norm": 12.471224202357552,
+      "learning_rate": 2.998499340434389e-05,
+      "loss": 0.7046,
+      "step": 370
+    },
+    {
+      "epoch": 0.02479932128173334,
+      "grad_norm": 4.147359416986547,
+      "learning_rate": 2.9983571999959013e-05,
+      "loss": 0.761,
+      "step": 380
+    },
+    {
+      "epoch": 0.025451934999673693,
+      "grad_norm": 34.84722866603778,
+      "learning_rate": 2.9982086326647533e-05,
+      "loss": 0.757,
+      "step": 390
+    },
+    {
+      "epoch": 0.026104548717614043,
+      "grad_norm": 5.245498180313093,
+      "learning_rate": 2.998053639078193e-05,
+      "loss": 0.7536,
+      "step": 400
+    },
+    {
+      "epoch": 0.026757162435554396,
+      "grad_norm": 36.55990241841121,
+      "learning_rate": 2.997892219901034e-05,
+      "loss": 0.7395,
+      "step": 410
+    },
+    {
+      "epoch": 0.027409776153494745,
+      "grad_norm": 5.03198653806696,
+      "learning_rate": 2.9977243758256494e-05,
+      "loss": 0.7208,
+      "step": 420
+    },
+    {
+      "epoch": 0.028062389871435098,
+      "grad_norm": 11.376914733036081,
+      "learning_rate": 2.997550107571972e-05,
+      "loss": 0.719,
+      "step": 430
+    },
+    {
+      "epoch": 0.028715003589375447,
+      "grad_norm": 2.958119684662306,
+      "learning_rate": 2.9973694158874898e-05,
+      "loss": 0.7271,
+      "step": 440
+    },
+    {
+      "epoch": 0.0293676173073158,
+      "grad_norm": 6.037096737490817,
+      "learning_rate": 2.9971823015472418e-05,
+      "loss": 0.7356,
+      "step": 450
+    },
+    {
+      "epoch": 0.03002023102525615,
+      "grad_norm": 5.3042973640363575,
+      "learning_rate": 2.9969887653538164e-05,
+      "loss": 0.7207,
+      "step": 460
+    },
+    {
+      "epoch": 0.030672844743196502,
+      "grad_norm": 2.4985603001745624,
+      "learning_rate": 2.996788808137347e-05,
+      "loss": 0.7769,
+      "step": 470
+    },
+    {
+      "epoch": 0.03132545846113685,
+      "grad_norm": 7.607065841315647,
+      "learning_rate": 2.9965824307555084e-05,
+      "loss": 0.7091,
+      "step": 480
+    },
+    {
+      "epoch": 0.03197807217907721,
+      "grad_norm": 4.322533035107957,
+      "learning_rate": 2.9963696340935144e-05,
+      "loss": 0.7114,
+      "step": 490
+    },
+    {
+      "epoch": 0.03263068589701756,
+      "grad_norm": 5.878565903250334,
+      "learning_rate": 2.9961504190641108e-05,
+      "loss": 0.7284,
+      "step": 500
+    },
+    {
+      "epoch": 0.033283299614957906,
+      "grad_norm": 5.0026507027119855,
+      "learning_rate": 2.9959247866075764e-05,
+      "loss": 0.6992,
+      "step": 510
+    },
+    {
+      "epoch": 0.033935913332898256,
+      "grad_norm": 7.12632150273901,
+      "learning_rate": 2.9956927376917137e-05,
+      "loss": 0.7285,
+      "step": 520
+    },
+    {
+      "epoch": 0.03458852705083861,
+      "grad_norm": 5.211123255860348,
+      "learning_rate": 2.9954542733118496e-05,
+      "loss": 0.7511,
+      "step": 530
+    },
+    {
+      "epoch": 0.03524114076877896,
+      "grad_norm": 9.925273547498618,
+      "learning_rate": 2.995209394490827e-05,
+      "loss": 0.7699,
+      "step": 540
+    },
+    {
+      "epoch": 0.03589375448671931,
+      "grad_norm": 7.418381681996765,
+      "learning_rate": 2.9949581022790025e-05,
+      "loss": 0.759,
+      "step": 550
+    },
+    {
+      "epoch": 0.03654636820465966,
+      "grad_norm": 4.352380973507467,
+      "learning_rate": 2.9947003977542423e-05,
+      "loss": 0.7537,
+      "step": 560
+    },
+    {
+      "epoch": 0.037198981922600016,
+      "grad_norm": 9.712842120769198,
+      "learning_rate": 2.9944362820219167e-05,
+      "loss": 0.7063,
+      "step": 570
+    },
+    {
+      "epoch": 0.037851595640540366,
+      "grad_norm": 5.757600819230482,
+      "learning_rate": 2.994165756214895e-05,
+      "loss": 0.7893,
+      "step": 580
+    },
+    {
+      "epoch": 0.038504209358480715,
+      "grad_norm": 5.529209601152462,
+      "learning_rate": 2.9938888214935426e-05,
+      "loss": 0.6771,
+      "step": 590
+    },
+    {
+      "epoch": 0.039156823076421064,
+      "grad_norm": 10.550479346499758,
+      "learning_rate": 2.9936054790457127e-05,
+      "loss": 0.737,
+      "step": 600
+    },
+    {
+      "epoch": 0.03980943679436142,
+      "grad_norm": 8.284279553451016,
+      "learning_rate": 2.9933157300867437e-05,
+      "loss": 0.7182,
+      "step": 610
+    },
+    {
+      "epoch": 0.04046205051230177,
+      "grad_norm": 8.18511648646326,
+      "learning_rate": 2.9930195758594542e-05,
+      "loss": 0.6901,
+      "step": 620
+    },
+    {
+      "epoch": 0.04111466423024212,
+      "grad_norm": 14.569754827631956,
+      "learning_rate": 2.9927170176341365e-05,
+      "loss": 0.7008,
+      "step": 630
+    },
+    {
+      "epoch": 0.04176727794818247,
+      "grad_norm": 4.214581273685441,
+      "learning_rate": 2.992408056708551e-05,
+      "loss": 0.7489,
+      "step": 640
+    },
+    {
+      "epoch": 0.042419891666122825,
+      "grad_norm": 10.038596627079452,
+      "learning_rate": 2.9920926944079224e-05,
+      "loss": 0.7649,
+      "step": 650
+    },
+    {
+      "epoch": 0.043072505384063174,
+      "grad_norm": 2.386544029221306,
+      "learning_rate": 2.9917709320849305e-05,
+      "loss": 0.7223,
+      "step": 660
+    },
+    {
+      "epoch": 0.043725119102003523,
+      "grad_norm": 8.286359254511249,
+      "learning_rate": 2.9914427711197096e-05,
+      "loss": 0.7089,
+      "step": 670
+    },
+    {
+      "epoch": 0.04437773281994387,
+      "grad_norm": 4.235819327444911,
+      "learning_rate": 2.9911082129198372e-05,
+      "loss": 0.7138,
+      "step": 680
+    },
+    {
+      "epoch": 0.04503034653788423,
+      "grad_norm": 5.187338033698449,
+      "learning_rate": 2.9907672589203316e-05,
+      "loss": 0.7192,
+      "step": 690
+    },
+    {
+      "epoch": 0.04568296025582458,
+      "grad_norm": 6.360475337181379,
+      "learning_rate": 2.9904199105836443e-05,
+      "loss": 0.7094,
+      "step": 700
+    },
+    {
+      "epoch": 0.04633557397376493,
+      "grad_norm": 4.906400836156689,
+      "learning_rate": 2.990066169399654e-05,
+      "loss": 0.654,
+      "step": 710
+    },
+    {
+      "epoch": 0.04698818769170528,
+      "grad_norm": 17.600495314130633,
+      "learning_rate": 2.9897060368856603e-05,
+      "loss": 0.7299,
+      "step": 720
+    },
+    {
+      "epoch": 0.04764080140964563,
+      "grad_norm": 7.765935941492389,
+      "learning_rate": 2.989339514586377e-05,
+      "loss": 0.7486,
+      "step": 730
+    },
+    {
+      "epoch": 0.04829341512758598,
+      "grad_norm": 7.30026395137639,
+      "learning_rate": 2.9889666040739252e-05,
+      "loss": 0.6941,
+      "step": 740
+    },
+    {
+      "epoch": 0.04894602884552633,
+      "grad_norm": 4.676985481218465,
+      "learning_rate": 2.9885873069478275e-05,
+      "loss": 0.7701,
+      "step": 750
+    },
+    {
+      "epoch": 0.04959864256346668,
+      "grad_norm": 42.50656974727186,
+      "learning_rate": 2.9882016248350006e-05,
+      "loss": 0.7428,
+      "step": 760
+    },
+    {
+      "epoch": 0.05025125628140704,
+      "grad_norm": 3.9893667031114766,
+      "learning_rate": 2.9878095593897474e-05,
+      "loss": 0.7204,
+      "step": 770
+    },
+    {
+      "epoch": 0.05090386999934739,
+      "grad_norm": 8.909028486553332,
+      "learning_rate": 2.9874111122937518e-05,
+      "loss": 0.7336,
+      "step": 780
+    },
+    {
+      "epoch": 0.051556483717287736,
+      "grad_norm": 5.256925284136456,
+      "learning_rate": 2.9870062852560698e-05,
+      "loss": 0.7674,
+      "step": 790
+    },
+    {
+      "epoch": 0.052209097435228086,
+      "grad_norm": 5.835535487534073,
+      "learning_rate": 2.986595080013123e-05,
+      "loss": 0.7547,
+      "step": 800
+    },
+    {
+      "epoch": 0.05286171115316844,
+      "grad_norm": 4.7337998648314565,
+      "learning_rate": 2.9861774983286913e-05,
+      "loss": 0.7412,
+      "step": 810
+    },
+    {
+      "epoch": 0.05351432487110879,
+      "grad_norm": 4.020304406250962,
+      "learning_rate": 2.9857535419939053e-05,
+      "loss": 0.7351,
+      "step": 820
+    },
+    {
+      "epoch": 0.05416693858904914,
+      "grad_norm": 7.005748568175158,
+      "learning_rate": 2.9853232128272367e-05,
+      "loss": 0.7146,
+      "step": 830
+    },
+    {
+      "epoch": 0.05481955230698949,
+      "grad_norm": 12.598315147497464,
+      "learning_rate": 2.984886512674494e-05,
+      "loss": 0.7066,
+      "step": 840
+    },
+    {
+      "epoch": 0.055472166024929846,
+      "grad_norm": 5.636755294839953,
+      "learning_rate": 2.9844434434088114e-05,
+      "loss": 0.8033,
+      "step": 850
+    },
+    {
+      "epoch": 0.056124779742870196,
+      "grad_norm": 2.5964949457129305,
+      "learning_rate": 2.9839940069306436e-05,
+      "loss": 0.718,
+      "step": 860
+    },
+    {
+      "epoch": 0.056777393460810545,
+      "grad_norm": 5.496060434333994,
+      "learning_rate": 2.9835382051677548e-05,
+      "loss": 0.7382,
+      "step": 870
+    },
+    {
+      "epoch": 0.057430007178750894,
+      "grad_norm": 3.367511777906771,
+      "learning_rate": 2.9830760400752117e-05,
+      "loss": 0.7049,
+      "step": 880
+    },
+    {
+      "epoch": 0.05808262089669125,
+      "grad_norm": 12.228282751386294,
+      "learning_rate": 2.9826075136353762e-05,
+      "loss": 0.7135,
+      "step": 890
+    },
+    {
+      "epoch": 0.0587352346146316,
+      "grad_norm": 7.426066867205744,
+      "learning_rate": 2.9821326278578955e-05,
+      "loss": 0.6966,
+      "step": 900
+    },
+    {
+      "epoch": 0.05938784833257195,
+      "grad_norm": 5.720080945169142,
+      "learning_rate": 2.981651384779693e-05,
+      "loss": 0.7325,
+      "step": 910
+    },
+    {
+      "epoch": 0.0600404620505123,
+      "grad_norm": 3.3362738196336275,
+      "learning_rate": 2.9811637864649622e-05,
+      "loss": 0.7013,
+      "step": 920
+    },
+    {
+      "epoch": 0.060693075768452655,
+      "grad_norm": 5.5481143050516675,
+      "learning_rate": 2.980669835005154e-05,
+      "loss": 0.7107,
+      "step": 930
+    },
+    {
+      "epoch": 0.061345689486393004,
+      "grad_norm": 2.7247889305754533,
+      "learning_rate": 2.980169532518971e-05,
+      "loss": 0.6839,
+      "step": 940
+    },
+    {
+      "epoch": 0.06199830320433335,
+      "grad_norm": 12.705144630158374,
+      "learning_rate": 2.9796628811523576e-05,
+      "loss": 0.7061,
+      "step": 950
+    },
+    {
+      "epoch": 0.0626509169222737,
+      "grad_norm": 3.1174966376805777,
+      "learning_rate": 2.9791498830784896e-05,
+      "loss": 0.706,
+      "step": 960
+    },
+    {
+      "epoch": 0.06330353064021406,
+      "grad_norm": 6.454819870022971,
+      "learning_rate": 2.9786305404977657e-05,
+      "loss": 0.6901,
+      "step": 970
+    },
+    {
+      "epoch": 0.06395614435815442,
+      "grad_norm": 8.62099817289566,
+      "learning_rate": 2.9781048556377982e-05,
+      "loss": 0.6737,
+      "step": 980
+    },
+    {
+      "epoch": 0.06460875807609476,
+      "grad_norm": 12.649532843245389,
+      "learning_rate": 2.977572830753404e-05,
+      "loss": 0.6777,
+      "step": 990
+    },
+    {
+      "epoch": 0.06526137179403511,
+      "grad_norm": 5.019508830810828,
+      "learning_rate": 2.9770344681265925e-05,
+      "loss": 0.7125,
+      "step": 1000
+    },
+    {
+      "epoch": 0.06591398551197546,
+      "grad_norm": 5.417114630539967,
+      "learning_rate": 2.9764897700665595e-05,
+      "loss": 0.7558,
+      "step": 1010
+    },
+    {
+      "epoch": 0.06656659922991581,
+      "grad_norm": 13.487574757960102,
+      "learning_rate": 2.975938738909674e-05,
+      "loss": 0.7305,
+      "step": 1020
+    },
+    {
+      "epoch": 0.06721921294785617,
+      "grad_norm": 4.115297871929447,
+      "learning_rate": 2.97538137701947e-05,
+      "loss": 0.7382,
+      "step": 1030
+    },
+    {
+      "epoch": 0.06787182666579651,
+      "grad_norm": 4.218133725965425,
+      "learning_rate": 2.974817686786636e-05,
+      "loss": 0.7131,
+      "step": 1040
+    },
+    {
+      "epoch": 0.06852444038373687,
+      "grad_norm": 23.754945260227526,
+      "learning_rate": 2.9742476706290044e-05,
+      "loss": 0.6854,
+      "step": 1050
+    },
+    {
+      "epoch": 0.06917705410167722,
+      "grad_norm": 9.992382581534882,
+      "learning_rate": 2.973671330991541e-05,
