Upload folder using huggingface_hub

.gitattributes

@@ -58,3 +58,23 @@ rank_128/group_size_117/layer_full/512/base/0_128_e20_3e-5/checkpoint-792/tokeni
 rank_128/group_size_117/layer_full/512/base/0_128_e20_3e-5/checkpoint-891/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 rank_128/group_size_117/layer_full/512/base/0_128_e20_3e-5/checkpoint-99/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 rank_128/group_size_117/layer_full/512/base/0_128_e20_3e-5/checkpoint-990/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1089/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1188/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1287/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1386/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1485/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1584/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1683/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1782/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1881/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1960/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-198/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-297/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-396/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-495/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-594/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-693/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-792/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-891/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-99/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-990/tokenizer.json filter=lfs diff=lfs merge=lfs -text

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1089/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

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1089/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": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1089/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e4a9c51a82338e5e2173c63a05987f5a555d0cce60832aacea4f52675c83f2c
+size 671150064

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1089/latest

@@ -0,0 +1 @@
+global_step1086

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1089/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0d8f54fbede0cf358858de55932400bbb763665f7990498526f5807fdc85ce9
+size 14960

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1089/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db8fb1d4305ad6b2d4013ee4271ede46990b68e2e2545f0196b1750f446b146a
+size 14960

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1089/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ae222c4d317932c51d56d1236af36ff138cff41d75c6b352ab348942a3a0139
+size 14960

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1089/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d08549c4b8b8d9bbe544befae9053e55ed5952962255d771e8d618a655f731
+size 14960

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1089/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f5732da49b5e59a527db7d939120260906634e2dc802138366591f879aa6be3
+size 1064

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1089/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|>"
+}

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1089/tokenizer.json

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

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1089/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"
+}

