Upload folder using huggingface_hub

.gitattributes

@@ -93,3 +93,23 @@ group_size_100/layer_full/512/base/0_256_e20_3e-5/checkpoint-784/tokenizer.json
 group_size_100/layer_full/512/base/0_256_e20_3e-5/checkpoint-882/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 group_size_100/layer_full/512/base/0_256_e20_3e-5/checkpoint-98/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 group_size_100/layer_full/512/base/0_256_e20_3e-5/checkpoint-980/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1032/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1118/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1204/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1290/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1376/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1462/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1548/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1634/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-172/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-258/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-344/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-430/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-516/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-602/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-688/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-774/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-86/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-860/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-946/tokenizer.json filter=lfs diff=lfs merge=lfs -text

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1032/README.md

@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.1-8B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1032/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.1-8B",
+  "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": 512,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1032/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21dd0ba4ef6634f15aacd2336065bab808d8cf1269390e86a29ab2af3430e8f8
+size 1342239008

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1032/latest

@@ -0,0 +1 @@
+global_step1023

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1032/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbc2a6fbaf017b16f8442c828ff65d68060239ce221610f80f1a8ec0e5be7359
+size 14960

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1032/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:affa0c0500848c4b41d17c2be50150012dc4c82f7275955ebc3fe462e9f1853c
+size 14960

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1032/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cf272f67f2bd436f94f07aef3c103359e49fc7971f3b913cc4678a1438dd23a
+size 14960

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1032/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0a7b072fe3ea79c690b83ccd90018a96cb7e9848c794b90cddf7e8b84c2f288
+size 14960

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1032/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdc8bb3da1a5320a038616ab5584bd21094a4ae5480e9329e3124fc7ad076c6e
+size 1064

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1032/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1032/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1032/tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1032/trainer_state.json