+      "loss": 0.7224,
+      "step": 1060
+    },
+    {
+      "epoch": 0.06982966781961757,
+      "grad_norm": 9.022842665053004,
+      "learning_rate": 2.973088670346336e-05,
+      "loss": 0.69,
+      "step": 1070
+    },
+    {
+      "epoch": 0.07048228153755792,
+      "grad_norm": 7.180693480173149,
+      "learning_rate": 2.97249969119259e-05,
+      "loss": 0.6752,
+      "step": 1080
+    },
+    {
+      "epoch": 0.07113489525549826,
+      "grad_norm": 4.631581340679664,
+      "learning_rate": 2.9719043960566088e-05,
+      "loss": 0.7078,
+      "step": 1090
+    },
+    {
+      "epoch": 0.07178750897343862,
+      "grad_norm": 3.8365551360021497,
+      "learning_rate": 2.9713027874917867e-05,
+      "loss": 0.7455,
+      "step": 1100
+    },
+    {
+      "epoch": 0.07244012269137898,
+      "grad_norm": 20.612721990589407,
+      "learning_rate": 2.9706948680785984e-05,
+      "loss": 0.7123,
+      "step": 1110
+    },
+    {
+      "epoch": 0.07309273640931932,
+      "grad_norm": 8.515913036269723,
+      "learning_rate": 2.9700806404245893e-05,
+      "loss": 0.6755,
+      "step": 1120
+    },
+    {
+      "epoch": 0.07374535012725968,
+      "grad_norm": 8.702591994450561,
+      "learning_rate": 2.9694601071643607e-05,
+      "loss": 0.743,
+      "step": 1130
+    },
+    {
+      "epoch": 0.07439796384520003,
+      "grad_norm": 20.204623397644042,
+      "learning_rate": 2.968833270959562e-05,
+      "loss": 0.6995,
+      "step": 1140
+    },
+    {
+      "epoch": 0.07505057756314037,
+      "grad_norm": 3.4150625200259563,
+      "learning_rate": 2.9682001344988768e-05,
+      "loss": 0.7245,
+      "step": 1150
+    },
+    {
+      "epoch": 0.07570319128108073,
+      "grad_norm": 4.827412673105033,
+      "learning_rate": 2.967560700498013e-05,
+      "loss": 0.6764,
+      "step": 1160
+    },
+    {
+      "epoch": 0.07635580499902107,
+      "grad_norm": 5.9778449783108965,
+      "learning_rate": 2.9669149716996897e-05,
+      "loss": 0.7094,
+      "step": 1170
+    },
+    {
+      "epoch": 0.07700841871696143,
+      "grad_norm": 4.626419468156439,
+      "learning_rate": 2.9662629508736278e-05,
+      "loss": 0.7139,
+      "step": 1180
+    },
+    {
+      "epoch": 0.07766103243490179,
+      "grad_norm": 8.23953369228554,
+      "learning_rate": 2.9656046408165344e-05,
+      "loss": 0.7132,
+      "step": 1190
+    },
+    {
+      "epoch": 0.07831364615284213,
+      "grad_norm": 5.755275462407804,
+      "learning_rate": 2.964940044352095e-05,
+      "loss": 0.6923,
+      "step": 1200
+    },
+    {
+      "epoch": 0.07896625987078248,
+      "grad_norm": 3.8396649246253816,
+      "learning_rate": 2.9642691643309572e-05,
+      "loss": 0.7082,
+      "step": 1210
+    },
+    {
+      "epoch": 0.07961887358872284,
+      "grad_norm": 5.7429454484886415,
+      "learning_rate": 2.963592003630723e-05,
+      "loss": 0.7095,
+      "step": 1220
+    },
+    {
+      "epoch": 0.08027148730666318,
+      "grad_norm": 17.628494673763004,
+      "learning_rate": 2.962908565155932e-05,
+      "loss": 0.7309,
+      "step": 1230
+    },
+    {
+      "epoch": 0.08092410102460354,
+      "grad_norm": 4.83400055237192,
+      "learning_rate": 2.9622188518380528e-05,
+      "loss": 0.6925,
+      "step": 1240
+    },
+    {
+      "epoch": 0.08157671474254388,
+      "grad_norm": 3.1535973307593905,
+      "learning_rate": 2.9615228666354667e-05,
+      "loss": 0.7441,
+      "step": 1250
+    },
+    {
+      "epoch": 0.08222932846048424,
+      "grad_norm": 4.085385929026401,
+      "learning_rate": 2.9608206125334586e-05,
+      "loss": 0.7137,
+      "step": 1260
+    },
+    {
+      "epoch": 0.0828819421784246,
+      "grad_norm": 4.299591870123697,
+      "learning_rate": 2.9601120925442016e-05,
+      "loss": 0.7515,
+      "step": 1270
+    },
+    {
+      "epoch": 0.08353455589636494,
+      "grad_norm": 12.873434323415678,
+      "learning_rate": 2.959397309706746e-05,
+      "loss": 0.6852,
+      "step": 1280
+    },
+    {
+      "epoch": 0.0841871696143053,
+      "grad_norm": 6.427088345402557,
+      "learning_rate": 2.958676267087004e-05,
+      "loss": 0.6499,
+      "step": 1290
+    },
+    {
+      "epoch": 0.08483978333224565,
+      "grad_norm": 4.70723263638176,
+      "learning_rate": 2.9579489677777387e-05,
+      "loss": 0.6803,
+      "step": 1300
+    },
+    {
+      "epoch": 0.08549239705018599,
+      "grad_norm": 4.819218491318424,
+      "learning_rate": 2.9572154148985495e-05,
+      "loss": 0.6798,
+      "step": 1310
+    },
+    {
+      "epoch": 0.08614501076812635,
+      "grad_norm": 3.0652661968089827,
+      "learning_rate": 2.9564756115958592e-05,
+      "loss": 0.6935,
+      "step": 1320
+    },
+    {
+      "epoch": 0.08679762448606669,
+      "grad_norm": 5.997224165634556,
+      "learning_rate": 2.9557295610429017e-05,
+      "loss": 0.7133,
+      "step": 1330
+    },
+    {
+      "epoch": 0.08745023820400705,
+      "grad_norm": 3.3593003375605717,
+      "learning_rate": 2.954977266439706e-05,
+      "loss": 0.7335,
+      "step": 1340
+    },
+    {
+      "epoch": 0.0881028519219474,
+      "grad_norm": 4.161242018302672,
+      "learning_rate": 2.954218731013083e-05,
+      "loss": 0.7054,
+      "step": 1350
+    },
+    {
+      "epoch": 0.08875546563988775,
+      "grad_norm": 5.827431481546491,
+      "learning_rate": 2.953453958016614e-05,
+      "loss": 0.6321,
+      "step": 1360
+    },
+    {
+      "epoch": 0.0894080793578281,
+      "grad_norm": 7.1039105888444904,
+      "learning_rate": 2.952682950730634e-05,
+      "loss": 0.6941,
+      "step": 1370
+    },
+    {
+      "epoch": 0.09006069307576846,
+      "grad_norm": 2.7616336275225892,
+      "learning_rate": 2.951905712462219e-05,
+      "loss": 0.6928,
+      "step": 1380
+    },
+    {
+      "epoch": 0.0907133067937088,
+      "grad_norm": 4.261061690296871,
+      "learning_rate": 2.9511222465451716e-05,
+      "loss": 0.7176,
+      "step": 1390
+    },
+    {
+      "epoch": 0.09136592051164916,
+      "grad_norm": 5.4134818862551395,
+      "learning_rate": 2.950332556340006e-05,
+      "loss": 0.7048,
+      "step": 1400
+    },
+    {
+      "epoch": 0.0920185342295895,
+      "grad_norm": 6.3477656240577085,
+      "learning_rate": 2.949536645233935e-05,
+      "loss": 0.6842,
+      "step": 1410
+    },
+    {
+      "epoch": 0.09267114794752986,
+      "grad_norm": 63.477804314776044,
+      "learning_rate": 2.9487345166408545e-05,
+      "loss": 0.6876,
+      "step": 1420
+    },
+    {
+      "epoch": 0.09332376166547021,
+      "grad_norm": 4.368664541213622,
+      "learning_rate": 2.9479261740013286e-05,
+      "loss": 0.6913,
+      "step": 1430
+    },
+    {
+      "epoch": 0.09397637538341055,
+      "grad_norm": 9.476938465079238,
+      "learning_rate": 2.9471116207825754e-05,
+      "loss": 0.6891,
+      "step": 1440
+    },
+    {
+      "epoch": 0.09462898910135091,
+      "grad_norm": 8.434794578560851,
+      "learning_rate": 2.9462908604784523e-05,
+      "loss": 0.6585,
+      "step": 1450
+    },
+    {
+      "epoch": 0.09528160281929127,
+      "grad_norm": 4.798759761163433,
+      "learning_rate": 2.945463896609441e-05,
+      "loss": 0.6736,
+      "step": 1460
+    },
+    {
+      "epoch": 0.09593421653723161,
+      "grad_norm": 9.782724872581115,
+      "learning_rate": 2.9446307327226306e-05,
+      "loss": 0.6659,
+      "step": 1470
+    },
+    {
+      "epoch": 0.09658683025517197,
+      "grad_norm": 3.997516099278308,
+      "learning_rate": 2.9437913723917058e-05,
+      "loss": 0.6527,
+      "step": 1480
+    },
+    {
+      "epoch": 0.09723944397311232,
+      "grad_norm": 4.623015725563099,
+      "learning_rate": 2.942945819216928e-05,
+      "loss": 0.7274,
+      "step": 1490
+    },
+    {
+      "epoch": 0.09789205769105266,
+      "grad_norm": 3.2197835799755055,
+      "learning_rate": 2.942094076825123e-05,
+      "loss": 0.6966,
+      "step": 1500
+    },
+    {
+      "epoch": 0.09854467140899302,
+      "grad_norm": 3.5107988249516984,
+      "learning_rate": 2.9412361488696628e-05,
+      "loss": 0.7235,
+      "step": 1510
+    },
+    {
+      "epoch": 0.09919728512693336,
+      "grad_norm": 18.7865650951996,
+      "learning_rate": 2.9403720390304518e-05,
+      "loss": 0.7382,
+      "step": 1520
+    },
+    {
+      "epoch": 0.09984989884487372,
+      "grad_norm": 3.85598692653545,
+      "learning_rate": 2.93950175101391e-05,
+      "loss": 0.7475,
+      "step": 1530
+    },
+    {
+      "epoch": 0.10050251256281408,
+      "grad_norm": 20.459657003411998,
+      "learning_rate": 2.938625288552957e-05,
+      "loss": 0.6558,
+      "step": 1540
+    },
+    {
+      "epoch": 0.10115512628075442,
+      "grad_norm": 6.416583997846208,
+      "learning_rate": 2.9377426554069976e-05,
+      "loss": 0.7205,
+      "step": 1550
+    },
+    {
+      "epoch": 0.10180773999869477,
+      "grad_norm": 5.532087704430113,
+      "learning_rate": 2.936853855361904e-05,
+      "loss": 0.7189,
+      "step": 1560
+    },
+    {
+      "epoch": 0.10246035371663513,
+      "grad_norm": 4.756518458886862,
+      "learning_rate": 2.9359588922299986e-05,
+      "loss": 0.7088,
+      "step": 1570
+    },
+    {
+      "epoch": 0.10311296743457547,
+      "grad_norm": 5.775658785412931,
+      "learning_rate": 2.9350577698500408e-05,
+      "loss": 0.682,
+      "step": 1580
+    },
+    {
+      "epoch": 0.10376558115251583,
+      "grad_norm": 7.714313915746094,
+      "learning_rate": 2.9341504920872087e-05,
+      "loss": 0.7393,
+      "step": 1590
+    },
+    {
+      "epoch": 0.10441819487045617,
+      "grad_norm": 11.153510433173501,
+      "learning_rate": 2.933237062833082e-05,
+      "loss": 0.6616,
+      "step": 1600
+    },
+    {
+      "epoch": 0.10507080858839653,
+      "grad_norm": 4.575896778703132,
+      "learning_rate": 2.9323174860056258e-05,
+      "loss": 0.7168,
+      "step": 1610
+    },
+    {
+      "epoch": 0.10572342230633688,
+      "grad_norm": 46.2282201673799,
+      "learning_rate": 2.9313917655491744e-05,
+      "loss": 0.7016,
+      "step": 1620
+    },
+    {
+      "epoch": 0.10637603602427723,
+      "grad_norm": 51.80540559466864,
+      "learning_rate": 2.9304599054344148e-05,
+      "loss": 0.6709,
+      "step": 1630
+    },
+    {
+      "epoch": 0.10702864974221758,
+      "grad_norm": 4.607057564284905,
+      "learning_rate": 2.9295219096583663e-05,
+      "loss": 0.6894,
+      "step": 1640
+    },
+    {
+      "epoch": 0.10768126346015794,
+      "grad_norm": 4.158724628963882,
+      "learning_rate": 2.9285777822443686e-05,
+      "loss": 0.6847,
+      "step": 1650
+    },
+    {
+      "epoch": 0.10833387717809828,
+      "grad_norm": 6.634813921115065,
+      "learning_rate": 2.92762752724206e-05,
+      "loss": 0.7094,
+      "step": 1660
+    },
+    {
+      "epoch": 0.10898649089603864,
+      "grad_norm": 2.437577662086608,
+      "learning_rate": 2.926671148727362e-05,
+      "loss": 0.69,
+      "step": 1670
+    },
+    {
+      "epoch": 0.10963910461397898,
+      "grad_norm": 22.722071681603026,
+      "learning_rate": 2.925708650802463e-05,
+      "loss": 0.704,
+      "step": 1680
+    },
+    {
+      "epoch": 0.11029171833191934,
+      "grad_norm": 2.913996227830109,
+      "learning_rate": 2.9247400375957976e-05,
+      "loss": 0.7211,
+      "step": 1690
+    },
+    {
+      "epoch": 0.11094433204985969,
+      "grad_norm": 5.279852146043678,
+      "learning_rate": 2.923765313262032e-05,
+      "loss": 0.6693,
+      "step": 1700
+    },
+    {
+      "epoch": 0.11159694576780003,
+      "grad_norm": 4.47116557104752,
+      "learning_rate": 2.9227844819820434e-05,
+      "loss": 0.6958,
+      "step": 1710
+    },
+    {
+      "epoch": 0.11224955948574039,
+      "grad_norm": 6.9451125709413,
+      "learning_rate": 2.9217975479629047e-05,
+      "loss": 0.6549,
+      "step": 1720
+    },
+    {
+      "epoch": 0.11290217320368075,
+      "grad_norm": 8.218016152925602,
+      "learning_rate": 2.920804515437865e-05,
+      "loss": 0.7034,
+      "step": 1730
+    },
+    {
+      "epoch": 0.11355478692162109,
+      "grad_norm": 4.725968454405007,
+      "learning_rate": 2.9198053886663314e-05,
+      "loss": 0.7292,
+      "step": 1740
+    },
+    {
+      "epoch": 0.11420740063956145,
+      "grad_norm": 8.078717621365517,
+      "learning_rate": 2.9188001719338514e-05,
+      "loss": 0.6556,