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1089/trainer_state.json

@@ -0,0 +1,1553 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.0,
+  "eval_steps": 500,
+  "global_step": 1089,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05063291139240506,
+      "grad_norm": 3.4980525970458984,
+      "learning_rate": 1.2244897959183673e-06,
+      "loss": 1.6467,
+      "step": 5
+    },
+    {
+      "epoch": 0.10126582278481013,
+      "grad_norm": 2.9643654823303223,
+      "learning_rate": 2.7551020408163266e-06,
+      "loss": 1.6536,
+      "step": 10
+    },
+    {
+      "epoch": 0.1518987341772152,
+      "grad_norm": 2.9791953563690186,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 1.666,
+      "step": 15
+    },
+    {
+      "epoch": 0.20253164556962025,
+      "grad_norm": 2.6827096939086914,
+      "learning_rate": 5.816326530612245e-06,
+      "loss": 1.5566,
+      "step": 20
+    },
+    {
+      "epoch": 0.25316455696202533,
+      "grad_norm": 2.3671700954437256,
+      "learning_rate": 7.346938775510204e-06,
+      "loss": 1.5781,
+      "step": 25
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 3.708879232406616,
+      "learning_rate": 8.877551020408163e-06,
+      "loss": 1.5619,
+      "step": 30
+    },
+    {
+      "epoch": 0.35443037974683544,
+      "grad_norm": 2.66953706741333,
+      "learning_rate": 1.0408163265306123e-05,
+      "loss": 1.4739,
+      "step": 35
+    },
+    {
+      "epoch": 0.4050632911392405,
+      "grad_norm": 3.1258773803710938,
+      "learning_rate": 1.1938775510204082e-05,
+      "loss": 1.4944,
+      "step": 40
+    },
+    {
+      "epoch": 0.45569620253164556,
+      "grad_norm": 2.905057907104492,
+      "learning_rate": 1.3469387755102042e-05,
+      "loss": 1.3855,
+      "step": 45
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "grad_norm": 2.4417102336883545,
+      "learning_rate": 1.5e-05,
+      "loss": 1.3961,
+      "step": 50
+    },
+    {
+      "epoch": 0.5569620253164557,
+      "grad_norm": 2.6814239025115967,
+      "learning_rate": 1.6530612244897957e-05,
+      "loss": 1.2905,
+      "step": 55
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 3.3076088428497314,
+      "learning_rate": 1.806122448979592e-05,
+      "loss": 1.2598,
+      "step": 60
+    },
+    {
+      "epoch": 0.6582278481012658,
+      "grad_norm": 2.7890193462371826,
+      "learning_rate": 1.9591836734693877e-05,
+      "loss": 1.2,
+      "step": 65
+    },
+    {
+      "epoch": 0.7088607594936709,
+      "grad_norm": 2.4030416011810303,
+      "learning_rate": 2.1122448979591836e-05,
+      "loss": 1.2148,
+      "step": 70
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 2.4205846786499023,
+      "learning_rate": 2.2653061224489794e-05,
+      "loss": 1.2163,
+      "step": 75
+    },
+    {
+      "epoch": 0.810126582278481,
+      "grad_norm": 2.9943370819091797,
+      "learning_rate": 2.4183673469387756e-05,
+      "loss": 1.1494,
+      "step": 80
+    },
+    {
+      "epoch": 0.8607594936708861,
+      "grad_norm": 2.5231359004974365,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 1.1404,
+      "step": 85
+    },
+    {
+      "epoch": 0.9113924050632911,
+      "grad_norm": 3.446718692779541,
+      "learning_rate": 2.7244897959183673e-05,
+      "loss": 1.0815,
+      "step": 90
+    },
+    {
+      "epoch": 0.9620253164556962,
+      "grad_norm": 3.4152660369873047,
+      "learning_rate": 2.877551020408163e-05,
+      "loss": 1.0733,
+      "step": 95
+    },
+    {
+      "epoch": 1.010126582278481,
+      "grad_norm": 4.289358615875244,
+      "learning_rate": 2.9999978649819432e-05,
+      "loss": 1.0755,
+      "step": 100
+    },
+    {
+      "epoch": 1.0607594936708862,
+      "grad_norm": 3.5033681392669678,
+      "learning_rate": 2.999923139988104e-05,
+      "loss": 1.0308,
+      "step": 105
+    },
+    {
+      "epoch": 1.111392405063291,
+      "grad_norm": 3.502793788909912,
+      "learning_rate": 2.9997416701690675e-05,
+      "loss": 0.9201,
+      "step": 110
+    },
+    {
+      "epoch": 1.1620253164556962,
+      "grad_norm": 2.977989912033081,
+      "learning_rate": 2.999453468439471e-05,
+      "loss": 0.9366,
+      "step": 115
+    },
+    {
+      "epoch": 1.2126582278481013,
+      "grad_norm": 3.385281801223755,
+      "learning_rate": 2.9990585553097278e-05,
+      "loss": 0.873,
+      "step": 120
+    },
+    {
+      "epoch": 1.2632911392405064,
+      "grad_norm": 3.4536044597625732,
+      "learning_rate": 2.9985569588845665e-05,
+      "loss": 0.9513,
+      "step": 125
+    },
+    {
+      "epoch": 1.3139240506329113,
+      "grad_norm": 3.455348253250122,
+      "learning_rate": 2.9979487148610315e-05,
+      "loss": 0.9035,
+      "step": 130
+    },
+    {
+      "epoch": 1.3645569620253164,
+      "grad_norm": 3.171076774597168,
+      "learning_rate": 2.997233866525942e-05,
+      "loss": 0.8489,
+      "step": 135
+    },
+    {
+      "epoch": 1.4151898734177215,
+      "grad_norm": 3.0069353580474854,
+      "learning_rate": 2.996412464752812e-05,
+      "loss": 0.8202,
+      "step": 140
+    },
+    {
+      "epoch": 1.4658227848101266,
+      "grad_norm": 2.801588296890259,
+      "learning_rate": 2.995484567998229e-05,
+      "loss": 0.7959,
+      "step": 145
+    },
+    {
+      "epoch": 1.5164556962025317,
+      "grad_norm": 2.8108527660369873,
+      "learning_rate": 2.994450242297695e-05,
+      "loss": 0.7332,
+      "step": 150
+    },
+    {
+      "epoch": 1.5670886075949366,
+      "grad_norm": 3.3879706859588623,
+      "learning_rate": 2.9933095612609253e-05,
+      "loss": 0.7345,
+      "step": 155
+    },
+    {
+      "epoch": 1.6177215189873417,
+      "grad_norm": 3.4273533821105957,
+      "learning_rate": 2.992062606066612e-05,
+      "loss": 0.7658,
+      "step": 160
+    },
+    {
+      "epoch": 1.6683544303797468,
+      "grad_norm": 4.3649444580078125,
+      "learning_rate": 2.9907094654566445e-05,
+      "loss": 0.7349,
+      "step": 165
+    },
+    {
+      "epoch": 1.7189873417721517,
+      "grad_norm": 3.840703248977661,
+      "learning_rate": 2.989250235729796e-05,
+      "loss": 0.6883,
+      "step": 170
+    },
+    {
+      "epoch": 1.769620253164557,
+      "grad_norm": 3.321861743927002,
+      "learning_rate": 2.987685020734869e-05,
+      "loss": 0.6445,
+      "step": 175
+    },
+    {
+      "epoch": 1.820253164556962,
+      "grad_norm": 4.948067665100098,
+      "learning_rate": 2.986013931863306e-05,
+      "loss": 0.6853,
+      "step": 180
+    },
+    {
+      "epoch": 1.870886075949367,
+      "grad_norm": 3.2912204265594482,
+      "learning_rate": 2.984237088041259e-05,
+      "loss": 0.6809,
+      "step": 185
+    },
+    {
+      "epoch": 1.9215189873417722,
+      "grad_norm": 3.854374647140503,
+      "learning_rate": 2.9823546157211303e-05,
+      "loss": 0.6823,
+      "step": 190
+    },
+    {
+      "epoch": 1.972151898734177,
+      "grad_norm": 3.8937790393829346,
+      "learning_rate": 2.980366648872571e-05,
+      "loss": 0.6421,
+      "step": 195
+    },
+    {
+      "epoch": 2.020253164556962,
+      "grad_norm": 3.1727030277252197,
+      "learning_rate": 2.9782733289729448e-05,
+      "loss": 0.5468,
+      "step": 200
+    },
+    {
+      "epoch": 2.070886075949367,
+      "grad_norm": 3.526210308074951,
+      "learning_rate": 2.9760748049972646e-05,
+      "loss": 0.5887,
+      "step": 205
+    },
+    {
+      "epoch": 2.1215189873417724,
+      "grad_norm": 2.802851915359497,
+      "learning_rate": 2.9737712334075847e-05,
+      "loss": 0.5184,
+      "step": 210
+    },
+    {
+      "epoch": 2.1721518987341772,
+      "grad_norm": 4.610970497131348,
+      "learning_rate": 2.97136277814187e-05,
+      "loss": 0.5158,
+      "step": 215
+    },
+    {
+      "epoch": 2.222784810126582,
+      "grad_norm": 3.258543014526367,
+      "learning_rate": 2.9688496106023274e-05,
+      "loss": 0.5302,
+      "step": 220
+    },
+    {
+      "epoch": 2.2734177215189875,
+      "grad_norm": 3.7272274494171143,
+      "learning_rate": 2.966231909643208e-05,
+      "loss": 0.4942,
+      "step": 225
+    },
+    {
+      "epoch": 2.3240506329113924,
+      "grad_norm": 3.0091631412506104,
+      "learning_rate": 2.9635098615580783e-05,
+      "loss": 0.4892,
+      "step": 230
+    },
+    {
+      "epoch": 2.3746835443037977,
+      "grad_norm": 3.477494716644287,
+      "learning_rate": 2.960683660066562e-05,
+      "loss": 0.4488,
+      "step": 235
+    },
+    {
+      "epoch": 2.4253164556962026,
+      "grad_norm": 2.9678242206573486,
+      "learning_rate": 2.9577535063005555e-05,
+      "loss": 0.439,
+      "step": 240
+    },
+    {
+      "epoch": 2.4759493670886075,
+      "grad_norm": 4.674062728881836,
+      "learning_rate": 2.9547196087899116e-05,
+      "loss": 0.4748,
+      "step": 245
+    },
+    {
+      "epoch": 2.526582278481013,
+      "grad_norm": 3.2280211448669434,
+      "learning_rate": 2.9515821834475986e-05,
+      "loss": 0.4618,
+      "step": 250
+    },
+    {
+      "epoch": 2.5772151898734177,
+      "grad_norm": 4.220160484313965,
+      "learning_rate": 2.9483414535543386e-05,
+      "loss": 0.423,
+      "step": 255
+    },
+    {
+      "epoch": 2.6278481012658226,
+      "grad_norm": 3.365264415740967,
+      "learning_rate": 2.9449976497427127e-05,
+      "loss": 0.3989,
+      "step": 260
+    },
+    {
+      "epoch": 2.678481012658228,
+      "grad_norm": 3.159595251083374,
+      "learning_rate": 2.94155100998075e-05,
+      "loss": 0.4103,
+      "step": 265
+    },
+    {
+      "epoch": 2.729113924050633,
+      "grad_norm": 3.472161293029785,
+      "learning_rate": 2.938001779554991e-05,
+      "loss": 0.4164,
+      "step": 270