@@ -0,0 +1,1476 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.0,
+  "eval_steps": 500,
+  "global_step": 1032,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05865102639296188,
+      "grad_norm": 0.8587596416473389,
+      "learning_rate": 1.411764705882353e-06,
+      "loss": 1.6979,
+      "step": 5
+    },
+    {
+      "epoch": 0.11730205278592376,
+      "grad_norm": 0.8847993016242981,
+      "learning_rate": 3.1764705882352943e-06,
+      "loss": 1.665,
+      "step": 10
+    },
+    {
+      "epoch": 0.17595307917888564,
+      "grad_norm": 0.843494713306427,
+      "learning_rate": 4.941176470588235e-06,
+      "loss": 1.6549,
+      "step": 15
+    },
+    {
+      "epoch": 0.23460410557184752,
+      "grad_norm": 0.675523042678833,
+      "learning_rate": 6.705882352941177e-06,
+      "loss": 1.6421,
+      "step": 20
+    },
+    {
+      "epoch": 0.2932551319648094,
+      "grad_norm": 0.7297828197479248,
+      "learning_rate": 8.470588235294118e-06,
+      "loss": 1.616,
+      "step": 25
+    },
+    {
+      "epoch": 0.3519061583577713,
+      "grad_norm": 0.6939984560012817,
+      "learning_rate": 1.023529411764706e-05,
+      "loss": 1.6368,
+      "step": 30
+    },
+    {
+      "epoch": 0.41055718475073316,
+      "grad_norm": 0.6109864115715027,
+      "learning_rate": 1.2e-05,
+      "loss": 1.5477,
+      "step": 35
+    },
+    {
+      "epoch": 0.46920821114369504,
+      "grad_norm": 0.5642703175544739,
+      "learning_rate": 1.3764705882352941e-05,
+      "loss": 1.5555,
+      "step": 40
+    },
+    {
+      "epoch": 0.5278592375366569,
+      "grad_norm": 0.5742537379264832,
+      "learning_rate": 1.5529411764705886e-05,
+      "loss": 1.565,
+      "step": 45
+    },
+    {
+      "epoch": 0.5865102639296188,
+      "grad_norm": 0.586601734161377,
+      "learning_rate": 1.7294117647058823e-05,
+      "loss": 1.5015,
+      "step": 50
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.6344695091247559,
+      "learning_rate": 1.9058823529411764e-05,
+      "loss": 1.4895,
+      "step": 55
+    },
+    {
+      "epoch": 0.7038123167155426,
+      "grad_norm": 0.5736978054046631,
+      "learning_rate": 2.0823529411764705e-05,
+      "loss": 1.5151,
+      "step": 60
+    },
+    {
+      "epoch": 0.7624633431085044,
+      "grad_norm": 0.6642257571220398,
+      "learning_rate": 2.2588235294117646e-05,
+      "loss": 1.5098,
+      "step": 65
+    },
+    {
+      "epoch": 0.8211143695014663,
+      "grad_norm": 0.6018787026405334,
+      "learning_rate": 2.4352941176470587e-05,
+      "loss": 1.4935,
+      "step": 70
+    },
+    {
+      "epoch": 0.8797653958944281,
+      "grad_norm": 0.5532670617103577,
+      "learning_rate": 2.6117647058823532e-05,
+      "loss": 1.4452,
+      "step": 75
+    },
+    {
+      "epoch": 0.9384164222873901,
+      "grad_norm": 0.710066020488739,
+      "learning_rate": 2.7882352941176473e-05,
+      "loss": 1.4699,
+      "step": 80
+    },
+    {
+      "epoch": 0.9970674486803519,
+      "grad_norm": 0.7423866391181946,
+      "learning_rate": 2.9647058823529414e-05,
+      "loss": 1.3994,
+      "step": 85
+    },
+    {
+      "epoch": 1.0469208211143695,
+      "grad_norm": 0.6278711557388306,
+      "learning_rate": 2.9999545918564296e-05,
+      "loss": 1.4367,
+      "step": 90
+    },
+    {
+      "epoch": 1.1055718475073313,
+      "grad_norm": 1.0214080810546875,
+      "learning_rate": 2.999770125984927e-05,
+      "loss": 1.3484,
+      "step": 95
+    },
+    {
+      "epoch": 1.1642228739002933,
+      "grad_norm": 0.7089139223098755,
+      "learning_rate": 2.9994437818135727e-05,
+      "loss": 1.3716,
+      "step": 100
+    },
+    {
+      "epoch": 1.2228739002932552,
+      "grad_norm": 0.6738442778587341,
+      "learning_rate": 2.9989755902145345e-05,
+      "loss": 1.2964,
+      "step": 105
+    },
+    {
+      "epoch": 1.281524926686217,
+      "grad_norm": 0.93358314037323,
+      "learning_rate": 2.9983655954787524e-05,
+      "loss": 1.3178,
+      "step": 110
+    },
+    {
+      "epoch": 1.3401759530791788,
+      "grad_norm": 0.8929201364517212,
+      "learning_rate": 2.9976138553117475e-05,
+      "loss": 1.3054,
+      "step": 115
+    },
+    {
+      "epoch": 1.3988269794721409,
+      "grad_norm": 0.7999489307403564,
+      "learning_rate": 2.9967204408281618e-05,
+      "loss": 1.3322,
+      "step": 120
+    },
+    {
+      "epoch": 1.4574780058651027,
+      "grad_norm": 0.9014801979064941,
+      "learning_rate": 2.9956854365450334e-05,
+      "loss": 1.2172,
+      "step": 125
+    },
+    {
+      "epoch": 1.5161290322580645,
+      "grad_norm": 0.8600694537162781,
+      "learning_rate": 2.9945089403737992e-05,
+      "loss": 1.2395,
+      "step": 130
+    },
+    {
+      "epoch": 1.5747800586510263,
+      "grad_norm": 0.8276307582855225,
+      "learning_rate": 2.993191063611033e-05,
+      "loss": 1.2443,
+      "step": 135
+    },
+    {
+      "epoch": 1.6334310850439882,
+      "grad_norm": 1.1944879293441772,
+      "learning_rate": 2.9917319309279167e-05,
+      "loss": 1.1981,
+      "step": 140
+    },
+    {
+      "epoch": 1.6920821114369502,
+      "grad_norm": 0.9493594169616699,
+      "learning_rate": 2.990131680358447e-05,
+      "loss": 1.197,
+      "step": 145
+    },
+    {
+      "epoch": 1.750733137829912,
+      "grad_norm": 0.8087087273597717,
+      "learning_rate": 2.9883904632863765e-05,
+      "loss": 1.151,
+      "step": 150
+    },
+    {
+      "epoch": 1.8093841642228738,
+      "grad_norm": 1.0508242845535278,
+      "learning_rate": 2.9865084444308933e-05,
+      "loss": 1.1387,
+      "step": 155
+    },
+    {
+      "epoch": 1.868035190615836,
+      "grad_norm": 0.8509999513626099,
+      "learning_rate": 2.98448580183104e-05,
+      "loss": 1.1557,
+      "step": 160
+    },
+    {
+      "epoch": 1.9266862170087977,
+      "grad_norm": 0.8426937460899353,
+      "learning_rate": 2.9823227268288677e-05,
+      "loss": 1.1069,
+      "step": 165
+    },
+    {
+      "epoch": 1.9853372434017595,
+      "grad_norm": 0.9207291007041931,
+      "learning_rate": 2.980019424051337e-05,
+      "loss": 1.1039,
+      "step": 170
+    },
+    {
+      "epoch": 2.035190615835777,
+      "grad_norm": 0.9143871068954468,
+      "learning_rate": 2.9775761113909628e-05,
+      "loss": 1.1063,
+      "step": 175
+    },
+    {
+      "epoch": 2.093841642228739,
+      "grad_norm": 0.9446623921394348,
+      "learning_rate": 2.9749930199851966e-05,
+      "loss": 1.0862,
+      "step": 180
+    },
+    {
+      "epoch": 2.1524926686217007,
+      "grad_norm": 0.9225357174873352,
+      "learning_rate": 2.9722703941945646e-05,
+      "loss": 1.051,
+      "step": 185
+    },
+    {
+      "epoch": 2.2111436950146626,
+      "grad_norm": 0.9399577379226685,
+      "learning_rate": 2.9694084915795506e-05,
+      "loss": 1.0305,
+      "step": 190
+    },
+    {
+      "epoch": 2.2697947214076244,
+      "grad_norm": 1.1311970949172974,
+      "learning_rate": 2.966407582876229e-05,
+      "loss": 0.9822,
+      "step": 195
+    },
+    {
+      "epoch": 2.3284457478005867,
+      "grad_norm": 1.1564215421676636,
+      "learning_rate": 2.9632679519706553e-05,
+      "loss": 1.0094,
+      "step": 200
+    },
+    {
+      "epoch": 2.3870967741935485,
+      "grad_norm": 1.3596452474594116,
+      "learning_rate": 2.9599898958720088e-05,
+      "loss": 1.0323,
+      "step": 205
+    },
+    {
+      "epoch": 2.4457478005865103,
+      "grad_norm": 0.9719135761260986,
+      "learning_rate": 2.9565737246844976e-05,
+      "loss": 1.0168,
+      "step": 210
+    },
+    {
+      "epoch": 2.504398826979472,
+      "grad_norm": 1.2797770500183105,
+      "learning_rate": 2.9530197615780202e-05,
+      "loss": 0.9826,
+      "step": 215
+    },
+    {
+      "epoch": 2.563049853372434,
+      "grad_norm": 1.0977298021316528,
+      "learning_rate": 2.9493283427575955e-05,
+      "loss": 0.946,
+      "step": 220
+    },
+    {
+      "epoch": 2.621700879765396,
+      "grad_norm": 1.093330979347229,
+      "learning_rate": 2.9454998174315572e-05,
+      "loss": 0.9502,
+      "step": 225
+    },
+    {
+      "epoch": 2.6803519061583576,
+      "grad_norm": 1.2540782690048218,
+      "learning_rate": 2.941534547778518e-05,
+      "loss": 0.9617,
+      "step": 230
+    },
+    {
+      "epoch": 2.73900293255132,
+      "grad_norm": 1.3939732313156128,
+      "learning_rate": 2.9374329089131082e-05,
+      "loss": 0.9205,
+      "step": 235
+    },
+    {
+      "epoch": 2.7976539589442817,
+      "grad_norm": 1.4037718772888184,
+      "learning_rate": 2.933195288850491e-05,
+      "loss": 0.9274,
+      "step": 240
+    },
+    {
+      "epoch": 2.8563049853372435,
+      "grad_norm": 1.2683528661727905,
+      "learning_rate": 2.9288220884696535e-05,
+      "loss": 0.9016,
+      "step": 245
+    },
+    {
+      "epoch": 2.9149560117302054,
+      "grad_norm": 1.2677197456359863,
+      "learning_rate": 2.924313721475486e-05,
+      "loss": 0.9143,
+      "step": 250
+    },
+    {
+      "epoch": 2.973607038123167,
+      "grad_norm": 1.1638188362121582,
+      "learning_rate": 2.919670614359644e-05,
+      "loss": 0.8975,
+      "step": 255
+    },
+    {
+      "epoch": 3.0234604105571847,
+      "grad_norm": 1.1116777658462524,
+      "learning_rate": 2.9148932063602026e-05,
+      "loss": 0.8464,
+      "step": 260
+    },
+    {
+      "epoch": 3.0821114369501466,
+      "grad_norm": 1.2918649911880493,
+      "learning_rate": 2.9099819494201052e-05,
+      "loss": 0.8562,
+      "step": 265
+    },
+    {
+      "epoch": 3.1407624633431084,
+      "grad_norm": 1.2727012634277344,
+      "learning_rate": 2.904937308144409e-05,
+      "loss": 0.8165,
+      "step": 270
+    },
+    {
+      "epoch": 3.19941348973607,
+      "grad_norm": 1.3380333185195923,
+      "learning_rate": 2.8997597597563333e-05,
+      "loss": 0.7949,
+      "step": 275
+    },
+    {
+      "epoch": 3.258064516129032,
+      "grad_norm": 1.3585141897201538,
+      "learning_rate": 2.8944497940521135e-05,
+      "loss": 0.8175,
+      "step": 280
+    },
+    {
+      "epoch": 3.3167155425219943,
+      "grad_norm": 1.3035612106323242,
+      "learning_rate": 2.8890079133546676e-05,
+      "loss": 0.7723,
+      "step": 285
+    },
+    {
+      "epoch": 3.375366568914956,
+      "grad_norm": 1.337160587310791,
+      "learning_rate": 2.883434632466077e-05,
+      "loss": 0.799,
+      "step": 290
+    },
+    {
+      "epoch": 3.434017595307918,
+      "grad_norm": 1.2794411182403564,
+      "learning_rate": 2.8777304786188847e-05,
+      "loss": 0.8098,
+      "step": 295
+    },
+    {
+      "epoch": 3.4926686217008798,
+      "grad_norm": 1.6959810256958008,
+      "learning_rate": 2.8718959914262185e-05,
+      "loss": 0.779,
+      "step": 300
+    },
+    {
+      "epoch": 3.5513196480938416,
+      "grad_norm": 1.2770452499389648,
+      "learning_rate": 2.865931722830746e-05,
+      "loss": 0.7574,
+      "step": 305
+    },
+    {
+      "epoch": 3.6099706744868034,
+      "grad_norm": 1.4143999814987183,
+      "learning_rate": 2.8598382370524593e-05,
+      "loss": 0.751,
+      "step": 310
+    },
+    {
+      "epoch": 3.6686217008797652,
+      "grad_norm": 1.5334277153015137,
+      "learning_rate": 2.853616110535299e-05,
+      "loss": 0.7468,
+      "step": 315
+    },
+    {
+      "epoch": 3.7272727272727275,
+      "grad_norm": 1.3932515382766724,
+      "learning_rate": 2.8472659318926242e-05,
+      "loss": 0.7526,
+      "step": 320
+    },
+    {
+      "epoch": 3.7859237536656893,
+      "grad_norm": 1.7445088624954224,
+      "learning_rate": 2.8407883018515293e-05,
+      "loss": 0.7266,
+      "step": 325
+    },
+    {
+      "epoch": 3.844574780058651,
+      "grad_norm": 1.4015307426452637,
+      "learning_rate": 2.8341838331960148e-05,
+      "loss": 0.6991,
+      "step": 330
+    },
+    {
+      "epoch": 3.903225806451613,
+      "grad_norm": 1.6155469417572021,
+      "learning_rate": 2.8274531507090175e-05,
+      "loss": 0.7441,
+      "step": 335
+    },
+    {
+      "epoch": 3.961876832844575,
+      "grad_norm": 1.4563353061676025,
+      "learning_rate": 2.8205968911133063e-05,
+      "loss": 0.7398,
+      "step": 340
+    },
+    {
+      "epoch": 4.011730205278592,
+      "grad_norm": 1.5465773344039917,
+      "learning_rate": 2.81361570301125e-05,
+      "loss": 0.7079,
+      "step": 345
+    },
+    {
+      "epoch": 4.070381231671554,
+      "grad_norm": 1.7146860361099243,
+      "learning_rate": 2.8065102468234564e-05,
+      "loss": 0.6398,
+      "step": 350
+    },
+    {
+      "epoch": 4.129032258064516,
+      "grad_norm": 1.5548095703125,
+      "learning_rate": 2.7992811947262987e-05,
+      "loss": 0.676,
+      "step": 355
+    },
+    {
+      "epoch": 4.187683284457478,
+      "grad_norm": 1.4299269914627075,
+      "learning_rate": 2.791929230588326e-05,
+      "loss": 0.6525,
+      "step": 360
+    },
+    {
+      "epoch": 4.24633431085044,
+      "grad_norm": 1.4415459632873535,
+      "learning_rate": 2.7844550499055713e-05,
+      "loss": 0.6276,
+      "step": 365
+    },
+    {
+      "epoch": 4.3049853372434015,
+      "grad_norm": 1.5755006074905396,
+      "learning_rate": 2.776859359735756e-05,
+      "loss": 0.6344,
+      "step": 370
+    },
+    {
+      "epoch": 4.363636363636363,
+      "grad_norm": 1.6027603149414062,
+      "learning_rate": 2.769142878631403e-05,
+      "loss": 0.662,
+      "step": 375
+    },
+    {
+      "epoch": 4.422287390029325,
+      "grad_norm": 1.484080195426941,
+      "learning_rate": 2.7613063365718615e-05,
+      "loss": 0.6234,
+      "step": 380
+    },
+    {
+      "epoch": 4.480938416422287,
+      "grad_norm": 1.7750574350357056,
+      "learning_rate": 2.7533504748942494e-05,
+      "loss": 0.6296,
+      "step": 385
+    },
+    {
+      "epoch": 4.539589442815249,
+      "grad_norm": 1.3946748971939087,
+      "learning_rate": 2.745276046223326e-05,
+      "loss": 0.6464,
+      "step": 390
+    },
+    {
+      "epoch": 4.5982404692082115,
+      "grad_norm": 2.107388734817505,
+      "learning_rate": 2.7370838144002902e-05,
+      "loss": 0.6136,
+      "step": 395
+    },
+    {
+      "epoch": 4.656891495601173,
+      "grad_norm": 1.6728172302246094,
+      "learning_rate": 2.7287745544105237e-05,
+      "loss": 0.6329,
+      "step": 400
+    },
+    {
+      "epoch": 4.715542521994135,
+      "grad_norm": 1.5250803232192993,
+      "learning_rate": 2.7203490523102758e-05,
+      "loss": 0.5953,
+      "step": 405
+    },
+    {
+      "epoch": 4.774193548387097,
+      "grad_norm": 1.4544414281845093,
+      "learning_rate": 2.7118081051523037e-05,
+      "loss": 0.6057,
+      "step": 410
+    },
+    {
+      "epoch": 4.832844574780059,
+      "grad_norm": 1.3960272073745728,
+      "learning_rate": 2.7031525209104695e-05,
+      "loss": 0.5475,
+      "step": 415
+    },
+    {
+      "epoch": 4.891495601173021,
+      "grad_norm": 1.5430188179016113,
+      "learning_rate": 2.694383118403308e-05,
+      "loss": 0.5767,
+      "step": 420
+    },
+    {
+      "epoch": 4.9501466275659824,
+      "grad_norm": 1.4782837629318237,
+      "learning_rate": 2.6855007272165644e-05,
+      "loss": 0.6098,
+      "step": 425
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.5061590671539307,
+      "learning_rate": 2.676506187624718e-05,
+      "loss": 0.5728,
+      "step": 430
+    },
+    {
+      "epoch": 5.058651026392962,
+      "grad_norm": 1.426033854484558,
+      "learning_rate": 2.6674003505114885e-05,
+      "loss": 0.5272,
+      "step": 435
+    },
+    {
+      "epoch": 5.117302052785924,
+      "grad_norm": 1.9145780801773071,
+      "learning_rate": 2.658184077289347e-05,
+      "loss": 0.5207,
+      "step": 440
+    },
+    {
+      "epoch": 5.1759530791788855,
+      "grad_norm": 1.5162384510040283,
+      "learning_rate": 2.6488582398180217e-05,
+      "loss": 0.5466,
+      "step": 445
+    },
+    {
+      "epoch": 5.234604105571847,
+      "grad_norm": 1.5765867233276367,
+      "learning_rate": 2.639423720322023e-05,
+      "loss": 0.532,
+      "step": 450
+    },
+    {
+      "epoch": 5.293255131964809,
+      "grad_norm": 1.6061979532241821,
+      "learning_rate": 2.6298814113071846e-05,
+      "loss": 0.5115,
+      "step": 455
+    },
+    {
+      "epoch": 5.351906158357771,
+      "grad_norm": 1.7579784393310547,
+      "learning_rate": 2.620232215476231e-05,
+      "loss": 0.5534,
+      "step": 460
+    },
+    {
+      "epoch": 5.410557184750733,
+      "grad_norm": 1.5701087713241577,
+      "learning_rate": 2.6104770456433837e-05,
+      "loss": 0.5281,
+      "step": 465
+    },
+    {
+      "epoch": 5.469208211143695,
+      "grad_norm": 1.5090984106063843,
+      "learning_rate": 2.600616824648008e-05,
+      "loss": 0.5121,
+      "step": 470
+    },
+    {
+      "epoch": 5.527859237536656,
+      "grad_norm": 2.6270909309387207,
+      "learning_rate": 2.590652485267311e-05,
+      "loss": 0.5043,
+      "step": 475
+    },
+    {
+      "epoch": 5.586510263929619,
+      "grad_norm": 1.7012410163879395,
+      "learning_rate": 2.5805849701281047e-05,
+      "loss": 0.5113,
+      "step": 480
+    },
+    {
+      "epoch": 5.645161290322581,
+      "grad_norm": 1.852084755897522,
+      "learning_rate": 2.5704152316176287e-05,
+      "loss": 0.476,
+      "step": 485
+    },
+    {
+      "epoch": 5.703812316715543,
+      "grad_norm": 1.3544026613235474,
+      "learning_rate": 2.5601442317934576e-05,
+      "loss": 0.5069,
+      "step": 490
+    },
+    {
+      "epoch": 5.762463343108505,
+      "grad_norm": 1.512239694595337,
+      "learning_rate": 2.5497729422924893e-05,
+      "loss": 0.5143,
+      "step": 495
+    },
+    {
+      "epoch": 5.821114369501466,
+      "grad_norm": 2.261417865753174,
+      "learning_rate": 2.539302344239029e-05,
+      "loss": 0.5075,
+      "step": 500
+    },
+    {
+      "epoch": 5.879765395894428,
+      "grad_norm": 1.6451923847198486,
+      "learning_rate": 2.5287334281519725e-05,
+      "loss": 0.4866,
+      "step": 505
+    },
+    {
+      "epoch": 5.93841642228739,
+      "grad_norm": 1.8043715953826904,
+      "learning_rate": 2.518067193851105e-05,
+      "loss": 0.4805,
+      "step": 510
+    },
+    {
+      "epoch": 5.997067448680352,
+      "grad_norm": 1.4476629495620728,
+      "learning_rate": 2.507304650362519e-05,
+      "loss": 0.4782,
+      "step": 515
+    },
+    {
+      "epoch": 6.0469208211143695,
+      "grad_norm": 2.0781941413879395,
+      "learning_rate": 2.4964468158231576e-05,
+      "loss": 0.4424,
+      "step": 520
+    },
+    {
+      "epoch": 6.105571847507331,
+      "grad_norm": 1.587519884109497,
+      "learning_rate": 2.4854947173845008e-05,
+      "loss": 0.4706,
+      "step": 525
+    },
+    {
+      "epoch": 6.164222873900293,
+      "grad_norm": 1.8226568698883057,
+      "learning_rate": 2.4744493911153962e-05,
+      "loss": 0.4592,
+      "step": 530
+    },
+    {
+      "epoch": 6.222873900293255,
+      "grad_norm": 1.5768177509307861,
+      "learning_rate": 2.463311881904048e-05,
+      "loss": 0.4225,
+      "step": 535
+    },
+    {
+      "epoch": 6.281524926686217,
+      "grad_norm": 1.6065932512283325,
+      "learning_rate": 2.4520832433591675e-05,
+      "loss": 0.4401,
+      "step": 540
+    },
+    {
+      "epoch": 6.340175953079179,
+      "grad_norm": 1.2971386909484863,
+      "learning_rate": 2.4407645377103056e-05,
+      "loss": 0.4538,
+      "step": 545
+    },
+    {
+      "epoch": 6.39882697947214,
+      "grad_norm": 1.838926076889038,
+      "learning_rate": 2.4293568357073634e-05,
+      "loss": 0.4272,
+      "step": 550
+    },
+    {
+      "epoch": 6.457478005865102,
+      "grad_norm": 2.197988986968994,
+      "learning_rate": 2.4178612165192992e-05,
+      "loss": 0.429,
+      "step": 555
+    },
+    {
+      "epoch": 6.516129032258064,
+      "grad_norm": 1.371309757232666,
+      "learning_rate": 2.406278767632041e-05,
+      "loss": 0.3993,
+      "step": 560
+    },
+    {
+      "epoch": 6.574780058651027,
+      "grad_norm": 1.592514157295227,
+      "learning_rate": 2.394610584745608e-05,
+      "loss": 0.3996,
+      "step": 565
+    },
+    {
+      "epoch": 6.633431085043989,
+      "grad_norm": 1.7009004354476929,
+      "learning_rate": 2.3828577716704583e-05,
+      "loss": 0.4013,
+      "step": 570
+    },
+    {
+      "epoch": 6.69208211143695,
+      "grad_norm": 1.5580384731292725,
+      "learning_rate": 2.371021440223069e-05,
+      "loss": 0.425,
+      "step": 575
+    },
+    {
+      "epoch": 6.750733137829912,
+      "grad_norm": 1.570862054824829,
+      "learning_rate": 2.3591027101207578e-05,
+      "loss": 0.4936,
+      "step": 580
+    },
+    {
+      "epoch": 6.809384164222874,
+      "grad_norm": 1.7335824966430664,
+      "learning_rate": 2.347102708875757e-05,
+      "loss": 0.4141,
+      "step": 585
+    },
+    {
+      "epoch": 6.868035190615836,
+      "grad_norm": 1.7174583673477173,
+      "learning_rate": 2.3350225716885522e-05,
+      "loss": 0.406,
+      "step": 590
+    },
+    {
+      "epoch": 6.926686217008798,
+      "grad_norm": 1.6045186519622803,
+      "learning_rate": 2.3228634413404916e-05,
+      "loss": 0.4233,
+      "step": 595
+    },
+    {
+      "epoch": 6.9853372434017595,
+      "grad_norm": 1.520074725151062,
+      "learning_rate": 2.3106264680856776e-05,
+      "loss": 0.4129,
+      "step": 600
+    },
+    {
+      "epoch": 7.035190615835777,
+      "grad_norm": 1.4023849964141846,
+      "learning_rate": 2.298312809542156e-05,
+      "loss": 0.4094,
+      "step": 605
+    },
+    {
+      "epoch": 7.093841642228739,
+      "grad_norm": 1.4728856086730957,
+      "learning_rate": 2.2859236305824e-05,
+      "loss": 0.3425,
+      "step": 610
+    },
+    {
+      "epoch": 7.152492668621701,
+      "grad_norm": 1.5377256870269775,
+      "learning_rate": 2.273460103223122e-05,
+      "loss": 0.3866,
+      "step": 615
+    },
+    {
+      "epoch": 7.211143695014663,
+      "grad_norm": 1.6293245553970337,
+      "learning_rate": 2.260923406514389e-05,
+      "loss": 0.3651,
+      "step": 620
+    },
+    {
+      "epoch": 7.269794721407624,
+      "grad_norm": 1.79743230342865,
+      "learning_rate": 2.248314726428095e-05,
+      "loss": 0.3466,
+      "step": 625
+    },
+    {
+      "epoch": 7.328445747800586,
+      "grad_norm": 1.446027398109436,
+      "learning_rate": 2.2356352557457624e-05,
+      "loss": 0.4,
+      "step": 630
+    },
+    {
+      "epoch": 7.387096774193548,
+      "grad_norm": 1.5968126058578491,
+      "learning_rate": 2.2228861939457056e-05,
+      "loss": 0.3575,
+      "step": 635
+    },
+    {
+      "epoch": 7.44574780058651,
+      "grad_norm": 1.3783931732177734,
+      "learning_rate": 2.210068747089561e-05,
+      "loss": 0.368,
+      "step": 640
+    },
+    {
+      "epoch": 7.504398826979472,
+      "grad_norm": 1.5377360582351685,
+      "learning_rate": 2.1971841277081947e-05,
+      "loss": 0.3604,
+      "step": 645
+    },
+    {
+      "epoch": 7.563049853372434,
+      "grad_norm": 1.6163183450698853,
+      "learning_rate": 2.184233554686994e-05,
+      "loss": 0.3591,
+      "step": 650
+    },
+    {
+      "epoch": 7.621700879765396,
+      "grad_norm": 1.9343562126159668,
+      "learning_rate": 2.1712182531505642e-05,
+      "loss": 0.3543,
+      "step": 655
+    },
+    {
+      "epoch": 7.680351906158358,
+      "grad_norm": 1.860203504562378,
+      "learning_rate": 2.1581394543468286e-05,
+      "loss": 0.362,
+      "step": 660
+    },
+    {
+      "epoch": 7.73900293255132,
+      "grad_norm": 1.7694545984268188,
+      "learning_rate": 2.1449983955305543e-05,
+      "loss": 0.36,
+      "step": 665
+    },
+    {
+      "epoch": 7.797653958944282,
+      "grad_norm": 1.5436360836029053,
+      "learning_rate": 2.131796319846309e-05,
+      "loss": 0.3752,
+      "step": 670
+    },
+    {
+      "epoch": 7.8563049853372435,
+      "grad_norm": 2.079392671585083,
+      "learning_rate": 2.1185344762108556e-05,
+      "loss": 0.3711,
+      "step": 675
+    },
+    {
+      "epoch": 7.914956011730205,
+      "grad_norm": 1.5377277135849,
+      "learning_rate": 2.1052141191950083e-05,
+      "loss": 0.3431,
+      "step": 680
+    },
+    {
+      "epoch": 7.973607038123167,
+      "grad_norm": 1.4733537435531616,
+      "learning_rate": 2.0918365089049492e-05,
+      "loss": 0.3714,
+      "step": 685
+    },
+    {
+      "epoch": 8.023460410557185,
+      "grad_norm": 1.7115830183029175,
+      "learning_rate": 2.078402910863022e-05,
+      "loss": 0.3286,
+      "step": 690
+    },
+    {
+      "epoch": 8.082111436950147,
+      "grad_norm": 1.6873016357421875,
+      "learning_rate": 2.0649145958880112e-05,
+      "loss": 0.3573,
+      "step": 695
+    },
+    {
+      "epoch": 8.140762463343108,
+      "grad_norm": 1.8315602540969849,
+      "learning_rate": 2.0513728399749288e-05,
+      "loss": 0.3325,
+      "step": 700
+    },
+    {
+      "epoch": 8.19941348973607,
+      "grad_norm": 1.827303171157837,
+      "learning_rate": 2.0377789241742973e-05,
+      "loss": 0.3387,
+      "step": 705
+    },
+    {
+      "epoch": 8.258064516129032,
+      "grad_norm": 1.9863218069076538,
+      "learning_rate": 2.0241341344709678e-05,
+      "loss": 0.3124,
+      "step": 710
+    },
+    {
+      "epoch": 8.316715542521994,
+      "grad_norm": 1.8508158922195435,
+      "learning_rate": 2.0104397616624646e-05,
+      "loss": 0.3279,
+      "step": 715
+    },
+    {
+      "epoch": 8.375366568914956,
+      "grad_norm": 1.636530876159668,
+      "learning_rate": 1.996697101236875e-05,
+      "loss": 0.3249,
+      "step": 720
+    },
+    {
+      "epoch": 8.434017595307918,
+      "grad_norm": 1.4390839338302612,
+      "learning_rate": 1.9829074532502958e-05,
+      "loss": 0.3019,
+      "step": 725
+    },
+    {
+      "epoch": 8.49266862170088,
+      "grad_norm": 1.6479607820510864,
+      "learning_rate": 1.9690721222038488e-05,
+      "loss": 0.3259,
+      "step": 730
+    },
+    {
+      "epoch": 8.551319648093841,
+      "grad_norm": 1.9377621412277222,
+      "learning_rate": 1.955192416920275e-05,
+      "loss": 0.3287,
+      "step": 735
+    },
+    {
+      "epoch": 8.609970674486803,
+      "grad_norm": 1.6579439640045166,
+      "learning_rate": 1.9412696504201194e-05,
+      "loss": 0.3323,
+      "step": 740
+    },
+    {
+      "epoch": 8.668621700879765,
+      "grad_norm": 1.8197572231292725,
+      "learning_rate": 1.927305139797519e-05,
+      "loss": 0.2997,
+      "step": 745
+    },
+    {
+      "epoch": 8.727272727272727,
+      "grad_norm": 1.4135760068893433,
+      "learning_rate": 1.913300206095607e-05,
+      "loss": 0.3396,
+      "step": 750
+    },
+    {
+      "epoch": 8.785923753665688,
+      "grad_norm": 1.576826572418213,
+      "learning_rate": 1.8992561741815397e-05,
+      "loss": 0.3044,
+      "step": 755
+    },
+    {
+      "epoch": 8.84457478005865,
+      "grad_norm": 1.696305751800537,
+      "learning_rate": 1.8851743726211665e-05,
+      "loss": 0.3068,
+      "step": 760
+    },
+    {
+      "epoch": 8.903225806451612,
+      "grad_norm": 1.5686278343200684,
+      "learning_rate": 1.8710561335533467e-05,
+      "loss": 0.2817,
+      "step": 765
+    },
+    {
+      "epoch": 8.961876832844574,
+      "grad_norm": 1.822142481803894,
+      "learning_rate": 1.856902792563928e-05,
+      "loss": 0.2894,
+      "step": 770
+    },
+    {
+      "epoch": 9.011730205278592,
+      "grad_norm": 3.2489266395568848,
+      "learning_rate": 1.8427156885594026e-05,
+      "loss": 0.3153,
+      "step": 775
+    },
+    {
+      "epoch": 9.070381231671554,
+      "grad_norm": 1.5879300832748413,
+      "learning_rate": 1.8284961636402418e-05,
+      "loss": 0.2708,
+      "step": 780
+    },
+    {
+      "epoch": 9.129032258064516,
+      "grad_norm": 1.7300035953521729,
+      "learning_rate": 1.8142455629739413e-05,
+      "loss": 0.2691,
+      "step": 785
+    },
+    {
+      "epoch": 9.187683284457478,
+      "grad_norm": 1.6516594886779785,
+      "learning_rate": 1.7999652346677577e-05,
+      "loss": 0.2942,
+      "step": 790
+    },
+    {
+      "epoch": 9.24633431085044,
+      "grad_norm": 1.6192295551300049,
+      "learning_rate": 1.785656529641188e-05,
+      "loss": 0.2963,
+      "step": 795
+    },
+    {
+      "epoch": 9.304985337243401,
+      "grad_norm": 1.7734555006027222,
+      "learning_rate": 1.771320801498165e-05,
+      "loss": 0.2987,
+      "step": 800
+    },
+    {
+      "epoch": 9.363636363636363,
+      "grad_norm": 1.5193028450012207,
+      "learning_rate": 1.7569594063990106e-05,
+      "loss": 0.2901,
+      "step": 805
+    },
+    {
+      "epoch": 9.422287390029325,
+      "grad_norm": 1.9062447547912598,
+      "learning_rate": 1.7425737029321407e-05,
+      "loss": 0.2633,
+      "step": 810
+    },
+    {
+      "epoch": 9.480938416422287,
+      "grad_norm": 1.6332511901855469,
+      "learning_rate": 1.728165051985544e-05,
+      "loss": 0.2982,
+      "step": 815
+    },
+    {
+      "epoch": 9.539589442815249,
+      "grad_norm": 1.7536693811416626,
+      "learning_rate": 1.713734816618042e-05,
+      "loss": 0.2668,
+      "step": 820
+    },
+    {
+      "epoch": 9.59824046920821,
+      "grad_norm": 1.4995721578598022,
+      "learning_rate": 1.6992843619303415e-05,
+      "loss": 0.2774,
+      "step": 825
+    },
+    {
+      "epoch": 9.656891495601172,
+      "grad_norm": 1.9364445209503174,
+      "learning_rate": 1.684815054935899e-05,
+      "loss": 0.3034,
+      "step": 830
+    },
+    {
+      "epoch": 9.715542521994134,
+      "grad_norm": 1.689841866493225,
+      "learning_rate": 1.6703282644315985e-05,
+      "loss": 0.2696,
+      "step": 835
+    },
+    {
+      "epoch": 9.774193548387096,
+      "grad_norm": 2.015406370162964,
+      "learning_rate": 1.6558253608682665e-05,
+      "loss": 0.2836,
+      "step": 840
+    },
+    {
+      "epoch": 9.832844574780058,
+      "grad_norm": 1.4139841794967651,
+      "learning_rate": 1.641307716221024e-05,
+      "loss": 0.2725,
+      "step": 845
+    },
+    {
+      "epoch": 9.89149560117302,
+      "grad_norm": 1.5893827676773071,
+      "learning_rate": 1.626776703859499e-05,
+      "loss": 0.2675,
+      "step": 850
+    },
+    {
+      "epoch": 9.950146627565982,
+      "grad_norm": 1.6394363641738892,
+      "learning_rate": 1.612233698417906e-05,
+      "loss": 0.2775,
+      "step": 855
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.5809170007705688,
+      "learning_rate": 1.5976800756650055e-05,
+      "loss": 0.2525,
+      "step": 860
+    },
+    {
+      "epoch": 10.058651026392962,
+      "grad_norm": 1.722279667854309,
+      "learning_rate": 1.583117212373955e-05,
+      "loss": 0.239,
+      "step": 865
+    },
+    {
+      "epoch": 10.117302052785924,
+      "grad_norm": 1.4771348237991333,
+      "learning_rate": 1.568546486192069e-05,
+      "loss": 0.2719,
+      "step": 870
+    },
+    {
+      "epoch": 10.175953079178885,
+      "grad_norm": 1.8491390943527222,
+      "learning_rate": 1.553969275510489e-05,
+      "loss": 0.2585,
+      "step": 875
+    },
+    {
+      "epoch": 10.234604105571847,
+      "grad_norm": 1.7717721462249756,
+      "learning_rate": 1.539386959333793e-05,
+      "loss": 0.2481,
+      "step": 880
+    },
+    {
+      "epoch": 10.29325513196481,
+      "grad_norm": 1.4404025077819824,
+      "learning_rate": 1.524800917149538e-05,
+      "loss": 0.2441,
+      "step": 885
+    },
+    {
+      "epoch": 10.351906158357771,
+      "grad_norm": 1.5100393295288086,
+      "learning_rate": 1.5102125287977604e-05,
+      "loss": 0.2674,
+      "step": 890
+    },
+    {
+      "epoch": 10.410557184750733,
+      "grad_norm": 1.9897160530090332,
+      "learning_rate": 1.4956231743404466e-05,
+      "loss": 0.2558,
+      "step": 895
+    },
+    {
+      "epoch": 10.469208211143695,
+      "grad_norm": 1.7335450649261475,
+      "learning_rate": 1.4810342339309738e-05,
+      "loss": 0.2472,
+      "step": 900
+    },
+    {
+      "epoch": 10.527859237536656,
+      "grad_norm": 2.008821725845337,
+      "learning_rate": 1.466447087683552e-05,
+      "loss": 0.2403,
+      "step": 905
+    },
+    {
+      "epoch": 10.586510263929618,
+      "grad_norm": 1.489761233329773,
+      "learning_rate": 1.4518631155426629e-05,
+      "loss": 0.235,
+      "step": 910
+    },
+    {
+      "epoch": 10.64516129032258,
+      "grad_norm": 1.5563368797302246,
+      "learning_rate": 1.4372836971525184e-05,
+      "loss": 0.2396,
+      "step": 915
+    },
+    {
+      "epoch": 10.703812316715542,
+      "grad_norm": 1.7141892910003662,
+      "learning_rate": 1.4227102117265432e-05,
+      "loss": 0.2442,
+      "step": 920
+    },
+    {
+      "epoch": 10.762463343108504,
+      "grad_norm": 1.568986415863037,
+      "learning_rate": 1.408144037916906e-05,
+      "loss": 0.2485,
+      "step": 925
+    },
+    {
+      "epoch": 10.821114369501466,
+      "grad_norm": 1.3690587282180786,
+      "learning_rate": 1.393586553684096e-05,
+      "loss": 0.267,
+      "step": 930
+    },
+    {
+      "epoch": 10.879765395894427,
+      "grad_norm": 1.4901823997497559,
+      "learning_rate": 1.3790391361665658e-05,
+      "loss": 0.2479,
+      "step": 935
+    },
+    {
+      "epoch": 10.93841642228739,
+      "grad_norm": 1.538944959640503,
+      "learning_rate": 1.3645031615504593e-05,
+      "loss": 0.2568,
+      "step": 940
+    },
+    {
+      "epoch": 10.997067448680351,
+      "grad_norm": 1.584997296333313,
+      "learning_rate": 1.34998000493942e-05,
+      "loss": 0.2513,
+      "step": 945
+    },
+    {
+      "epoch": 11.04692082111437,
+      "grad_norm": 1.578392744064331,
+      "learning_rate": 1.3354710402245081e-05,
+      "loss": 0.216,
+      "step": 950
+    },
+    {
+      "epoch": 11.105571847507331,
+      "grad_norm": 1.5702141523361206,
+      "learning_rate": 1.3209776399542298e-05,
+      "loss": 0.2341,
+      "step": 955
+    },
+    {
+      "epoch": 11.164222873900293,
+      "grad_norm": 1.2398377656936646,
+      "learning_rate": 1.3065011752046955e-05,
+      "loss": 0.2045,
+      "step": 960
+    },
+    {
+      "epoch": 11.222873900293255,
+      "grad_norm": 1.6778515577316284,
+      "learning_rate": 1.2920430154499123e-05,
+      "loss": 0.2226,
+      "step": 965
+    },
+    {
+      "epoch": 11.281524926686217,
+      "grad_norm": 1.3014507293701172,
+      "learning_rate": 1.277604528432237e-05,
+      "loss": 0.2013,
+      "step": 970
+    },
+    {
+      "epoch": 11.340175953079179,
+      "grad_norm": 1.6591119766235352,
+      "learning_rate": 1.2631870800329839e-05,
+      "loss": 0.2198,
+      "step": 975
+    },
+    {
+      "epoch": 11.39882697947214,
+      "grad_norm": 1.5535308122634888,
+      "learning_rate": 1.248792034143212e-05,
+      "loss": 0.2071,
+      "step": 980
+    },
+    {
+      "epoch": 11.457478005865102,
+      "grad_norm": 1.5089534521102905,
+      "learning_rate": 1.2344207525347039e-05,
+      "loss": 0.2101,
+      "step": 985
+    },
+    {
+      "epoch": 11.516129032258064,
+      "grad_norm": 1.3858919143676758,
+      "learning_rate": 1.2200745947311409e-05,
+      "loss": 0.234,
+      "step": 990
+    },
+    {
+      "epoch": 11.574780058651026,
+      "grad_norm": 1.6462393999099731,
+      "learning_rate": 1.2057549178794888e-05,
+      "loss": 0.2265,
+      "step": 995
+    },
+    {
+      "epoch": 11.633431085043988,
+      "grad_norm": 1.351588249206543,
+      "learning_rate": 1.1914630766216173e-05,
+      "loss": 0.2495,
+      "step": 1000
+    },
+    {
+      "epoch": 11.69208211143695,
+      "grad_norm": 1.450875163078308,
+      "learning_rate": 1.1772004229661474e-05,
+      "loss": 0.2256,
+      "step": 1005
+    },
+    {
+      "epoch": 11.750733137829911,
+      "grad_norm": 1.5337797403335571,
+      "learning_rate": 1.162968306160551e-05,
+      "loss": 0.227,
+      "step": 1010
+    },
+    {
+      "epoch": 11.809384164222873,
+      "grad_norm": 1.6182599067687988,
+      "learning_rate": 1.148768072563514e-05,
+      "loss": 0.2465,
+      "step": 1015
+    },
+    {
+      "epoch": 11.868035190615835,
+      "grad_norm": 1.4571447372436523,
+      "learning_rate": 1.1346010655175707e-05,
+      "loss": 0.2218,
+      "step": 1020
+    },
+    {
+      "epoch": 11.926686217008797,
+      "grad_norm": 1.6681259870529175,
+      "learning_rate": 1.1204686252220202e-05,
+      "loss": 0.2513,
+      "step": 1025
+    },
+    {
+      "epoch": 11.985337243401759,
+      "grad_norm": 1.3346493244171143,
+      "learning_rate": 1.1063720886061473e-05,
+      "loss": 0.2367,
+      "step": 1030
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1700,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.296895245401457e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1032/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8661d4af4b612fdd59ee0a2ad90ad8380b6dba00c9fff95f2ddecfcdbfc43a38
+size 7608