+      "step": 1750
+    },
+    {
+      "epoch": 0.11486001435750179,
+      "grad_norm": 9.045448414751244,
+      "learning_rate": 2.9177888695520933e-05,
+      "loss": 0.7223,
+      "step": 1760
+    },
+    {
+      "epoch": 0.11551262807544214,
+      "grad_norm": 4.318313439658446,
+      "learning_rate": 2.916771485858829e-05,
+      "loss": 0.6762,
+      "step": 1770
+    },
+    {
+      "epoch": 0.1161652417933825,
+      "grad_norm": 13.078874026489483,
+      "learning_rate": 2.9157480252179156e-05,
+      "loss": 0.7189,
+      "step": 1780
+    },
+    {
+      "epoch": 0.11681785551132284,
+      "grad_norm": 8.585825980992096,
+      "learning_rate": 2.9147184920192745e-05,
+      "loss": 0.7142,
+      "step": 1790
+    },
+    {
+      "epoch": 0.1174704692292632,
+      "grad_norm": 138.05135197182966,
+      "learning_rate": 2.9136828906788765e-05,
+      "loss": 0.6514,
+      "step": 1800
+    },
+    {
+      "epoch": 0.11812308294720356,
+      "grad_norm": 2.9764498791953167,
+      "learning_rate": 2.9126412256387172e-05,
+      "loss": 0.6835,
+      "step": 1810
+    },
+    {
+      "epoch": 0.1187756966651439,
+      "grad_norm": 10.553495101154766,
+      "learning_rate": 2.9115935013668038e-05,
+      "loss": 0.7049,
+      "step": 1820
+    },
+    {
+      "epoch": 0.11942831038308425,
+      "grad_norm": 3.8520760029457755,
+      "learning_rate": 2.910539722357132e-05,
+      "loss": 0.6805,
+      "step": 1830
+    },
+    {
+      "epoch": 0.1200809241010246,
+      "grad_norm": 6.002281391018973,
+      "learning_rate": 2.9094798931296692e-05,
+      "loss": 0.7044,
+      "step": 1840
+    },
+    {
+      "epoch": 0.12073353781896495,
+      "grad_norm": 9.04002888227592,
+      "learning_rate": 2.9084140182303328e-05,
+      "loss": 0.7221,
+      "step": 1850
+    },
+    {
+      "epoch": 0.12138615153690531,
+      "grad_norm": 2.324509546376411,
+      "learning_rate": 2.907342102230972e-05,
+      "loss": 0.7,
+      "step": 1860
+    },
+    {
+      "epoch": 0.12203876525484565,
+      "grad_norm": 4.136482440945801,
+      "learning_rate": 2.9062641497293485e-05,
+      "loss": 0.7213,
+      "step": 1870
+    },
+    {
+      "epoch": 0.12269137897278601,
+      "grad_norm": 2.9193932096141673,
+      "learning_rate": 2.9051801653491158e-05,
+      "loss": 0.6656,
+      "step": 1880
+    },
+    {
+      "epoch": 0.12334399269072636,
+      "grad_norm": 6.319528726800553,
+      "learning_rate": 2.9040901537398008e-05,
+      "loss": 0.6701,
+      "step": 1890
+    },
+    {
+      "epoch": 0.1239966064086667,
+      "grad_norm": 3.5042010027049533,
+      "learning_rate": 2.9029941195767824e-05,
+      "loss": 0.6454,
+      "step": 1900
+    },
+    {
+      "epoch": 0.12464922012660706,
+      "grad_norm": 4.3096531856338895,
+      "learning_rate": 2.9018920675612712e-05,
+      "loss": 0.6818,
+      "step": 1910
+    },
+    {
+      "epoch": 0.1253018338445474,
+      "grad_norm": 6.849873350879978,
+      "learning_rate": 2.900784002420292e-05,
+      "loss": 0.7674,
+      "step": 1920
+    },
+    {
+      "epoch": 0.12595444756248778,
+      "grad_norm": 7.645127543651015,
+      "learning_rate": 2.89966992890666e-05,
+      "loss": 0.7,
+      "step": 1930
+    },
+    {
+      "epoch": 0.12660706128042812,
+      "grad_norm": 3.334578297503325,
+      "learning_rate": 2.8985498517989623e-05,
+      "loss": 0.6783,
+      "step": 1940
+    },
+    {
+      "epoch": 0.12725967499836846,
+      "grad_norm": 7.91381208921764,
+      "learning_rate": 2.897423775901538e-05,
+      "loss": 0.7327,
+      "step": 1950
+    },
+    {
+      "epoch": 0.12791228871630883,
+      "grad_norm": 7.74516810255062,
+      "learning_rate": 2.8962917060444562e-05,
+      "loss": 0.7145,
+      "step": 1960
+    },
+    {
+      "epoch": 0.12856490243424917,
+      "grad_norm": 5.468499401345368,
+      "learning_rate": 2.8951536470834957e-05,
+      "loss": 0.6807,
+      "step": 1970
+    },
+    {
+      "epoch": 0.12921751615218952,
+      "grad_norm": 3.7005534196349963,
+      "learning_rate": 2.894009603900125e-05,
+      "loss": 0.7004,
+      "step": 1980
+    },
+    {
+      "epoch": 0.12987012987012986,
+      "grad_norm": 3.6355286647446716,
+      "learning_rate": 2.89285958140148e-05,
+      "loss": 0.6804,
+      "step": 1990
+    },
+    {
+      "epoch": 0.13052274358807023,
+      "grad_norm": 4.199898882057381,
+      "learning_rate": 2.891703584520343e-05,
+      "loss": 0.7268,
+      "step": 2000
+    },
+    {
+      "epoch": 0.13117535730601057,
+      "grad_norm": 4.9058604480600385,
+      "learning_rate": 2.8905416182151244e-05,
+      "loss": 0.7168,
+      "step": 2010
+    },
+    {
+      "epoch": 0.1318279710239509,
+      "grad_norm": 4.2197732320304535,
+      "learning_rate": 2.8893736874698367e-05,
+      "loss": 0.701,
+      "step": 2020
+    },
+    {
+      "epoch": 0.13248058474189128,
+      "grad_norm": 4.66981547707892,
+      "learning_rate": 2.888199797294078e-05,
+      "loss": 0.6624,
+      "step": 2030
+    },
+    {
+      "epoch": 0.13313319845983163,
+      "grad_norm": 2.1811717459296274,
+      "learning_rate": 2.887019952723006e-05,
+      "loss": 0.7181,
+      "step": 2040
+    },
+    {
+      "epoch": 0.13378581217777197,
+      "grad_norm": 5.9404267175163135,
+      "learning_rate": 2.8858341588173194e-05,
+      "loss": 0.7231,
+      "step": 2050
+    },
+    {
+      "epoch": 0.13443842589571234,
+      "grad_norm": 3.279458419701383,
+      "learning_rate": 2.884642420663236e-05,
+      "loss": 0.6863,
+      "step": 2060
+    },
+    {
+      "epoch": 0.13509103961365268,
+      "grad_norm": 3.441960856231174,
+      "learning_rate": 2.8834447433724693e-05,
+      "loss": 0.6985,
+      "step": 2070
+    },
+    {
+      "epoch": 0.13574365333159302,
+      "grad_norm": 6.296333990212765,
+      "learning_rate": 2.8822411320822074e-05,
+      "loss": 0.7166,
+      "step": 2080
+    },
+    {
+      "epoch": 0.1363962670495334,
+      "grad_norm": 4.087401381303271,
+      "learning_rate": 2.881031591955092e-05,
+      "loss": 0.6765,
+      "step": 2090
+    },
+    {
+      "epoch": 0.13704888076747374,
+      "grad_norm": 6.6119114402937305,
+      "learning_rate": 2.879816128179195e-05,
+      "loss": 0.7228,
+      "step": 2100
+    },
+    {
+      "epoch": 0.13770149448541408,
+      "grad_norm": 4.897020539614396,
+      "learning_rate": 2.8785947459679953e-05,
+      "loss": 0.7173,
+      "step": 2110
+    },
+    {
+      "epoch": 0.13835410820335445,
+      "grad_norm": 3.482291928967508,
+      "learning_rate": 2.87736745056036e-05,
+      "loss": 0.685,
+      "step": 2120
+    },
+    {
+      "epoch": 0.1390067219212948,
+      "grad_norm": 12.111542144788995,
+      "learning_rate": 2.876134247220517e-05,
+      "loss": 0.7198,
+      "step": 2130
+    },
+    {
+      "epoch": 0.13965933563923513,
+      "grad_norm": 7.1442170238273786,
+      "learning_rate": 2.8748951412380384e-05,
+      "loss": 0.7549,
+      "step": 2140
+    },
+    {
+      "epoch": 0.14031194935717548,
+      "grad_norm": 4.841978475189581,
+      "learning_rate": 2.873650137927811e-05,
+      "loss": 0.6388,
+      "step": 2150
+    },
+    {
+      "epoch": 0.14096456307511585,
+      "grad_norm": 4.053407088369962,
+      "learning_rate": 2.872399242630018e-05,
+      "loss": 0.6837,
+      "step": 2160
+    },
+    {
+      "epoch": 0.1416171767930562,
+      "grad_norm": 2.537769446137546,
+      "learning_rate": 2.871142460710117e-05,
+      "loss": 0.678,
+      "step": 2170
+    },
+    {
+      "epoch": 0.14226979051099653,
+      "grad_norm": 6.452520531522298,
+      "learning_rate": 2.8698797975588133e-05,
+      "loss": 0.669,
+      "step": 2180
+    },
+    {
+      "epoch": 0.1429224042289369,
+      "grad_norm": 6.840893292905677,
+      "learning_rate": 2.868611258592038e-05,
+      "loss": 0.7022,
+      "step": 2190
+    },
+    {
+      "epoch": 0.14357501794687724,
+      "grad_norm": 4.634307774411798,
+      "learning_rate": 2.867336849250926e-05,
+      "loss": 0.6873,
+      "step": 2200
+    },
+    {
+      "epoch": 0.14422763166481758,
+      "grad_norm": 3.74851807876996,
+      "learning_rate": 2.866056575001793e-05,
+      "loss": 0.6946,
+      "step": 2210
+    },
+    {
+      "epoch": 0.14488024538275796,
+      "grad_norm": 2.0416537952666123,
+      "learning_rate": 2.8647704413361095e-05,
+      "loss": 0.6637,
+      "step": 2220
+    },
+    {
+      "epoch": 0.1455328591006983,
+      "grad_norm": 3.555607066840982,
+      "learning_rate": 2.863478453770479e-05,
+      "loss": 0.71,
+      "step": 2230
+    },
+    {
+      "epoch": 0.14618547281863864,
+      "grad_norm": 5.481578146356155,
+      "learning_rate": 2.862180617846615e-05,
+      "loss": 0.7335,
+      "step": 2240
+    },
+    {
+      "epoch": 0.146838086536579,
+      "grad_norm": 4.089959406196587,
+      "learning_rate": 2.8608769391313153e-05,
+      "loss": 0.6951,
+      "step": 2250
+    },
+    {
+      "epoch": 0.14749070025451935,
+      "grad_norm": 4.054901293812647,
+      "learning_rate": 2.8595674232164403e-05,
+      "loss": 0.6933,
+      "step": 2260
+    },
+    {
+      "epoch": 0.1481433139724597,
+      "grad_norm": 11.977393154495003,
+      "learning_rate": 2.8582520757188858e-05,
+      "loss": 0.6793,
+      "step": 2270
+    },
+    {
+      "epoch": 0.14879592769040006,
+      "grad_norm": 9.862463610911956,
+      "learning_rate": 2.856930902280563e-05,
+      "loss": 0.693,
+      "step": 2280
+    },
+    {
+      "epoch": 0.1494485414083404,
+      "grad_norm": 6.6933607998065305,
+      "learning_rate": 2.8556039085683717e-05,
+      "loss": 0.6512,
+      "step": 2290
+    },
+    {
+      "epoch": 0.15010115512628075,
+      "grad_norm": 13.33031435802581,
+      "learning_rate": 2.8542711002741765e-05,
+      "loss": 0.6818,
+      "step": 2300
+    },
+    {
+      "epoch": 0.1507537688442211,
+      "grad_norm": 3.55607266109624,
+      "learning_rate": 2.8529324831147817e-05,
+      "loss": 0.6969,
+      "step": 2310
+    },
+    {
+      "epoch": 0.15140638256216146,
+      "grad_norm": 2.76158562626684,
+      "learning_rate": 2.8515880628319084e-05,
+      "loss": 0.6469,
+      "step": 2320
+    },
+    {
+      "epoch": 0.1520589962801018,
+      "grad_norm": 14.835614032644079,
+      "learning_rate": 2.8502378451921686e-05,
+      "loss": 0.7095,
+      "step": 2330
+    },
+    {
+      "epoch": 0.15271160999804215,
+      "grad_norm": 3.837370004844092,
+      "learning_rate": 2.8488818359870418e-05,
+      "loss": 0.6549,
+      "step": 2340
+    },
+    {
+      "epoch": 0.15336422371598252,
+      "grad_norm": 8.077714625547088,
+      "learning_rate": 2.8475200410328477e-05,
+      "loss": 0.7036,
+      "step": 2350
+    },
+    {
+      "epoch": 0.15401683743392286,
+      "grad_norm": 4.208380267696714,
+      "learning_rate": 2.846152466170724e-05,
+      "loss": 0.7083,
+      "step": 2360
+    },
+    {
+      "epoch": 0.1546694511518632,
+      "grad_norm": 5.882366675192563,
+      "learning_rate": 2.8447791172665994e-05,
+      "loss": 0.6774,
+      "step": 2370
+    },
+    {
+      "epoch": 0.15532206486980357,
+      "grad_norm": 10.332970110344341,
+      "learning_rate": 2.8434000002111686e-05,
+      "loss": 0.6871,
+      "step": 2380
+    },
+    {
+      "epoch": 0.15597467858774391,
+      "grad_norm": 5.233682432902447,
+      "learning_rate": 2.84201512091987e-05,
+      "loss": 0.6685,
+      "step": 2390
+    },
+    {
+      "epoch": 0.15662729230568426,
+      "grad_norm": 4.051922217192083,
+      "learning_rate": 2.840624485332855e-05,
+      "loss": 0.6893,
+      "step": 2400
+    },
+    {
+      "epoch": 0.15727990602362463,
+      "grad_norm": 8.208037033800602,
+      "learning_rate": 2.8392280994149673e-05,
+      "loss": 0.7163,
+      "step": 2410
+    },
+    {
+      "epoch": 0.15793251974156497,
+      "grad_norm": 6.38338502443,
+      "learning_rate": 2.8378259691557143e-05,
+      "loss": 0.6738,
+      "step": 2420
+    },
+    {
+      "epoch": 0.1585851334595053,
+      "grad_norm": 5.91196516331796,
+      "learning_rate": 2.8364181005692437e-05,
+      "loss": 0.6777,
+      "step": 2430
+    },
+    {
+      "epoch": 0.15923774717744568,
+      "grad_norm": 4.255829123415314,
+      "learning_rate": 2.835004499694316e-05,
+      "loss": 0.7101,
+      "step": 2440
+    },
+    {
+      "epoch": 0.15989036089538602,