+    },
+    {
+      "epoch": 2.779746835443038,
+      "grad_norm": 3.7458016872406006,
+      "learning_rate": 2.9343502110530332e-05,
+      "loss": 0.3774,
+      "step": 275
+    },
+    {
+      "epoch": 2.830379746835443,
+      "grad_norm": 3.9665720462799072,
+      "learning_rate": 2.930596564345554e-05,
+      "loss": 0.3615,
+      "step": 280
+    },
+    {
+      "epoch": 2.8810126582278484,
+      "grad_norm": 3.497344732284546,
+      "learning_rate": 2.9267411065678146e-05,
+      "loss": 0.3737,
+      "step": 285
+    },
+    {
+      "epoch": 2.9316455696202532,
+      "grad_norm": 3.826024293899536,
+      "learning_rate": 2.9227841121006524e-05,
+      "loss": 0.3397,
+      "step": 290
+    },
+    {
+      "epoch": 2.982278481012658,
+      "grad_norm": 3.507917881011963,
+      "learning_rate": 2.9187258625509518e-05,
+      "loss": 0.3496,
+      "step": 295
+    },
+    {
+      "epoch": 3.030379746835443,
+      "grad_norm": 4.524459362030029,
+      "learning_rate": 2.914566646731605e-05,
+      "loss": 0.3471,
+      "step": 300
+    },
+    {
+      "epoch": 3.081012658227848,
+      "grad_norm": 3.779264211654663,
+      "learning_rate": 2.9103067606409555e-05,
+      "loss": 0.3081,
+      "step": 305
+    },
+    {
+      "epoch": 3.131645569620253,
+      "grad_norm": 3.9139416217803955,
+      "learning_rate": 2.9059465074417343e-05,
+      "loss": 0.3065,
+      "step": 310
+    },
+    {
+      "epoch": 3.1822784810126583,
+      "grad_norm": 3.71647310256958,
+      "learning_rate": 2.9014861974394856e-05,
+      "loss": 0.3024,
+      "step": 315
+    },
+    {
+      "epoch": 3.232911392405063,
+      "grad_norm": 3.003744125366211,
+      "learning_rate": 2.896926148060482e-05,
+      "loss": 0.2942,
+      "step": 320
+    },
+    {
+      "epoch": 3.2835443037974685,
+      "grad_norm": 4.5852251052856445,
+      "learning_rate": 2.892266683829135e-05,
+      "loss": 0.2626,
+      "step": 325
+    },
+    {
+      "epoch": 3.3341772151898734,
+      "grad_norm": 3.427046298980713,
+      "learning_rate": 2.887508136344899e-05,
+      "loss": 0.2565,
+      "step": 330
+    },
+    {
+      "epoch": 3.3848101265822783,
+      "grad_norm": 3.712449789047241,
+      "learning_rate": 2.882650844258672e-05,
+      "loss": 0.2455,
+      "step": 335
+    },
+    {
+      "epoch": 3.4354430379746836,
+      "grad_norm": 3.4680449962615967,
+      "learning_rate": 2.877695153248697e-05,
+      "loss": 0.2485,
+      "step": 340
+    },
+    {
+      "epoch": 3.4860759493670885,
+      "grad_norm": 3.1136488914489746,
+      "learning_rate": 2.8726414159959585e-05,
+      "loss": 0.2724,
+      "step": 345
+    },
+    {
+      "epoch": 3.536708860759494,
+      "grad_norm": 3.908705234527588,
+      "learning_rate": 2.867489992159086e-05,
+      "loss": 0.2657,
+      "step": 350
+    },
+    {
+      "epoch": 3.5873417721518988,
+      "grad_norm": 4.278017044067383,
+      "learning_rate": 2.8622412483487553e-05,
+      "loss": 0.2669,
+      "step": 355
+    },
+    {
+      "epoch": 3.6379746835443036,
+      "grad_norm": 3.4697976112365723,
+      "learning_rate": 2.8568955581016003e-05,
+      "loss": 0.2427,
+      "step": 360
+    },
+    {
+      "epoch": 3.688607594936709,
+      "grad_norm": 3.08229398727417,
+      "learning_rate": 2.8514533018536286e-05,
+      "loss": 0.2494,
+      "step": 365
+    },
+    {
+      "epoch": 3.739240506329114,
+      "grad_norm": 3.35378098487854,
+      "learning_rate": 2.8459148669131476e-05,
+      "loss": 0.2383,
+      "step": 370
+    },
+    {
+      "epoch": 3.7898734177215188,
+      "grad_norm": 3.133762836456299,
+      "learning_rate": 2.8402806474331994e-05,
+      "loss": 0.2387,
+      "step": 375
+    },
+    {
+      "epoch": 3.840506329113924,
+      "grad_norm": 3.7151851654052734,
+      "learning_rate": 2.8345510443835116e-05,
+      "loss": 0.2373,
+      "step": 380
+    },
+    {
+      "epoch": 3.891139240506329,
+      "grad_norm": 3.03208327293396,
+      "learning_rate": 2.828726465521963e-05,
+      "loss": 0.2159,
+      "step": 385
+    },
+    {
+      "epoch": 3.9417721518987343,
+      "grad_norm": 3.15083646774292,
+      "learning_rate": 2.8228073253655608e-05,
+      "loss": 0.2152,
+      "step": 390
+    },
+    {
+      "epoch": 3.992405063291139,
+      "grad_norm": 3.210649013519287,
+      "learning_rate": 2.8167940451609444e-05,
+      "loss": 0.2213,
+      "step": 395
+    },
+    {
+      "epoch": 4.040506329113924,
+      "grad_norm": 3.083118200302124,
+      "learning_rate": 2.8106870528544044e-05,
+      "loss": 0.1842,
+      "step": 400
+    },
+    {
+      "epoch": 4.091139240506329,
+      "grad_norm": 3.1503756046295166,
+      "learning_rate": 2.804486783061428e-05,
+      "loss": 0.1861,
+      "step": 405
+    },
+    {
+      "epoch": 4.141772151898734,
+      "grad_norm": 2.813202381134033,
+      "learning_rate": 2.798193677035768e-05,
+      "loss": 0.1755,
+      "step": 410
+    },
+    {
+      "epoch": 4.192405063291139,
+      "grad_norm": 3.875789165496826,
+      "learning_rate": 2.7918081826380428e-05,
+      "loss": 0.1762,
+      "step": 415
+    },
+    {
+      "epoch": 4.243037974683545,
+      "grad_norm": 3.8627779483795166,
+      "learning_rate": 2.785330754303858e-05,
+      "loss": 0.1723,
+      "step": 420
+    },
+    {
+      "epoch": 4.293670886075949,
+      "grad_norm": 2.6941754817962646,
+      "learning_rate": 2.7787618530114724e-05,
+      "loss": 0.1606,
+      "step": 425
+    },
+    {
+      "epoch": 4.3443037974683545,
+      "grad_norm": 3.605570077896118,
+      "learning_rate": 2.7721019462489862e-05,
+      "loss": 0.17,
+      "step": 430
+    },
+    {
+      "epoch": 4.39493670886076,
+      "grad_norm": 2.771569013595581,
+      "learning_rate": 2.7653515079810744e-05,
+      "loss": 0.1738,
+      "step": 435
+    },
+    {
+      "epoch": 4.445569620253164,
+      "grad_norm": 3.381185531616211,
+      "learning_rate": 2.758511018615254e-05,
+      "loss": 0.1645,
+      "step": 440
+    },
+    {
+      "epoch": 4.49620253164557,
+      "grad_norm": 2.929736375808716,
+      "learning_rate": 2.751580964967699e-05,
+      "loss": 0.1758,
+      "step": 445
+    },
+    {
+      "epoch": 4.546835443037975,
+      "grad_norm": 4.251176357269287,
+      "learning_rate": 2.7445618402285894e-05,
+      "loss": 0.1675,
+      "step": 450
+    },
+    {
+      "epoch": 4.597468354430379,
+      "grad_norm": 3.2119245529174805,
+      "learning_rate": 2.7374541439270174e-05,
+      "loss": 0.1662,
+      "step": 455
+    },
+    {
+      "epoch": 4.648101265822785,
+      "grad_norm": 3.273690700531006,
+      "learning_rate": 2.730258381895434e-05,
+      "loss": 0.1649,
+      "step": 460
+    },
+    {
+      "epoch": 4.69873417721519,
+      "grad_norm": 2.8210129737854004,
+      "learning_rate": 2.722975066233653e-05,
+      "loss": 0.1471,
+      "step": 465
+    },
+    {
+      "epoch": 4.749367088607595,
+      "grad_norm": 3.1151881217956543,
+      "learning_rate": 2.7156047152724046e-05,
+      "loss": 0.1519,
+      "step": 470
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 3.13199782371521,
+      "learning_rate": 2.7081478535364496e-05,
+      "loss": 0.1537,
+      "step": 475
+    },
+    {
+      "epoch": 4.850632911392405,
+      "grad_norm": 2.7968389987945557,
+      "learning_rate": 2.700605011707248e-05,
+      "loss": 0.1447,
+      "step": 480
+    },
+    {
+      "epoch": 4.9012658227848105,
+      "grad_norm": 3.166747570037842,
+      "learning_rate": 2.692976726585194e-05,
+      "loss": 0.1426,
+      "step": 485
+    },
+    {
+      "epoch": 4.951898734177215,
+      "grad_norm": 3.1832809448242188,
+      "learning_rate": 2.6852635410514125e-05,
+      "loss": 0.1386,
+      "step": 490
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.532459735870361,
+      "learning_rate": 2.6774660040291257e-05,
+      "loss": 0.1481,
+      "step": 495
+    },
+    {
+      "epoch": 5.050632911392405,
+      "grad_norm": 2.8513097763061523,
+      "learning_rate": 2.6695846704445842e-05,
+      "loss": 0.1118,
+      "step": 500
+    },
+    {
+      "epoch": 5.10126582278481,
+      "grad_norm": 2.8358778953552246,
+      "learning_rate": 2.6616201011875792e-05,
+      "loss": 0.1259,
+      "step": 505
+    },
+    {
+      "epoch": 5.151898734177215,
+      "grad_norm": 2.5484566688537598,
+      "learning_rate": 2.6535728630715228e-05,
+      "loss": 0.1108,
+      "step": 510
+    },
+    {
+      "epoch": 5.2025316455696204,
+      "grad_norm": 2.7051589488983154,
+      "learning_rate": 2.645443528793111e-05,
+      "loss": 0.1196,
+      "step": 515
+    },
+    {
+      "epoch": 5.253164556962025,
+      "grad_norm": 2.469198226928711,
+      "learning_rate": 2.6372326768915658e-05,
+      "loss": 0.1255,
+      "step": 520
+    },
+    {
+      "epoch": 5.30379746835443,
+      "grad_norm": 2.5851681232452393,
+      "learning_rate": 2.628940891707462e-05,
+      "loss": 0.1204,
+      "step": 525
+    },
+    {
+      "epoch": 5.3544303797468356,
+      "grad_norm": 2.605705499649048,
+      "learning_rate": 2.6205687633411445e-05,
+      "loss": 0.1127,
+      "step": 530
+    },
+    {
+      "epoch": 5.405063291139241,
+      "grad_norm": 2.959566593170166,
+      "learning_rate": 2.6121168876107274e-05,
+      "loss": 0.1158,
+      "step": 535
+    },
+    {
+      "epoch": 5.455696202531645,
+      "grad_norm": 2.3968331813812256,
+      "learning_rate": 2.6035858660096975e-05,
+      "loss": 0.1249,
+      "step": 540
+    },
+    {
+      "epoch": 5.506329113924051,
+      "grad_norm": 4.327753067016602,
+      "learning_rate": 2.594976305664103e-05,
+      "loss": 0.1169,
+      "step": 545