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1032/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/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, exclude_frozen_parameters):
+    """
+    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,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+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 _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+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() if _has_callable(shape, 'numel') else math.prod(shape)
+            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,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _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,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _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, exclude_frozen_parameters=False):
+    """
+    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``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    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, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    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``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    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("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    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,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1118/README.md

@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.1-8B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1118/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.1-8B",
+  "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": 512,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1118/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc70f37a423a70b10986d503112a2602e1a73bffb01695e19ab8e8b3832615b
+size 1342239008

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1118/latest

@@ -0,0 +1 @@
+global_step1108

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1118/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:119ad96afde990509964cfb66f9d5c366e8920a7615aff744197bfd6471fc3e7
+size 14960

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1118/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85785c0195d2b2ea6e03843d79c12004e10f290cbe2564bdbea3e8c53a02cd8d
+size 14960

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1118/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:756595f0bc9ac6bfc63512f8f9620fa4f53b85868777201f891a3192f9edb542
+size 14960

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1118/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc12f93cc519333a14efc88e73b256999cf5da3f6289d8946beace09c700f8c
+size 14960

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1118/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f4379eab8d63174ac13c671e91120c1ec15abc0bd0aa2e48beaeb70c18ce4de
+size 1064

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1118/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1118/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1118/tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1118/trainer_state.json