+      "grad_norm": 6.462145986397376,
+      "learning_rate": 2.833585172594279e-05,
+      "loss": 0.7031,
+      "step": 2450
+    },
+    {
+      "epoch": 0.16054297461332637,
+      "grad_norm": 4.701946326296281,
+      "learning_rate": 2.8321601253570425e-05,
+      "loss": 0.7195,
+      "step": 2460
+    },
+    {
+      "epoch": 0.16119558833126674,
+      "grad_norm": 2.7081882046671337,
+      "learning_rate": 2.830729364095051e-05,
+      "loss": 0.697,
+      "step": 2470
+    },
+    {
+      "epoch": 0.16184820204920708,
+      "grad_norm": 12.027371026479301,
+      "learning_rate": 2.8292928949452578e-05,
+      "loss": 0.6701,
+      "step": 2480
+    },
+    {
+      "epoch": 0.16250081576714742,
+      "grad_norm": 4.375553205119334,
+      "learning_rate": 2.8278507240691e-05,
+      "loss": 0.6698,
+      "step": 2490
+    },
+    {
+      "epoch": 0.16315342948508776,
+      "grad_norm": 2.3145460407904968,
+      "learning_rate": 2.8264028576524714e-05,
+      "loss": 0.6619,
+      "step": 2500
+    },
+    {
+      "epoch": 0.16380604320302813,
+      "grad_norm": 9.62186450170952,
+      "learning_rate": 2.824949301905694e-05,
+      "loss": 0.7049,
+      "step": 2510
+    },
+    {
+      "epoch": 0.16445865692096848,
+      "grad_norm": 3.242262212053335,
+      "learning_rate": 2.8234900630634945e-05,
+      "loss": 0.6684,
+      "step": 2520
+    },
+    {
+      "epoch": 0.16511127063890882,
+      "grad_norm": 5.874441891397036,
+      "learning_rate": 2.8220251473849747e-05,
+      "loss": 0.6841,
+      "step": 2530
+    },
+    {
+      "epoch": 0.1657638843568492,
+      "grad_norm": 5.5132935867506685,
+      "learning_rate": 2.8205545611535876e-05,
+      "loss": 0.7077,
+      "step": 2540
+    },
+    {
+      "epoch": 0.16641649807478953,
+      "grad_norm": 4.178673623014923,
+      "learning_rate": 2.8190783106771076e-05,
+      "loss": 0.6779,
+      "step": 2550
+    },
+    {
+      "epoch": 0.16706911179272987,
+      "grad_norm": 3.8308465742128974,
+      "learning_rate": 2.8175964022876057e-05,
+      "loss": 0.6638,
+      "step": 2560
+    },
+    {
+      "epoch": 0.16772172551067024,
+      "grad_norm": 3.122478077844367,
+      "learning_rate": 2.8161088423414197e-05,
+      "loss": 0.7063,
+      "step": 2570
+    },
+    {
+      "epoch": 0.1683743392286106,
+      "grad_norm": 4.633331835812846,
+      "learning_rate": 2.8146156372191306e-05,
+      "loss": 0.6555,
+      "step": 2580
+    },
+    {
+      "epoch": 0.16902695294655093,
+      "grad_norm": 17.541201672163616,
+      "learning_rate": 2.8131167933255323e-05,
+      "loss": 0.7001,
+      "step": 2590
+    },
+    {
+      "epoch": 0.1696795666644913,
+      "grad_norm": 6.134101489242109,
+      "learning_rate": 2.8116123170896046e-05,
+      "loss": 0.7173,
+      "step": 2600
+    },
+    {
+      "epoch": 0.17033218038243164,
+      "grad_norm": 8.073444833192916,
+      "learning_rate": 2.8101022149644868e-05,
+      "loss": 0.6771,
+      "step": 2610
+    },
+    {
+      "epoch": 0.17098479410037198,
+      "grad_norm": 6.780231733384814,
+      "learning_rate": 2.8085864934274488e-05,
+      "loss": 0.7313,
+      "step": 2620
+    },
+    {
+      "epoch": 0.17163740781831235,
+      "grad_norm": 3.857057315644847,
+      "learning_rate": 2.8070651589798638e-05,
+      "loss": 0.6844,
+      "step": 2630
+    },
+    {
+      "epoch": 0.1722900215362527,
+      "grad_norm": 2.6968793212573106,
+      "learning_rate": 2.805538218147181e-05,
+      "loss": 0.6806,
+      "step": 2640
+    },
+    {
+      "epoch": 0.17294263525419304,
+      "grad_norm": 3.347039146921558,
+      "learning_rate": 2.8040056774788968e-05,
+      "loss": 0.6993,
+      "step": 2650
+    },
+    {
+      "epoch": 0.17359524897213338,
+      "grad_norm": 3.3015836383740456,
+      "learning_rate": 2.8024675435485257e-05,
+      "loss": 0.7268,
+      "step": 2660
+    },
+    {
+      "epoch": 0.17424786269007375,
+      "grad_norm": 3.317639807807373,
+      "learning_rate": 2.8009238229535758e-05,
+      "loss": 0.6674,
+      "step": 2670
+    },
+    {
+      "epoch": 0.1749004764080141,
+      "grad_norm": 5.874714621247871,
+      "learning_rate": 2.7993745223155156e-05,
+      "loss": 0.6571,
+      "step": 2680
+    },
+    {
+      "epoch": 0.17555309012595444,
+      "grad_norm": 3.435629734690448,
+      "learning_rate": 2.7978196482797496e-05,
+      "loss": 0.6998,
+      "step": 2690
+    },
+    {
+      "epoch": 0.1762057038438948,
+      "grad_norm": 30.168294226928044,
+      "learning_rate": 2.7962592075155875e-05,
+      "loss": 0.6531,
+      "step": 2700
+    },
+    {
+      "epoch": 0.17685831756183515,
+      "grad_norm": 3.6088167890096865,
+      "learning_rate": 2.794693206716217e-05,
+      "loss": 0.644,
+      "step": 2710
+    },
+    {
+      "epoch": 0.1775109312797755,
+      "grad_norm": 5.471338847334227,
+      "learning_rate": 2.7931216525986733e-05,
+      "loss": 0.6864,
+      "step": 2720
+    },
+    {
+      "epoch": 0.17816354499771586,
+      "grad_norm": 3.5451837616331763,
+      "learning_rate": 2.7915445519038124e-05,
+      "loss": 0.6794,
+      "step": 2730
+    },
+    {
+      "epoch": 0.1788161587156562,
+      "grad_norm": 4.9951779955670705,
+      "learning_rate": 2.7899619113962806e-05,
+      "loss": 0.6702,
+      "step": 2740
+    },
+    {
+      "epoch": 0.17946877243359655,
+      "grad_norm": 6.849902588089016,
+      "learning_rate": 2.7883737378644866e-05,
+      "loss": 0.679,
+      "step": 2750
+    },
+    {
+      "epoch": 0.18012138615153692,
+      "grad_norm": 11.250488948793029,
+      "learning_rate": 2.786780038120572e-05,
+      "loss": 0.7153,
+      "step": 2760
+    },
+    {
+      "epoch": 0.18077399986947726,
+      "grad_norm": 13.184900398210909,
+      "learning_rate": 2.7851808190003803e-05,
+      "loss": 0.6734,
+      "step": 2770
+    },
+    {
+      "epoch": 0.1814266135874176,
+      "grad_norm": 7.234749638062084,
+      "learning_rate": 2.7835760873634318e-05,
+      "loss": 0.6677,
+      "step": 2780
+    },
+    {
+      "epoch": 0.18207922730535797,
+      "grad_norm": 13.085129406019094,
+      "learning_rate": 2.7819658500928897e-05,
+      "loss": 0.691,
+      "step": 2790
+    },
+    {
+      "epoch": 0.1827318410232983,
+      "grad_norm": 3.5248377823535,
+      "learning_rate": 2.780350114095533e-05,
+      "loss": 0.6397,
+      "step": 2800
+    },
+    {
+      "epoch": 0.18338445474123866,
+      "grad_norm": 26.796889805025064,
+      "learning_rate": 2.7787288863017263e-05,
+      "loss": 0.7222,
+      "step": 2810
+    },
+    {
+      "epoch": 0.184037068459179,
+      "grad_norm": 3.125330335323775,
+      "learning_rate": 2.77710217366539e-05,
+      "loss": 0.7082,
+      "step": 2820
+    },
+    {
+      "epoch": 0.18468968217711937,
+      "grad_norm": 5.07678317608623,
+      "learning_rate": 2.775469983163972e-05,
+      "loss": 0.642,
+      "step": 2830
+    },
+    {
+      "epoch": 0.1853422958950597,
+      "grad_norm": 3.8465548570361605,
+      "learning_rate": 2.773832321798414e-05,
+      "loss": 0.735,
+      "step": 2840
+    },
+    {
+      "epoch": 0.18599490961300005,
+      "grad_norm": 2.596039278811819,
+      "learning_rate": 2.7721891965931252e-05,
+      "loss": 0.6885,
+      "step": 2850
+    },
+    {
+      "epoch": 0.18664752333094042,
+      "grad_norm": 14.003078667143276,
+      "learning_rate": 2.7705406145959505e-05,
+      "loss": 0.7036,
+      "step": 2860
+    },
+    {
+      "epoch": 0.18730013704888077,
+      "grad_norm": 4.5877627845774365,
+      "learning_rate": 2.7688865828781413e-05,
+      "loss": 0.6995,
+      "step": 2870
+    },
+    {
+      "epoch": 0.1879527507668211,
+      "grad_norm": 7.044776485625493,
+      "learning_rate": 2.767227108534323e-05,
+      "loss": 0.7161,
+      "step": 2880
+    },
+    {
+      "epoch": 0.18860536448476148,
+      "grad_norm": 3.072683258675077,
+      "learning_rate": 2.765562198682468e-05,
+      "loss": 0.7406,
+      "step": 2890
+    },
+    {
+      "epoch": 0.18925797820270182,
+      "grad_norm": 8.84720999495458,
+      "learning_rate": 2.763891860463861e-05,
+      "loss": 0.6727,
+      "step": 2900
+    },
+    {
+      "epoch": 0.18991059192064216,
+      "grad_norm": 9.494450604703584,
+      "learning_rate": 2.7622161010430717e-05,
+      "loss": 0.6859,
+      "step": 2910
+    },
+    {
+      "epoch": 0.19056320563858253,
+      "grad_norm": 2.803990269441359,
+      "learning_rate": 2.7605349276079238e-05,
+      "loss": 0.7,
+      "step": 2920
+    },
+    {
+      "epoch": 0.19121581935652288,
+      "grad_norm": 6.501435928194476,
+      "learning_rate": 2.7588483473694613e-05,
+      "loss": 0.66,
+      "step": 2930
+    },
+    {
+      "epoch": 0.19186843307446322,
+      "grad_norm": 3.9434365221991667,
+      "learning_rate": 2.7571563675619202e-05,
+      "loss": 0.6575,
+      "step": 2940
+    },
+    {
+      "epoch": 0.1925210467924036,
+      "grad_norm": 6.473206095572867,
+      "learning_rate": 2.7554589954426986e-05,
+      "loss": 0.6509,
+      "step": 2950
+    },
+    {
+      "epoch": 0.19317366051034393,
+      "grad_norm": 6.359600241231479,
+      "learning_rate": 2.7537562382923217e-05,
+      "loss": 0.6554,
+      "step": 2960
+    },
+    {
+      "epoch": 0.19382627422828427,
+      "grad_norm": 9.209939347687689,
+      "learning_rate": 2.752048103414413e-05,
+      "loss": 0.723,
+      "step": 2970
+    },
+    {
+      "epoch": 0.19447888794622464,
+      "grad_norm": 23.703947692957573,
+      "learning_rate": 2.7503345981356633e-05,
+      "loss": 0.6927,
+      "step": 2980
+    },
+    {
+      "epoch": 0.19513150166416499,
+      "grad_norm": 8.212074266427711,
+      "learning_rate": 2.7486157298057986e-05,
+      "loss": 0.6999,
+      "step": 2990
+    },
+    {
+      "epoch": 0.19578411538210533,
+      "grad_norm": 5.189620722030213,
+      "learning_rate": 2.7468915057975487e-05,
+      "loss": 0.6722,
+      "step": 3000
+    },
+    {
+      "epoch": 0.19643672910004567,
+      "grad_norm": 4.021048004797352,
+      "learning_rate": 2.745161933506614e-05,
+      "loss": 0.66,
+      "step": 3010
+    },
+    {
+      "epoch": 0.19708934281798604,
+      "grad_norm": 4.156307822377388,
+      "learning_rate": 2.7434270203516373e-05,
+      "loss": 0.6987,
+      "step": 3020
+    },
+    {
+      "epoch": 0.19774195653592638,
+      "grad_norm": 4.75441596904026,
+      "learning_rate": 2.7416867737741683e-05,
+      "loss": 0.6963,
+      "step": 3030
+    },
+    {
+      "epoch": 0.19839457025386673,
+      "grad_norm": 5.880889862093012,
+      "learning_rate": 2.739941201238635e-05,
+      "loss": 0.6445,
+      "step": 3040
+    },
+    {
+      "epoch": 0.1990471839718071,
+      "grad_norm": 4.686264689115436,
+      "learning_rate": 2.738190310232308e-05,
+      "loss": 0.751,
+      "step": 3050
+    },
+    {
+      "epoch": 0.19969979768974744,
+      "grad_norm": 5.015165789251315,
+      "learning_rate": 2.7364341082652716e-05,
+      "loss": 0.6676,
+      "step": 3060
+    },
+    {
+      "epoch": 0.20035241140768778,
+      "grad_norm": 4.629542414090964,
+      "learning_rate": 2.734672602870391e-05,
+      "loss": 0.6625,
+      "step": 3070
+    },
+    {
+      "epoch": 0.20100502512562815,
+      "grad_norm": 3.582640218606122,
+      "learning_rate": 2.7329058016032773e-05,
+      "loss": 0.7243,
+      "step": 3080
+    },
+    {
+      "epoch": 0.2016576388435685,
+      "grad_norm": 35.16576433756719,
+      "learning_rate": 2.7311337120422588e-05,
+      "loss": 0.6734,
+      "step": 3090
+    },
+    {
+      "epoch": 0.20231025256150884,
+      "grad_norm": 8.429048501615004,
+      "learning_rate": 2.729356341788347e-05,
+      "loss": 0.6761,
+      "step": 3100
+    },
+    {
+      "epoch": 0.2029628662794492,
+      "grad_norm": 10.361847043143795,
+      "learning_rate": 2.727573698465202e-05,
+      "loss": 0.691,
+      "step": 3110
+    },
+    {
+      "epoch": 0.20361547999738955,
+      "grad_norm": 3.125915545815778,
+      "learning_rate": 2.7257857897191044e-05,
+      "loss": 0.6439,
+      "step": 3120
+    },
+    {
+      "epoch": 0.2042680937153299,
+      "grad_norm": 3.7497179561089937,
+      "learning_rate": 2.7239926232189167e-05,
+      "loss": 0.6707,
+      "step": 3130
+    },
+    {
+      "epoch": 0.20492070743327026,
+      "grad_norm": 3.56873592233637,