+    },
+    {
+      "epoch": 5.556962025316456,
+      "grad_norm": 2.5143179893493652,
+      "learning_rate": 2.586288819289349e-05,
+      "loss": 0.1149,
+      "step": 550
+    },
+    {
+      "epoch": 5.6075949367088604,
+      "grad_norm": 2.9387834072113037,
+      "learning_rate": 2.5775240251465914e-05,
+      "loss": 0.1173,
+      "step": 555
+    },
+    {
+      "epoch": 5.658227848101266,
+      "grad_norm": 2.727640390396118,
+      "learning_rate": 2.568682546998738e-05,
+      "loss": 0.1069,
+      "step": 560
+    },
+    {
+      "epoch": 5.708860759493671,
+      "grad_norm": 2.930460214614868,
+      "learning_rate": 2.5597650140660555e-05,
+      "loss": 0.1096,
+      "step": 565
+    },
+    {
+      "epoch": 5.759493670886076,
+      "grad_norm": 2.747501850128174,
+      "learning_rate": 2.5507720609813928e-05,
+      "loss": 0.105,
+      "step": 570
+    },
+    {
+      "epoch": 5.810126582278481,
+      "grad_norm": 2.5990662574768066,
+      "learning_rate": 2.541704327745013e-05,
+      "loss": 0.1147,
+      "step": 575
+    },
+    {
+      "epoch": 5.860759493670886,
+      "grad_norm": 2.7866060733795166,
+      "learning_rate": 2.5325624596790486e-05,
+      "loss": 0.1134,
+      "step": 580
+    },
+    {
+      "epoch": 5.911392405063291,
+      "grad_norm": 2.9491360187530518,
+      "learning_rate": 2.523347107381576e-05,
+      "loss": 0.1039,
+      "step": 585
+    },
+    {
+      "epoch": 5.962025316455696,
+      "grad_norm": 2.775834321975708,
+      "learning_rate": 2.514058926680312e-05,
+      "loss": 0.109,
+      "step": 590
+    },
+    {
+      "epoch": 6.010126582278481,
+      "grad_norm": 3.1889455318450928,
+      "learning_rate": 2.5046985785859453e-05,
+      "loss": 0.1048,
+      "step": 595
+    },
+    {
+      "epoch": 6.060759493670886,
+      "grad_norm": 2.762517213821411,
+      "learning_rate": 2.4952667292450887e-05,
+      "loss": 0.0884,
+      "step": 600
+    },
+    {
+      "epoch": 6.111392405063291,
+      "grad_norm": 1.801896095275879,
+      "learning_rate": 2.4857640498928756e-05,
+      "loss": 0.0907,
+      "step": 605
+    },
+    {
+      "epoch": 6.162025316455696,
+      "grad_norm": 2.1080682277679443,
+      "learning_rate": 2.4761912168051903e-05,
+      "loss": 0.0892,
+      "step": 610
+    },
+    {
+      "epoch": 6.2126582278481015,
+      "grad_norm": 2.79091215133667,
+      "learning_rate": 2.4665489112505372e-05,
+      "loss": 0.0936,
+      "step": 615
+    },
+    {
+      "epoch": 6.263291139240506,
+      "grad_norm": 2.5198278427124023,
+      "learning_rate": 2.4568378194415583e-05,
+      "loss": 0.0973,
+      "step": 620
+    },
+    {
+      "epoch": 6.313924050632911,
+      "grad_norm": 2.038583278656006,
+      "learning_rate": 2.447058632486197e-05,
+      "loss": 0.0915,
+      "step": 625
+    },
+    {
+      "epoch": 6.364556962025317,
+      "grad_norm": 3.310605049133301,
+      "learning_rate": 2.4372120463385167e-05,
+      "loss": 0.0936,
+      "step": 630
+    },
+    {
+      "epoch": 6.415189873417722,
+      "grad_norm": 2.2550792694091797,
+      "learning_rate": 2.427298761749168e-05,
+      "loss": 0.1016,
+      "step": 635
+    },
+    {
+      "epoch": 6.465822784810126,
+      "grad_norm": 2.7243216037750244,
+      "learning_rate": 2.4173194842155208e-05,
+      "loss": 0.0888,
+      "step": 640
+    },
+    {
+      "epoch": 6.516455696202532,
+      "grad_norm": 2.442253351211548,
+      "learning_rate": 2.4072749239314565e-05,
+      "loss": 0.0901,
+      "step": 645
+    },
+    {
+      "epoch": 6.567088607594937,
+      "grad_norm": 2.2244441509246826,
+      "learning_rate": 2.397165795736824e-05,
+      "loss": 0.0919,
+      "step": 650
+    },
+    {
+      "epoch": 6.6177215189873415,
+      "grad_norm": 2.14775013923645,
+      "learning_rate": 2.386992819066569e-05,
+      "loss": 0.0903,
+      "step": 655
+    },
+    {
+      "epoch": 6.668354430379747,
+      "grad_norm": 2.5285158157348633,
+      "learning_rate": 2.3767567178995323e-05,
+      "loss": 0.0899,
+      "step": 660
+    },
+    {
+      "epoch": 6.718987341772152,
+      "grad_norm": 2.9994752407073975,
+      "learning_rate": 2.366458220706928e-05,
+      "loss": 0.095,
+      "step": 665
+    },
+    {
+      "epoch": 6.769620253164557,
+      "grad_norm": 2.355753183364868,
+      "learning_rate": 2.3560980604004977e-05,
+      "loss": 0.0866,
+      "step": 670
+    },
+    {
+      "epoch": 6.820253164556962,
+      "grad_norm": 2.467966318130493,
+      "learning_rate": 2.345676974280355e-05,
+      "loss": 0.0841,
+      "step": 675
+    },
+    {
+      "epoch": 6.870886075949367,
+      "grad_norm": 2.32102632522583,
+      "learning_rate": 2.335195703982513e-05,
+      "loss": 0.0879,
+      "step": 680
+    },
+    {
+      "epoch": 6.921518987341772,
+      "grad_norm": 2.34090518951416,
+      "learning_rate": 2.324654995426102e-05,
+      "loss": 0.0892,
+      "step": 685
+    },
+    {
+      "epoch": 6.972151898734177,
+      "grad_norm": 2.4923956394195557,
+      "learning_rate": 2.3140555987602886e-05,
+      "loss": 0.0861,
+      "step": 690
+    },
+    {
+      "epoch": 7.020253164556962,
+      "grad_norm": 2.2103333473205566,
+      "learning_rate": 2.3033982683108867e-05,
+      "loss": 0.0792,
+      "step": 695
+    },
+    {
+      "epoch": 7.0708860759493675,
+      "grad_norm": 2.5478057861328125,
+      "learning_rate": 2.2926837625266776e-05,
+      "loss": 0.074,
+      "step": 700
+    },
+    {
+      "epoch": 7.121518987341772,
+      "grad_norm": 2.4020633697509766,
+      "learning_rate": 2.281912843925429e-05,
+      "loss": 0.0729,
+      "step": 705
+    },
+    {
+      "epoch": 7.172151898734177,
+      "grad_norm": 1.8848402500152588,
+      "learning_rate": 2.2710862790396353e-05,
+      "loss": 0.0707,
+      "step": 710
+    },
+    {
+      "epoch": 7.222784810126583,
+      "grad_norm": 2.636121988296509,
+      "learning_rate": 2.26020483836196e-05,
+      "loss": 0.0847,
+      "step": 715
+    },
+    {
+      "epoch": 7.273417721518987,
+      "grad_norm": 2.489856719970703,
+      "learning_rate": 2.249269296290405e-05,
+      "loss": 0.0789,
+      "step": 720
+    },
+    {
+      "epoch": 7.324050632911392,
+      "grad_norm": 2.441281795501709,
+      "learning_rate": 2.238280431073199e-05,
+      "loss": 0.0815,
+      "step": 725
+    },
+    {
+      "epoch": 7.374683544303798,
+      "grad_norm": 2.4158310890197754,
+      "learning_rate": 2.2272390247534127e-05,
+      "loss": 0.0767,
+      "step": 730
+    },
+    {
+      "epoch": 7.425316455696202,
+      "grad_norm": 1.5769174098968506,
+      "learning_rate": 2.2161458631133e-05,
+      "loss": 0.0758,
+      "step": 735
+    },
+    {
+      "epoch": 7.4759493670886075,
+      "grad_norm": 2.136112928390503,
+      "learning_rate": 2.2050017356183806e-05,
+      "loss": 0.0805,
+      "step": 740
+    },
+    {
+      "epoch": 7.526582278481013,
+      "grad_norm": 2.3461337089538574,
+      "learning_rate": 2.1938074353612533e-05,
+      "loss": 0.0831,
+      "step": 745
+    },
+    {
+      "epoch": 7.577215189873417,
+      "grad_norm": 2.017784833908081,
+      "learning_rate": 2.182563759005155e-05,
+      "loss": 0.0769,
+      "step": 750
+    },
+    {
+      "epoch": 7.627848101265823,
+      "grad_norm": 1.7009460926055908,
+      "learning_rate": 2.1712715067272655e-05,
+      "loss": 0.0743,
+      "step": 755
+    },
+    {
+      "epoch": 7.678481012658228,
+      "grad_norm": 1.948912262916565,
+      "learning_rate": 2.1599314821617598e-05,
+      "loss": 0.0769,
+      "step": 760
+    },
+    {
+      "epoch": 7.729113924050633,
+      "grad_norm": 1.9673391580581665,
+      "learning_rate": 2.1485444923426167e-05,
+      "loss": 0.081,
+      "step": 765
+    },
+    {
+      "epoch": 7.779746835443038,
+      "grad_norm": 2.3732705116271973,
+      "learning_rate": 2.1371113476461855e-05,
+      "loss": 0.0773,
+      "step": 770
+    },
+    {
+      "epoch": 7.830379746835443,
+      "grad_norm": 1.866337776184082,
+      "learning_rate": 2.1256328617335124e-05,
+      "loss": 0.0759,
+      "step": 775
+    },
+    {
+      "epoch": 7.881012658227848,
+      "grad_norm": 2.141129970550537,
+      "learning_rate": 2.1141098514924367e-05,
+      "loss": 0.0733,
+      "step": 780
+    },
+    {
+      "epoch": 7.931645569620253,
+      "grad_norm": 2.2540833950042725,
+      "learning_rate": 2.1025431369794546e-05,
+      "loss": 0.0749,
+      "step": 785
+    },
+    {
+      "epoch": 7.982278481012658,
+      "grad_norm": 1.980592966079712,
+      "learning_rate": 2.0909335413613563e-05,
+      "loss": 0.0717,
+      "step": 790
+    },
+    {
+      "epoch": 8.030379746835443,
+      "grad_norm": 2.3790063858032227,
+      "learning_rate": 2.079281890856648e-05,
+      "loss": 0.071,
+      "step": 795
+    },
+    {
+      "epoch": 8.081012658227849,
+      "grad_norm": 1.9786341190338135,
+      "learning_rate": 2.067589014676749e-05,
+      "loss": 0.0671,
+      "step": 800
+    },
+    {
+      "epoch": 8.131645569620254,
+      "grad_norm": 1.850415825843811,
+      "learning_rate": 2.0558557449669818e-05,
+      "loss": 0.0706,
+      "step": 805
+    },
+    {
+      "epoch": 8.182278481012657,
+      "grad_norm": 1.740311622619629,
+      "learning_rate": 2.0440829167473486e-05,
+      "loss": 0.0696,
+      "step": 810
+    },
+    {
+      "epoch": 8.232911392405063,
+      "grad_norm": 1.6912726163864136,
+      "learning_rate": 2.0322713678531067e-05,
+      "loss": 0.0737,
+      "step": 815
+    },
+    {
+      "epoch": 8.283544303797468,
+      "grad_norm": 1.9001421928405762,
+      "learning_rate": 2.020421938875143e-05,
+      "loss": 0.0662,