@@ -0,0 +1,1595 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 13.0,
+  "eval_steps": 500,
+  "global_step": 1118,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05865102639296188,
+      "grad_norm": 0.8587596416473389,
+      "learning_rate": 1.411764705882353e-06,
+      "loss": 1.6979,
+      "step": 5
+    },
+    {
+      "epoch": 0.11730205278592376,
+      "grad_norm": 0.8847993016242981,
+      "learning_rate": 3.1764705882352943e-06,
+      "loss": 1.665,
+      "step": 10
+    },
+    {
+      "epoch": 0.17595307917888564,
+      "grad_norm": 0.843494713306427,
+      "learning_rate": 4.941176470588235e-06,
+      "loss": 1.6549,
+      "step": 15
+    },
+    {
+      "epoch": 0.23460410557184752,
+      "grad_norm": 0.675523042678833,
+      "learning_rate": 6.705882352941177e-06,
+      "loss": 1.6421,
+      "step": 20
+    },
+    {
+      "epoch": 0.2932551319648094,
+      "grad_norm": 0.7297828197479248,
+      "learning_rate": 8.470588235294118e-06,
+      "loss": 1.616,
+      "step": 25
+    },
+    {
+      "epoch": 0.3519061583577713,
+      "grad_norm": 0.6939984560012817,
+      "learning_rate": 1.023529411764706e-05,
+      "loss": 1.6368,
+      "step": 30
+    },
+    {
+      "epoch": 0.41055718475073316,
+      "grad_norm": 0.6109864115715027,
+      "learning_rate": 1.2e-05,
+      "loss": 1.5477,
+      "step": 35
+    },
+    {
+      "epoch": 0.46920821114369504,
+      "grad_norm": 0.5642703175544739,
+      "learning_rate": 1.3764705882352941e-05,
+      "loss": 1.5555,
+      "step": 40
+    },
+    {
+      "epoch": 0.5278592375366569,
+      "grad_norm": 0.5742537379264832,
+      "learning_rate": 1.5529411764705886e-05,
+      "loss": 1.565,
+      "step": 45
+    },
+    {
+      "epoch": 0.5865102639296188,
+      "grad_norm": 0.586601734161377,
+      "learning_rate": 1.7294117647058823e-05,
+      "loss": 1.5015,
+      "step": 50
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.6344695091247559,
+      "learning_rate": 1.9058823529411764e-05,
+      "loss": 1.4895,
+      "step": 55
+    },
+    {
+      "epoch": 0.7038123167155426,
+      "grad_norm": 0.5736978054046631,
+      "learning_rate": 2.0823529411764705e-05,
+      "loss": 1.5151,
+      "step": 60
+    },
+    {
+      "epoch": 0.7624633431085044,
+      "grad_norm": 0.6642257571220398,
+      "learning_rate": 2.2588235294117646e-05,
+      "loss": 1.5098,
+      "step": 65
+    },
+    {
+      "epoch": 0.8211143695014663,
+      "grad_norm": 0.6018787026405334,
+      "learning_rate": 2.4352941176470587e-05,
+      "loss": 1.4935,
+      "step": 70
+    },
+    {
+      "epoch": 0.8797653958944281,
+      "grad_norm": 0.5532670617103577,
+      "learning_rate": 2.6117647058823532e-05,
+      "loss": 1.4452,
+      "step": 75
+    },
+    {
+      "epoch": 0.9384164222873901,
+      "grad_norm": 0.710066020488739,
+      "learning_rate": 2.7882352941176473e-05,
+      "loss": 1.4699,
+      "step": 80
+    },
+    {
+      "epoch": 0.9970674486803519,
+      "grad_norm": 0.7423866391181946,
+      "learning_rate": 2.9647058823529414e-05,
+      "loss": 1.3994,
+      "step": 85
+    },
+    {
+      "epoch": 1.0469208211143695,
+      "grad_norm": 0.6278711557388306,
+      "learning_rate": 2.9999545918564296e-05,
+      "loss": 1.4367,
+      "step": 90
+    },
+    {
+      "epoch": 1.1055718475073313,
+      "grad_norm": 1.0214080810546875,
+      "learning_rate": 2.999770125984927e-05,
+      "loss": 1.3484,
+      "step": 95
+    },
+    {
+      "epoch": 1.1642228739002933,
+      "grad_norm": 0.7089139223098755,
+      "learning_rate": 2.9994437818135727e-05,
+      "loss": 1.3716,
+      "step": 100
+    },
+    {
+      "epoch": 1.2228739002932552,
+      "grad_norm": 0.6738442778587341,
+      "learning_rate": 2.9989755902145345e-05,
+      "loss": 1.2964,
+      "step": 105
+    },
+    {
+      "epoch": 1.281524926686217,
+      "grad_norm": 0.93358314037323,
+      "learning_rate": 2.9983655954787524e-05,
+      "loss": 1.3178,
+      "step": 110
+    },
+    {
+      "epoch": 1.3401759530791788,
+      "grad_norm": 0.8929201364517212,
+      "learning_rate": 2.9976138553117475e-05,
+      "loss": 1.3054,
+      "step": 115
+    },
+    {
+      "epoch": 1.3988269794721409,
+      "grad_norm": 0.7999489307403564,
+      "learning_rate": 2.9967204408281618e-05,
+      "loss": 1.3322,
+      "step": 120
+    },
+    {
+      "epoch": 1.4574780058651027,
+      "grad_norm": 0.9014801979064941,
+      "learning_rate": 2.9956854365450334e-05,
+      "loss": 1.2172,
+      "step": 125
+    },
+    {
+      "epoch": 1.5161290322580645,
+      "grad_norm": 0.8600694537162781,
+      "learning_rate": 2.9945089403737992e-05,
+      "loss": 1.2395,
+      "step": 130
+    },
+    {
+      "epoch": 1.5747800586510263,
+      "grad_norm": 0.8276307582855225,
+      "learning_rate": 2.993191063611033e-05,
+      "loss": 1.2443,
+      "step": 135
+    },
+    {
+      "epoch": 1.6334310850439882,
+      "grad_norm": 1.1944879293441772,
+      "learning_rate": 2.9917319309279167e-05,
+      "loss": 1.1981,
+      "step": 140
+    },
+    {
+      "epoch": 1.6920821114369502,
+      "grad_norm": 0.9493594169616699,
+      "learning_rate": 2.990131680358447e-05,
+      "loss": 1.197,
+      "step": 145
+    },
+    {
+      "epoch": 1.750733137829912,
+      "grad_norm": 0.8087087273597717,
+      "learning_rate": 2.9883904632863765e-05,
+      "loss": 1.151,
+      "step": 150
+    },
+    {
+      "epoch": 1.8093841642228738,
+      "grad_norm": 1.0508242845535278,
+      "learning_rate": 2.9865084444308933e-05,
+      "loss": 1.1387,
+      "step": 155
+    },
+    {
+      "epoch": 1.868035190615836,
+      "grad_norm": 0.8509999513626099,
+      "learning_rate": 2.98448580183104e-05,
+      "loss": 1.1557,
+      "step": 160
+    },
+    {
+      "epoch": 1.9266862170087977,
+      "grad_norm": 0.8426937460899353,
+      "learning_rate": 2.9823227268288677e-05,
+      "loss": 1.1069,
+      "step": 165
+    },
+    {
+      "epoch": 1.9853372434017595,
+      "grad_norm": 0.9207291007041931,
+      "learning_rate": 2.980019424051337e-05,
+      "loss": 1.1039,
+      "step": 170
+    },
+    {
+      "epoch": 2.035190615835777,
+      "grad_norm": 0.9143871068954468,
+      "learning_rate": 2.9775761113909628e-05,
+      "loss": 1.1063,
+      "step": 175
+    },
+    {
+      "epoch": 2.093841642228739,
+      "grad_norm": 0.9446623921394348,
+      "learning_rate": 2.9749930199851966e-05,
+      "loss": 1.0862,
+      "step": 180
+    },
+    {
+      "epoch": 2.1524926686217007,
+      "grad_norm": 0.9225357174873352,
+      "learning_rate": 2.9722703941945646e-05,
+      "loss": 1.051,
+      "step": 185
+    },
+    {
+      "epoch": 2.2111436950146626,
+      "grad_norm": 0.9399577379226685,
+      "learning_rate": 2.9694084915795506e-05,
+      "loss": 1.0305,
+      "step": 190
+    },
+    {
+      "epoch": 2.2697947214076244,
+      "grad_norm": 1.1311970949172974,
+      "learning_rate": 2.966407582876229e-05,
+      "loss": 0.9822,
+      "step": 195
+    },
+    {
+      "epoch": 2.3284457478005867,
+      "grad_norm": 1.1564215421676636,
+      "learning_rate": 2.9632679519706553e-05,
+      "loss": 1.0094,
+      "step": 200
+    },
+    {
+      "epoch": 2.3870967741935485,
+      "grad_norm": 1.3596452474594116,
+      "learning_rate": 2.9599898958720088e-05,
+      "loss": 1.0323,
+      "step": 205
+    },
+    {
+      "epoch": 2.4457478005865103,
+      "grad_norm": 0.9719135761260986,
+      "learning_rate": 2.9565737246844976e-05,
+      "loss": 1.0168,
+      "step": 210
+    },
+    {
+      "epoch": 2.504398826979472,
+      "grad_norm": 1.2797770500183105,
+      "learning_rate": 2.9530197615780202e-05,
+      "loss": 0.9826,
+      "step": 215
+    },
+    {
+      "epoch": 2.563049853372434,
+      "grad_norm": 1.0977298021316528,
+      "learning_rate": 2.9493283427575955e-05,
+      "loss": 0.946,
+      "step": 220
+    },
+    {
+      "epoch": 2.621700879765396,
+      "grad_norm": 1.093330979347229,
+      "learning_rate": 2.9454998174315572e-05,
+      "loss": 0.9502,
+      "step": 225
+    },
+    {
+      "epoch": 2.6803519061583576,
+      "grad_norm": 1.2540782690048218,
+      "learning_rate": 2.941534547778518e-05,
+      "loss": 0.9617,
+      "step": 230
+    },
+    {
+      "epoch": 2.73900293255132,
+      "grad_norm": 1.3939732313156128,
+      "learning_rate": 2.9374329089131082e-05,
+      "loss": 0.9205,
+      "step": 235
+    },
+    {
+      "epoch": 2.7976539589442817,
+      "grad_norm": 1.4037718772888184,
+      "learning_rate": 2.933195288850491e-05,
+      "loss": 0.9274,
+      "step": 240
+    },
+    {
+      "epoch": 2.8563049853372435,
+      "grad_norm": 1.2683528661727905,
+      "learning_rate": 2.9288220884696535e-05,
+      "loss": 0.9016,
+      "step": 245
+    },
+    {
+      "epoch": 2.9149560117302054,
+      "grad_norm": 1.2677197456359863,
+      "learning_rate": 2.924313721475486e-05,
+      "loss": 0.9143,
+      "step": 250
+    },
+    {
+      "epoch": 2.973607038123167,
+      "grad_norm": 1.1638188362121582,
+      "learning_rate": 2.919670614359644e-05,
+      "loss": 0.8975,
+      "step": 255
+    },
+    {
+      "epoch": 3.0234604105571847,
+      "grad_norm": 1.1116777658462524,
+      "learning_rate": 2.9148932063602026e-05,
+      "loss": 0.8464,
+      "step": 260
+    },
+    {
+      "epoch": 3.0821114369501466,
+      "grad_norm": 1.2918649911880493,
+      "learning_rate": 2.9099819494201052e-05,
+      "loss": 0.8562,
+      "step": 265
+    },
+    {
+      "epoch": 3.1407624633431084,
+      "grad_norm": 1.2727012634277344,
+      "learning_rate": 2.904937308144409e-05,
+      "loss": 0.8165,
+      "step": 270
+    },
+    {
+      "epoch": 3.19941348973607,
+      "grad_norm": 1.3380333185195923,
+      "learning_rate": 2.8997597597563333e-05,
+      "loss": 0.7949,
+      "step": 275
+    },
+    {
+      "epoch": 3.258064516129032,
+      "grad_norm": 1.3585141897201538,
+      "learning_rate": 2.8944497940521135e-05,
+      "loss": 0.8175,
+      "step": 280
+    },
+    {
+      "epoch": 3.3167155425219943,
+      "grad_norm": 1.3035612106323242,
+      "learning_rate": 2.8890079133546676e-05,
+      "loss": 0.7723,
+      "step": 285
+    },
+    {
+      "epoch": 3.375366568914956,
+      "grad_norm": 1.337160587310791,
+      "learning_rate": 2.883434632466077e-05,
+      "loss": 0.799,
+      "step": 290
+    },
+    {
+      "epoch": 3.434017595307918,
+      "grad_norm": 1.2794411182403564,
+      "learning_rate": 2.8777304786188847e-05,
+      "loss": 0.8098,
+      "step": 295
+    },
+    {
+      "epoch": 3.4926686217008798,
+      "grad_norm": 1.6959810256958008,
+      "learning_rate": 2.8718959914262185e-05,
+      "loss": 0.779,
+      "step": 300
+    },
+    {
+      "epoch": 3.5513196480938416,
+      "grad_norm": 1.2770452499389648,
+      "learning_rate": 2.865931722830746e-05,
+      "loss": 0.7574,
+      "step": 305
+    },
+    {
+      "epoch": 3.6099706744868034,
+      "grad_norm": 1.4143999814987183,
+      "learning_rate": 2.8598382370524593e-05,
+      "loss": 0.751,
+      "step": 310
+    },
+    {
+      "epoch": 3.6686217008797652,
+      "grad_norm": 1.5334277153015137,
+      "learning_rate": 2.853616110535299e-05,
+      "loss": 0.7468,
+      "step": 315
+    },
+    {
+      "epoch": 3.7272727272727275,
+      "grad_norm": 1.3932515382766724,
+      "learning_rate": 2.8472659318926242e-05,
+      "loss": 0.7526,
+      "step": 320
+    },
+    {
+      "epoch": 3.7859237536656893,
+      "grad_norm": 1.7445088624954224,
+      "learning_rate": 2.8407883018515293e-05,
+      "loss": 0.7266,
+      "step": 325
+    },
+    {
+      "epoch": 3.844574780058651,
+      "grad_norm": 1.4015307426452637,
+      "learning_rate": 2.8341838331960148e-05,
+      "loss": 0.6991,
+      "step": 330
+    },
+    {
+      "epoch": 3.903225806451613,
+      "grad_norm": 1.6155469417572021,
+      "learning_rate": 2.8274531507090175e-05,
+      "loss": 0.7441,
+      "step": 335
+    },
+    {
+      "epoch": 3.961876832844575,
+      "grad_norm": 1.4563353061676025,
+      "learning_rate": 2.8205968911133063e-05,
+      "loss": 0.7398,
+      "step": 340
+    },
+    {
+      "epoch": 4.011730205278592,
+      "grad_norm": 1.5465773344039917,
+      "learning_rate": 2.81361570301125e-05,
+      "loss": 0.7079,
+      "step": 345
+    },
+    {
+      "epoch": 4.070381231671554,
+      "grad_norm": 1.7146860361099243,
+      "learning_rate": 2.8065102468234564e-05,
+      "loss": 0.6398,
+      "step": 350
+    },
+    {
+      "epoch": 4.129032258064516,
+      "grad_norm": 1.5548095703125,
+      "learning_rate": 2.7992811947262987e-05,
+      "loss": 0.676,
+      "step": 355
+    },
+    {
+      "epoch": 4.187683284457478,
+      "grad_norm": 1.4299269914627075,
+      "learning_rate": 2.791929230588326e-05,
+      "loss": 0.6525,
+      "step": 360
+    },
+    {
+      "epoch": 4.24633431085044,
+      "grad_norm": 1.4415459632873535,
+      "learning_rate": 2.7844550499055713e-05,
+      "loss": 0.6276,
+      "step": 365
+    },
+    {
+      "epoch": 4.3049853372434015,
+      "grad_norm": 1.5755006074905396,
+      "learning_rate": 2.776859359735756e-05,
+      "loss": 0.6344,
+      "step": 370
+    },
+    {
+      "epoch": 4.363636363636363,
+      "grad_norm": 1.6027603149414062,
+      "learning_rate": 2.769142878631403e-05,
+      "loss": 0.662,
+      "step": 375
+    },
+    {
+      "epoch": 4.422287390029325,
+      "grad_norm": 1.484080195426941,
+      "learning_rate": 2.7613063365718615e-05,
+      "loss": 0.6234,
+      "step": 380
+    },
+    {
+      "epoch": 4.480938416422287,
+      "grad_norm": 1.7750574350357056,
+      "learning_rate": 2.7533504748942494e-05,
+      "loss": 0.6296,
+      "step": 385
+    },
+    {
+      "epoch": 4.539589442815249,
+      "grad_norm": 1.3946748971939087,
+      "learning_rate": 2.745276046223326e-05,
+      "loss": 0.6464,
+      "step": 390
+    },
+    {
+      "epoch": 4.5982404692082115,
+      "grad_norm": 2.107388734817505,
+      "learning_rate": 2.7370838144002902e-05,
+      "loss": 0.6136,
+      "step": 395
+    },
+    {
+      "epoch": 4.656891495601173,
+      "grad_norm": 1.6728172302246094,
+      "learning_rate": 2.7287745544105237e-05,
+      "loss": 0.6329,
+      "step": 400
+    },
+    {
+      "epoch": 4.715542521994135,
+      "grad_norm": 1.5250803232192993,
+      "learning_rate": 2.7203490523102758e-05,
+      "loss": 0.5953,
+      "step": 405
+    },
+    {
+      "epoch": 4.774193548387097,
+      "grad_norm": 1.4544414281845093,
+      "learning_rate": 2.7118081051523037e-05,
+      "loss": 0.6057,
+      "step": 410
+    },
+    {
+      "epoch": 4.832844574780059,
+      "grad_norm": 1.3960272073745728,
+      "learning_rate": 2.7031525209104695e-05,
+      "loss": 0.5475,
+      "step": 415
+    },
+    {
+      "epoch": 4.891495601173021,
+      "grad_norm": 1.5430188179016113,
+      "learning_rate": 2.694383118403308e-05,
+      "loss": 0.5767,
+      "step": 420
+    },
+    {
+      "epoch": 4.9501466275659824,
+      "grad_norm": 1.4782837629318237,
+      "learning_rate": 2.6855007272165644e-05,
+      "loss": 0.6098,
+      "step": 425
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.5061590671539307,
+      "learning_rate": 2.676506187624718e-05,
+      "loss": 0.5728,
+      "step": 430
+    },
+    {
+      "epoch": 5.058651026392962,
+      "grad_norm": 1.426033854484558,
+      "learning_rate": 2.6674003505114885e-05,
+      "loss": 0.5272,
+      "step": 435
+    },
+    {
+      "epoch": 5.117302052785924,
+      "grad_norm": 1.9145780801773071,
+      "learning_rate": 2.658184077289347e-05,
+      "loss": 0.5207,
+      "step": 440
+    },
+    {
+      "epoch": 5.1759530791788855,
+      "grad_norm": 1.5162384510040283,
+      "learning_rate": 2.6488582398180217e-05,
+      "loss": 0.5466,
+      "step": 445
+    },
+    {
+      "epoch": 5.234604105571847,
+      "grad_norm": 1.5765867233276367,
+      "learning_rate": 2.639423720322023e-05,
+      "loss": 0.532,
+      "step": 450
+    },
+    {
+      "epoch": 5.293255131964809,
+      "grad_norm": 1.6061979532241821,
+      "learning_rate": 2.6298814113071846e-05,
+      "loss": 0.5115,
+      "step": 455
+    },
+    {
+      "epoch": 5.351906158357771,
+      "grad_norm": 1.7579784393310547,
+      "learning_rate": 2.620232215476231e-05,
+      "loss": 0.5534,
+      "step": 460
+    },
+    {
+      "epoch": 5.410557184750733,
+      "grad_norm": 1.5701087713241577,
+      "learning_rate": 2.6104770456433837e-05,
+      "loss": 0.5281,
+      "step": 465
+    },
+    {
+      "epoch": 5.469208211143695,
+      "grad_norm": 1.5090984106063843,
+      "learning_rate": 2.600616824648008e-05,
+      "loss": 0.5121,
+      "step": 470
+    },
+    {
+      "epoch": 5.527859237536656,
+      "grad_norm": 2.6270909309387207,
+      "learning_rate": 2.590652485267311e-05,
+      "loss": 0.5043,
+      "step": 475
+    },
+    {
+      "epoch": 5.586510263929619,
+      "grad_norm": 1.7012410163879395,
+      "learning_rate": 2.5805849701281047e-05,
+      "loss": 0.5113,
+      "step": 480
+    },
+    {
+      "epoch": 5.645161290322581,
+      "grad_norm": 1.852084755897522,
+      "learning_rate": 2.5704152316176287e-05,
+      "loss": 0.476,
+      "step": 485
+    },
+    {
+      "epoch": 5.703812316715543,
+      "grad_norm": 1.3544026613235474,
+      "learning_rate": 2.5601442317934576e-05,
+      "loss": 0.5069,
+      "step": 490
+    },
+    {
+      "epoch": 5.762463343108505,
+      "grad_norm": 1.512239694595337,
+      "learning_rate": 2.5497729422924893e-05,
+      "loss": 0.5143,
+      "step": 495
+    },
+    {
+      "epoch": 5.821114369501466,
+      "grad_norm": 2.261417865753174,
+      "learning_rate": 2.539302344239029e-05,
+      "loss": 0.5075,
+      "step": 500
+    },
+    {
+      "epoch": 5.879765395894428,
+      "grad_norm": 1.6451923847198486,
+      "learning_rate": 2.5287334281519725e-05,
+      "loss": 0.4866,
+      "step": 505
+    },
+    {
+      "epoch": 5.93841642228739,
+      "grad_norm": 1.8043715953826904,
+      "learning_rate": 2.518067193851105e-05,
+      "loss": 0.4805,
+      "step": 510
+    },
+    {
+      "epoch": 5.997067448680352,
+      "grad_norm": 1.4476629495620728,
+      "learning_rate": 2.507304650362519e-05,
+      "loss": 0.4782,
+      "step": 515
+    },
+    {
+      "epoch": 6.0469208211143695,
+      "grad_norm": 2.0781941413879395,
+      "learning_rate": 2.4964468158231576e-05,
+      "loss": 0.4424,
+      "step": 520
+    },
+    {
+      "epoch": 6.105571847507331,
+      "grad_norm": 1.587519884109497,
+      "learning_rate": 2.4854947173845008e-05,
+      "loss": 0.4706,
+      "step": 525
+    },
+    {
+      "epoch": 6.164222873900293,
+      "grad_norm": 1.8226568698883057,
+      "learning_rate": 2.4744493911153962e-05,
+      "loss": 0.4592,
+      "step": 530
+    },
+    {
+      "epoch": 6.222873900293255,
+      "grad_norm": 1.5768177509307861,
+      "learning_rate": 2.463311881904048e-05,
+      "loss": 0.4225,
+      "step": 535
+    },
+    {
+      "epoch": 6.281524926686217,
+      "grad_norm": 1.6065932512283325,
+      "learning_rate": 2.4520832433591675e-05,
+      "loss": 0.4401,
+      "step": 540
+    },
+    {
+      "epoch": 6.340175953079179,
+      "grad_norm": 1.2971386909484863,
+      "learning_rate": 2.4407645377103056e-05,
+      "loss": 0.4538,
+      "step": 545
+    },
+    {
+      "epoch": 6.39882697947214,
+      "grad_norm": 1.838926076889038,
+      "learning_rate": 2.4293568357073634e-05,
+      "loss": 0.4272,
+      "step": 550
+    },
+    {
+      "epoch": 6.457478005865102,
+      "grad_norm": 2.197988986968994,
+      "learning_rate": 2.4178612165192992e-05,
+      "loss": 0.429,
+      "step": 555
+    },
+    {
+      "epoch": 6.516129032258064,
+      "grad_norm": 1.371309757232666,
+      "learning_rate": 2.406278767632041e-05,
+      "loss": 0.3993,
+      "step": 560
+    },