+      "learning_rate": 2.722194206656056e-05,
+      "loss": 0.6673,
+      "step": 3140
+    },
+    {
+      "epoch": 0.2055733211512106,
+      "grad_norm": 10.54660445254849,
+      "learning_rate": 2.7203905477444574e-05,
+      "loss": 0.6829,
+      "step": 3150
+    },
+    {
+      "epoch": 0.20622593486915095,
+      "grad_norm": 3.6820544103925608,
+      "learning_rate": 2.7185816542205407e-05,
+      "loss": 0.6568,
+      "step": 3160
+    },
+    {
+      "epoch": 0.2068785485870913,
+      "grad_norm": 8.593912019069307,
+      "learning_rate": 2.7167675338431813e-05,
+      "loss": 0.6375,
+      "step": 3170
+    },
+    {
+      "epoch": 0.20753116230503166,
+      "grad_norm": 4.561901523582492,
+      "learning_rate": 2.7149481943936718e-05,
+      "loss": 0.6929,
+      "step": 3180
+    },
+    {
+      "epoch": 0.208183776022972,
+      "grad_norm": 3.3662024382508022,
+      "learning_rate": 2.7131236436756917e-05,
+      "loss": 0.7155,
+      "step": 3190
+    },
+    {
+      "epoch": 0.20883638974091234,
+      "grad_norm": 3.4110738212405542,
+      "learning_rate": 2.7112938895152733e-05,
+      "loss": 0.7195,
+      "step": 3200
+    },
+    {
+      "epoch": 0.2094890034588527,
+      "grad_norm": 3.6699604643477413,
+      "learning_rate": 2.709458939760768e-05,
+      "loss": 0.6266,
+      "step": 3210
+    },
+    {
+      "epoch": 0.21014161717679306,
+      "grad_norm": 1.7543595371849152,
+      "learning_rate": 2.7076188022828125e-05,
+      "loss": 0.6956,
+      "step": 3220
+    },
+    {
+      "epoch": 0.2107942308947334,
+      "grad_norm": 3.9842297097437647,
+      "learning_rate": 2.7057734849742944e-05,
+      "loss": 0.6616,
+      "step": 3230
+    },
+    {
+      "epoch": 0.21144684461267377,
+      "grad_norm": 5.223697167736633,
+      "learning_rate": 2.7039229957503207e-05,
+      "loss": 0.6951,
+      "step": 3240
+    },
+    {
+      "epoch": 0.2120994583306141,
+      "grad_norm": 4.189342719626237,
+      "learning_rate": 2.7020673425481807e-05,
+      "loss": 0.6937,
+      "step": 3250
+    },
+    {
+      "epoch": 0.21275207204855445,
+      "grad_norm": 5.746674612678528,
+      "learning_rate": 2.700206533327315e-05,
+      "loss": 0.6897,
+      "step": 3260
+    },
+    {
+      "epoch": 0.21340468576649482,
+      "grad_norm": 7.965064539148002,
+      "learning_rate": 2.6983405760692782e-05,
+      "loss": 0.6999,
+      "step": 3270
+    },
+    {
+      "epoch": 0.21405729948443517,
+      "grad_norm": 3.6218679643616953,
+      "learning_rate": 2.696469478777708e-05,
+      "loss": 0.6702,
+      "step": 3280
+    },
+    {
+      "epoch": 0.2147099132023755,
+      "grad_norm": 4.021322876113058,
+      "learning_rate": 2.6945932494782878e-05,
+      "loss": 0.736,
+      "step": 3290
+    },
+    {
+      "epoch": 0.21536252692031588,
+      "grad_norm": 5.6555927379479245,
+      "learning_rate": 2.692711896218715e-05,
+      "loss": 0.6576,
+      "step": 3300
+    },
+    {
+      "epoch": 0.21601514063825622,
+      "grad_norm": 5.56743771282241,
+      "learning_rate": 2.6908254270686633e-05,
+      "loss": 0.6824,
+      "step": 3310
+    },
+    {
+      "epoch": 0.21666775435619656,
+      "grad_norm": 51.07644011063222,
+      "learning_rate": 2.688933850119753e-05,
+      "loss": 0.6517,
+      "step": 3320
+    },
+    {
+      "epoch": 0.2173203680741369,
+      "grad_norm": 6.112257177604341,
+      "learning_rate": 2.6870371734855092e-05,
+      "loss": 0.6619,
+      "step": 3330
+    },
+    {
+      "epoch": 0.21797298179207727,
+      "grad_norm": 2.531145729460449,
+      "learning_rate": 2.685135405301335e-05,
+      "loss": 0.7057,
+      "step": 3340
+    },
+    {
+      "epoch": 0.21862559551001762,
+      "grad_norm": 1.995398951056393,
+      "learning_rate": 2.6832285537244697e-05,
+      "loss": 0.687,
+      "step": 3350
+    },
+    {
+      "epoch": 0.21927820922795796,
+      "grad_norm": 2.3570011145840364,
+      "learning_rate": 2.6813166269339587e-05,
+      "loss": 0.6698,
+      "step": 3360
+    },
+    {
+      "epoch": 0.21993082294589833,
+      "grad_norm": 3.6679571799521327,
+      "learning_rate": 2.6793996331306157e-05,
+      "loss": 0.6715,
+      "step": 3370
+    },
+    {
+      "epoch": 0.22058343666383867,
+      "grad_norm": 28.476293508674676,
+      "learning_rate": 2.6774775805369875e-05,
+      "loss": 0.66,
+      "step": 3380
+    },
+    {
+      "epoch": 0.22123605038177901,
+      "grad_norm": 3.2467702810162637,
+      "learning_rate": 2.675550477397321e-05,
+      "loss": 0.6721,
+      "step": 3390
+    },
+    {
+      "epoch": 0.22188866409971938,
+      "grad_norm": 1.6459151219515613,
+      "learning_rate": 2.6736183319775253e-05,
+      "loss": 0.7111,
+      "step": 3400
+    },
+    {
+      "epoch": 0.22254127781765973,
+      "grad_norm": 3.964489549873003,
+      "learning_rate": 2.6716811525651386e-05,
+      "loss": 0.7202,
+      "step": 3410
+    },
+    {
+      "epoch": 0.22319389153560007,
+      "grad_norm": 2.1839922437285586,
+      "learning_rate": 2.6697389474692896e-05,
+      "loss": 0.6455,
+      "step": 3420
+    },
+    {
+      "epoch": 0.22384650525354044,
+      "grad_norm": 6.5190517278902,
+      "learning_rate": 2.6677917250206642e-05,
+      "loss": 0.6543,
+      "step": 3430
+    },
+    {
+      "epoch": 0.22449911897148078,
+      "grad_norm": 3.0950755352607677,
+      "learning_rate": 2.6658394935714707e-05,
+      "loss": 0.6567,
+      "step": 3440
+    },
+    {
+      "epoch": 0.22515173268942112,
+      "grad_norm": 22.06688372148941,
+      "learning_rate": 2.6638822614954007e-05,
+      "loss": 0.673,
+      "step": 3450
+    },
+    {
+      "epoch": 0.2258043464073615,
+      "grad_norm": 4.066518820487963,
+      "learning_rate": 2.6619200371875952e-05,
+      "loss": 0.6879,
+      "step": 3460
+    },
+    {
+      "epoch": 0.22645696012530184,
+      "grad_norm": 3.121077860957678,
+      "learning_rate": 2.659952829064609e-05,
+      "loss": 0.6874,
+      "step": 3470
+    },
+    {
+      "epoch": 0.22710957384324218,
+      "grad_norm": 2.6914813691439923,
+      "learning_rate": 2.6579806455643734e-05,
+      "loss": 0.6774,
+      "step": 3480
+    },
+    {
+      "epoch": 0.22776218756118255,
+      "grad_norm": 4.968423508767704,
+      "learning_rate": 2.656003495146162e-05,
+      "loss": 0.6941,
+      "step": 3490
+    },
+    {
+      "epoch": 0.2284148012791229,
+      "grad_norm": 3.7025765443419836,
+      "learning_rate": 2.6540213862905497e-05,
+      "loss": 0.697,
+      "step": 3500
+    },
+    {
+      "epoch": 0.22906741499706323,
+      "grad_norm": 3.5133821241789924,
+      "learning_rate": 2.652034327499383e-05,
+      "loss": 0.6825,
+      "step": 3510
+    },
+    {
+      "epoch": 0.22972002871500358,
+      "grad_norm": 3.204727293127362,
+      "learning_rate": 2.6500423272957385e-05,
+      "loss": 0.6552,
+      "step": 3520
+    },
+    {
+      "epoch": 0.23037264243294395,
+      "grad_norm": 10.477867050932252,
+      "learning_rate": 2.6480453942238878e-05,
+      "loss": 0.7001,
+      "step": 3530
+    },
+    {
+      "epoch": 0.2310252561508843,
+      "grad_norm": 4.290081854975228,
+      "learning_rate": 2.6460435368492618e-05,
+      "loss": 0.7023,
+      "step": 3540
+    },
+    {
+      "epoch": 0.23167786986882463,
+      "grad_norm": 2.1041454905838695,
+      "learning_rate": 2.6440367637584127e-05,
+      "loss": 0.6998,
+      "step": 3550
+    },
+    {
+      "epoch": 0.232330483586765,
+      "grad_norm": 10.10346106723381,
+      "learning_rate": 2.642025083558978e-05,
+      "loss": 0.7233,
+      "step": 3560
+    },
+    {
+      "epoch": 0.23298309730470534,
+      "grad_norm": 2.801890474132496,
+      "learning_rate": 2.6400085048796427e-05,
+      "loss": 0.6821,
+      "step": 3570
+    },
+    {
+      "epoch": 0.2336357110226457,
+      "grad_norm": 3.935419895594201,
+      "learning_rate": 2.6379870363701032e-05,
+      "loss": 0.7208,
+      "step": 3580
+    },
+    {
+      "epoch": 0.23428832474058606,
+      "grad_norm": 8.554570222512323,
+      "learning_rate": 2.6359606867010294e-05,
+      "loss": 0.6633,
+      "step": 3590
+    },
+    {
+      "epoch": 0.2349409384585264,
+      "grad_norm": 6.675371241157707,
+      "learning_rate": 2.6339294645640287e-05,
+      "loss": 0.6769,
+      "step": 3600
+    },
+    {
+      "epoch": 0.23559355217646674,
+      "grad_norm": 6.178285461410454,
+      "learning_rate": 2.631893378671607e-05,
+      "loss": 0.7073,
+      "step": 3610
+    },
+    {
+      "epoch": 0.2362461658944071,
+      "grad_norm": 17.744119879081158,
+      "learning_rate": 2.6298524377571334e-05,
+      "loss": 0.7105,
+      "step": 3620
+    },
+    {
+      "epoch": 0.23689877961234745,
+      "grad_norm": 16.785021253384297,
+      "learning_rate": 2.6278066505748003e-05,
+      "loss": 0.6887,
+      "step": 3630
+    },
+    {
+      "epoch": 0.2375513933302878,
+      "grad_norm": 3.2589997614122734,
+      "learning_rate": 2.6257560258995883e-05,
+      "loss": 0.6263,
+      "step": 3640
+    },
+    {
+      "epoch": 0.23820400704822817,
+      "grad_norm": 3.492404598170054,
+      "learning_rate": 2.6237005725272266e-05,
+      "loss": 0.7226,
+      "step": 3650
+    },
+    {
+      "epoch": 0.2388566207661685,
+      "grad_norm": 7.319922437830172,
+      "learning_rate": 2.621640299274156e-05,
+      "loss": 0.6675,
+      "step": 3660
+    },
+    {
+      "epoch": 0.23950923448410885,
+      "grad_norm": 2.2589380963047687,
+      "learning_rate": 2.6195752149774927e-05,
+      "loss": 0.7007,
+      "step": 3670
+    },
+    {
+      "epoch": 0.2401618482020492,
+      "grad_norm": 3.531831136500981,
+      "learning_rate": 2.6175053284949867e-05,
+      "loss": 0.6375,
+      "step": 3680
+    },
+    {
+      "epoch": 0.24081446191998956,
+      "grad_norm": 3.79013354707819,
+      "learning_rate": 2.6154306487049882e-05,
+      "loss": 0.6911,
+      "step": 3690
+    },
+    {
+      "epoch": 0.2414670756379299,
+      "grad_norm": 6.397972453338,
+      "learning_rate": 2.613351184506405e-05,
+      "loss": 0.7063,
+      "step": 3700
+    },
+    {
+      "epoch": 0.24211968935587025,
+      "grad_norm": 1.9616647412861352,
+      "learning_rate": 2.6112669448186684e-05,
+      "loss": 0.6643,
+      "step": 3710
+    },
+    {
+      "epoch": 0.24277230307381062,
+      "grad_norm": 5.149479530478246,
+      "learning_rate": 2.6091779385816927e-05,
+      "loss": 0.682,
+      "step": 3720
+    },
+    {
+      "epoch": 0.24342491679175096,
+      "grad_norm": 33.6135334189408,
+      "learning_rate": 2.607084174755837e-05,
+      "loss": 0.6874,
+      "step": 3730
+    },
+    {
+      "epoch": 0.2440775305096913,
+      "grad_norm": 8.824063553443779,
+      "learning_rate": 2.604985662321867e-05,
+      "loss": 0.6784,
+      "step": 3740
+    },
+    {
+      "epoch": 0.24473014422763167,
+      "grad_norm": 4.503480413045945,
+      "learning_rate": 2.602882410280917e-05,
+      "loss": 0.66,
+      "step": 3750
+    },
+    {
+      "epoch": 0.24538275794557202,
+      "grad_norm": 2.976817523113899,
+      "learning_rate": 2.600774427654451e-05,
+      "loss": 0.6528,
+      "step": 3760
+    },
+    {
+      "epoch": 0.24603537166351236,
+      "grad_norm": 3.7759204222408096,
+      "learning_rate": 2.5986617234842235e-05,
+      "loss": 0.7417,
+      "step": 3770
+    },
+    {
+      "epoch": 0.24668798538145273,
+      "grad_norm": 1.8006275301713257,
+      "learning_rate": 2.596544306832241e-05,
+      "loss": 0.6103,
+      "step": 3780
+    },
+    {
+      "epoch": 0.24734059909939307,
+      "grad_norm": 8.715287590950098,
+      "learning_rate": 2.5944221867807232e-05,
+      "loss": 0.6805,
+      "step": 3790
+    },
+    {
+      "epoch": 0.2479932128173334,
+      "grad_norm": 2.512279584335586,
+      "learning_rate": 2.5922953724320642e-05,
+      "loss": 0.6252,
+      "step": 3800
+    },
+    {
+      "epoch": 0.24864582653527378,
+      "grad_norm": 9.093713085191398,
+      "learning_rate": 2.590163872908794e-05,
+      "loss": 0.6693,
+      "step": 3810
+    },
+    {
+      "epoch": 0.24929844025321413,
+      "grad_norm": 2.605969794050745,
+      "learning_rate": 2.5880276973535374e-05,
+      "loss": 0.7169,
+      "step": 3820
+    },
+    {
+      "epoch": 0.24995105397115447,
+      "grad_norm": 1.7406155460998103,
+      "learning_rate": 2.5858868549289773e-05,