+      "step": 820
+    },
+    {
+      "epoch": 8.334177215189873,
+      "grad_norm": 1.8828890323638916,
+      "learning_rate": 2.0085354731001502e-05,
+      "loss": 0.0703,
+      "step": 825
+    },
+    {
+      "epoch": 8.384810126582279,
+      "grad_norm": 1.4946229457855225,
+      "learning_rate": 1.9966128164506153e-05,
+      "loss": 0.0691,
+      "step": 830
+    },
+    {
+      "epoch": 8.435443037974684,
+      "grad_norm": 2.7881011962890625,
+      "learning_rate": 1.9846548174246144e-05,
+      "loss": 0.0727,
+      "step": 835
+    },
+    {
+      "epoch": 8.48607594936709,
+      "grad_norm": 1.8071367740631104,
+      "learning_rate": 1.9726623270354314e-05,
+      "loss": 0.0657,
+      "step": 840
+    },
+    {
+      "epoch": 8.536708860759493,
+      "grad_norm": 1.4970042705535889,
+      "learning_rate": 1.9606361987509905e-05,
+      "loss": 0.0698,
+      "step": 845
+    },
+    {
+      "epoch": 8.587341772151898,
+      "grad_norm": 1.7957663536071777,
+      "learning_rate": 1.9485772884331215e-05,
+      "loss": 0.0698,
+      "step": 850
+    },
+    {
+      "epoch": 8.637974683544304,
+      "grad_norm": 1.6136796474456787,
+      "learning_rate": 1.936486454276647e-05,
+      "loss": 0.0716,
+      "step": 855
+    },
+    {
+      "epoch": 8.688607594936709,
+      "grad_norm": 1.5621618032455444,
+      "learning_rate": 1.9243645567483096e-05,
+      "loss": 0.0675,
+      "step": 860
+    },
+    {
+      "epoch": 8.739240506329114,
+      "grad_norm": 1.7963391542434692,
+      "learning_rate": 1.9122124585255348e-05,
+      "loss": 0.0681,
+      "step": 865
+    },
+    {
+      "epoch": 8.78987341772152,
+      "grad_norm": 2.201146364212036,
+      "learning_rate": 1.900031024435037e-05,
+      "loss": 0.0717,
+      "step": 870
+    },
+    {
+      "epoch": 8.840506329113925,
+      "grad_norm": 1.4939143657684326,
+      "learning_rate": 1.887821121391272e-05,
+      "loss": 0.0713,
+      "step": 875
+    },
+    {
+      "epoch": 8.891139240506329,
+      "grad_norm": 1.4898556470870972,
+      "learning_rate": 1.8755836183347416e-05,
+      "loss": 0.0646,
+      "step": 880
+    },
+    {
+      "epoch": 8.941772151898734,
+      "grad_norm": 1.6174167394638062,
+      "learning_rate": 1.863319386170154e-05,
+      "loss": 0.0645,
+      "step": 885
+    },
+    {
+      "epoch": 8.99240506329114,
+      "grad_norm": 1.5976531505584717,
+      "learning_rate": 1.8510292977044434e-05,
+      "loss": 0.0688,
+      "step": 890
+    },
+    {
+      "epoch": 9.040506329113924,
+      "grad_norm": 1.7708168029785156,
+      "learning_rate": 1.838714227584658e-05,
+      "loss": 0.0621,
+      "step": 895
+    },
+    {
+      "epoch": 9.09113924050633,
+      "grad_norm": 1.2461936473846436,
+      "learning_rate": 1.8263750522357107e-05,
+      "loss": 0.0583,
+      "step": 900
+    },
+    {
+      "epoch": 9.141772151898735,
+      "grad_norm": 1.1864615678787231,
+      "learning_rate": 1.814012649798007e-05,
+      "loss": 0.0614,
+      "step": 905
+    },
+    {
+      "epoch": 9.192405063291138,
+      "grad_norm": 1.408365249633789,
+      "learning_rate": 1.8016279000649523e-05,
+      "loss": 0.0661,
+      "step": 910
+    },
+    {
+      "epoch": 9.243037974683544,
+      "grad_norm": 1.521738886833191,
+      "learning_rate": 1.7892216844203395e-05,
+      "loss": 0.0643,
+      "step": 915
+    },
+    {
+      "epoch": 9.29367088607595,
+      "grad_norm": 1.6638453006744385,
+      "learning_rate": 1.7767948857756226e-05,
+      "loss": 0.0653,
+      "step": 920
+    },
+    {
+      "epoch": 9.344303797468354,
+      "grad_norm": 1.9698224067687988,
+      "learning_rate": 1.7643483885070827e-05,
+      "loss": 0.0656,
+      "step": 925
+    },
+    {
+      "epoch": 9.39493670886076,
+      "grad_norm": 1.5151782035827637,
+      "learning_rate": 1.751883078392891e-05,
+      "loss": 0.0638,
+      "step": 930
+    },
+    {
+      "epoch": 9.445569620253165,
+      "grad_norm": 1.6791659593582153,
+      "learning_rate": 1.739399842550069e-05,
+      "loss": 0.0642,
+      "step": 935
+    },
+    {
+      "epoch": 9.496202531645569,
+      "grad_norm": 1.4712715148925781,
+      "learning_rate": 1.726899569371357e-05,
+      "loss": 0.0651,
+      "step": 940
+    },
+    {
+      "epoch": 9.546835443037974,
+      "grad_norm": 1.313909888267517,
+      "learning_rate": 1.7143831484619884e-05,
+      "loss": 0.0579,
+      "step": 945
+    },
+    {
+      "epoch": 9.59746835443038,
+      "grad_norm": 1.5802178382873535,
+      "learning_rate": 1.7018514705763804e-05,
+      "loss": 0.0655,
+      "step": 950
+    },
+    {
+      "epoch": 9.648101265822785,
+      "grad_norm": 1.674559473991394,
+      "learning_rate": 1.6893054275547407e-05,
+      "loss": 0.0633,
+      "step": 955
+    },
+    {
+      "epoch": 9.69873417721519,
+      "grad_norm": 2.3455135822296143,
+      "learning_rate": 1.6767459122595998e-05,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 9.749367088607595,
+      "grad_norm": 1.1516377925872803,
+      "learning_rate": 1.6641738185122663e-05,
+      "loss": 0.0585,
+      "step": 965
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": 1.211869478225708,
+      "learning_rate": 1.6515900410292188e-05,
+      "loss": 0.0684,
+      "step": 970
+    },
+    {
+      "epoch": 9.850632911392404,
+      "grad_norm": 1.3427664041519165,
+      "learning_rate": 1.6389954753584303e-05,
+      "loss": 0.0613,
+      "step": 975
+    },
+    {
+      "epoch": 9.90126582278481,
+      "grad_norm": 0.9951387643814087,
+      "learning_rate": 1.626391017815635e-05,
+      "loss": 0.071,
+      "step": 980
+    },
+    {
+      "epoch": 9.951898734177215,
+      "grad_norm": 2.0930867195129395,
+      "learning_rate": 1.6137775654205414e-05,
+      "loss": 0.0655,
+      "step": 985
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.7130424976348877,
+      "learning_rate": 1.601156015832993e-05,
+      "loss": 0.0622,
+      "step": 990
+    },
+    {
+      "epoch": 10.050632911392405,
+      "grad_norm": 1.5401997566223145,
+      "learning_rate": 1.5885272672890842e-05,
+      "loss": 0.0621,
+      "step": 995
+    },
+    {
+      "epoch": 10.10126582278481,
+      "grad_norm": 1.5477750301361084,
+      "learning_rate": 1.5758922185372387e-05,
+      "loss": 0.0574,
+      "step": 1000
+    },
+    {
+      "epoch": 10.151898734177216,
+      "grad_norm": 1.1239627599716187,
+      "learning_rate": 1.5632517687742438e-05,
+      "loss": 0.0599,
+      "step": 1005
+    },
+    {
+      "epoch": 10.20253164556962,
+      "grad_norm": 1.1288483142852783,
+      "learning_rate": 1.5506068175812618e-05,
+      "loss": 0.059,
+      "step": 1010
+    },
+    {
+      "epoch": 10.253164556962025,
+      "grad_norm": 1.120748519897461,
+      "learning_rate": 1.5379582648598056e-05,
+      "loss": 0.0602,
+      "step": 1015
+    },
+    {
+      "epoch": 10.30379746835443,
+      "grad_norm": 1.4478673934936523,
+      "learning_rate": 1.5253070107677006e-05,
+      "loss": 0.0609,
+      "step": 1020
+    },
+    {
+      "epoch": 10.354430379746836,
+      "grad_norm": 1.0375020503997803,
+      "learning_rate": 1.5126539556550172e-05,
+      "loss": 0.0593,
+      "step": 1025
+    },
+    {
+      "epoch": 10.405063291139241,
+      "grad_norm": 1.6543164253234863,
+      "learning_rate": 1.5e-05,
+      "loss": 0.0598,
+      "step": 1030
+    },
+    {
+      "epoch": 10.455696202531646,
+      "grad_norm": 1.5519331693649292,
+      "learning_rate": 1.4873460443449834e-05,
+      "loss": 0.0614,
+      "step": 1035
+    },
+    {
+      "epoch": 10.50632911392405,
+      "grad_norm": 1.8383262157440186,
+      "learning_rate": 1.4746929892322996e-05,
+      "loss": 0.0582,
+      "step": 1040
+    },
+    {
+      "epoch": 10.556962025316455,
+      "grad_norm": 1.509050726890564,
+      "learning_rate": 1.4620417351401945e-05,
+      "loss": 0.0646,
+      "step": 1045
+    },
+    {
+      "epoch": 10.60759493670886,
+      "grad_norm": 1.1060560941696167,
+      "learning_rate": 1.4493931824187385e-05,
+      "loss": 0.0577,
+      "step": 1050
+    },
+    {
+      "epoch": 10.658227848101266,
+      "grad_norm": 1.5542149543762207,
+      "learning_rate": 1.4367482312257564e-05,
+      "loss": 0.06,
+      "step": 1055
+    },
+    {
+      "epoch": 10.708860759493671,
+      "grad_norm": 0.8741584420204163,
+      "learning_rate": 1.4241077814627618e-05,
+      "loss": 0.0591,
+      "step": 1060
+    },
+    {
+      "epoch": 10.759493670886076,
+      "grad_norm": 1.3523668050765991,
+      "learning_rate": 1.411472732710916e-05,
+      "loss": 0.0582,
+      "step": 1065
+    },
+    {
+      "epoch": 10.810126582278482,
+      "grad_norm": 0.9250157475471497,
+      "learning_rate": 1.3988439841670075e-05,
+      "loss": 0.055,
+      "step": 1070
+    },
+    {
+      "epoch": 10.860759493670885,
+      "grad_norm": 1.4959791898727417,
+      "learning_rate": 1.3862224345794585e-05,
+      "loss": 0.0572,
+      "step": 1075
+    },
+    {
+      "epoch": 10.91139240506329,
+      "grad_norm": 1.737217664718628,
+      "learning_rate": 1.3736089821843653e-05,
+      "loss": 0.057,
+      "step": 1080
+    },
+    {
+      "epoch": 10.962025316455696,
+      "grad_norm": 1.0605052709579468,
+      "learning_rate": 1.3610045246415703e-05,
+      "loss": 0.0534,
+      "step": 1085
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1960,
+  "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": 3.7377709163361075e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1089/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a436d9e507a65e167f35408ec1bb674e772877bdfffc477144f5ecc24f0321
+size 7608