+    {
+      "epoch": 6.574780058651027,
+      "grad_norm": 1.592514157295227,
+      "learning_rate": 2.394610584745608e-05,
+      "loss": 0.3996,
+      "step": 565
+    },
+    {
+      "epoch": 6.633431085043989,
+      "grad_norm": 1.7009004354476929,
+      "learning_rate": 2.3828577716704583e-05,
+      "loss": 0.4013,
+      "step": 570
+    },
+    {
+      "epoch": 6.69208211143695,
+      "grad_norm": 1.5580384731292725,
+      "learning_rate": 2.371021440223069e-05,
+      "loss": 0.425,
+      "step": 575
+    },
+    {
+      "epoch": 6.750733137829912,
+      "grad_norm": 1.570862054824829,
+      "learning_rate": 2.3591027101207578e-05,
+      "loss": 0.4936,
+      "step": 580
+    },
+    {
+      "epoch": 6.809384164222874,
+      "grad_norm": 1.7335824966430664,
+      "learning_rate": 2.347102708875757e-05,
+      "loss": 0.4141,
+      "step": 585
+    },
+    {
+      "epoch": 6.868035190615836,
+      "grad_norm": 1.7174583673477173,
+      "learning_rate": 2.3350225716885522e-05,
+      "loss": 0.406,
+      "step": 590
+    },
+    {
+      "epoch": 6.926686217008798,
+      "grad_norm": 1.6045186519622803,
+      "learning_rate": 2.3228634413404916e-05,
+      "loss": 0.4233,
+      "step": 595
+    },
+    {
+      "epoch": 6.9853372434017595,
+      "grad_norm": 1.520074725151062,
+      "learning_rate": 2.3106264680856776e-05,
+      "loss": 0.4129,
+      "step": 600
+    },
+    {
+      "epoch": 7.035190615835777,
+      "grad_norm": 1.4023849964141846,
+      "learning_rate": 2.298312809542156e-05,
+      "loss": 0.4094,
+      "step": 605
+    },
+    {
+      "epoch": 7.093841642228739,
+      "grad_norm": 1.4728856086730957,
+      "learning_rate": 2.2859236305824e-05,
+      "loss": 0.3425,
+      "step": 610
+    },
+    {
+      "epoch": 7.152492668621701,
+      "grad_norm": 1.5377256870269775,
+      "learning_rate": 2.273460103223122e-05,
+      "loss": 0.3866,
+      "step": 615
+    },
+    {
+      "epoch": 7.211143695014663,
+      "grad_norm": 1.6293245553970337,
+      "learning_rate": 2.260923406514389e-05,
+      "loss": 0.3651,
+      "step": 620
+    },
+    {
+      "epoch": 7.269794721407624,
+      "grad_norm": 1.79743230342865,
+      "learning_rate": 2.248314726428095e-05,
+      "loss": 0.3466,
+      "step": 625
+    },
+    {
+      "epoch": 7.328445747800586,
+      "grad_norm": 1.446027398109436,
+      "learning_rate": 2.2356352557457624e-05,
+      "loss": 0.4,
+      "step": 630
+    },
+    {
+      "epoch": 7.387096774193548,
+      "grad_norm": 1.5968126058578491,
+      "learning_rate": 2.2228861939457056e-05,
+      "loss": 0.3575,
+      "step": 635
+    },
+    {
+      "epoch": 7.44574780058651,
+      "grad_norm": 1.3783931732177734,
+      "learning_rate": 2.210068747089561e-05,
+      "loss": 0.368,
+      "step": 640
+    },
+    {
+      "epoch": 7.504398826979472,
+      "grad_norm": 1.5377360582351685,
+      "learning_rate": 2.1971841277081947e-05,
+      "loss": 0.3604,
+      "step": 645
+    },
+    {
+      "epoch": 7.563049853372434,
+      "grad_norm": 1.6163183450698853,
+      "learning_rate": 2.184233554686994e-05,
+      "loss": 0.3591,
+      "step": 650
+    },
+    {
+      "epoch": 7.621700879765396,
+      "grad_norm": 1.9343562126159668,
+      "learning_rate": 2.1712182531505642e-05,
+      "loss": 0.3543,
+      "step": 655
+    },
+    {
+      "epoch": 7.680351906158358,
+      "grad_norm": 1.860203504562378,
+      "learning_rate": 2.1581394543468286e-05,
+      "loss": 0.362,
+      "step": 660
+    },
+    {
+      "epoch": 7.73900293255132,
+      "grad_norm": 1.7694545984268188,
+      "learning_rate": 2.1449983955305543e-05,
+      "loss": 0.36,
+      "step": 665
+    },
+    {
+      "epoch": 7.797653958944282,
+      "grad_norm": 1.5436360836029053,
+      "learning_rate": 2.131796319846309e-05,
+      "loss": 0.3752,
+      "step": 670
+    },
+    {
+      "epoch": 7.8563049853372435,
+      "grad_norm": 2.079392671585083,
+      "learning_rate": 2.1185344762108556e-05,
+      "loss": 0.3711,
+      "step": 675
+    },
+    {
+      "epoch": 7.914956011730205,
+      "grad_norm": 1.5377277135849,
+      "learning_rate": 2.1052141191950083e-05,
+      "loss": 0.3431,
+      "step": 680
+    },
+    {
+      "epoch": 7.973607038123167,
+      "grad_norm": 1.4733537435531616,
+      "learning_rate": 2.0918365089049492e-05,
+      "loss": 0.3714,
+      "step": 685
+    },
+    {
+      "epoch": 8.023460410557185,
+      "grad_norm": 1.7115830183029175,
+      "learning_rate": 2.078402910863022e-05,
+      "loss": 0.3286,
+      "step": 690
+    },
+    {
+      "epoch": 8.082111436950147,
+      "grad_norm": 1.6873016357421875,
+      "learning_rate": 2.0649145958880112e-05,
+      "loss": 0.3573,
+      "step": 695
+    },
+    {
+      "epoch": 8.140762463343108,
+      "grad_norm": 1.8315602540969849,
+      "learning_rate": 2.0513728399749288e-05,
+      "loss": 0.3325,
+      "step": 700
+    },
+    {
+      "epoch": 8.19941348973607,
+      "grad_norm": 1.827303171157837,
+      "learning_rate": 2.0377789241742973e-05,
+      "loss": 0.3387,
+      "step": 705
+    },
+    {
+      "epoch": 8.258064516129032,
+      "grad_norm": 1.9863218069076538,
+      "learning_rate": 2.0241341344709678e-05,
+      "loss": 0.3124,
+      "step": 710
+    },
+    {
+      "epoch": 8.316715542521994,
+      "grad_norm": 1.8508158922195435,
+      "learning_rate": 2.0104397616624646e-05,
+      "loss": 0.3279,
+      "step": 715
+    },
+    {
+      "epoch": 8.375366568914956,
+      "grad_norm": 1.636530876159668,
+      "learning_rate": 1.996697101236875e-05,
+      "loss": 0.3249,
+      "step": 720
+    },
+    {
+      "epoch": 8.434017595307918,
+      "grad_norm": 1.4390839338302612,
+      "learning_rate": 1.9829074532502958e-05,
+      "loss": 0.3019,
+      "step": 725
+    },
+    {
+      "epoch": 8.49266862170088,
+      "grad_norm": 1.6479607820510864,
+      "learning_rate": 1.9690721222038488e-05,
+      "loss": 0.3259,
+      "step": 730
+    },
+    {
+      "epoch": 8.551319648093841,
+      "grad_norm": 1.9377621412277222,
+      "learning_rate": 1.955192416920275e-05,
+      "loss": 0.3287,
+      "step": 735
+    },
+    {
+      "epoch": 8.609970674486803,
+      "grad_norm": 1.6579439640045166,
+      "learning_rate": 1.9412696504201194e-05,
+      "loss": 0.3323,
+      "step": 740
+    },
+    {
+      "epoch": 8.668621700879765,
+      "grad_norm": 1.8197572231292725,
+      "learning_rate": 1.927305139797519e-05,
+      "loss": 0.2997,
+      "step": 745
+    },
+    {
+      "epoch": 8.727272727272727,
+      "grad_norm": 1.4135760068893433,
+      "learning_rate": 1.913300206095607e-05,
+      "loss": 0.3396,
+      "step": 750
+    },
+    {
+      "epoch": 8.785923753665688,
+      "grad_norm": 1.576826572418213,
+      "learning_rate": 1.8992561741815397e-05,
+      "loss": 0.3044,
+      "step": 755
+    },
+    {
+      "epoch": 8.84457478005865,
+      "grad_norm": 1.696305751800537,
+      "learning_rate": 1.8851743726211665e-05,
+      "loss": 0.3068,
+      "step": 760
+    },
+    {
+      "epoch": 8.903225806451612,
+      "grad_norm": 1.5686278343200684,
+      "learning_rate": 1.8710561335533467e-05,
+      "loss": 0.2817,
+      "step": 765
+    },
+    {
+      "epoch": 8.961876832844574,
+      "grad_norm": 1.822142481803894,
+      "learning_rate": 1.856902792563928e-05,
+      "loss": 0.2894,
+      "step": 770
+    },
+    {
+      "epoch": 9.011730205278592,
+      "grad_norm": 3.2489266395568848,
+      "learning_rate": 1.8427156885594026e-05,
+      "loss": 0.3153,
+      "step": 775
+    },
+    {
+      "epoch": 9.070381231671554,
+      "grad_norm": 1.5879300832748413,
+      "learning_rate": 1.8284961636402418e-05,
+      "loss": 0.2708,
+      "step": 780
+    },
+    {
+      "epoch": 9.129032258064516,
+      "grad_norm": 1.7300035953521729,
+      "learning_rate": 1.8142455629739413e-05,
+      "loss": 0.2691,
+      "step": 785
+    },
+    {
+      "epoch": 9.187683284457478,
+      "grad_norm": 1.6516594886779785,
+      "learning_rate": 1.7999652346677577e-05,
+      "loss": 0.2942,
+      "step": 790
+    },
+    {
+      "epoch": 9.24633431085044,
+      "grad_norm": 1.6192295551300049,
+      "learning_rate": 1.785656529641188e-05,
+      "loss": 0.2963,
+      "step": 795
+    },
+    {
+      "epoch": 9.304985337243401,
+      "grad_norm": 1.7734555006027222,
+      "learning_rate": 1.771320801498165e-05,
+      "loss": 0.2987,
+      "step": 800
+    },
+    {
+      "epoch": 9.363636363636363,
+      "grad_norm": 1.5193028450012207,
+      "learning_rate": 1.7569594063990106e-05,
+      "loss": 0.2901,
+      "step": 805
+    },
+    {
+      "epoch": 9.422287390029325,
+      "grad_norm": 1.9062447547912598,
+      "learning_rate": 1.7425737029321407e-05,
+      "loss": 0.2633,
+      "step": 810
+    },
+    {
+      "epoch": 9.480938416422287,
+      "grad_norm": 1.6332511901855469,
+      "learning_rate": 1.728165051985544e-05,
+      "loss": 0.2982,
+      "step": 815
+    },
+    {
+      "epoch": 9.539589442815249,
+      "grad_norm": 1.7536693811416626,
+      "learning_rate": 1.713734816618042e-05,
+      "loss": 0.2668,
+      "step": 820
+    },
+    {
+      "epoch": 9.59824046920821,
+      "grad_norm": 1.4995721578598022,
+      "learning_rate": 1.6992843619303415e-05,
+      "loss": 0.2774,
+      "step": 825
+    },
+    {
+      "epoch": 9.656891495601172,
+      "grad_norm": 1.9364445209503174,
+      "learning_rate": 1.684815054935899e-05,
+      "loss": 0.3034,
+      "step": 830
+    },
+    {
+      "epoch": 9.715542521994134,
+      "grad_norm": 1.689841866493225,
+      "learning_rate": 1.6703282644315985e-05,
+      "loss": 0.2696,
+      "step": 835
+    },
+    {
+      "epoch": 9.774193548387096,
+      "grad_norm": 2.015406370162964,
+      "learning_rate": 1.6558253608682665e-05,
+      "loss": 0.2836,
+      "step": 840
+    },
+    {
+      "epoch": 9.832844574780058,
+      "grad_norm": 1.4139841794967651,
+      "learning_rate": 1.641307716221024e-05,
+      "loss": 0.2725,
+      "step": 845
+    },
+    {
+      "epoch": 9.89149560117302,
+      "grad_norm": 1.5893827676773071,
+      "learning_rate": 1.626776703859499e-05,
+      "loss": 0.2675,
+      "step": 850
+    },
+    {
+      "epoch": 9.950146627565982,
+      "grad_norm": 1.6394363641738892,
+      "learning_rate": 1.612233698417906e-05,
+      "loss": 0.2775,
+      "step": 855
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.5809170007705688,
+      "learning_rate": 1.5976800756650055e-05,
+      "loss": 0.2525,
+      "step": 860
+    },
+    {
+      "epoch": 10.058651026392962,
+      "grad_norm": 1.722279667854309,
+      "learning_rate": 1.583117212373955e-05,
+      "loss": 0.239,
+      "step": 865
+    },
+    {
+      "epoch": 10.117302052785924,
+      "grad_norm": 1.4771348237991333,
+      "learning_rate": 1.568546486192069e-05,
+      "loss": 0.2719,
+      "step": 870
+    },
+    {
+      "epoch": 10.175953079178885,
+      "grad_norm": 1.8491390943527222,
+      "learning_rate": 1.553969275510489e-05,
+      "loss": 0.2585,
+      "step": 875
+    },
+    {
+      "epoch": 10.234604105571847,
+      "grad_norm": 1.7717721462249756,
+      "learning_rate": 1.539386959333793e-05,
+      "loss": 0.2481,
+      "step": 880
+    },
+    {
+      "epoch": 10.29325513196481,
+      "grad_norm": 1.4404025077819824,
+      "learning_rate": 1.524800917149538e-05,
+      "loss": 0.2441,
+      "step": 885
+    },
+    {
+      "epoch": 10.351906158357771,
+      "grad_norm": 1.5100393295288086,
+      "learning_rate": 1.5102125287977604e-05,
+      "loss": 0.2674,
+      "step": 890
+    },
+    {
+      "epoch": 10.410557184750733,
+      "grad_norm": 1.9897160530090332,
+      "learning_rate": 1.4956231743404466e-05,
+      "loss": 0.2558,
+      "step": 895
+    },
+    {
+      "epoch": 10.469208211143695,
+      "grad_norm": 1.7335450649261475,
+      "learning_rate": 1.4810342339309738e-05,
+      "loss": 0.2472,
+      "step": 900
+    },
+    {
+      "epoch": 10.527859237536656,
+      "grad_norm": 2.008821725845337,
+      "learning_rate": 1.466447087683552e-05,
+      "loss": 0.2403,
+      "step": 905
+    },
+    {
+      "epoch": 10.586510263929618,
+      "grad_norm": 1.489761233329773,
+      "learning_rate": 1.4518631155426629e-05,
+      "loss": 0.235,
+      "step": 910
+    },
+    {
+      "epoch": 10.64516129032258,
+      "grad_norm": 1.5563368797302246,
+      "learning_rate": 1.4372836971525184e-05,
+      "loss": 0.2396,
+      "step": 915
+    },
+    {
+      "epoch": 10.703812316715542,
+      "grad_norm": 1.7141892910003662,
+      "learning_rate": 1.4227102117265432e-05,
+      "loss": 0.2442,
+      "step": 920
+    },
+    {
+      "epoch": 10.762463343108504,
+      "grad_norm": 1.568986415863037,
+      "learning_rate": 1.408144037916906e-05,
+      "loss": 0.2485,
+      "step": 925
+    },
+    {
+      "epoch": 10.821114369501466,
+      "grad_norm": 1.3690587282180786,
+      "learning_rate": 1.393586553684096e-05,
+      "loss": 0.267,
+      "step": 930
+    },
+    {
+      "epoch": 10.879765395894427,
+      "grad_norm": 1.4901823997497559,
+      "learning_rate": 1.3790391361665658e-05,
+      "loss": 0.2479,
+      "step": 935
+    },
+    {
+      "epoch": 10.93841642228739,
+      "grad_norm": 1.538944959640503,
+      "learning_rate": 1.3645031615504593e-05,
+      "loss": 0.2568,
+      "step": 940
+    },
+    {
+      "epoch": 10.997067448680351,
+      "grad_norm": 1.584997296333313,
+      "learning_rate": 1.34998000493942e-05,
+      "loss": 0.2513,
+      "step": 945
+    },
+    {
+      "epoch": 11.04692082111437,
+      "grad_norm": 1.578392744064331,
+      "learning_rate": 1.3354710402245081e-05,
+      "loss": 0.216,
+      "step": 950
+    },
+    {
+      "epoch": 11.105571847507331,
+      "grad_norm": 1.5702141523361206,
+      "learning_rate": 1.3209776399542298e-05,
+      "loss": 0.2341,
+      "step": 955
+    },
+    {
+      "epoch": 11.164222873900293,
+      "grad_norm": 1.2398377656936646,
+      "learning_rate": 1.3065011752046955e-05,
+      "loss": 0.2045,
+      "step": 960
+    },
+    {
+      "epoch": 11.222873900293255,
+      "grad_norm": 1.6778515577316284,
+      "learning_rate": 1.2920430154499123e-05,
+      "loss": 0.2226,
+      "step": 965
+    },
+    {
+      "epoch": 11.281524926686217,
+      "grad_norm": 1.3014507293701172,
+      "learning_rate": 1.277604528432237e-05,
+      "loss": 0.2013,
+      "step": 970
+    },
+    {
+      "epoch": 11.340175953079179,
+      "grad_norm": 1.6591119766235352,
+      "learning_rate": 1.2631870800329839e-05,
+      "loss": 0.2198,
+      "step": 975
+    },
+    {
+      "epoch": 11.39882697947214,
+      "grad_norm": 1.5535308122634888,
+      "learning_rate": 1.248792034143212e-05,
+      "loss": 0.2071,
+      "step": 980
+    },
+    {
+      "epoch": 11.457478005865102,
+      "grad_norm": 1.5089534521102905,
+      "learning_rate": 1.2344207525347039e-05,
+      "loss": 0.2101,
+      "step": 985
+    },
+    {
+      "epoch": 11.516129032258064,
+      "grad_norm": 1.3858919143676758,
+      "learning_rate": 1.2200745947311409e-05,
+      "loss": 0.234,
+      "step": 990
+    },
+    {
+      "epoch": 11.574780058651026,
+      "grad_norm": 1.6462393999099731,
+      "learning_rate": 1.2057549178794888e-05,
+      "loss": 0.2265,
+      "step": 995
+    },
+    {
+      "epoch": 11.633431085043988,
+      "grad_norm": 1.351588249206543,
+      "learning_rate": 1.1914630766216173e-05,
+      "loss": 0.2495,
+      "step": 1000
+    },
+    {
+      "epoch": 11.69208211143695,
+      "grad_norm": 1.450875163078308,
+      "learning_rate": 1.1772004229661474e-05,
+      "loss": 0.2256,
+      "step": 1005
+    },
+    {
+      "epoch": 11.750733137829911,
+      "grad_norm": 1.5337797403335571,
+      "learning_rate": 1.162968306160551e-05,
+      "loss": 0.227,
+      "step": 1010
+    },
+    {
+      "epoch": 11.809384164222873,
+      "grad_norm": 1.6182599067687988,
+      "learning_rate": 1.148768072563514e-05,
+      "loss": 0.2465,
+      "step": 1015
+    },
+    {
+      "epoch": 11.868035190615835,
+      "grad_norm": 1.4571447372436523,
+      "learning_rate": 1.1346010655175707e-05,
+      "loss": 0.2218,
+      "step": 1020
+    },
+    {
+      "epoch": 11.926686217008797,
+      "grad_norm": 1.6681259870529175,
+      "learning_rate": 1.1204686252220202e-05,
+      "loss": 0.2513,
+      "step": 1025
+    },
+    {
+      "epoch": 11.985337243401759,
+      "grad_norm": 1.3346493244171143,
+      "learning_rate": 1.1063720886061473e-05,
+      "loss": 0.2367,
+      "step": 1030
+    },
+    {
+      "epoch": 12.035190615835777,
+      "grad_norm": 1.4893953800201416,
+      "learning_rate": 1.0923127892027488e-05,
+      "loss": 0.2275,
+      "step": 1035
+    },
+    {
+      "epoch": 12.093841642228739,
+      "grad_norm": 1.3146791458129883,
+      "learning_rate": 1.0782920570219772e-05,
+      "loss": 0.227,
+      "step": 1040
+    },
+    {
+      "epoch": 12.1524926686217,
+      "grad_norm": 1.4524919986724854,
+      "learning_rate": 1.0643112184255273e-05,
+      "loss": 0.1991,
+      "step": 1045
+    },
+    {
+      "epoch": 12.211143695014663,
+      "grad_norm": 1.4916414022445679,
+      "learning_rate": 1.0503715960011583e-05,
+      "loss": 0.1957,
+      "step": 1050
+    },
+    {
+      "epoch": 12.269794721407624,
+      "grad_norm": 1.4291622638702393,
+      "learning_rate": 1.036474508437579e-05,
+      "loss": 0.208,
+      "step": 1055
+    },
+    {
+      "epoch": 12.328445747800586,
+      "grad_norm": 1.364890217781067,
+      "learning_rate": 1.0226212703996979e-05,
+      "loss": 0.1996,
+      "step": 1060
+    },
+    {
+      "epoch": 12.387096774193548,
+      "grad_norm": 1.507483959197998,
+      "learning_rate": 1.0088131924042571e-05,
+      "loss": 0.2256,
+      "step": 1065
+    },
+    {
+      "epoch": 12.44574780058651,
+      "grad_norm": 1.5189411640167236,
+      "learning_rate": 9.950515806958595e-06,
+      "loss": 0.2133,
+      "step": 1070
+    },
+    {
+      "epoch": 12.504398826979472,
+      "grad_norm": 1.3920835256576538,
+      "learning_rate": 9.813377371233928e-06,
+      "loss": 0.2137,
+      "step": 1075
+    },
+    {
+      "epoch": 12.563049853372434,
+      "grad_norm": 1.4195996522903442,
+      "learning_rate": 9.676729590168794e-06,
+      "loss": 0.2018,
+      "step": 1080
+    },
+    {
+      "epoch": 12.621700879765395,
+      "grad_norm": 1.4136230945587158,
+      "learning_rate": 9.540585390647472e-06,
+      "loss": 0.2193,
+      "step": 1085
+    },
+    {
+      "epoch": 12.680351906158357,
+      "grad_norm": 1.835013747215271,
+      "learning_rate": 9.404957651915394e-06,
+      "loss": 0.2205,
+      "step": 1090
+    },
+    {
+      "epoch": 12.739002932551319,
+      "grad_norm": 1.5377280712127686,
+      "learning_rate": 9.26985920436081e-06,
+      "loss": 0.1994,
+      "step": 1095
+    },
+    {
+      "epoch": 12.79765395894428,
+      "grad_norm": 1.3562695980072021,
+      "learning_rate": 9.135302828300996e-06,
+      "loss": 0.1906,
+      "step": 1100
+    },
+    {
+      "epoch": 12.856304985337243,
+      "grad_norm": 1.3233888149261475,
+      "learning_rate": 9.001301252773242e-06,
+      "loss": 0.2192,
+      "step": 1105
+    },
+    {
+      "epoch": 12.914956011730204,
+      "grad_norm": 1.3167542219161987,
+      "learning_rate": 8.867867154330694e-06,
+      "loss": 0.217,
+      "step": 1110
+    },
+    {
+      "epoch": 12.973607038123166,
+      "grad_norm": 1.9798552989959717,
+      "learning_rate": 8.735013155843165e-06,
+      "loss": 0.1922,
+      "step": 1115
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1700,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.821172725415936e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1118/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8661d4af4b612fdd59ee0a2ad90ad8380b6dba00c9fff95f2ddecfcdbfc43a38
+size 7608