+      "loss": 0.673,
+      "step": 3830
+    },
+    {
+      "epoch": 0.2506036676890948,
+      "grad_norm": 24.750209614800486,
+      "learning_rate": 2.5837413548178127e-05,
+      "loss": 0.7151,
+      "step": 3840
+    },
+    {
+      "epoch": 0.25125628140703515,
+      "grad_norm": 1.9145264355240845,
+      "learning_rate": 2.581591206222723e-05,
+      "loss": 0.697,
+      "step": 3850
+    },
+    {
+      "epoch": 0.25190889512497555,
+      "grad_norm": 4.162446186072935,
+      "learning_rate": 2.5794364183663235e-05,
+      "loss": 0.6978,
+      "step": 3860
+    },
+    {
+      "epoch": 0.2525615088429159,
+      "grad_norm": 16.83424712366737,
+      "learning_rate": 2.5772770004911307e-05,
+      "loss": 0.6709,
+      "step": 3870
+    },
+    {
+      "epoch": 0.25321412256085624,
+      "grad_norm": 5.706826041185719,
+      "learning_rate": 2.57511296185952e-05,
+      "loss": 0.6275,
+      "step": 3880
+    },
+    {
+      "epoch": 0.2538667362787966,
+      "grad_norm": 7.487078662155924,
+      "learning_rate": 2.572944311753687e-05,
+      "loss": 0.707,
+      "step": 3890
+    },
+    {
+      "epoch": 0.2545193499967369,
+      "grad_norm": 4.599310176375447,
+      "learning_rate": 2.570771059475606e-05,
+      "loss": 0.6573,
+      "step": 3900
+    },
+    {
+      "epoch": 0.25517196371467726,
+      "grad_norm": 2.758393828851342,
+      "learning_rate": 2.5685932143469927e-05,
+      "loss": 0.6944,
+      "step": 3910
+    },
+    {
+      "epoch": 0.25582457743261766,
+      "grad_norm": 21.68704478201106,
+      "learning_rate": 2.566410785709263e-05,
+      "loss": 0.6714,
+      "step": 3920
+    },
+    {
+      "epoch": 0.256477191150558,
+      "grad_norm": 3.78818613516299,
+      "learning_rate": 2.5642237829234913e-05,
+      "loss": 0.7082,
+      "step": 3930
+    },
+    {
+      "epoch": 0.25712980486849835,
+      "grad_norm": 5.879311136389752,
+      "learning_rate": 2.562032215370373e-05,
+      "loss": 0.676,
+      "step": 3940
+    },
+    {
+      "epoch": 0.2577824185864387,
+      "grad_norm": 2.7847168991870905,
+      "learning_rate": 2.559836092450183e-05,
+      "loss": 0.6798,
+      "step": 3950
+    },
+    {
+      "epoch": 0.25843503230437903,
+      "grad_norm": 4.112944354600252,
+      "learning_rate": 2.5576354235827354e-05,
+      "loss": 0.6865,
+      "step": 3960
+    },
+    {
+      "epoch": 0.2590876460223194,
+      "grad_norm": 5.714785342853446,
+      "learning_rate": 2.555430218207343e-05,
+      "loss": 0.6798,
+      "step": 3970
+    },
+    {
+      "epoch": 0.2597402597402597,
+      "grad_norm": 4.862160034847451,
+      "learning_rate": 2.553220485782778e-05,
+      "loss": 0.729,
+      "step": 3980
+    },
+    {
+      "epoch": 0.2603928734582001,
+      "grad_norm": 3.1205186373681713,
+      "learning_rate": 2.5510062357872285e-05,
+      "loss": 0.7087,
+      "step": 3990
+    },
+    {
+      "epoch": 0.26104548717614046,
+      "grad_norm": 7.094777843607683,
+      "learning_rate": 2.5487874777182615e-05,
+      "loss": 0.7291,
+      "step": 4000
+    },
+    {
+      "epoch": 0.2616981008940808,
+      "grad_norm": 4.923924966818384,
+      "learning_rate": 2.54656422109278e-05,
+      "loss": 0.6984,
+      "step": 4010
+    },
+    {
+      "epoch": 0.26235071461202114,
+      "grad_norm": 5.84865229806092,
+      "learning_rate": 2.5443364754469823e-05,
+      "loss": 0.6943,
+      "step": 4020
+    },
+    {
+      "epoch": 0.2630033283299615,
+      "grad_norm": 5.789406461188536,
+      "learning_rate": 2.5421042503363218e-05,
+      "loss": 0.6773,
+      "step": 4030
+    },
+    {
+      "epoch": 0.2636559420479018,
+      "grad_norm": 5.041801808124959,
+      "learning_rate": 2.539867555335465e-05,
+      "loss": 0.6933,
+      "step": 4040
+    },
+    {
+      "epoch": 0.2643085557658422,
+      "grad_norm": 4.582258734296027,
+      "learning_rate": 2.5376264000382525e-05,
+      "loss": 0.6671,
+      "step": 4050
+    },
+    {
+      "epoch": 0.26496116948378257,
+      "grad_norm": 3.5384290519868875,
+      "learning_rate": 2.5353807940576542e-05,
+      "loss": 0.657,
+      "step": 4060
+    },
+    {
+      "epoch": 0.2656137832017229,
+      "grad_norm": 11.349344350556114,
+      "learning_rate": 2.5331307470257322e-05,
+      "loss": 0.7067,
+      "step": 4070
+    },
+    {
+      "epoch": 0.26626639691966325,
+      "grad_norm": 3.768338440648807,
+      "learning_rate": 2.530876268593597e-05,
+      "loss": 0.6564,
+      "step": 4080
+    },
+    {
+      "epoch": 0.2669190106376036,
+      "grad_norm": 6.106759762838668,
+      "learning_rate": 2.5286173684313667e-05,
+      "loss": 0.6767,
+      "step": 4090
+    },
+    {
+      "epoch": 0.26757162435554394,
+      "grad_norm": 8.634680581251073,
+      "learning_rate": 2.526354056228125e-05,
+      "loss": 0.7171,
+      "step": 4100
+    },
+    {
+      "epoch": 0.2682242380734843,
+      "grad_norm": 21.27548735763032,
+      "learning_rate": 2.5240863416918805e-05,
+      "loss": 0.6866,
+      "step": 4110
+    },
+    {
+      "epoch": 0.2688768517914247,
+      "grad_norm": 4.472184788538698,
+      "learning_rate": 2.5218142345495246e-05,
+      "loss": 0.6467,
+      "step": 4120
+    },
+    {
+      "epoch": 0.269529465509365,
+      "grad_norm": 363.8219860041446,
+      "learning_rate": 2.5195377445467905e-05,
+      "loss": 0.6524,
+      "step": 4130
+    },
+    {
+      "epoch": 0.27018207922730536,
+      "grad_norm": 5.253740522188672,
+      "learning_rate": 2.5172568814482094e-05,
+      "loss": 0.6984,
+      "step": 4140
+    },
+    {
+      "epoch": 0.2708346929452457,
+      "grad_norm": 2.880982518554529,
+      "learning_rate": 2.514971655037072e-05,
+      "loss": 0.6775,
+      "step": 4150
+    },
+    {
+      "epoch": 0.27148730666318605,
+      "grad_norm": 3.842728021491472,
+      "learning_rate": 2.5126820751153825e-05,
+      "loss": 0.6392,
+      "step": 4160
+    },
+    {
+      "epoch": 0.2721399203811264,
+      "grad_norm": 4.609029259080438,
+      "learning_rate": 2.510388151503819e-05,
+      "loss": 0.6674,
+      "step": 4170
+    },
+    {
+      "epoch": 0.2727925340990668,
+      "grad_norm": 9.747845142610567,
+      "learning_rate": 2.5080898940416927e-05,
+      "loss": 0.6236,
+      "step": 4180
+    },
+    {
+      "epoch": 0.27344514781700713,
+      "grad_norm": 2.9805241050929348,
+      "learning_rate": 2.5057873125869017e-05,
+      "loss": 0.6835,
+      "step": 4190
+    },
+    {
+      "epoch": 0.27409776153494747,
+      "grad_norm": 106.07926539562291,
+      "learning_rate": 2.5034804170158925e-05,
+      "loss": 0.6394,
+      "step": 4200
+    },
+    {
+      "epoch": 0.2747503752528878,
+      "grad_norm": 5.554717373667031,
+      "learning_rate": 2.501169217223615e-05,
+      "loss": 0.6558,
+      "step": 4210
+    },
+    {
+      "epoch": 0.27540298897082816,
+      "grad_norm": 9.051439573328066,
+      "learning_rate": 2.498853723123482e-05,
+      "loss": 0.6682,
+      "step": 4220
+    },
+    {
+      "epoch": 0.2760556026887685,
+      "grad_norm": 2.950104313961938,
+      "learning_rate": 2.496533944647325e-05,
+      "loss": 0.6912,
+      "step": 4230
+    },
+    {
+      "epoch": 0.2767082164067089,
+      "grad_norm": 2.721831318519013,
+      "learning_rate": 2.494209891745354e-05,
+      "loss": 0.6344,
+      "step": 4240
+    },
+    {
+      "epoch": 0.27736083012464924,
+      "grad_norm": 3.139038444339525,
+      "learning_rate": 2.4918815743861113e-05,
+      "loss": 0.6582,
+      "step": 4250
+    },
+    {
+      "epoch": 0.2780134438425896,
+      "grad_norm": 34.47266488137286,
+      "learning_rate": 2.4895490025564323e-05,
+      "loss": 0.6491,
+      "step": 4260
+    },
+    {
+      "epoch": 0.2786660575605299,
+      "grad_norm": 6.804982368395946,
+      "learning_rate": 2.4872121862614e-05,
+      "loss": 0.6766,
+      "step": 4270
+    },
+    {
+      "epoch": 0.27931867127847027,
+      "grad_norm": 4.937357646966404,
+      "learning_rate": 2.4848711355243038e-05,
+      "loss": 0.6779,
+      "step": 4280
+    },
+    {
+      "epoch": 0.2799712849964106,
+      "grad_norm": 3.22339790826578,
+      "learning_rate": 2.4825258603865952e-05,
+      "loss": 0.6732,
+      "step": 4290
+    },
+    {
+      "epoch": 0.28062389871435095,
+      "grad_norm": 5.450160928852526,
+      "learning_rate": 2.4801763709078466e-05,
+      "loss": 0.6637,
+      "step": 4300
+    },
+    {
+      "epoch": 0.28127651243229135,
+      "grad_norm": 4.818596483449563,
+      "learning_rate": 2.4778226771657054e-05,
+      "loss": 0.6325,
+      "step": 4310
+    },
+    {
+      "epoch": 0.2819291261502317,
+      "grad_norm": 17.57607019240089,
+      "learning_rate": 2.4754647892558536e-05,
+      "loss": 0.6927,
+      "step": 4320
+    },
+    {
+      "epoch": 0.28258173986817203,
+      "grad_norm": 6.082993937740036,
+      "learning_rate": 2.4731027172919623e-05,
+      "loss": 0.6717,
+      "step": 4330
+    },
+    {
+      "epoch": 0.2832343535861124,
+      "grad_norm": 65.13799954231784,
+      "learning_rate": 2.47073647140565e-05,
+      "loss": 0.6354,
+      "step": 4340
+    },
+    {
+      "epoch": 0.2838869673040527,
+      "grad_norm": 4.5660574643583125,
+      "learning_rate": 2.468366061746438e-05,
+      "loss": 0.6963,
+      "step": 4350
+    },
+    {
+      "epoch": 0.28453958102199306,
+      "grad_norm": 2.282525842359472,
+      "learning_rate": 2.4659914984817065e-05,
+      "loss": 0.6632,
+      "step": 4360
+    },
+    {
+      "epoch": 0.28519219473993346,
+      "grad_norm": 2.6517071641202814,
+      "learning_rate": 2.4636127917966536e-05,
+      "loss": 0.7145,
+      "step": 4370
+    },
+    {
+      "epoch": 0.2858448084578738,
+      "grad_norm": 4.738045556857019,
+      "learning_rate": 2.4612299518942476e-05,
+      "loss": 0.7087,
+      "step": 4380
+    },
+    {
+      "epoch": 0.28649742217581414,
+      "grad_norm": 5.169948622487004,
+      "learning_rate": 2.4588429889951872e-05,
+      "loss": 0.632,
+      "step": 4390
+    },
+    {
+      "epoch": 0.2871500358937545,
+      "grad_norm": 2.386433835669107,
+      "learning_rate": 2.4564519133378545e-05,
+      "loss": 0.6696,
+      "step": 4400
+    },
+    {
+      "epoch": 0.2878026496116948,
+      "grad_norm": 2.262021691782428,
+      "learning_rate": 2.454056735178273e-05,
+      "loss": 0.6918,
+      "step": 4410
+    },
+    {
+      "epoch": 0.28845526332963517,
+      "grad_norm": 3.2213155651118286,
+      "learning_rate": 2.4516574647900635e-05,
+      "loss": 0.667,
+      "step": 4420
+    },
+    {
+      "epoch": 0.28910787704757557,
+      "grad_norm": 6.9747348967457405,
+      "learning_rate": 2.4492541124643987e-05,
+      "loss": 0.6761,
+      "step": 4430
+    },
+    {
+      "epoch": 0.2897604907655159,
+      "grad_norm": 6.9858902006653345,
+      "learning_rate": 2.4468466885099602e-05,
+      "loss": 0.6454,
+      "step": 4440
+    },
+    {
+      "epoch": 0.29041310448345625,
+      "grad_norm": 2.834408013972733,
+      "learning_rate": 2.444435203252894e-05,
+      "loss": 0.6961,
+      "step": 4450
+    },
+    {
+      "epoch": 0.2910657182013966,
+      "grad_norm": 2.770208579931205,
+      "learning_rate": 2.4420196670367668e-05,
+      "loss": 0.6895,
+      "step": 4460
+    },
+    {
+      "epoch": 0.29171833191933694,
+      "grad_norm": 6.617102756430502,
+      "learning_rate": 2.43960009022252e-05,
+      "loss": 0.6772,
+      "step": 4470
+    },
+    {
+      "epoch": 0.2923709456372773,
+      "grad_norm": 7.760094006549052,
+      "learning_rate": 2.4371764831884272e-05,
+      "loss": 0.6283,
+      "step": 4480
+    },
+    {
+      "epoch": 0.2930235593552176,
+      "grad_norm": 3.207368003644612,
+      "learning_rate": 2.4347488563300482e-05,
+      "loss": 0.6547,
+      "step": 4490
+    },
+    {
+      "epoch": 0.293676173073158,
+      "grad_norm": 4.982915873993841,
+      "learning_rate": 2.432317220060186e-05,
+      "loss": 0.6844,
+      "step": 4500
+    },
+    {
+      "epoch": 0.29432878679109836,
+      "grad_norm": 4.769955128072813,
+      "learning_rate": 2.429881584808839e-05,
+      "loss": 0.6594,
+      "step": 4510
+    },
+    {
+      "epoch": 0.2949814005090387,
+      "grad_norm": 15.559397928313343,
+      "learning_rate": 2.427441961023161e-05,
+      "loss": 0.6796,
+      "step": 4520
+    },
+    {