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1089/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)

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1188/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

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1188/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": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1188/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4204375b6a5fc6e9604274f9db1581da4c23b504dcd961fa5d20594e44bf490
+size 671150064

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1188/latest

@@ -0,0 +1 @@
+global_step1185

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1188/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:390a28503dd3fd721de9663e77b0951a91b18e5b92c3f2e50f3fccfb22310e21
+size 14960

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1188/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e9d471f52bd4969f81a01897049934220bb3fe2626a9526b32129b9a7fb3fb1
+size 14960

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1188/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74f65f3d62ae726f94e7268a605e601e430c6b063c2c27765755dd40d33f1ec7
+size 14960

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1188/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:455df32e01a83ae81dc685e4d2978656d6b28071f101d6ece27f5dbd3783a1c2
+size 14960

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1188/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d0293976b3d2d915a4672685a2461d40055701d93a4c060e95a9d27b0097888
+size 1064

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1188/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|>"
+}

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1188/tokenizer.json

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

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1188/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"
+}

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1188/trainer_state.json

@@ -0,0 +1,1693 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.0,
+  "eval_steps": 500,
+  "global_step": 1188,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05063291139240506,
+      "grad_norm": 3.4980525970458984,
+      "learning_rate": 1.2244897959183673e-06,
+      "loss": 1.6467,
+      "step": 5
+    },
+    {
+      "epoch": 0.10126582278481013,
+      "grad_norm": 2.9643654823303223,
+      "learning_rate": 2.7551020408163266e-06,
+      "loss": 1.6536,
+      "step": 10
+    },
+    {
+      "epoch": 0.1518987341772152,
+      "grad_norm": 2.9791953563690186,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 1.666,
+      "step": 15
+    },
+    {
+      "epoch": 0.20253164556962025,
+      "grad_norm": 2.6827096939086914,
+      "learning_rate": 5.816326530612245e-06,
+      "loss": 1.5566,
+      "step": 20
+    },
+    {
+      "epoch": 0.25316455696202533,
+      "grad_norm": 2.3671700954437256,
+      "learning_rate": 7.346938775510204e-06,
+      "loss": 1.5781,
+      "step": 25
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 3.708879232406616,
+      "learning_rate": 8.877551020408163e-06,
+      "loss": 1.5619,
+      "step": 30
+    },
+    {
+      "epoch": 0.35443037974683544,
+      "grad_norm": 2.66953706741333,
+      "learning_rate": 1.0408163265306123e-05,
+      "loss": 1.4739,
+      "step": 35
+    },
+    {
+      "epoch": 0.4050632911392405,
+      "grad_norm": 3.1258773803710938,
+      "learning_rate": 1.1938775510204082e-05,
+      "loss": 1.4944,
+      "step": 40
+    },
+    {
+      "epoch": 0.45569620253164556,
+      "grad_norm": 2.905057907104492,
+      "learning_rate": 1.3469387755102042e-05,
+      "loss": 1.3855,
+      "step": 45
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "grad_norm": 2.4417102336883545,
+      "learning_rate": 1.5e-05,
+      "loss": 1.3961,
+      "step": 50
+    },
+    {
+      "epoch": 0.5569620253164557,
+      "grad_norm": 2.6814239025115967,
+      "learning_rate": 1.6530612244897957e-05,
+      "loss": 1.2905,
+      "step": 55
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 3.3076088428497314,
+      "learning_rate": 1.806122448979592e-05,
+      "loss": 1.2598,
+      "step": 60
+    },
+    {
+      "epoch": 0.6582278481012658,
+      "grad_norm": 2.7890193462371826,
+      "learning_rate": 1.9591836734693877e-05,
+      "loss": 1.2,
+      "step": 65
+    },
+    {
+      "epoch": 0.7088607594936709,
+      "grad_norm": 2.4030416011810303,
+      "learning_rate": 2.1122448979591836e-05,
+      "loss": 1.2148,
+      "step": 70
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 2.4205846786499023,
+      "learning_rate": 2.2653061224489794e-05,
+      "loss": 1.2163,
+      "step": 75
+    },
+    {
+      "epoch": 0.810126582278481,
+      "grad_norm": 2.9943370819091797,
+      "learning_rate": 2.4183673469387756e-05,
+      "loss": 1.1494,
+      "step": 80
+    },
+    {
+      "epoch": 0.8607594936708861,
+      "grad_norm": 2.5231359004974365,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 1.1404,
+      "step": 85
+    },
+    {
+      "epoch": 0.9113924050632911,
+      "grad_norm": 3.446718692779541,
+      "learning_rate": 2.7244897959183673e-05,
+      "loss": 1.0815,
+      "step": 90
+    },
+    {
+      "epoch": 0.9620253164556962,
+      "grad_norm": 3.4152660369873047,
+      "learning_rate": 2.877551020408163e-05,
+      "loss": 1.0733,
+      "step": 95
+    },
+    {
+      "epoch": 1.010126582278481,
+      "grad_norm": 4.289358615875244,
+      "learning_rate": 2.9999978649819432e-05,
+      "loss": 1.0755,
+      "step": 100
+    },
+    {
+      "epoch": 1.0607594936708862,
+      "grad_norm": 3.5033681392669678,
+      "learning_rate": 2.999923139988104e-05,
+      "loss": 1.0308,
+      "step": 105
+    },
+    {
+      "epoch": 1.111392405063291,
+      "grad_norm": 3.502793788909912,
+      "learning_rate": 2.9997416701690675e-05,
+      "loss": 0.9201,
+      "step": 110
+    },
+    {
+      "epoch": 1.1620253164556962,
+      "grad_norm": 2.977989912033081,
+      "learning_rate": 2.999453468439471e-05,
+      "loss": 0.9366,
+      "step": 115
+    },
+    {
+      "epoch": 1.2126582278481013,
+      "grad_norm": 3.385281801223755,
+      "learning_rate": 2.9990585553097278e-05,
+      "loss": 0.873,
+      "step": 120
+    },
+    {
+      "epoch": 1.2632911392405064,
+      "grad_norm": 3.4536044597625732,
+      "learning_rate": 2.9985569588845665e-05,
+      "loss": 0.9513,
+      "step": 125
+    },
+    {
+      "epoch": 1.3139240506329113,
+      "grad_norm": 3.455348253250122,
+      "learning_rate": 2.9979487148610315e-05,
+      "loss": 0.9035,
+      "step": 130
+    },
+    {
+      "epoch": 1.3645569620253164,
+      "grad_norm": 3.171076774597168,
+      "learning_rate": 2.997233866525942e-05,
+      "loss": 0.8489,
+      "step": 135
+    },
+    {
+      "epoch": 1.4151898734177215,
+      "grad_norm": 3.0069353580474854,
+      "learning_rate": 2.996412464752812e-05,
+      "loss": 0.8202,
+      "step": 140
+    },
+    {
+      "epoch": 1.4658227848101266,
+      "grad_norm": 2.801588296890259,
+      "learning_rate": 2.995484567998229e-05,
+      "loss": 0.7959,
+      "step": 145
+    },
+    {
+      "epoch": 1.5164556962025317,
+      "grad_norm": 2.8108527660369873,
+      "learning_rate": 2.994450242297695e-05,
+      "loss": 0.7332,
+      "step": 150
+    },
+    {
+      "epoch": 1.5670886075949366,
+      "grad_norm": 3.3879706859588623,
+      "learning_rate": 2.9933095612609253e-05,
+      "loss": 0.7345,
+      "step": 155
+    },
+    {
+      "epoch": 1.6177215189873417,
+      "grad_norm": 3.4273533821105957,
+      "learning_rate": 2.992062606066612e-05,
+      "loss": 0.7658,
+      "step": 160
+    },
+    {
+      "epoch": 1.6683544303797468,
+      "grad_norm": 4.3649444580078125,
+      "learning_rate": 2.9907094654566445e-05,
+      "loss": 0.7349,
+      "step": 165
+    },
+    {
+      "epoch": 1.7189873417721517,
+      "grad_norm": 3.840703248977661,
+      "learning_rate": 2.989250235729796e-05,
+      "loss": 0.6883,
+      "step": 170
+    },
+    {
+      "epoch": 1.769620253164557,
+      "grad_norm": 3.321861743927002,
+      "learning_rate": 2.987685020734869e-05,
+      "loss": 0.6445,
+      "step": 175
+    },
+    {
+      "epoch": 1.820253164556962,
+      "grad_norm": 4.948067665100098,
+      "learning_rate": 2.986013931863306e-05,
+      "loss": 0.6853,
+      "step": 180
+    },
+    {
+      "epoch": 1.870886075949367,
+      "grad_norm": 3.2912204265594482,
+      "learning_rate": 2.984237088041259e-05,
+      "loss": 0.6809,
+      "step": 185
+    },
+    {
+      "epoch": 1.9215189873417722,
+      "grad_norm": 3.854374647140503,
+      "learning_rate": 2.9823546157211303e-05,
+      "loss": 0.6823,
+      "step": 190
+    },
+    {
+      "epoch": 1.972151898734177,
+      "grad_norm": 3.8937790393829346,
+      "learning_rate": 2.980366648872571e-05,
+      "loss": 0.6421,
+      "step": 195
+    },
+    {
+      "epoch": 2.020253164556962,
+      "grad_norm": 3.1727030277252197,
+      "learning_rate": 2.9782733289729448e-05,
+      "loss": 0.5468,
+      "step": 200
+    },
+    {
+      "epoch": 2.070886075949367,
+      "grad_norm": 3.526210308074951,
+      "learning_rate": 2.9760748049972646e-05,
+      "loss": 0.5887,
+      "step": 205
+    },
+    {
+      "epoch": 2.1215189873417724,
+      "grad_norm": 2.802851915359497,
+      "learning_rate": 2.9737712334075847e-05,
+      "loss": 0.5184,
+      "step": 210
+    },
+    {
+      "epoch": 2.1721518987341772,
+      "grad_norm": 4.610970497131348,
+      "learning_rate": 2.97136277814187e-05,
+      "loss": 0.5158,
+      "step": 215
+    },
+    {
+      "epoch": 2.222784810126582,
+      "grad_norm": 3.258543014526367,
+      "learning_rate": 2.9688496106023274e-05,
+      "loss": 0.5302,
+      "step": 220
+    },
+    {
+      "epoch": 2.2734177215189875,
+      "grad_norm": 3.7272274494171143,
+      "learning_rate": 2.966231909643208e-05,
+      "loss": 0.4942,
+      "step": 225
+    },
+    {
+      "epoch": 2.3240506329113924,
+      "grad_norm": 3.0091631412506104,
+      "learning_rate": 2.9635098615580783e-05,
+      "loss": 0.4892,
+      "step": 230
+    },
+    {
+      "epoch": 2.3746835443037977,
+      "grad_norm": 3.477494716644287,
+      "learning_rate": 2.960683660066562e-05,
+      "loss": 0.4488,
+      "step": 235
+    },
+    {
+      "epoch": 2.4253164556962026,
+      "grad_norm": 2.9678242206573486,
+      "learning_rate": 2.9577535063005555e-05,
+      "loss": 0.439,
+      "step": 240
+    },
+    {
+      "epoch": 2.4759493670886075,
+      "grad_norm": 4.674062728881836,
+      "learning_rate": 2.9547196087899116e-05,
+      "loss": 0.4748,
+      "step": 245
+    },
+    {
+      "epoch": 2.526582278481013,
+      "grad_norm": 3.2280211448669434,
+      "learning_rate": 2.9515821834475986e-05,
+      "loss": 0.4618,
+      "step": 250
+    },
+    {
+      "epoch": 2.5772151898734177,
+      "grad_norm": 4.220160484313965,
+      "learning_rate": 2.9483414535543386e-05,
+      "loss": 0.423,
+      "step": 255
+    },
+    {
+      "epoch": 2.6278481012658226,
+      "grad_norm": 3.365264415740967,
+      "learning_rate": 2.9449976497427127e-05,