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1118/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/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, exclude_frozen_parameters):
+    """
+    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,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+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 _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+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() if _has_callable(shape, 'numel') else math.prod(shape)
+            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,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _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,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _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, exclude_frozen_parameters=False):
+    """
+    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``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    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, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    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``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    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("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    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,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1204/README.md

@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.1-8B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1204/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.1-8B",
+  "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": 512,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1204/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53804c0becb8126f6c50b3e0355bc51bca2a10b400882eb043ad0c2cc4cfaaa8
+size 1342239008

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1204/latest

@@ -0,0 +1 @@
+global_step1193

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1204/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf3d027f216b7ca9c04bda2b012bb01e9679153cf0786414e9f0e9cdfec859f
+size 14960

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1204/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f76580e5a6afa8680a74aa5df75f7703d09845385c13438b8f67b107cb4a3718
+size 14960

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1204/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f8a90f9a2cbcb504298dcff44616fface05b9762c3a47267dd15809e92be47b
+size 14960

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1204/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c21d74cf436c03cc0531daec90d7b4d651a7498ce98a8d2d264f047bfc03e1e4
+size 14960

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1204/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70dbb5ae7adf67949489aae898a7332f44a918a711c7d97026e132da146bd303
+size 1064

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1204/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1204/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1204/tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1204/trainer_state.json