+      "epoch": 0.29563401422697905,
+      "grad_norm": 1.8238291681792838,
+      "learning_rate": 2.4249983591674123e-05,
+      "loss": 0.6909,
+      "step": 4530
+    },
+    {
+      "epoch": 0.2962866279449194,
+      "grad_norm": 6.342739682478503,
+      "learning_rate": 2.4225507897229163e-05,
+      "loss": 0.6159,
+      "step": 4540
+    },
+    {
+      "epoch": 0.29693924166285973,
+      "grad_norm": 9.919227547257767,
+      "learning_rate": 2.4200992631880154e-05,
+      "loss": 0.6904,
+      "step": 4550
+    },
+    {
+      "epoch": 0.29759185538080013,
+      "grad_norm": 3.7408822158426234,
+      "learning_rate": 2.417643790078024e-05,
+      "loss": 0.6687,
+      "step": 4560
+    },
+    {
+      "epoch": 0.2982444690987405,
+      "grad_norm": 3.1384506669870293,
+      "learning_rate": 2.4151843809251855e-05,
+      "loss": 0.7191,
+      "step": 4570
+    },
+    {
+      "epoch": 0.2988970828166808,
+      "grad_norm": 3.5015910483221684,
+      "learning_rate": 2.4127210462786255e-05,
+      "loss": 0.6586,
+      "step": 4580
+    },
+    {
+      "epoch": 0.29954969653462116,
+      "grad_norm": 3.9707619680987936,
+      "learning_rate": 2.410253796704307e-05,
+      "loss": 0.6968,
+      "step": 4590
+    },
+    {
+      "epoch": 0.3002023102525615,
+      "grad_norm": 4.706277494109596,
+      "learning_rate": 2.4077826427849867e-05,
+      "loss": 0.6933,
+      "step": 4600
+    },
+    {
+      "epoch": 0.30085492397050184,
+      "grad_norm": 1.520537682976707,
+      "learning_rate": 2.4053075951201666e-05,
+      "loss": 0.6868,
+      "step": 4610
+    },
+    {
+      "epoch": 0.3015075376884422,
+      "grad_norm": 2.5680418797343116,
+      "learning_rate": 2.4028286643260507e-05,
+      "loss": 0.6254,
+      "step": 4620
+    },
+    {
+      "epoch": 0.3021601514063826,
+      "grad_norm": 5.251605560389514,
+      "learning_rate": 2.4003458610354988e-05,
+      "loss": 0.6993,
+      "step": 4630
+    },
+    {
+      "epoch": 0.3028127651243229,
+      "grad_norm": 7.585261117342086,
+      "learning_rate": 2.397859195897981e-05,
+      "loss": 0.6427,
+      "step": 4640
+    },
+    {
+      "epoch": 0.30346537884226327,
+      "grad_norm": 5.643680495196406,
+      "learning_rate": 2.3953686795795324e-05,
+      "loss": 0.6594,
+      "step": 4650
+    },
+    {
+      "epoch": 0.3041179925602036,
+      "grad_norm": 8.250100337487616,
+      "learning_rate": 2.3928743227627055e-05,
+      "loss": 0.6693,
+      "step": 4660
+    },
+    {
+      "epoch": 0.30477060627814395,
+      "grad_norm": 4.867583869481904,
+      "learning_rate": 2.3903761361465286e-05,
+      "loss": 0.6703,
+      "step": 4670
+    },
+    {
+      "epoch": 0.3054232199960843,
+      "grad_norm": 8.954704318465929,
+      "learning_rate": 2.3878741304464537e-05,
+      "loss": 0.6714,
+      "step": 4680
+    },
+    {
+      "epoch": 0.3060758337140247,
+      "grad_norm": 3.2721913590097427,
+      "learning_rate": 2.385368316394317e-05,
+      "loss": 0.6611,
+      "step": 4690
+    },
+    {
+      "epoch": 0.30672844743196503,
+      "grad_norm": 4.795659908514144,
+      "learning_rate": 2.382858704738288e-05,
+      "loss": 0.6574,
+      "step": 4700
+    },
+    {
+      "epoch": 0.3073810611499054,
+      "grad_norm": 6.665483115358767,
+      "learning_rate": 2.3803453062428258e-05,
+      "loss": 0.6953,
+      "step": 4710
+    },
+    {
+      "epoch": 0.3080336748678457,
+      "grad_norm": 2.3307511028486454,
+      "learning_rate": 2.377828131688632e-05,
+      "loss": 0.701,
+      "step": 4720
+    },
+    {
+      "epoch": 0.30868628858578606,
+      "grad_norm": 5.400233277827547,
+      "learning_rate": 2.375307191872606e-05,
+      "loss": 0.6575,
+      "step": 4730
+    },
+    {
+      "epoch": 0.3093389023037264,
+      "grad_norm": 11.992545673600683,
+      "learning_rate": 2.3727824976077948e-05,
+      "loss": 0.649,
+      "step": 4740
+    },
+    {
+      "epoch": 0.3099915160216668,
+      "grad_norm": 8.495543714235616,
+      "learning_rate": 2.3702540597233534e-05,
+      "loss": 0.6512,
+      "step": 4750
+    },
+    {
+      "epoch": 0.31064412973960714,
+      "grad_norm": 4.70397191327332,
+      "learning_rate": 2.3677218890644915e-05,
+      "loss": 0.7181,
+      "step": 4760
+    },
+    {
+      "epoch": 0.3112967434575475,
+      "grad_norm": 2.343276522812816,
+      "learning_rate": 2.365185996492429e-05,
+      "loss": 0.6674,
+      "step": 4770
+    },
+    {
+      "epoch": 0.31194935717548783,
+      "grad_norm": 8.473831735394866,
+      "learning_rate": 2.362646392884353e-05,
+      "loss": 0.6315,
+      "step": 4780
+    },
+    {
+      "epoch": 0.31260197089342817,
+      "grad_norm": 8.747856095472184,
+      "learning_rate": 2.360103089133366e-05,
+      "loss": 0.6515,
+      "step": 4790
+    },
+    {
+      "epoch": 0.3132545846113685,
+      "grad_norm": 3.291537769224359,
+      "learning_rate": 2.3575560961484424e-05,
+      "loss": 0.6503,
+      "step": 4800
+    },
+    {
+      "epoch": 0.31390719832930886,
+      "grad_norm": 6.039997299901094,
+      "learning_rate": 2.3550054248543815e-05,
+      "loss": 0.6745,
+      "step": 4810
+    },
+    {
+      "epoch": 0.31455981204724925,
+      "grad_norm": 3.8499254690114926,
+      "learning_rate": 2.352451086191758e-05,
+      "loss": 0.6777,
+      "step": 4820
+    },
+    {
+      "epoch": 0.3152124257651896,
+      "grad_norm": 4.716777667209856,
+      "learning_rate": 2.3498930911168793e-05,
+      "loss": 0.6176,
+      "step": 4830
+    },
+    {
+      "epoch": 0.31586503948312994,
+      "grad_norm": 1.9400354838321467,
+      "learning_rate": 2.3473314506017343e-05,
+      "loss": 0.7005,
+      "step": 4840
+    },
+    {
+      "epoch": 0.3165176532010703,
+      "grad_norm": 3.219880433320904,
+      "learning_rate": 2.3447661756339496e-05,
+      "loss": 0.7128,
+      "step": 4850
+    },
+    {
+      "epoch": 0.3171702669190106,
+      "grad_norm": 2.8512997858968068,
+      "learning_rate": 2.34219727721674e-05,
+      "loss": 0.6683,
+      "step": 4860
+    },
+    {
+      "epoch": 0.31782288063695097,
+      "grad_norm": 19.226311711082776,
+      "learning_rate": 2.3396247663688627e-05,
+      "loss": 0.6853,
+      "step": 4870
+    },
+    {
+      "epoch": 0.31847549435489136,
+      "grad_norm": 4.223645344092681,
+      "learning_rate": 2.3370486541245703e-05,
+      "loss": 0.6904,
+      "step": 4880
+    },
+    {
+      "epoch": 0.3191281080728317,
+      "grad_norm": 5.234619317117684,
+      "learning_rate": 2.334468951533562e-05,
+      "loss": 0.6708,
+      "step": 4890
+    },
+    {
+      "epoch": 0.31978072179077205,
+      "grad_norm": 2.1429171576497215,
+      "learning_rate": 2.3318856696609384e-05,
+      "loss": 0.6734,
+      "step": 4900
+    },
+    {
+      "epoch": 0.3204333355087124,
+      "grad_norm": 3.508871143887552,
+      "learning_rate": 2.3292988195871503e-05,
+      "loss": 0.6806,
+      "step": 4910
+    },
+    {
+      "epoch": 0.32108594922665273,
+      "grad_norm": 12.968809417220816,
+      "learning_rate": 2.3267084124079555e-05,
+      "loss": 0.6633,
+      "step": 4920
+    },
+    {
+      "epoch": 0.3217385629445931,
+      "grad_norm": 4.101668757924199,
+      "learning_rate": 2.3241144592343686e-05,
+      "loss": 0.6585,
+      "step": 4930
+    },
+    {
+      "epoch": 0.3223911766625335,
+      "grad_norm": 4.363073823894001,
+      "learning_rate": 2.3215169711926147e-05,
+      "loss": 0.6538,
+      "step": 4940
+    },
+    {
+      "epoch": 0.3230437903804738,
+      "grad_norm": 12.245523685894241,
+      "learning_rate": 2.31891595942408e-05,
+      "loss": 0.6637,
+      "step": 4950
+    },
+    {
+      "epoch": 0.32369640409841416,
+      "grad_norm": 5.435880397881584,
+      "learning_rate": 2.3163114350852648e-05,
+      "loss": 0.6633,
+      "step": 4960
+    },
+    {
+      "epoch": 0.3243490178163545,
+      "grad_norm": 8.129148392597296,
+      "learning_rate": 2.3137034093477376e-05,
+      "loss": 0.7278,
+      "step": 4970
+    },
+    {
+      "epoch": 0.32500163153429484,
+      "grad_norm": 4.359321402490296,
+      "learning_rate": 2.3110918933980834e-05,
+      "loss": 0.7478,
+      "step": 4980
+    },
+    {
+      "epoch": 0.3256542452522352,
+      "grad_norm": 6.075218466766879,
+      "learning_rate": 2.3084768984378586e-05,
+      "loss": 0.6677,
+      "step": 4990
+    },
+    {
+      "epoch": 0.32630685897017553,
+      "grad_norm": 2.9896494008560706,
+      "learning_rate": 2.3058584356835427e-05,
+      "loss": 0.6513,
+      "step": 5000
+    },
+    {
+      "epoch": 0.3269594726881159,
+      "grad_norm": 1.4754266962232805,
+      "learning_rate": 2.3032365163664883e-05,
+      "loss": 0.6464,
+      "step": 5010
+    },
+    {
+      "epoch": 0.32761208640605627,
+      "grad_norm": 3.0595670396268004,
+      "learning_rate": 2.3006111517328757e-05,
+      "loss": 0.6421,
+      "step": 5020
+    },
+    {
+      "epoch": 0.3282647001239966,
+      "grad_norm": 2.5999764771497795,
+      "learning_rate": 2.2979823530436612e-05,
+      "loss": 0.7156,
+      "step": 5030
+    },
+    {
+      "epoch": 0.32891731384193695,
+      "grad_norm": 4.010936330179149,
+      "learning_rate": 2.2953501315745333e-05,
+      "loss": 0.7146,
+      "step": 5040
+    },
+    {
+      "epoch": 0.3295699275598773,
+      "grad_norm": 3.6987082623611443,
+      "learning_rate": 2.2927144986158597e-05,
+      "loss": 0.6457,
+      "step": 5050
+    },
+    {
+      "epoch": 0.33022254127781764,
+      "grad_norm": 2.904767386336742,
+      "learning_rate": 2.2900754654726412e-05,
+      "loss": 0.6609,
+      "step": 5060
+    },
+    {
+      "epoch": 0.33087515499575804,
+      "grad_norm": 5.91499319274459,
+      "learning_rate": 2.2874330434644644e-05,
+      "loss": 0.6455,
+      "step": 5070
+    },
+    {
+      "epoch": 0.3315277687136984,
+      "grad_norm": 4.274881122564761,
+      "learning_rate": 2.284787243925451e-05,
+      "loss": 0.6086,
+      "step": 5080
+    },
+    {
+      "epoch": 0.3321803824316387,
+      "grad_norm": 4.586045428018205,
+      "learning_rate": 2.2821380782042088e-05,
+      "loss": 0.6295,
+      "step": 5090
+    },
+    {
+      "epoch": 0.33283299614957906,
+      "grad_norm": 6.21240217104972,
+      "learning_rate": 2.279485557663786e-05,
+      "loss": 0.651,
+      "step": 5100
+    },
+    {
+      "epoch": 0.3334856098675194,
+      "grad_norm": 7.236323907724817,
+      "learning_rate": 2.276829693681619e-05,
+      "loss": 0.6892,
+      "step": 5110
+    },
+    {
+      "epoch": 0.33413822358545975,
+      "grad_norm": 3.238196874607574,
+      "learning_rate": 2.2741704976494863e-05,
+      "loss": 0.6669,
+      "step": 5120
+    },
+    {
+      "epoch": 0.3347908373034001,
+      "grad_norm": 3.477662878877292,
+      "learning_rate": 2.2715079809734578e-05,
+      "loss": 0.6244,
+      "step": 5130
+    },
+    {
+      "epoch": 0.3354434510213405,
+      "grad_norm": 3.320324994232007,
+      "learning_rate": 2.2688421550738473e-05,
+      "loss": 0.6908,
+      "step": 5140
+    },
+    {
+      "epoch": 0.33609606473928083,
+      "grad_norm": 4.370531906823192,
+      "learning_rate": 2.2661730313851622e-05,
+      "loss": 0.6874,
+      "step": 5150
+    },
+    {
+      "epoch": 0.3367486784572212,
+      "grad_norm": 7.874452844412553,
+      "learning_rate": 2.2635006213560556e-05,
+      "loss": 0.6677,
+      "step": 5160
+    },
+    {
+      "epoch": 0.3374012921751615,
+      "grad_norm": 11.683763528940291,
+      "learning_rate": 2.2608249364492764e-05,
+      "loss": 0.6705,
+      "step": 5170
+    },
+    {
+      "epoch": 0.33805390589310186,
+      "grad_norm": 3.023259120676624,
+      "learning_rate": 2.2581459881416205e-05,
+      "loss": 0.6199,
+      "step": 5180
+    },
+    {
+      "epoch": 0.3387065196110422,
+      "grad_norm": 8.323397957099377,
+      "learning_rate": 2.255463787923881e-05,
+      "loss": 0.6681,
+      "step": 5190
+    },
+    {
+      "epoch": 0.3393591333289826,
+      "grad_norm": 34.47067119815863,
+      "learning_rate": 2.2527783473008e-05,
+      "loss": 0.6697,
+      "step": 5200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 15323,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4214567069273293e+19,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3a6a5052a9445cc570063f5939fdeea3ff8007e9c2718674bb335b9eea0bfff
+size 6520