+      "loss": 0.3989,
+      "step": 260
+    },
+    {
+      "epoch": 2.678481012658228,
+      "grad_norm": 3.159595251083374,
+      "learning_rate": 2.94155100998075e-05,
+      "loss": 0.4103,
+      "step": 265
+    },
+    {
+      "epoch": 2.729113924050633,
+      "grad_norm": 3.472161293029785,
+      "learning_rate": 2.938001779554991e-05,
+      "loss": 0.4164,
+      "step": 270
+    },
+    {
+      "epoch": 2.779746835443038,
+      "grad_norm": 3.7458016872406006,
+      "learning_rate": 2.9343502110530332e-05,
+      "loss": 0.3774,
+      "step": 275
+    },
+    {
+      "epoch": 2.830379746835443,
+      "grad_norm": 3.9665720462799072,
+      "learning_rate": 2.930596564345554e-05,
+      "loss": 0.3615,
+      "step": 280
+    },
+    {
+      "epoch": 2.8810126582278484,
+      "grad_norm": 3.497344732284546,
+      "learning_rate": 2.9267411065678146e-05,
+      "loss": 0.3737,
+      "step": 285
+    },
+    {
+      "epoch": 2.9316455696202532,
+      "grad_norm": 3.826024293899536,
+      "learning_rate": 2.9227841121006524e-05,
+      "loss": 0.3397,
+      "step": 290
+    },
+    {
+      "epoch": 2.982278481012658,
+      "grad_norm": 3.507917881011963,
+      "learning_rate": 2.9187258625509518e-05,
+      "loss": 0.3496,
+      "step": 295
+    },
+    {
+      "epoch": 3.030379746835443,
+      "grad_norm": 4.524459362030029,
+      "learning_rate": 2.914566646731605e-05,
+      "loss": 0.3471,
+      "step": 300
+    },
+    {
+      "epoch": 3.081012658227848,
+      "grad_norm": 3.779264211654663,
+      "learning_rate": 2.9103067606409555e-05,
+      "loss": 0.3081,
+      "step": 305
+    },
+    {
+      "epoch": 3.131645569620253,
+      "grad_norm": 3.9139416217803955,
+      "learning_rate": 2.9059465074417343e-05,
+      "loss": 0.3065,
+      "step": 310
+    },
+    {
+      "epoch": 3.1822784810126583,
+      "grad_norm": 3.71647310256958,
+      "learning_rate": 2.9014861974394856e-05,
+      "loss": 0.3024,
+      "step": 315
+    },
+    {
+      "epoch": 3.232911392405063,
+      "grad_norm": 3.003744125366211,
+      "learning_rate": 2.896926148060482e-05,
+      "loss": 0.2942,
+      "step": 320
+    },
+    {
+      "epoch": 3.2835443037974685,
+      "grad_norm": 4.5852251052856445,
+      "learning_rate": 2.892266683829135e-05,
+      "loss": 0.2626,
+      "step": 325
+    },
+    {
+      "epoch": 3.3341772151898734,
+      "grad_norm": 3.427046298980713,
+      "learning_rate": 2.887508136344899e-05,
+      "loss": 0.2565,
+      "step": 330
+    },
+    {
+      "epoch": 3.3848101265822783,
+      "grad_norm": 3.712449789047241,
+      "learning_rate": 2.882650844258672e-05,
+      "loss": 0.2455,
+      "step": 335
+    },
+    {
+      "epoch": 3.4354430379746836,
+      "grad_norm": 3.4680449962615967,
+      "learning_rate": 2.877695153248697e-05,
+      "loss": 0.2485,
+      "step": 340
+    },
+    {
+      "epoch": 3.4860759493670885,
+      "grad_norm": 3.1136488914489746,
+      "learning_rate": 2.8726414159959585e-05,
+      "loss": 0.2724,
+      "step": 345
+    },
+    {
+      "epoch": 3.536708860759494,
+      "grad_norm": 3.908705234527588,
+      "learning_rate": 2.867489992159086e-05,
+      "loss": 0.2657,
+      "step": 350
+    },
+    {
+      "epoch": 3.5873417721518988,
+      "grad_norm": 4.278017044067383,
+      "learning_rate": 2.8622412483487553e-05,
+      "loss": 0.2669,
+      "step": 355
+    },
+    {
+      "epoch": 3.6379746835443036,
+      "grad_norm": 3.4697976112365723,
+      "learning_rate": 2.8568955581016003e-05,
+      "loss": 0.2427,
+      "step": 360
+    },
+    {
+      "epoch": 3.688607594936709,
+      "grad_norm": 3.08229398727417,
+      "learning_rate": 2.8514533018536286e-05,
+      "loss": 0.2494,
+      "step": 365
+    },
+    {
+      "epoch": 3.739240506329114,
+      "grad_norm": 3.35378098487854,
+      "learning_rate": 2.8459148669131476e-05,
+      "loss": 0.2383,
+      "step": 370
+    },
+    {
+      "epoch": 3.7898734177215188,
+      "grad_norm": 3.133762836456299,
+      "learning_rate": 2.8402806474331994e-05,
+      "loss": 0.2387,
+      "step": 375
+    },
+    {
+      "epoch": 3.840506329113924,
+      "grad_norm": 3.7151851654052734,
+      "learning_rate": 2.8345510443835116e-05,
+      "loss": 0.2373,
+      "step": 380
+    },
+    {
+      "epoch": 3.891139240506329,
+      "grad_norm": 3.03208327293396,
+      "learning_rate": 2.828726465521963e-05,
+      "loss": 0.2159,
+      "step": 385
+    },
+    {
+      "epoch": 3.9417721518987343,
+      "grad_norm": 3.15083646774292,
+      "learning_rate": 2.8228073253655608e-05,
+      "loss": 0.2152,
+      "step": 390
+    },
+    {
+      "epoch": 3.992405063291139,
+      "grad_norm": 3.210649013519287,
+      "learning_rate": 2.8167940451609444e-05,
+      "loss": 0.2213,
+      "step": 395
+    },
+    {
+      "epoch": 4.040506329113924,
+      "grad_norm": 3.083118200302124,
+      "learning_rate": 2.8106870528544044e-05,
+      "loss": 0.1842,
+      "step": 400
+    },
+    {
+      "epoch": 4.091139240506329,
+      "grad_norm": 3.1503756046295166,
+      "learning_rate": 2.804486783061428e-05,
+      "loss": 0.1861,
+      "step": 405
+    },
+    {
+      "epoch": 4.141772151898734,
+      "grad_norm": 2.813202381134033,
+      "learning_rate": 2.798193677035768e-05,
+      "loss": 0.1755,
+      "step": 410
+    },
+    {
+      "epoch": 4.192405063291139,
+      "grad_norm": 3.875789165496826,
+      "learning_rate": 2.7918081826380428e-05,
+      "loss": 0.1762,
+      "step": 415
+    },
+    {
+      "epoch": 4.243037974683545,
+      "grad_norm": 3.8627779483795166,
+      "learning_rate": 2.785330754303858e-05,
+      "loss": 0.1723,
+      "step": 420
+    },
+    {
+      "epoch": 4.293670886075949,
+      "grad_norm": 2.6941754817962646,
+      "learning_rate": 2.7787618530114724e-05,
+      "loss": 0.1606,
+      "step": 425
+    },
+    {
+      "epoch": 4.3443037974683545,
+      "grad_norm": 3.605570077896118,
+      "learning_rate": 2.7721019462489862e-05,
+      "loss": 0.17,
+      "step": 430
+    },
+    {
+      "epoch": 4.39493670886076,
+      "grad_norm": 2.771569013595581,
+      "learning_rate": 2.7653515079810744e-05,
+      "loss": 0.1738,
+      "step": 435
+    },
+    {
+      "epoch": 4.445569620253164,
+      "grad_norm": 3.381185531616211,
+      "learning_rate": 2.758511018615254e-05,
+      "loss": 0.1645,
+      "step": 440
+    },
+    {
+      "epoch": 4.49620253164557,
+      "grad_norm": 2.929736375808716,
+      "learning_rate": 2.751580964967699e-05,
+      "loss": 0.1758,
+      "step": 445
+    },
+    {
+      "epoch": 4.546835443037975,
+      "grad_norm": 4.251176357269287,
+      "learning_rate": 2.7445618402285894e-05,
+      "loss": 0.1675,
+      "step": 450
+    },
+    {
+      "epoch": 4.597468354430379,
+      "grad_norm": 3.2119245529174805,
+      "learning_rate": 2.7374541439270174e-05,
+      "loss": 0.1662,
+      "step": 455
+    },
+    {
+      "epoch": 4.648101265822785,
+      "grad_norm": 3.273690700531006,
+      "learning_rate": 2.730258381895434e-05,
+      "loss": 0.1649,
+      "step": 460
+    },
+    {
+      "epoch": 4.69873417721519,
+      "grad_norm": 2.8210129737854004,
+      "learning_rate": 2.722975066233653e-05,
+      "loss": 0.1471,
+      "step": 465
+    },
+    {
+      "epoch": 4.749367088607595,
+      "grad_norm": 3.1151881217956543,
+      "learning_rate": 2.7156047152724046e-05,
+      "loss": 0.1519,
+      "step": 470
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 3.13199782371521,
+      "learning_rate": 2.7081478535364496e-05,
+      "loss": 0.1537,
+      "step": 475
+    },
+    {
+      "epoch": 4.850632911392405,
+      "grad_norm": 2.7968389987945557,
+      "learning_rate": 2.700605011707248e-05,
+      "loss": 0.1447,
+      "step": 480
+    },
+    {
+      "epoch": 4.9012658227848105,
+      "grad_norm": 3.166747570037842,
+      "learning_rate": 2.692976726585194e-05,
+      "loss": 0.1426,
+      "step": 485
+    },
+    {
+      "epoch": 4.951898734177215,
+      "grad_norm": 3.1832809448242188,
+      "learning_rate": 2.6852635410514125e-05,
+      "loss": 0.1386,
+      "step": 490
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.532459735870361,
+      "learning_rate": 2.6774660040291257e-05,
+      "loss": 0.1481,
+      "step": 495
+    },
+    {
+      "epoch": 5.050632911392405,
+      "grad_norm": 2.8513097763061523,
+      "learning_rate": 2.6695846704445842e-05,
+      "loss": 0.1118,
+      "step": 500
+    },
+    {
+      "epoch": 5.10126582278481,
+      "grad_norm": 2.8358778953552246,
+      "learning_rate": 2.6616201011875792e-05,
+      "loss": 0.1259,
+      "step": 505
+    },
+    {
+      "epoch": 5.151898734177215,
+      "grad_norm": 2.5484566688537598,
+      "learning_rate": 2.6535728630715228e-05,
+      "loss": 0.1108,
+      "step": 510
+    },
+    {
+      "epoch": 5.2025316455696204,
+      "grad_norm": 2.7051589488983154,
+      "learning_rate": 2.645443528793111e-05,
+      "loss": 0.1196,
+      "step": 515
+    },
+    {
+      "epoch": 5.253164556962025,
+      "grad_norm": 2.469198226928711,
+      "learning_rate": 2.6372326768915658e-05,
+      "loss": 0.1255,
+      "step": 520
+    },
+    {
+      "epoch": 5.30379746835443,
+      "grad_norm": 2.5851681232452393,
+      "learning_rate": 2.628940891707462e-05,
+      "loss": 0.1204,
+      "step": 525
+    },
+    {
+      "epoch": 5.3544303797468356,
+      "grad_norm": 2.605705499649048,
+      "learning_rate": 2.6205687633411445e-05,
+      "loss": 0.1127,
+      "step": 530
+    },
+    {
+      "epoch": 5.405063291139241,
+      "grad_norm": 2.959566593170166,
+      "learning_rate": 2.6121168876107274e-05,
+      "loss": 0.1158,
+      "step": 535
+    },
+    {
+      "epoch": 5.455696202531645,
+      "grad_norm": 2.3968331813812256,
+      "learning_rate": 2.6035858660096975e-05,
+      "loss": 0.1249,
+      "step": 540
+    },
+    {
+      "epoch": 5.506329113924051,
+      "grad_norm": 4.327753067016602,
+      "learning_rate": 2.594976305664103e-05,
+      "loss": 0.1169,
+      "step": 545
+    },
+    {
+      "epoch": 5.556962025316456,
+      "grad_norm": 2.5143179893493652,
+      "learning_rate": 2.586288819289349e-05,
+      "loss": 0.1149,
+      "step": 550
+    },
+    {
+      "epoch": 5.6075949367088604,
+      "grad_norm": 2.9387834072113037,
+      "learning_rate": 2.5775240251465914e-05,
+      "loss": 0.1173,
+      "step": 555
+    },
+    {
+      "epoch": 5.658227848101266,
+      "grad_norm": 2.727640390396118,
+      "learning_rate": 2.568682546998738e-05,
+      "loss": 0.1069,
+      "step": 560
+    },
+    {
+      "epoch": 5.708860759493671,
+      "grad_norm": 2.930460214614868,
+      "learning_rate": 2.5597650140660555e-05,
+      "loss": 0.1096,
+      "step": 565
+    },
+    {
+      "epoch": 5.759493670886076,
+      "grad_norm": 2.747501850128174,
+      "learning_rate": 2.5507720609813928e-05,
+      "loss": 0.105,
+      "step": 570
+    },
+    {
+      "epoch": 5.810126582278481,
+      "grad_norm": 2.5990662574768066,
+      "learning_rate": 2.541704327745013e-05,
+      "loss": 0.1147,
+      "step": 575
+    },
+    {
+      "epoch": 5.860759493670886,