@@ -0,0 +1,1714 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 14.0,
+  "eval_steps": 500,
+  "global_step": 1204,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05865102639296188,
+      "grad_norm": 0.8587596416473389,
+      "learning_rate": 1.411764705882353e-06,
+      "loss": 1.6979,
+      "step": 5
+    },
+    {
+      "epoch": 0.11730205278592376,
+      "grad_norm": 0.8847993016242981,
+      "learning_rate": 3.1764705882352943e-06,
+      "loss": 1.665,
+      "step": 10
+    },
+    {
+      "epoch": 0.17595307917888564,
+      "grad_norm": 0.843494713306427,
+      "learning_rate": 4.941176470588235e-06,
+      "loss": 1.6549,
+      "step": 15
+    },
+    {
+      "epoch": 0.23460410557184752,
+      "grad_norm": 0.675523042678833,
+      "learning_rate": 6.705882352941177e-06,
+      "loss": 1.6421,
+      "step": 20
+    },
+    {
+      "epoch": 0.2932551319648094,
+      "grad_norm": 0.7297828197479248,
+      "learning_rate": 8.470588235294118e-06,
+      "loss": 1.616,
+      "step": 25
+    },
+    {
+      "epoch": 0.3519061583577713,
+      "grad_norm": 0.6939984560012817,
+      "learning_rate": 1.023529411764706e-05,
+      "loss": 1.6368,
+      "step": 30
+    },
+    {
+      "epoch": 0.41055718475073316,
+      "grad_norm": 0.6109864115715027,
+      "learning_rate": 1.2e-05,
+      "loss": 1.5477,
+      "step": 35
+    },
+    {
+      "epoch": 0.46920821114369504,
+      "grad_norm": 0.5642703175544739,
+      "learning_rate": 1.3764705882352941e-05,
+      "loss": 1.5555,
+      "step": 40
+    },
+    {
+      "epoch": 0.5278592375366569,
+      "grad_norm": 0.5742537379264832,
+      "learning_rate": 1.5529411764705886e-05,
+      "loss": 1.565,
+      "step": 45
+    },
+    {
+      "epoch": 0.5865102639296188,
+      "grad_norm": 0.586601734161377,
+      "learning_rate": 1.7294117647058823e-05,
+      "loss": 1.5015,
+      "step": 50
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.6344695091247559,
+      "learning_rate": 1.9058823529411764e-05,
+      "loss": 1.4895,
+      "step": 55
+    },
+    {
+      "epoch": 0.7038123167155426,
+      "grad_norm": 0.5736978054046631,
+      "learning_rate": 2.0823529411764705e-05,
+      "loss": 1.5151,
+      "step": 60
+    },
+    {
+      "epoch": 0.7624633431085044,
+      "grad_norm": 0.6642257571220398,
+      "learning_rate": 2.2588235294117646e-05,
+      "loss": 1.5098,
+      "step": 65
+    },
+    {
+      "epoch": 0.8211143695014663,
+      "grad_norm": 0.6018787026405334,
+      "learning_rate": 2.4352941176470587e-05,
+      "loss": 1.4935,
+      "step": 70
+    },
+    {
+      "epoch": 0.8797653958944281,
+      "grad_norm": 0.5532670617103577,
+      "learning_rate": 2.6117647058823532e-05,
+      "loss": 1.4452,
+      "step": 75
+    },
+    {
+      "epoch": 0.9384164222873901,
+      "grad_norm": 0.710066020488739,
+      "learning_rate": 2.7882352941176473e-05,
+      "loss": 1.4699,
+      "step": 80
+    },
+    {
+      "epoch": 0.9970674486803519,
+      "grad_norm": 0.7423866391181946,
+      "learning_rate": 2.9647058823529414e-05,
+      "loss": 1.3994,
+      "step": 85
+    },
+    {
+      "epoch": 1.0469208211143695,
+      "grad_norm": 0.6278711557388306,
+      "learning_rate": 2.9999545918564296e-05,
+      "loss": 1.4367,
+      "step": 90
+    },
+    {
+      "epoch": 1.1055718475073313,
+      "grad_norm": 1.0214080810546875,
+      "learning_rate": 2.999770125984927e-05,
+      "loss": 1.3484,
+      "step": 95
+    },
+    {
+      "epoch": 1.1642228739002933,
+      "grad_norm": 0.7089139223098755,
+      "learning_rate": 2.9994437818135727e-05,
+      "loss": 1.3716,
+      "step": 100
+    },
+    {
+      "epoch": 1.2228739002932552,
+      "grad_norm": 0.6738442778587341,
+      "learning_rate": 2.9989755902145345e-05,
+      "loss": 1.2964,
+      "step": 105
+    },
+    {
+      "epoch": 1.281524926686217,
+      "grad_norm": 0.93358314037323,
+      "learning_rate": 2.9983655954787524e-05,
+      "loss": 1.3178,
+      "step": 110
+    },
+    {
+      "epoch": 1.3401759530791788,
+      "grad_norm": 0.8929201364517212,
+      "learning_rate": 2.9976138553117475e-05,
+      "loss": 1.3054,
+      "step": 115
+    },
+    {
+      "epoch": 1.3988269794721409,
+      "grad_norm": 0.7999489307403564,
+      "learning_rate": 2.9967204408281618e-05,
+      "loss": 1.3322,
+      "step": 120
+    },
+    {
+      "epoch": 1.4574780058651027,
+      "grad_norm": 0.9014801979064941,
+      "learning_rate": 2.9956854365450334e-05,
+      "loss": 1.2172,
+      "step": 125
+    },
+    {
+      "epoch": 1.5161290322580645,
+      "grad_norm": 0.8600694537162781,
+      "learning_rate": 2.9945089403737992e-05,
+      "loss": 1.2395,
+      "step": 130
+    },
+    {
+      "epoch": 1.5747800586510263,
+      "grad_norm": 0.8276307582855225,
+      "learning_rate": 2.993191063611033e-05,
+      "loss": 1.2443,
+      "step": 135
+    },
+    {
+      "epoch": 1.6334310850439882,
+      "grad_norm": 1.1944879293441772,
+      "learning_rate": 2.9917319309279167e-05,
+      "loss": 1.1981,
+      "step": 140
+    },
+    {
+      "epoch": 1.6920821114369502,
+      "grad_norm": 0.9493594169616699,
+      "learning_rate": 2.990131680358447e-05,
+      "loss": 1.197,
+      "step": 145
+    },
+    {
+      "epoch": 1.750733137829912,
+      "grad_norm": 0.8087087273597717,
+      "learning_rate": 2.9883904632863765e-05,
+      "loss": 1.151,
+      "step": 150
+    },
+    {
+      "epoch": 1.8093841642228738,
+      "grad_norm": 1.0508242845535278,
+      "learning_rate": 2.9865084444308933e-05,
+      "loss": 1.1387,
+      "step": 155
+    },
+    {
+      "epoch": 1.868035190615836,
+      "grad_norm": 0.8509999513626099,
+      "learning_rate": 2.98448580183104e-05,
+      "loss": 1.1557,
+      "step": 160
+    },
+    {
+      "epoch": 1.9266862170087977,
+      "grad_norm": 0.8426937460899353,
+      "learning_rate": 2.9823227268288677e-05,
+      "loss": 1.1069,
+      "step": 165
+    },
+    {
+      "epoch": 1.9853372434017595,
+      "grad_norm": 0.9207291007041931,
+      "learning_rate": 2.980019424051337e-05,
+      "loss": 1.1039,
+      "step": 170
+    },
+    {
+      "epoch": 2.035190615835777,
+      "grad_norm": 0.9143871068954468,
+      "learning_rate": 2.9775761113909628e-05,
+      "loss": 1.1063,
+      "step": 175
+    },
+    {
+      "epoch": 2.093841642228739,
+      "grad_norm": 0.9446623921394348,
+      "learning_rate": 2.9749930199851966e-05,
+      "loss": 1.0862,
+      "step": 180
+    },
+    {
+      "epoch": 2.1524926686217007,
+      "grad_norm": 0.9225357174873352,
+      "learning_rate": 2.9722703941945646e-05,
+      "loss": 1.051,
+      "step": 185
+    },
+    {
+      "epoch": 2.2111436950146626,
+      "grad_norm": 0.9399577379226685,
+      "learning_rate": 2.9694084915795506e-05,
+      "loss": 1.0305,
+      "step": 190
+    },
+    {
+      "epoch": 2.2697947214076244,
+      "grad_norm": 1.1311970949172974,
+      "learning_rate": 2.966407582876229e-05,
+      "loss": 0.9822,
+      "step": 195
+    },
+    {
+      "epoch": 2.3284457478005867,
+      "grad_norm": 1.1564215421676636,
+      "learning_rate": 2.9632679519706553e-05,
+      "loss": 1.0094,
+      "step": 200
+    },
+    {
+      "epoch": 2.3870967741935485,
+      "grad_norm": 1.3596452474594116,
+      "learning_rate": 2.9599898958720088e-05,
+      "loss": 1.0323,
+      "step": 205
+    },
+    {
+      "epoch": 2.4457478005865103,
+      "grad_norm": 0.9719135761260986,
+      "learning_rate": 2.9565737246844976e-05,
+      "loss": 1.0168,
+      "step": 210
+    },
+    {
+      "epoch": 2.504398826979472,
+      "grad_norm": 1.2797770500183105,
+      "learning_rate": 2.9530197615780202e-05,
+      "loss": 0.9826,
+      "step": 215
+    },
+    {
+      "epoch": 2.563049853372434,
+      "grad_norm": 1.0977298021316528,
+      "learning_rate": 2.9493283427575955e-05,
+      "loss": 0.946,
+      "step": 220
+    },
+    {
+      "epoch": 2.621700879765396,
+      "grad_norm": 1.093330979347229,
+      "learning_rate": 2.9454998174315572e-05,
+      "loss": 0.9502,
+      "step": 225
+    },
+    {
+      "epoch": 2.6803519061583576,
+      "grad_norm": 1.2540782690048218,
+      "learning_rate": 2.941534547778518e-05,
+      "loss": 0.9617,
+      "step": 230
+    },
+    {
+      "epoch": 2.73900293255132,
+      "grad_norm": 1.3939732313156128,
+      "learning_rate": 2.9374329089131082e-05,
+      "loss": 0.9205,
+      "step": 235
+    },
+    {
+      "epoch": 2.7976539589442817,
+      "grad_norm": 1.4037718772888184,
+      "learning_rate": 2.933195288850491e-05,
+      "loss": 0.9274,
+      "step": 240
+    },
+    {
+      "epoch": 2.8563049853372435,
+      "grad_norm": 1.2683528661727905,
+      "learning_rate": 2.9288220884696535e-05,
+      "loss": 0.9016,
+      "step": 245
+    },
+    {
+      "epoch": 2.9149560117302054,
+      "grad_norm": 1.2677197456359863,
+      "learning_rate": 2.924313721475486e-05,
+      "loss": 0.9143,
+      "step": 250
+    },
+    {
+      "epoch": 2.973607038123167,
+      "grad_norm": 1.1638188362121582,
+      "learning_rate": 2.919670614359644e-05,
+      "loss": 0.8975,
+      "step": 255
+    },
+    {
+      "epoch": 3.0234604105571847,
+      "grad_norm": 1.1116777658462524,
+      "learning_rate": 2.9148932063602026e-05,
+      "loss": 0.8464,
+      "step": 260
+    },
+    {
+      "epoch": 3.0821114369501466,
+      "grad_norm": 1.2918649911880493,
+      "learning_rate": 2.9099819494201052e-05,
+      "loss": 0.8562,
+      "step": 265
+    },
+    {
+      "epoch": 3.1407624633431084,
+      "grad_norm": 1.2727012634277344,
+      "learning_rate": 2.904937308144409e-05,
+      "loss": 0.8165,
+      "step": 270
+    },
+    {
+      "epoch": 3.19941348973607,
+      "grad_norm": 1.3380333185195923,
+      "learning_rate": 2.8997597597563333e-05,
+      "loss": 0.7949,
+      "step": 275
+    },
+    {
+      "epoch": 3.258064516129032,
+      "grad_norm": 1.3585141897201538,
+      "learning_rate": 2.8944497940521135e-05,
+      "loss": 0.8175,
+      "step": 280
+    },
+    {
+      "epoch": 3.3167155425219943,
+      "grad_norm": 1.3035612106323242,
+      "learning_rate": 2.8890079133546676e-05,
+      "loss": 0.7723,
+      "step": 285
+    },
+    {
+      "epoch": 3.375366568914956,
+      "grad_norm": 1.337160587310791,
+      "learning_rate": 2.883434632466077e-05,
+      "loss": 0.799,
+      "step": 290
+    },
+    {
+      "epoch": 3.434017595307918,
+      "grad_norm": 1.2794411182403564,
+      "learning_rate": 2.8777304786188847e-05,
+      "loss": 0.8098,
+      "step": 295
+    },
+    {
+      "epoch": 3.4926686217008798,
+      "grad_norm": 1.6959810256958008,
+      "learning_rate": 2.8718959914262185e-05,
+      "loss": 0.779,
+      "step": 300
+    },
+    {
+      "epoch": 3.5513196480938416,
+      "grad_norm": 1.2770452499389648,
+      "learning_rate": 2.865931722830746e-05,
+      "loss": 0.7574,
+      "step": 305
+    },
+    {
+      "epoch": 3.6099706744868034,
+      "grad_norm": 1.4143999814987183,
+      "learning_rate": 2.8598382370524593e-05,
+      "loss": 0.751,
+      "step": 310
+    },
+    {
+      "epoch": 3.6686217008797652,
+      "grad_norm": 1.5334277153015137,
+      "learning_rate": 2.853616110535299e-05,
+      "loss": 0.7468,
+      "step": 315
+    },
+    {
+      "epoch": 3.7272727272727275,
+      "grad_norm": 1.3932515382766724,
+      "learning_rate": 2.8472659318926242e-05,
+      "loss": 0.7526,
+      "step": 320
+    },
+    {
+      "epoch": 3.7859237536656893,
+      "grad_norm": 1.7445088624954224,
+      "learning_rate": 2.8407883018515293e-05,
+      "loss": 0.7266,
+      "step": 325
+    },
+    {
+      "epoch": 3.844574780058651,
+      "grad_norm": 1.4015307426452637,
+      "learning_rate": 2.8341838331960148e-05,
+      "loss": 0.6991,
+      "step": 330
+    },
+    {
+      "epoch": 3.903225806451613,
+      "grad_norm": 1.6155469417572021,
+      "learning_rate": 2.8274531507090175e-05,
+      "loss": 0.7441,
+      "step": 335
+    },
+    {
+      "epoch": 3.961876832844575,
+      "grad_norm": 1.4563353061676025,
+      "learning_rate": 2.8205968911133063e-05,
+      "loss": 0.7398,
+      "step": 340
+    },
+    {
+      "epoch": 4.011730205278592,
+      "grad_norm": 1.5465773344039917,
+      "learning_rate": 2.81361570301125e-05,
+      "loss": 0.7079,
+      "step": 345
+    },
+    {
+      "epoch": 4.070381231671554,
+      "grad_norm": 1.7146860361099243,
+      "learning_rate": 2.8065102468234564e-05,
+      "loss": 0.6398,
+      "step": 350
+    },
+    {
+      "epoch": 4.129032258064516,
+      "grad_norm": 1.5548095703125,
+      "learning_rate": 2.7992811947262987e-05,
+      "loss": 0.676,
+      "step": 355
+    },
+    {
+      "epoch": 4.187683284457478,
+      "grad_norm": 1.4299269914627075,
+      "learning_rate": 2.791929230588326e-05,
+      "loss": 0.6525,
+      "step": 360
+    },
+    {
+      "epoch": 4.24633431085044,
+      "grad_norm": 1.4415459632873535,
+      "learning_rate": 2.7844550499055713e-05,
+      "loss": 0.6276,
+      "step": 365
+    },
+    {
+      "epoch": 4.3049853372434015,
+      "grad_norm": 1.5755006074905396,
+      "learning_rate": 2.776859359735756e-05,
+      "loss": 0.6344,
+      "step": 370
+    },
+    {
+      "epoch": 4.363636363636363,
+      "grad_norm": 1.6027603149414062,
+      "learning_rate": 2.769142878631403e-05,
+      "loss": 0.662,
+      "step": 375
+    },
+    {
+      "epoch": 4.422287390029325,
+      "grad_norm": 1.484080195426941,
+      "learning_rate": 2.7613063365718615e-05,
+      "loss": 0.6234,
+      "step": 380
+    },
+    {
+      "epoch": 4.480938416422287,
+      "grad_norm": 1.7750574350357056,
+      "learning_rate": 2.7533504748942494e-05,
+      "loss": 0.6296,
+      "step": 385
+    },
+    {
+      "epoch": 4.539589442815249,
+      "grad_norm": 1.3946748971939087,
+      "learning_rate": 2.745276046223326e-05,
+      "loss": 0.6464,
+      "step": 390
+    },
+    {
+      "epoch": 4.5982404692082115,
+      "grad_norm": 2.107388734817505,
+      "learning_rate": 2.7370838144002902e-05,
+      "loss": 0.6136,
+      "step": 395
+    },
+    {
+      "epoch": 4.656891495601173,
+      "grad_norm": 1.6728172302246094,
+      "learning_rate": 2.7287745544105237e-05,
+      "loss": 0.6329,
+      "step": 400
+    },
+    {
+      "epoch": 4.715542521994135,
+      "grad_norm": 1.5250803232192993,
+      "learning_rate": 2.7203490523102758e-05,
+      "loss": 0.5953,
+      "step": 405
+    },
+    {
+      "epoch": 4.774193548387097,
+      "grad_norm": 1.4544414281845093,
+      "learning_rate": 2.7118081051523037e-05,
+      "loss": 0.6057,
+      "step": 410
+    },
+    {
+      "epoch": 4.832844574780059,
+      "grad_norm": 1.3960272073745728,
+      "learning_rate": 2.7031525209104695e-05,
+      "loss": 0.5475,
+      "step": 415
+    },
+    {
+      "epoch": 4.891495601173021,
+      "grad_norm": 1.5430188179016113,
+      "learning_rate": 2.694383118403308e-05,
+      "loss": 0.5767,
+      "step": 420
+    },
+    {
+      "epoch": 4.9501466275659824,
+      "grad_norm": 1.4782837629318237,
+      "learning_rate": 2.6855007272165644e-05,
+      "loss": 0.6098,
+      "step": 425
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.5061590671539307,
+      "learning_rate": 2.676506187624718e-05,
+      "loss": 0.5728,
+      "step": 430
+    },
+    {
+      "epoch": 5.058651026392962,
+      "grad_norm": 1.426033854484558,
+      "learning_rate": 2.6674003505114885e-05,
+      "loss": 0.5272,
+      "step": 435
+    },
+    {
+      "epoch": 5.117302052785924,
+      "grad_norm": 1.9145780801773071,
+      "learning_rate": 2.658184077289347e-05,
+      "loss": 0.5207,
+      "step": 440
+    },
+    {
+      "epoch": 5.1759530791788855,
+      "grad_norm": 1.5162384510040283,
+      "learning_rate": 2.6488582398180217e-05,
+      "loss": 0.5466,
+      "step": 445
+    },
+    {
+      "epoch": 5.234604105571847,
+      "grad_norm": 1.5765867233276367,
+      "learning_rate": 2.639423720322023e-05,
+      "loss": 0.532,
+      "step": 450
+    },
+    {
+      "epoch": 5.293255131964809,
+      "grad_norm": 1.6061979532241821,
+      "learning_rate": 2.6298814113071846e-05,
+      "loss": 0.5115,
+      "step": 455
+    },
+    {
+      "epoch": 5.351906158357771,
+      "grad_norm": 1.7579784393310547,
+      "learning_rate": 2.620232215476231e-05,
+      "loss": 0.5534,
+      "step": 460
+    },
+    {
+      "epoch": 5.410557184750733,
+      "grad_norm": 1.5701087713241577,
+      "learning_rate": 2.6104770456433837e-05,
+      "loss": 0.5281,
+      "step": 465
+    },
+    {
+      "epoch": 5.469208211143695,
+      "grad_norm": 1.5090984106063843,
+      "learning_rate": 2.600616824648008e-05,
+      "loss": 0.5121,
+      "step": 470
+    },
+    {
+      "epoch": 5.527859237536656,
+      "grad_norm": 2.6270909309387207,
+      "learning_rate": 2.590652485267311e-05,
+      "loss": 0.5043,
+      "step": 475
+    },
+    {
+      "epoch": 5.586510263929619,
+      "grad_norm": 1.7012410163879395,
+      "learning_rate": 2.5805849701281047e-05,
+      "loss": 0.5113,
+      "step": 480
+    },
+    {
+      "epoch": 5.645161290322581,
+      "grad_norm": 1.852084755897522,
+      "learning_rate": 2.5704152316176287e-05,
+      "loss": 0.476,
+      "step": 485
+    },
+    {
+      "epoch": 5.703812316715543,
+      "grad_norm": 1.3544026613235474,
+      "learning_rate": 2.5601442317934576e-05,
+      "loss": 0.5069,
+      "step": 490
+    },
+    {
+      "epoch": 5.762463343108505,
+      "grad_norm": 1.512239694595337,
+      "learning_rate": 2.5497729422924893e-05,
+      "loss": 0.5143,
+      "step": 495
+    },
+    {
+      "epoch": 5.821114369501466,
+      "grad_norm": 2.261417865753174,
+      "learning_rate": 2.539302344239029e-05,
+      "loss": 0.5075,
+      "step": 500
+    },
+    {
+      "epoch": 5.879765395894428,
+      "grad_norm": 1.6451923847198486,
+      "learning_rate": 2.5287334281519725e-05,
+      "loss": 0.4866,
+      "step": 505
+    },
+    {
+      "epoch": 5.93841642228739,
+      "grad_norm": 1.8043715953826904,
+      "learning_rate": 2.518067193851105e-05,
+      "loss": 0.4805,
+      "step": 510
+    },
+    {
+      "epoch": 5.997067448680352,
+      "grad_norm": 1.4476629495620728,
+      "learning_rate": 2.507304650362519e-05,
+      "loss": 0.4782,
+      "step": 515
+    },
+    {
+      "epoch": 6.0469208211143695,
+      "grad_norm": 2.0781941413879395,
+      "learning_rate": 2.4964468158231576e-05,
+      "loss": 0.4424,
+      "step": 520
+    },
+    {
+      "epoch": 6.105571847507331,
+      "grad_norm": 1.587519884109497,
+      "learning_rate": 2.4854947173845008e-05,
+      "loss": 0.4706,
+      "step": 525
+    },
+    {
+      "epoch": 6.164222873900293,
+      "grad_norm": 1.8226568698883057,
+      "learning_rate": 2.4744493911153962e-05,
+      "loss": 0.4592,
+      "step": 530
+    },
+    {
+      "epoch": 6.222873900293255,
+      "grad_norm": 1.5768177509307861,
+      "learning_rate": 2.463311881904048e-05,
+      "loss": 0.4225,
+      "step": 535
+    },
+    {
+      "epoch": 6.281524926686217,
+      "grad_norm": 1.6065932512283325,
+      "learning_rate": 2.4520832433591675e-05,
+      "loss": 0.4401,
+      "step": 540
+    },
+    {
+      "epoch": 6.340175953079179,
+      "grad_norm": 1.2971386909484863,
+      "learning_rate": 2.4407645377103056e-05,
+      "loss": 0.4538,
+      "step": 545
+    },
+    {
+      "epoch": 6.39882697947214,
+      "grad_norm": 1.838926076889038,
+      "learning_rate": 2.4293568357073634e-05,
+      "loss": 0.4272,
+      "step": 550
+    },
+    {
+      "epoch": 6.457478005865102,
+      "grad_norm": 2.197988986968994,
+      "learning_rate": 2.4178612165192992e-05,
+      "loss": 0.429,
+      "step": 555
+    },
+    {
+      "epoch": 6.516129032258064,
+      "grad_norm": 1.371309757232666,
+      "learning_rate": 2.406278767632041e-05,
+      "loss": 0.3993,
+      "step": 560
+    },
+    {
+      "epoch": 6.574780058651027,
+      "grad_norm": 1.592514157295227,
+      "learning_rate": 2.394610584745608e-05,
+      "loss": 0.3996,
+      "step": 565
+    },
+    {
+      "epoch": 6.633431085043989,
+      "grad_norm": 1.7009004354476929,
+      "learning_rate": 2.3828577716704583e-05,
+      "loss": 0.4013,
+      "step": 570
+    },
+    {
+      "epoch": 6.69208211143695,
+      "grad_norm": 1.5580384731292725,
+      "learning_rate": 2.371021440223069e-05,
+      "loss": 0.425,
+      "step": 575
+    },
+    {
+      "epoch": 6.750733137829912,
+      "grad_norm": 1.570862054824829,
+      "learning_rate": 2.3591027101207578e-05,
+      "loss": 0.4936,
+      "step": 580
+    },
+    {
+      "epoch": 6.809384164222874,
+      "grad_norm": 1.7335824966430664,
+      "learning_rate": 2.347102708875757e-05,
+      "loss": 0.4141,
+      "step": 585
+    },
+    {
+      "epoch": 6.868035190615836,
+      "grad_norm": 1.7174583673477173,
+      "learning_rate": 2.3350225716885522e-05,
+      "loss": 0.406,
+      "step": 590
+    },
+    {
+      "epoch": 6.926686217008798,
+      "grad_norm": 1.6045186519622803,
+      "learning_rate": 2.3228634413404916e-05,
+      "loss": 0.4233,
+      "step": 595
+    },
+    {
+      "epoch": 6.9853372434017595,
+      "grad_norm": 1.520074725151062,
+      "learning_rate": 2.3106264680856776e-05,
+      "loss": 0.4129,
+      "step": 600
+    },
+    {
+      "epoch": 7.035190615835777,
+      "grad_norm": 1.4023849964141846,
+      "learning_rate": 2.298312809542156e-05,
+      "loss": 0.4094,
+      "step": 605
+    },
+    {
+      "epoch": 7.093841642228739,
+      "grad_norm": 1.4728856086730957,
+      "learning_rate": 2.2859236305824e-05,
+      "loss": 0.3425,
+      "step": 610
+    },
+    {
+      "epoch": 7.152492668621701,
+      "grad_norm": 1.5377256870269775,
+      "learning_rate": 2.273460103223122e-05,
+      "loss": 0.3866,
+      "step": 615
+    },
+    {
+      "epoch": 7.211143695014663,
+      "grad_norm": 1.6293245553970337,
+      "learning_rate": 2.260923406514389e-05,
+      "loss": 0.3651,
+      "step": 620
+    },
+    {
+      "epoch": 7.269794721407624,
+      "grad_norm": 1.79743230342865,
+      "learning_rate": 2.248314726428095e-05,
+      "loss": 0.3466,
+      "step": 625
+    },
+    {
+      "epoch": 7.328445747800586,
+      "grad_norm": 1.446027398109436,
+      "learning_rate": 2.2356352557457624e-05,
+      "loss": 0.4,
+      "step": 630
+    },
+    {