checkpoint-5200/zero_to_fp32.py

@@ -0,0 +1,587 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel()
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)

checkpoint-5600/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Qwen/Qwen-VL-Chat
+---
+
+# 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 0.10.0

checkpoint-5600/adapter_config.json

@@ -0,0 +1,380 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen-VL-Chat",
+  "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": 16,
+  "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": [
+    "transformer.h.16.mlp.w1",
+    "transformer.visual.transformer.resblocks.13.attn.out_proj",
+    "transformer.h.28.mlp.w1",
+    "transformer.h.16.attn.c_attn",
+    "transformer.h.3.mlp.w1",
+    "transformer.visual.transformer.resblocks.29.attn.in_proj",
+    "transformer.visual.transformer.resblocks.19.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.47.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.34.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.4.attn.out_proj",
+    "transformer.h.31.attn.c_attn",
+    "transformer.h.16.mlp.w2",
+    "transformer.visual.transformer.resblocks.5.attn.out_proj",
+    "transformer.h.2.mlp.w1",
+    "transformer.visual.transformer.resblocks.7.attn.in_proj",
+    "transformer.h.20.mlp.w2",
+    "transformer.h.19.mlp.w1",
+    "transformer.visual.transformer.resblocks.18.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.27.attn.out_proj",
+    "transformer.visual.transformer.resblocks.10.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.43.mlp.c_fc",
+    "transformer.h.5.mlp.w1",
+    "transformer.visual.transformer.resblocks.15.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.25.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.10.attn.out_proj",
+    "transformer.visual.transformer.resblocks.4.mlp.c_fc",
+    "transformer.h.31.mlp.w2",
+    "transformer.visual.transformer.resblocks.37.attn.out_proj",
+    "transformer.h.8.attn.c_proj",
+    "transformer.h.29.attn.c_attn",
+    "transformer.visual.transformer.resblocks.24.mlp.c_proj",
+    "transformer.h.19.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.11.attn.out_proj",
+    "transformer.h.13.mlp.c_proj",
+    "transformer.h.27.mlp.c_proj",
+    "transformer.h.31.mlp.w1",
+    "transformer.visual.transformer.resblocks.7.mlp.c_proj",
+    "transformer.h.28.mlp.w2",
+    "transformer.visual.transformer.resblocks.3.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.13.attn.in_proj",
+    "transformer.h.21.attn.c_attn",
+    "transformer.visual.transformer.resblocks.23.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.33.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.42.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.3.attn.in_proj",
+    "transformer.h.13.mlp.w1",
+    "transformer.visual.transformer.resblocks.22.attn.out_proj",
+    "transformer.visual.transformer.resblocks.20.mlp.c_fc",
+    "transformer.h.26.mlp.w2",
+    "transformer.h.14.attn.c_attn",
+    "transformer.h.16.attn.c_proj",
+    "transformer.h.1.mlp.w1",
+    "transformer.visual.transformer.resblocks.21.attn.out_proj",
+    "transformer.visual.transformer.resblocks.39.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.4.attn.in_proj",
+    "transformer.h.29.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.12.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.14.attn.in_proj",
+    "transformer.h.28.attn.c_proj",
+    "transformer.h.18.mlp.w1",
+    "transformer.h.27.mlp.w2",
+    "transformer.h.18.attn.c_attn",
+    "transformer.visual.transformer.resblocks.33.attn.out_proj",
+    "transformer.h.5.mlp.w2",
+    "transformer.visual.transformer.resblocks.37.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.2.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.42.attn.out_proj",
+    "transformer.visual.transformer.resblocks.15.attn.in_proj",
+    "transformer.visual.transformer.resblocks.6.mlp.c_fc",
+    "transformer.h.13.mlp.w2",
+    "transformer.h.23.attn.c_proj",
+    "transformer.h.20.mlp.c_proj",
+    "transformer.h.14.mlp.w2",
+    "transformer.visual.transformer.resblocks.9.attn.in_proj",
+    "transformer.visual.transformer.resblocks.46.attn.in_proj",
+    "transformer.h.9.attn.c_attn",
+    "transformer.visual.transformer.resblocks.36.mlp.c_proj",
+    "transformer.h.31.attn.c_proj",
+    "transformer.visual.transformer.resblocks.19.mlp.c_fc",
+    "transformer.h.17.mlp.w1",
+    "transformer.h.2.attn.c_proj",
+    "transformer.visual.transformer.resblocks.47.attn.in_proj",
+    "transformer.visual.transformer.resblocks.45.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.46.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.27.attn.in_proj",
+    "transformer.visual.transformer.resblocks.26.attn.out_proj",
+    "transformer.h.22.attn.c_proj",
+    "transformer.visual.transformer.resblocks.40.attn.out_proj",
+    "transformer.visual.transformer.resblocks.46.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.18.attn.out_proj",
+    "transformer.h.27.attn.c_proj",
+    "transformer.visual.transformer.resblocks.26.attn.in_proj",
+    "transformer.h.4.mlp.w1",
+    "transformer.h.10.attn.c_proj",
+    "transformer.h.6.attn.c_attn",
+    "transformer.h.2.attn.c_attn",
+    "transformer.h.22.mlp.w1",
+    "transformer.visual.transformer.resblocks.39.mlp.c_fc",
+    "transformer.h.8.mlp.w2",
+    "transformer.h.4.attn.c_attn",
+    "transformer.h.26.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.29.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.5.mlp.c_proj",
+    "transformer.h.11.mlp.c_proj",
+    "transformer.h.0.mlp.w2",
+    "transformer.visual.transformer.resblocks.36.attn.out_proj",
+    "transformer.h.29.mlp.w1",
+    "transformer.h.12.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.2.attn.in_proj",
+    "transformer.visual.transformer.resblocks.2.mlp.c_fc",
+    "transformer.h.25.attn.c_attn",
+    "transformer.visual.transformer.resblocks.19.attn.in_proj",
+    "transformer.visual.transformer.resblocks.43.attn.out_proj",
+    "transformer.visual.transformer.resblocks.35.attn.out_proj",
+    "transformer.h.22.attn.c_attn",
+    "transformer.h.0.mlp.w1",
+    "transformer.h.3.attn.c_attn",
+    "transformer.h.28.attn.c_attn",
+    "transformer.visual.transformer.resblocks.25.attn.in_proj",
+    "transformer.visual.transformer.resblocks.34.attn.out_proj",
+    "transformer.h.21.attn.c_proj",
+    "transformer.h.6.attn.c_proj",
+    "transformer.visual.transformer.resblocks.11.mlp.c_proj",
+    "transformer.h.13.attn.c_attn",
+    "transformer.visual.transformer.resblocks.38.attn.out_proj",
+    "transformer.h.3.attn.c_proj",
+    "transformer.visual.transformer.resblocks.17.mlp.c_fc",
+    "transformer.h.26.mlp.w1",
+    "transformer.visual.transformer.resblocks.36.mlp.c_fc",
+    "transformer.h.26.attn.c_attn",
+    "transformer.visual.transformer.resblocks.29.attn.out_proj",
+    "transformer.h.7.mlp.w1",
+    "transformer.visual.transformer.resblocks.40.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.9.attn.out_proj",
+    "transformer.h.3.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.26.mlp.c_fc",
+    "transformer.h.11.mlp.w2",
+    "transformer.visual.transformer.resblocks.33.attn.in_proj",
+    "transformer.visual.transformer.resblocks.42.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.32.attn.out_proj",
+    "transformer.h.4.attn.c_proj",
+    "transformer.visual.transformer.resblocks.27.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.11.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.25.attn.out_proj",
+    "transformer.visual.transformer.resblocks.23.attn.in_proj",
+    "transformer.h.5.attn.c_attn",
+    "transformer.h.16.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.14.mlp.c_proj",
+    "transformer.h.22.mlp.w2",
+    "transformer.h.25.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.10.mlp.c_fc",
+    "transformer.h.24.mlp.c_proj",
+    "transformer.h.19.mlp.w2",
+    "transformer.h.14.mlp.w1",
+    "transformer.visual.transformer.resblocks.40.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.28.attn.out_proj",
+    "transformer.visual.transformer.resblocks.24.mlp.c_fc",
+    "transformer.h.8.attn.c_attn",
+    "transformer.h.9.mlp.w1",
+    "transformer.h.6.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.19.attn.out_proj",
+    "transformer.visual.transformer.resblocks.32.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.7.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.44.attn.in_proj",
+    "transformer.visual.transformer.resblocks.34.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.9.mlp.c_fc",
+    "transformer.visual.conv1",
+    "transformer.visual.transformer.resblocks.8.attn.out_proj",
+    "transformer.h.23.mlp.w2",
+    "transformer.h.7.mlp.w2",
+    "transformer.h.24.attn.c_proj",
+    "transformer.h.30.attn.c_proj",
+    "transformer.h.29.attn.c_proj",
+    "transformer.visual.transformer.resblocks.9.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.35.attn.in_proj",
+    "transformer.visual.transformer.resblocks.21.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.41.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.38.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.13.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.41.attn.out_proj",
+    "transformer.visual.transformer.resblocks.16.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.45.attn.out_proj",
+    "transformer.h.11.mlp.w1",
+    "transformer.visual.transformer.resblocks.16.attn.in_proj",
+    "transformer.visual.transformer.resblocks.47.attn.out_proj",
+    "transformer.h.9.attn.c_proj",
+    "transformer.h.31.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.12.attn.in_proj",
+    "transformer.visual.transformer.resblocks.28.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.20.attn.out_proj",
+    "transformer.h.12.attn.c_attn",
+    "transformer.h.24.mlp.w1",
+    "transformer.visual.transformer.resblocks.21.attn.in_proj",
+    "transformer.visual.transformer.resblocks.41.attn.in_proj",
+    "transformer.h.10.mlp.w1",
+    "transformer.h.1.mlp.w2",
+    "transformer.h.0.mlp.c_proj",
+    "transformer.h.22.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.18.attn.in_proj",
+    "transformer.visual.transformer.resblocks.38.mlp.c_proj",
+    "transformer.h.12.mlp.w1",
+    "transformer.h.1.attn.c_attn",
+    "transformer.visual.transformer.resblocks.31.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.44.mlp.c_proj",
+    "transformer.h.15.mlp.c_proj",
+    "transformer.h.6.mlp.w1",
+    "transformer.visual.transformer.resblocks.16.mlp.c_proj",
+    "transformer.h.13.attn.c_proj",
+    "transformer.h.15.attn.c_attn",
+    "transformer.h.15.mlp.w1",
+    "transformer.h.17.mlp.w2",
+    "transformer.visual.transformer.resblocks.10.attn.in_proj",
+    "transformer.h.26.attn.c_proj",
+    "transformer.visual.transformer.resblocks.20.attn.in_proj",
+    "transformer.h.10.mlp.w2",
+    "transformer.h.24.attn.c_attn",
+    "transformer.h.8.mlp.w1",
+    "transformer.h.23.mlp.w1",
+    "transformer.visual.transformer.resblocks.1.mlp.c_proj",
+    "transformer.h.4.mlp.w2",
+    "transformer.visual.transformer.resblocks.38.attn.in_proj",
+    "transformer.h.12.mlp.w2",
+    "transformer.h.7.attn.c_proj",
+    "transformer.h.4.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.31.attn.out_proj",
+    "transformer.visual.transformer.resblocks.17.mlp.c_proj",
+    "transformer.h.21.mlp.w2",
+    "transformer.visual.transformer.resblocks.5.attn.in_proj",
+    "transformer.h.18.attn.c_proj",
+    "transformer.visual.transformer.resblocks.31.mlp.c_fc",
+    "transformer.h.18.mlp.w2",
+    "transformer.visual.transformer.resblocks.6.attn.out_proj",
+    "transformer.visual.transformer.resblocks.8.attn.in_proj",
+    "transformer.visual.transformer.resblocks.30.mlp.c_proj",
+    "transformer.h.30.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.30.attn.out_proj",
+    "transformer.visual.transformer.resblocks.16.attn.out_proj",
+    "transformer.visual.transformer.resblocks.14.attn.out_proj",
+    "transformer.h.25.mlp.w1",
+    "transformer.visual.transformer.resblocks.45.attn.in_proj",
+    "transformer.h.11.attn.c_proj",
+    "transformer.visual.transformer.resblocks.30.attn.in_proj",
+    "transformer.visual.transformer.resblocks.43.mlp.c_proj",
+    "transformer.h.10.mlp.c_proj",
+    "transformer.h.21.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.43.attn.in_proj",
+    "transformer.visual.transformer.resblocks.3.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.44.attn.out_proj",
+    "transformer.h.23.attn.c_attn",
+    "transformer.visual.transformer.resblocks.22.attn.in_proj",
+    "transformer.visual.transformer.resblocks.6.attn.in_proj",
+    "transformer.visual.transformer.resblocks.44.mlp.c_fc",
+    "transformer.h.17.attn.c_attn",
+    "transformer.h.7.attn.c_attn",
+    "transformer.visual.transformer.resblocks.42.attn.in_proj",
+    "transformer.visual.transformer.resblocks.20.mlp.c_proj",
+    "transformer.h.8.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.17.attn.out_proj",
+    "transformer.h.14.attn.c_proj",
+    "transformer.visual.transformer.resblocks.40.attn.in_proj",
+    "transformer.h.25.attn.c_proj",
+    "transformer.h.28.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.35.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.36.attn.in_proj",
+    "transformer.visual.transformer.resblocks.41.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.14.mlp.c_fc",
+    "transformer.h.30.mlp.w2",
+    "transformer.h.20.mlp.w1",
+    "transformer.visual.transformer.resblocks.33.mlp.c_fc",
+    "transformer.h.29.mlp.w2",
+    "transformer.visual.transformer.resblocks.47.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.30.mlp.c_fc",
+    "transformer.h.10.attn.c_attn",
+    "transformer.visual.transformer.resblocks.1.attn.in_proj",
+    "transformer.h.1.attn.c_proj",
+    "transformer.visual.transformer.resblocks.8.mlp.c_proj",
+    "transformer.h.19.attn.c_proj",
+    "transformer.visual.transformer.resblocks.37.attn.in_proj",
+    "transformer.h.15.attn.c_proj",
+    "transformer.h.5.attn.c_proj",
+    "transformer.visual.transformer.resblocks.32.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.3.attn.out_proj",
+    "transformer.visual.transformer.resblocks.32.attn.in_proj",
+    "transformer.h.21.mlp.w1",
+    "transformer.h.23.mlp.c_proj",
+    "transformer.h.30.mlp.w1",
+    "transformer.h.0.attn.c_attn",
+    "transformer.visual.transformer.resblocks.24.attn.out_proj",
+    "transformer.visual.transformer.resblocks.31.attn.in_proj",
+    "transformer.h.18.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.25.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.22.mlp.c_fc",
+    "transformer.h.30.attn.c_attn",
+    "transformer.visual.transformer.resblocks.13.mlp.c_fc",
+    "transformer.h.17.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.24.attn.in_proj",
+    "transformer.h.11.attn.c_attn",
+    "transformer.h.2.mlp.w2",
+    "transformer.visual.transformer.resblocks.8.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.0.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.2.attn.out_proj",
+    "transformer.visual.transformer.resblocks.35.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.39.attn.out_proj",
+    "transformer.h.12.attn.c_proj",
+    "transformer.visual.transformer.resblocks.28.attn.in_proj",
+    "transformer.visual.transformer.resblocks.29.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.0.attn.out_proj",
+    "transformer.visual.transformer.resblocks.23.mlp.c_proj",
+    "transformer.h.20.attn.c_attn",
+    "transformer.visual.transformer.resblocks.7.attn.out_proj",
+    "transformer.visual.transformer.resblocks.15.attn.out_proj",
+    "transformer.h.7.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.1.attn.out_proj",
+    "transformer.h.3.mlp.w2",
+    "transformer.h.9.mlp.w2",
+    "transformer.visual.transformer.resblocks.34.attn.in_proj",
+    "transformer.h.27.attn.c_attn",
+    "transformer.visual.transformer.resblocks.12.mlp.c_fc",
+    "transformer.h.6.mlp.w2",
+    "transformer.visual.transformer.resblocks.39.attn.in_proj",
+    "transformer.h.15.mlp.w2",
+    "transformer.visual.transformer.resblocks.18.mlp.c_proj",
+    "transformer.h.0.attn.c_proj",
+    "transformer.h.19.attn.c_attn",
+    "transformer.visual.transformer.resblocks.27.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.23.attn.out_proj",
+    "transformer.h.14.mlp.c_proj",
+    "transformer.h.9.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.12.attn.out_proj",
+    "transformer.visual.transformer.resblocks.0.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.5.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.28.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.6.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.22.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.37.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.17.attn.in_proj",
+    "transformer.visual.transformer.resblocks.46.attn.out_proj",
+    "transformer.h.24.mlp.w2",
+    "transformer.h.27.mlp.w1",
+    "transformer.visual.transformer.resblocks.11.attn.in_proj",
+    "transformer.visual.transformer.resblocks.4.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.21.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.26.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.15.mlp.c_fc",
+    "transformer.h.2.mlp.c_proj",
+    "transformer.h.1.mlp.c_proj",
+    "transformer.h.5.mlp.c_proj",
+    "transformer.visual.transformer.resblocks.45.mlp.c_fc",
+    "transformer.visual.transformer.resblocks.0.attn.in_proj",
+    "transformer.h.25.mlp.w2",
+    "transformer.h.20.attn.c_proj",
+    "transformer.h.17.attn.c_proj",
+    "transformer.visual.transformer.resblocks.1.mlp.c_fc"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-5600/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d58bbd17a8ea8af13c051ea733b5e9e12a706cec08418f192ade564617649841
+size 469105640

checkpoint-5600/global_step5600/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7ed194eb4899c0868b70ce010ef0795ce7697e2cc444ee9fc3358ae29d7ec09
+size 351761648

checkpoint-5600/global_step5600/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d3406f13de85ce09e45bbfc7061da3603c58312b878011cb7648824a5162e87
+size 351761776

checkpoint-5600/global_step5600/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3630c9c4b3f996a0d3c2ea98b5ee83feafab32d891e14fbb398ab1a1b1f76a33
+size 351761776

checkpoint-5600/global_step5600/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:177d7350e06923b7382479b602d00af17a26232d675dd8260d5b3fc2db721893
+size 351761584

checkpoint-5600/global_step5600/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edd3fab7ab72fbb200ea0ebdccb24df934aed3c3e314c24865e665caba141b1b
+size 351763184

checkpoint-5600/global_step5600/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08de4f02f483d04712e8391b81df8a0bee7487580a62574675d088c33959dcc0
+size 351771440

checkpoint-5600/global_step5600/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3814659f386185f0002fe8e976af211866ddafbcb7e0ec9e77fa6b41800cfd
+size 351771632

checkpoint-5600/global_step5600/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d004f275a82a850b49170565201f6f4bd5b8a4c7d059f9cb3db6f1417866d1
+size 351771312

checkpoint-5600/global_step5600/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7de07368f9c41aaed1ab9ed9cef3f066510d429fddfa6808988adb6ee6fafd3f
+size 469584556

checkpoint-5600/latest

@@ -0,0 +1 @@
+global_step5600

checkpoint-5600/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d76689726238a02fa7d36c5dd9b19d6040a0e4dbe64b5f6c07799df93d3c5795
+size 15920

checkpoint-5600/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c2746c714a56b7f84bb7bddc8ce75304950560d893ae54da816f44fe8a0a8d5
+size 15920

checkpoint-5600/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4839b08537070bd768b6d679f3cc66f6fbabdaeeb1c7f4943e0636cf744793f6
+size 15920

checkpoint-5600/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ada358db4e262d944accb7b8444c68a5aa7c1ca633d52abe14905cca1a0ca8a0
+size 15920

checkpoint-5600/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:781e3074ca79f10e7ecc22e01388a1a3b2bfc6a02a19b58a30490f2df8b97cf8
+size 15920

checkpoint-5600/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:160aac05886e800bce5b75e8495f0afbda9d3a5b198b14bd2782a5c87a7f0192
+size 15920

checkpoint-5600/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6811bf940462363693e7b94f5efb17f811e37396fd4eb061426f5139caf76f5
+size 15920

checkpoint-5600/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8c02c6a1be640f832c5387e678a0712a48dd90a4175800fd5d65bc83663e8cc
+size 15920