+      "epoch": 7.387096774193548,
+      "grad_norm": 1.5968126058578491,
+      "learning_rate": 2.2228861939457056e-05,
+      "loss": 0.3575,
+      "step": 635
+    },
+    {
+      "epoch": 7.44574780058651,
+      "grad_norm": 1.3783931732177734,
+      "learning_rate": 2.210068747089561e-05,
+      "loss": 0.368,
+      "step": 640
+    },
+    {
+      "epoch": 7.504398826979472,
+      "grad_norm": 1.5377360582351685,
+      "learning_rate": 2.1971841277081947e-05,
+      "loss": 0.3604,
+      "step": 645
+    },
+    {
+      "epoch": 7.563049853372434,
+      "grad_norm": 1.6163183450698853,
+      "learning_rate": 2.184233554686994e-05,
+      "loss": 0.3591,
+      "step": 650
+    },
+    {
+      "epoch": 7.621700879765396,
+      "grad_norm": 1.9343562126159668,
+      "learning_rate": 2.1712182531505642e-05,
+      "loss": 0.3543,
+      "step": 655
+    },
+    {
+      "epoch": 7.680351906158358,
+      "grad_norm": 1.860203504562378,
+      "learning_rate": 2.1581394543468286e-05,
+      "loss": 0.362,
+      "step": 660
+    },
+    {
+      "epoch": 7.73900293255132,
+      "grad_norm": 1.7694545984268188,
+      "learning_rate": 2.1449983955305543e-05,
+      "loss": 0.36,
+      "step": 665
+    },
+    {
+      "epoch": 7.797653958944282,
+      "grad_norm": 1.5436360836029053,
+      "learning_rate": 2.131796319846309e-05,
+      "loss": 0.3752,
+      "step": 670
+    },
+    {
+      "epoch": 7.8563049853372435,
+      "grad_norm": 2.079392671585083,
+      "learning_rate": 2.1185344762108556e-05,
+      "loss": 0.3711,
+      "step": 675
+    },
+    {
+      "epoch": 7.914956011730205,
+      "grad_norm": 1.5377277135849,
+      "learning_rate": 2.1052141191950083e-05,
+      "loss": 0.3431,
+      "step": 680
+    },
+    {
+      "epoch": 7.973607038123167,
+      "grad_norm": 1.4733537435531616,
+      "learning_rate": 2.0918365089049492e-05,
+      "loss": 0.3714,
+      "step": 685
+    },
+    {
+      "epoch": 8.023460410557185,
+      "grad_norm": 1.7115830183029175,
+      "learning_rate": 2.078402910863022e-05,
+      "loss": 0.3286,
+      "step": 690
+    },
+    {
+      "epoch": 8.082111436950147,
+      "grad_norm": 1.6873016357421875,
+      "learning_rate": 2.0649145958880112e-05,
+      "loss": 0.3573,
+      "step": 695
+    },
+    {
+      "epoch": 8.140762463343108,
+      "grad_norm": 1.8315602540969849,
+      "learning_rate": 2.0513728399749288e-05,
+      "loss": 0.3325,
+      "step": 700
+    },
+    {
+      "epoch": 8.19941348973607,
+      "grad_norm": 1.827303171157837,
+      "learning_rate": 2.0377789241742973e-05,
+      "loss": 0.3387,
+      "step": 705
+    },
+    {
+      "epoch": 8.258064516129032,
+      "grad_norm": 1.9863218069076538,
+      "learning_rate": 2.0241341344709678e-05,
+      "loss": 0.3124,
+      "step": 710
+    },
+    {
+      "epoch": 8.316715542521994,
+      "grad_norm": 1.8508158922195435,
+      "learning_rate": 2.0104397616624646e-05,
+      "loss": 0.3279,
+      "step": 715
+    },
+    {
+      "epoch": 8.375366568914956,
+      "grad_norm": 1.636530876159668,
+      "learning_rate": 1.996697101236875e-05,
+      "loss": 0.3249,
+      "step": 720
+    },
+    {
+      "epoch": 8.434017595307918,
+      "grad_norm": 1.4390839338302612,
+      "learning_rate": 1.9829074532502958e-05,
+      "loss": 0.3019,
+      "step": 725
+    },
+    {
+      "epoch": 8.49266862170088,
+      "grad_norm": 1.6479607820510864,
+      "learning_rate": 1.9690721222038488e-05,
+      "loss": 0.3259,
+      "step": 730
+    },
+    {
+      "epoch": 8.551319648093841,
+      "grad_norm": 1.9377621412277222,
+      "learning_rate": 1.955192416920275e-05,
+      "loss": 0.3287,
+      "step": 735
+    },
+    {
+      "epoch": 8.609970674486803,
+      "grad_norm": 1.6579439640045166,
+      "learning_rate": 1.9412696504201194e-05,
+      "loss": 0.3323,
+      "step": 740
+    },
+    {
+      "epoch": 8.668621700879765,
+      "grad_norm": 1.8197572231292725,
+      "learning_rate": 1.927305139797519e-05,
+      "loss": 0.2997,
+      "step": 745
+    },
+    {
+      "epoch": 8.727272727272727,
+      "grad_norm": 1.4135760068893433,
+      "learning_rate": 1.913300206095607e-05,
+      "loss": 0.3396,
+      "step": 750
+    },
+    {
+      "epoch": 8.785923753665688,
+      "grad_norm": 1.576826572418213,
+      "learning_rate": 1.8992561741815397e-05,
+      "loss": 0.3044,
+      "step": 755
+    },
+    {
+      "epoch": 8.84457478005865,
+      "grad_norm": 1.696305751800537,
+      "learning_rate": 1.8851743726211665e-05,
+      "loss": 0.3068,
+      "step": 760
+    },
+    {
+      "epoch": 8.903225806451612,
+      "grad_norm": 1.5686278343200684,
+      "learning_rate": 1.8710561335533467e-05,
+      "loss": 0.2817,
+      "step": 765
+    },
+    {
+      "epoch": 8.961876832844574,
+      "grad_norm": 1.822142481803894,
+      "learning_rate": 1.856902792563928e-05,
+      "loss": 0.2894,
+      "step": 770
+    },
+    {
+      "epoch": 9.011730205278592,
+      "grad_norm": 3.2489266395568848,
+      "learning_rate": 1.8427156885594026e-05,
+      "loss": 0.3153,
+      "step": 775
+    },
+    {
+      "epoch": 9.070381231671554,
+      "grad_norm": 1.5879300832748413,
+      "learning_rate": 1.8284961636402418e-05,
+      "loss": 0.2708,
+      "step": 780
+    },
+    {
+      "epoch": 9.129032258064516,
+      "grad_norm": 1.7300035953521729,
+      "learning_rate": 1.8142455629739413e-05,
+      "loss": 0.2691,
+      "step": 785
+    },
+    {
+      "epoch": 9.187683284457478,
+      "grad_norm": 1.6516594886779785,
+      "learning_rate": 1.7999652346677577e-05,
+      "loss": 0.2942,
+      "step": 790
+    },
+    {
+      "epoch": 9.24633431085044,
+      "grad_norm": 1.6192295551300049,
+      "learning_rate": 1.785656529641188e-05,
+      "loss": 0.2963,
+      "step": 795
+    },
+    {
+      "epoch": 9.304985337243401,
+      "grad_norm": 1.7734555006027222,
+      "learning_rate": 1.771320801498165e-05,
+      "loss": 0.2987,
+      "step": 800
+    },
+    {
+      "epoch": 9.363636363636363,
+      "grad_norm": 1.5193028450012207,
+      "learning_rate": 1.7569594063990106e-05,
+      "loss": 0.2901,
+      "step": 805
+    },
+    {
+      "epoch": 9.422287390029325,
+      "grad_norm": 1.9062447547912598,
+      "learning_rate": 1.7425737029321407e-05,
+      "loss": 0.2633,
+      "step": 810
+    },
+    {
+      "epoch": 9.480938416422287,
+      "grad_norm": 1.6332511901855469,
+      "learning_rate": 1.728165051985544e-05,
+      "loss": 0.2982,
+      "step": 815
+    },
+    {
+      "epoch": 9.539589442815249,
+      "grad_norm": 1.7536693811416626,
+      "learning_rate": 1.713734816618042e-05,
+      "loss": 0.2668,
+      "step": 820
+    },
+    {
+      "epoch": 9.59824046920821,
+      "grad_norm": 1.4995721578598022,
+      "learning_rate": 1.6992843619303415e-05,
+      "loss": 0.2774,
+      "step": 825
+    },
+    {
+      "epoch": 9.656891495601172,
+      "grad_norm": 1.9364445209503174,
+      "learning_rate": 1.684815054935899e-05,
+      "loss": 0.3034,
+      "step": 830
+    },
+    {
+      "epoch": 9.715542521994134,
+      "grad_norm": 1.689841866493225,
+      "learning_rate": 1.6703282644315985e-05,
+      "loss": 0.2696,
+      "step": 835
+    },
+    {
+      "epoch": 9.774193548387096,
+      "grad_norm": 2.015406370162964,
+      "learning_rate": 1.6558253608682665e-05,
+      "loss": 0.2836,
+      "step": 840
+    },
+    {
+      "epoch": 9.832844574780058,
+      "grad_norm": 1.4139841794967651,
+      "learning_rate": 1.641307716221024e-05,
+      "loss": 0.2725,
+      "step": 845
+    },
+    {
+      "epoch": 9.89149560117302,
+      "grad_norm": 1.5893827676773071,
+      "learning_rate": 1.626776703859499e-05,
+      "loss": 0.2675,
+      "step": 850
+    },
+    {
+      "epoch": 9.950146627565982,
+      "grad_norm": 1.6394363641738892,
+      "learning_rate": 1.612233698417906e-05,
+      "loss": 0.2775,
+      "step": 855
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.5809170007705688,
+      "learning_rate": 1.5976800756650055e-05,
+      "loss": 0.2525,
+      "step": 860
+    },
+    {
+      "epoch": 10.058651026392962,
+      "grad_norm": 1.722279667854309,
+      "learning_rate": 1.583117212373955e-05,
+      "loss": 0.239,
+      "step": 865
+    },
+    {
+      "epoch": 10.117302052785924,
+      "grad_norm": 1.4771348237991333,
+      "learning_rate": 1.568546486192069e-05,
+      "loss": 0.2719,
+      "step": 870
+    },
+    {
+      "epoch": 10.175953079178885,
+      "grad_norm": 1.8491390943527222,
+      "learning_rate": 1.553969275510489e-05,
+      "loss": 0.2585,
+      "step": 875
+    },
+    {
+      "epoch": 10.234604105571847,
+      "grad_norm": 1.7717721462249756,
+      "learning_rate": 1.539386959333793e-05,
+      "loss": 0.2481,
+      "step": 880
+    },
+    {
+      "epoch": 10.29325513196481,
+      "grad_norm": 1.4404025077819824,
+      "learning_rate": 1.524800917149538e-05,
+      "loss": 0.2441,
+      "step": 885
+    },
+    {
+      "epoch": 10.351906158357771,
+      "grad_norm": 1.5100393295288086,
+      "learning_rate": 1.5102125287977604e-05,
+      "loss": 0.2674,
+      "step": 890
+    },
+    {
+      "epoch": 10.410557184750733,
+      "grad_norm": 1.9897160530090332,
+      "learning_rate": 1.4956231743404466e-05,
+      "loss": 0.2558,
+      "step": 895
+    },
+    {
+      "epoch": 10.469208211143695,
+      "grad_norm": 1.7335450649261475,
+      "learning_rate": 1.4810342339309738e-05,
+      "loss": 0.2472,
+      "step": 900
+    },
+    {
+      "epoch": 10.527859237536656,
+      "grad_norm": 2.008821725845337,
+      "learning_rate": 1.466447087683552e-05,
+      "loss": 0.2403,
+      "step": 905
+    },
+    {
+      "epoch": 10.586510263929618,
+      "grad_norm": 1.489761233329773,
+      "learning_rate": 1.4518631155426629e-05,
+      "loss": 0.235,
+      "step": 910
+    },
+    {
+      "epoch": 10.64516129032258,
+      "grad_norm": 1.5563368797302246,
+      "learning_rate": 1.4372836971525184e-05,
+      "loss": 0.2396,
+      "step": 915
+    },
+    {
+      "epoch": 10.703812316715542,
+      "grad_norm": 1.7141892910003662,
+      "learning_rate": 1.4227102117265432e-05,
+      "loss": 0.2442,
+      "step": 920
+    },
+    {
+      "epoch": 10.762463343108504,
+      "grad_norm": 1.568986415863037,
+      "learning_rate": 1.408144037916906e-05,
+      "loss": 0.2485,
+      "step": 925
+    },
+    {
+      "epoch": 10.821114369501466,
+      "grad_norm": 1.3690587282180786,
+      "learning_rate": 1.393586553684096e-05,
+      "loss": 0.267,
+      "step": 930
+    },
+    {
+      "epoch": 10.879765395894427,
+      "grad_norm": 1.4901823997497559,
+      "learning_rate": 1.3790391361665658e-05,
+      "loss": 0.2479,
+      "step": 935
+    },
+    {
+      "epoch": 10.93841642228739,
+      "grad_norm": 1.538944959640503,
+      "learning_rate": 1.3645031615504593e-05,
+      "loss": 0.2568,
+      "step": 940
+    },
+    {
+      "epoch": 10.997067448680351,
+      "grad_norm": 1.584997296333313,
+      "learning_rate": 1.34998000493942e-05,
+      "loss": 0.2513,
+      "step": 945
+    },
+    {
+      "epoch": 11.04692082111437,
+      "grad_norm": 1.578392744064331,
+      "learning_rate": 1.3354710402245081e-05,
+      "loss": 0.216,
+      "step": 950
+    },
+    {
+      "epoch": 11.105571847507331,
+      "grad_norm": 1.5702141523361206,
+      "learning_rate": 1.3209776399542298e-05,
+      "loss": 0.2341,
+      "step": 955
+    },
+    {
+      "epoch": 11.164222873900293,
+      "grad_norm": 1.2398377656936646,
+      "learning_rate": 1.3065011752046955e-05,
+      "loss": 0.2045,
+      "step": 960
+    },
+    {
+      "epoch": 11.222873900293255,
+      "grad_norm": 1.6778515577316284,
+      "learning_rate": 1.2920430154499123e-05,
+      "loss": 0.2226,
+      "step": 965
+    },
+    {
+      "epoch": 11.281524926686217,
+      "grad_norm": 1.3014507293701172,
+      "learning_rate": 1.277604528432237e-05,
+      "loss": 0.2013,
+      "step": 970
+    },
+    {
+      "epoch": 11.340175953079179,
+      "grad_norm": 1.6591119766235352,
+      "learning_rate": 1.2631870800329839e-05,
+      "loss": 0.2198,
+      "step": 975
+    },
+    {
+      "epoch": 11.39882697947214,
+      "grad_norm": 1.5535308122634888,
+      "learning_rate": 1.248792034143212e-05,
+      "loss": 0.2071,
+      "step": 980
+    },
+    {
+      "epoch": 11.457478005865102,
+      "grad_norm": 1.5089534521102905,
+      "learning_rate": 1.2344207525347039e-05,
+      "loss": 0.2101,
+      "step": 985
+    },
+    {
+      "epoch": 11.516129032258064,
+      "grad_norm": 1.3858919143676758,
+      "learning_rate": 1.2200745947311409e-05,
+      "loss": 0.234,
+      "step": 990
+    },
+    {
+      "epoch": 11.574780058651026,
+      "grad_norm": 1.6462393999099731,
+      "learning_rate": 1.2057549178794888e-05,
+      "loss": 0.2265,
+      "step": 995
+    },
+    {
+      "epoch": 11.633431085043988,
+      "grad_norm": 1.351588249206543,
+      "learning_rate": 1.1914630766216173e-05,
+      "loss": 0.2495,
+      "step": 1000
+    },
+    {
+      "epoch": 11.69208211143695,
+      "grad_norm": 1.450875163078308,
+      "learning_rate": 1.1772004229661474e-05,
+      "loss": 0.2256,
+      "step": 1005
+    },
+    {
+      "epoch": 11.750733137829911,
+      "grad_norm": 1.5337797403335571,
+      "learning_rate": 1.162968306160551e-05,
+      "loss": 0.227,
+      "step": 1010
+    },
+    {
+      "epoch": 11.809384164222873,
+      "grad_norm": 1.6182599067687988,
+      "learning_rate": 1.148768072563514e-05,
+      "loss": 0.2465,
+      "step": 1015
+    },
+    {
+      "epoch": 11.868035190615835,
+      "grad_norm": 1.4571447372436523,
+      "learning_rate": 1.1346010655175707e-05,
+      "loss": 0.2218,
+      "step": 1020
+    },
+    {
+      "epoch": 11.926686217008797,
+      "grad_norm": 1.6681259870529175,
+      "learning_rate": 1.1204686252220202e-05,
+      "loss": 0.2513,
+      "step": 1025
+    },
+    {
+      "epoch": 11.985337243401759,
+      "grad_norm": 1.3346493244171143,
+      "learning_rate": 1.1063720886061473e-05,
+      "loss": 0.2367,
+      "step": 1030
+    },
+    {
+      "epoch": 12.035190615835777,
+      "grad_norm": 1.4893953800201416,
+      "learning_rate": 1.0923127892027488e-05,
+      "loss": 0.2275,
+      "step": 1035
+    },
+    {
+      "epoch": 12.093841642228739,
+      "grad_norm": 1.3146791458129883,
+      "learning_rate": 1.0782920570219772e-05,
+      "loss": 0.227,
+      "step": 1040
+    },
+    {
+      "epoch": 12.1524926686217,
+      "grad_norm": 1.4524919986724854,
+      "learning_rate": 1.0643112184255273e-05,
+      "loss": 0.1991,
+      "step": 1045
+    },
+    {
+      "epoch": 12.211143695014663,
+      "grad_norm": 1.4916414022445679,
+      "learning_rate": 1.0503715960011583e-05,
+      "loss": 0.1957,
+      "step": 1050
+    },
+    {
+      "epoch": 12.269794721407624,
+      "grad_norm": 1.4291622638702393,
+      "learning_rate": 1.036474508437579e-05,
+      "loss": 0.208,
+      "step": 1055
+    },
+    {
+      "epoch": 12.328445747800586,
+      "grad_norm": 1.364890217781067,
+      "learning_rate": 1.0226212703996979e-05,
+      "loss": 0.1996,
+      "step": 1060
+    },
+    {
+      "epoch": 12.387096774193548,
+      "grad_norm": 1.507483959197998,
+      "learning_rate": 1.0088131924042571e-05,
+      "loss": 0.2256,
+      "step": 1065
+    },
+    {
+      "epoch": 12.44574780058651,
+      "grad_norm": 1.5189411640167236,
+      "learning_rate": 9.950515806958595e-06,
+      "loss": 0.2133,
+      "step": 1070
+    },
+    {
+      "epoch": 12.504398826979472,
+      "grad_norm": 1.3920835256576538,
+      "learning_rate": 9.813377371233928e-06,
+      "loss": 0.2137,
+      "step": 1075
+    },
+    {
+      "epoch": 12.563049853372434,
+      "grad_norm": 1.4195996522903442,
+      "learning_rate": 9.676729590168794e-06,
+      "loss": 0.2018,
+      "step": 1080
+    },
+    {
+      "epoch": 12.621700879765395,
+      "grad_norm": 1.4136230945587158,
+      "learning_rate": 9.540585390647472e-06,
+      "loss": 0.2193,
+      "step": 1085
+    },
+    {
+      "epoch": 12.680351906158357,
+      "grad_norm": 1.835013747215271,
+      "learning_rate": 9.404957651915394e-06,
+      "loss": 0.2205,
+      "step": 1090
+    },
+    {
+      "epoch": 12.739002932551319,
+      "grad_norm": 1.5377280712127686,
+      "learning_rate": 9.26985920436081e-06,
+      "loss": 0.1994,
+      "step": 1095
+    },
+    {
+      "epoch": 12.79765395894428,
+      "grad_norm": 1.3562695980072021,
+      "learning_rate": 9.135302828300996e-06,
+      "loss": 0.1906,
+      "step": 1100
+    },
+    {
+      "epoch": 12.856304985337243,
+      "grad_norm": 1.3233888149261475,
+      "learning_rate": 9.001301252773242e-06,
+      "loss": 0.2192,
+      "step": 1105
+    },
+    {
+      "epoch": 12.914956011730204,
+      "grad_norm": 1.3167542219161987,
+      "learning_rate": 8.867867154330694e-06,
+      "loss": 0.217,
+      "step": 1110
+    },
+    {
+      "epoch": 12.973607038123166,
+      "grad_norm": 1.9798552989959717,
+      "learning_rate": 8.735013155843165e-06,
+      "loss": 0.1922,
+      "step": 1115
+    },
+    {
+      "epoch": 13.023460410557185,
+      "grad_norm": 1.271328091621399,
+      "learning_rate": 8.60275182530297e-06,
+      "loss": 0.1681,
+      "step": 1120
+    },
+    {
+      "epoch": 13.082111436950147,
+      "grad_norm": 1.6954541206359863,
+      "learning_rate": 8.471095674636027e-06,
+      "loss": 0.2311,
+      "step": 1125
+    },
+    {
+      "epoch": 13.140762463343108,
+      "grad_norm": 1.3766568899154663,
+      "learning_rate": 8.340057158518236e-06,
+      "loss": 0.1965,
+      "step": 1130
+    },
+    {
+      "epoch": 13.19941348973607,
+      "grad_norm": 1.3400630950927734,
+      "learning_rate": 8.209648673197216e-06,
+      "loss": 0.1942,
+      "step": 1135
+    },
+    {
+      "epoch": 13.258064516129032,
+      "grad_norm": 1.3416330814361572,
+      "learning_rate": 8.079882555319685e-06,
+      "loss": 0.1942,
+      "step": 1140
+    },
+    {
+      "epoch": 13.316715542521994,
+      "grad_norm": 1.3350625038146973,
+      "learning_rate": 7.950771080764365e-06,
+      "loss": 0.19,
+      "step": 1145
+    },
+    {
+      "epoch": 13.375366568914956,
+      "grad_norm": 1.5160963535308838,
+      "learning_rate": 7.822326463480703e-06,
+      "loss": 0.1891,
+      "step": 1150
+    },
+    {
+      "epoch": 13.434017595307918,
+      "grad_norm": 1.380524754524231,
+      "learning_rate": 7.69456085433343e-06,
+      "loss": 0.1888,
+      "step": 1155
+    },
+    {
+      "epoch": 13.49266862170088,
+      "grad_norm": 1.4493212699890137,
+      "learning_rate": 7.567486339953083e-06,
+      "loss": 0.181,
+      "step": 1160
+    },
+    {
+      "epoch": 13.551319648093841,
+      "grad_norm": 1.5188981294631958,
+      "learning_rate": 7.4411149415926136e-06,
+      "loss": 0.192,
+      "step": 1165
+    },
+    {
+      "epoch": 13.609970674486803,
+      "grad_norm": 1.5929157733917236,
+      "learning_rate": 7.315458613990173e-06,
+      "loss": 0.1878,
+      "step": 1170
+    },
+    {
+      "epoch": 13.668621700879765,
+      "grad_norm": 1.3720182180404663,
+      "learning_rate": 7.190529244238215e-06,
+      "loss": 0.2131,
+      "step": 1175
+    },
+    {
+      "epoch": 13.727272727272727,
+      "grad_norm": 1.393882155418396,
+      "learning_rate": 7.066338650658925e-06,
+      "loss": 0.1853,
+      "step": 1180
+    },
+    {
+      "epoch": 13.785923753665688,
+      "grad_norm": 1.3680140972137451,
+      "learning_rate": 6.942898581686276e-06,
+      "loss": 0.1935,
+      "step": 1185
+    },
+    {
+      "epoch": 13.84457478005865,
+      "grad_norm": 1.807997465133667,
+      "learning_rate": 6.820220714754565e-06,
+      "loss": 0.1894,
+      "step": 1190
+    },
+    {
+      "epoch": 13.903225806451612,
+      "grad_norm": 1.4949736595153809,
+      "learning_rate": 6.698316655193763e-06,
+      "loss": 0.2078,
+      "step": 1195
+    },
+    {
+      "epoch": 13.961876832844574,
+      "grad_norm": 1.4242455959320068,
+      "learning_rate": 6.577197935131638e-06,
+      "loss": 0.2063,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1700,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.345376102480609e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1204/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8661d4af4b612fdd59ee0a2ad90ad8380b6dba00c9fff95f2ddecfcdbfc43a38
+size 7608

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1204/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/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, exclude_frozen_parameters):
+    """
+    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,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+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 _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+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() if _has_callable(shape, 'numel') else math.prod(shape)
+            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,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _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,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _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, exclude_frozen_parameters=False):
+    """
+    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``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    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, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    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``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    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("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    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,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1290/README.md

@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.1-8B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1290/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.1-8B",
+  "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": 512,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1290/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a489422d3f1e1beb793ed4415186f5f62dca3b99a876f0ad893cf01e469387
+size 1342239008

group_size_100/layer_full/512/base/1_256_e20_3e-5/checkpoint-1290/latest

@@ -0,0 +1 @@
+global_step1278