+      "grad_norm": 2.7866060733795166,
+      "learning_rate": 2.5325624596790486e-05,
+      "loss": 0.1134,
+      "step": 580
+    },
+    {
+      "epoch": 5.911392405063291,
+      "grad_norm": 2.9491360187530518,
+      "learning_rate": 2.523347107381576e-05,
+      "loss": 0.1039,
+      "step": 585
+    },
+    {
+      "epoch": 5.962025316455696,
+      "grad_norm": 2.775834321975708,
+      "learning_rate": 2.514058926680312e-05,
+      "loss": 0.109,
+      "step": 590
+    },
+    {
+      "epoch": 6.010126582278481,
+      "grad_norm": 3.1889455318450928,
+      "learning_rate": 2.5046985785859453e-05,
+      "loss": 0.1048,
+      "step": 595
+    },
+    {
+      "epoch": 6.060759493670886,
+      "grad_norm": 2.762517213821411,
+      "learning_rate": 2.4952667292450887e-05,
+      "loss": 0.0884,
+      "step": 600
+    },
+    {
+      "epoch": 6.111392405063291,
+      "grad_norm": 1.801896095275879,
+      "learning_rate": 2.4857640498928756e-05,
+      "loss": 0.0907,
+      "step": 605
+    },
+    {
+      "epoch": 6.162025316455696,
+      "grad_norm": 2.1080682277679443,
+      "learning_rate": 2.4761912168051903e-05,
+      "loss": 0.0892,
+      "step": 610
+    },
+    {
+      "epoch": 6.2126582278481015,
+      "grad_norm": 2.79091215133667,
+      "learning_rate": 2.4665489112505372e-05,
+      "loss": 0.0936,
+      "step": 615
+    },
+    {
+      "epoch": 6.263291139240506,
+      "grad_norm": 2.5198278427124023,
+      "learning_rate": 2.4568378194415583e-05,
+      "loss": 0.0973,
+      "step": 620
+    },
+    {
+      "epoch": 6.313924050632911,
+      "grad_norm": 2.038583278656006,
+      "learning_rate": 2.447058632486197e-05,
+      "loss": 0.0915,
+      "step": 625
+    },
+    {
+      "epoch": 6.364556962025317,
+      "grad_norm": 3.310605049133301,
+      "learning_rate": 2.4372120463385167e-05,
+      "loss": 0.0936,
+      "step": 630
+    },
+    {
+      "epoch": 6.415189873417722,
+      "grad_norm": 2.2550792694091797,
+      "learning_rate": 2.427298761749168e-05,
+      "loss": 0.1016,
+      "step": 635
+    },
+    {
+      "epoch": 6.465822784810126,
+      "grad_norm": 2.7243216037750244,
+      "learning_rate": 2.4173194842155208e-05,
+      "loss": 0.0888,
+      "step": 640
+    },
+    {
+      "epoch": 6.516455696202532,
+      "grad_norm": 2.442253351211548,
+      "learning_rate": 2.4072749239314565e-05,
+      "loss": 0.0901,
+      "step": 645
+    },
+    {
+      "epoch": 6.567088607594937,
+      "grad_norm": 2.2244441509246826,
+      "learning_rate": 2.397165795736824e-05,
+      "loss": 0.0919,
+      "step": 650
+    },
+    {
+      "epoch": 6.6177215189873415,
+      "grad_norm": 2.14775013923645,
+      "learning_rate": 2.386992819066569e-05,
+      "loss": 0.0903,
+      "step": 655
+    },
+    {
+      "epoch": 6.668354430379747,
+      "grad_norm": 2.5285158157348633,
+      "learning_rate": 2.3767567178995323e-05,
+      "loss": 0.0899,
+      "step": 660
+    },
+    {
+      "epoch": 6.718987341772152,
+      "grad_norm": 2.9994752407073975,
+      "learning_rate": 2.366458220706928e-05,
+      "loss": 0.095,
+      "step": 665
+    },
+    {
+      "epoch": 6.769620253164557,
+      "grad_norm": 2.355753183364868,
+      "learning_rate": 2.3560980604004977e-05,
+      "loss": 0.0866,
+      "step": 670
+    },
+    {
+      "epoch": 6.820253164556962,
+      "grad_norm": 2.467966318130493,
+      "learning_rate": 2.345676974280355e-05,
+      "loss": 0.0841,
+      "step": 675
+    },
+    {
+      "epoch": 6.870886075949367,
+      "grad_norm": 2.32102632522583,
+      "learning_rate": 2.335195703982513e-05,
+      "loss": 0.0879,
+      "step": 680
+    },
+    {
+      "epoch": 6.921518987341772,
+      "grad_norm": 2.34090518951416,
+      "learning_rate": 2.324654995426102e-05,
+      "loss": 0.0892,
+      "step": 685
+    },
+    {
+      "epoch": 6.972151898734177,
+      "grad_norm": 2.4923956394195557,
+      "learning_rate": 2.3140555987602886e-05,
+      "loss": 0.0861,
+      "step": 690
+    },
+    {
+      "epoch": 7.020253164556962,
+      "grad_norm": 2.2103333473205566,
+      "learning_rate": 2.3033982683108867e-05,
+      "loss": 0.0792,
+      "step": 695
+    },
+    {
+      "epoch": 7.0708860759493675,
+      "grad_norm": 2.5478057861328125,
+      "learning_rate": 2.2926837625266776e-05,
+      "loss": 0.074,
+      "step": 700
+    },
+    {
+      "epoch": 7.121518987341772,
+      "grad_norm": 2.4020633697509766,
+      "learning_rate": 2.281912843925429e-05,
+      "loss": 0.0729,
+      "step": 705
+    },
+    {
+      "epoch": 7.172151898734177,
+      "grad_norm": 1.8848402500152588,
+      "learning_rate": 2.2710862790396353e-05,
+      "loss": 0.0707,
+      "step": 710
+    },
+    {
+      "epoch": 7.222784810126583,
+      "grad_norm": 2.636121988296509,
+      "learning_rate": 2.26020483836196e-05,
+      "loss": 0.0847,
+      "step": 715
+    },
+    {
+      "epoch": 7.273417721518987,
+      "grad_norm": 2.489856719970703,
+      "learning_rate": 2.249269296290405e-05,
+      "loss": 0.0789,
+      "step": 720
+    },
+    {
+      "epoch": 7.324050632911392,
+      "grad_norm": 2.441281795501709,
+      "learning_rate": 2.238280431073199e-05,
+      "loss": 0.0815,
+      "step": 725
+    },
+    {
+      "epoch": 7.374683544303798,
+      "grad_norm": 2.4158310890197754,
+      "learning_rate": 2.2272390247534127e-05,
+      "loss": 0.0767,
+      "step": 730
+    },
+    {
+      "epoch": 7.425316455696202,
+      "grad_norm": 1.5769174098968506,
+      "learning_rate": 2.2161458631133e-05,
+      "loss": 0.0758,
+      "step": 735
+    },
+    {
+      "epoch": 7.4759493670886075,
+      "grad_norm": 2.136112928390503,
+      "learning_rate": 2.2050017356183806e-05,
+      "loss": 0.0805,
+      "step": 740
+    },
+    {
+      "epoch": 7.526582278481013,
+      "grad_norm": 2.3461337089538574,
+      "learning_rate": 2.1938074353612533e-05,
+      "loss": 0.0831,
+      "step": 745
+    },
+    {
+      "epoch": 7.577215189873417,
+      "grad_norm": 2.017784833908081,
+      "learning_rate": 2.182563759005155e-05,
+      "loss": 0.0769,
+      "step": 750
+    },
+    {
+      "epoch": 7.627848101265823,
+      "grad_norm": 1.7009460926055908,
+      "learning_rate": 2.1712715067272655e-05,
+      "loss": 0.0743,
+      "step": 755
+    },
+    {
+      "epoch": 7.678481012658228,
+      "grad_norm": 1.948912262916565,
+      "learning_rate": 2.1599314821617598e-05,
+      "loss": 0.0769,
+      "step": 760
+    },
+    {
+      "epoch": 7.729113924050633,
+      "grad_norm": 1.9673391580581665,
+      "learning_rate": 2.1485444923426167e-05,
+      "loss": 0.081,
+      "step": 765
+    },
+    {
+      "epoch": 7.779746835443038,
+      "grad_norm": 2.3732705116271973,
+      "learning_rate": 2.1371113476461855e-05,
+      "loss": 0.0773,
+      "step": 770
+    },
+    {
+      "epoch": 7.830379746835443,
+      "grad_norm": 1.866337776184082,
+      "learning_rate": 2.1256328617335124e-05,
+      "loss": 0.0759,
+      "step": 775
+    },
+    {
+      "epoch": 7.881012658227848,
+      "grad_norm": 2.141129970550537,
+      "learning_rate": 2.1141098514924367e-05,
+      "loss": 0.0733,
+      "step": 780
+    },
+    {
+      "epoch": 7.931645569620253,
+      "grad_norm": 2.2540833950042725,
+      "learning_rate": 2.1025431369794546e-05,
+      "loss": 0.0749,
+      "step": 785
+    },
+    {
+      "epoch": 7.982278481012658,
+      "grad_norm": 1.980592966079712,
+      "learning_rate": 2.0909335413613563e-05,
+      "loss": 0.0717,
+      "step": 790
+    },
+    {
+      "epoch": 8.030379746835443,
+      "grad_norm": 2.3790063858032227,
+      "learning_rate": 2.079281890856648e-05,
+      "loss": 0.071,
+      "step": 795
+    },
+    {
+      "epoch": 8.081012658227849,
+      "grad_norm": 1.9786341190338135,
+      "learning_rate": 2.067589014676749e-05,
+      "loss": 0.0671,
+      "step": 800
+    },
+    {
+      "epoch": 8.131645569620254,
+      "grad_norm": 1.850415825843811,
+      "learning_rate": 2.0558557449669818e-05,
+      "loss": 0.0706,
+      "step": 805
+    },
+    {
+      "epoch": 8.182278481012657,
+      "grad_norm": 1.740311622619629,
+      "learning_rate": 2.0440829167473486e-05,
+      "loss": 0.0696,
+      "step": 810
+    },
+    {
+      "epoch": 8.232911392405063,
+      "grad_norm": 1.6912726163864136,
+      "learning_rate": 2.0322713678531067e-05,
+      "loss": 0.0737,
+      "step": 815
+    },
+    {
+      "epoch": 8.283544303797468,
+      "grad_norm": 1.9001421928405762,
+      "learning_rate": 2.020421938875143e-05,
+      "loss": 0.0662,
+      "step": 820
+    },
+    {
+      "epoch": 8.334177215189873,
+      "grad_norm": 1.8828890323638916,
+      "learning_rate": 2.0085354731001502e-05,
+      "loss": 0.0703,
+      "step": 825
+    },
+    {
+      "epoch": 8.384810126582279,
+      "grad_norm": 1.4946229457855225,
+      "learning_rate": 1.9966128164506153e-05,
+      "loss": 0.0691,
+      "step": 830
+    },
+    {
+      "epoch": 8.435443037974684,
+      "grad_norm": 2.7881011962890625,
+      "learning_rate": 1.9846548174246144e-05,
+      "loss": 0.0727,
+      "step": 835
+    },
+    {
+      "epoch": 8.48607594936709,
+      "grad_norm": 1.8071367740631104,
+      "learning_rate": 1.9726623270354314e-05,
+      "loss": 0.0657,
+      "step": 840
+    },
+    {
+      "epoch": 8.536708860759493,
+      "grad_norm": 1.4970042705535889,
+      "learning_rate": 1.9606361987509905e-05,
+      "loss": 0.0698,
+      "step": 845
+    },
+    {
+      "epoch": 8.587341772151898,
+      "grad_norm": 1.7957663536071777,
+      "learning_rate": 1.9485772884331215e-05,
+      "loss": 0.0698,
+      "step": 850
+    },
+    {
+      "epoch": 8.637974683544304,
+      "grad_norm": 1.6136796474456787,
+      "learning_rate": 1.936486454276647e-05,
+      "loss": 0.0716,
+      "step": 855
+    },
+    {
+      "epoch": 8.688607594936709,
+      "grad_norm": 1.5621618032455444,
+      "learning_rate": 1.9243645567483096e-05,
+      "loss": 0.0675,
+      "step": 860
+    },
+    {
+      "epoch": 8.739240506329114,
+      "grad_norm": 1.7963391542434692,
+      "learning_rate": 1.9122124585255348e-05,
+      "loss": 0.0681,
+      "step": 865
+    },
+    {
+      "epoch": 8.78987341772152,
+      "grad_norm": 2.201146364212036,
+      "learning_rate": 1.900031024435037e-05,
+      "loss": 0.0717,
+      "step": 870
+    },
+    {
+      "epoch": 8.840506329113925,
+      "grad_norm": 1.4939143657684326,
+      "learning_rate": 1.887821121391272e-05,
+      "loss": 0.0713,
+      "step": 875
+    },
+    {
+      "epoch": 8.891139240506329,
+      "grad_norm": 1.4898556470870972,
+      "learning_rate": 1.8755836183347416e-05,
+      "loss": 0.0646,
+      "step": 880
+    },
+    {
+      "epoch": 8.941772151898734,
+      "grad_norm": 1.6174167394638062,
+      "learning_rate": 1.863319386170154e-05,
+      "loss": 0.0645,
+      "step": 885
+    },
+    {
+      "epoch": 8.99240506329114,
+      "grad_norm": 1.5976531505584717,
+      "learning_rate": 1.8510292977044434e-05,
+      "loss": 0.0688,
+      "step": 890
+    },
+    {
+      "epoch": 9.040506329113924,
+      "grad_norm": 1.7708168029785156,
+      "learning_rate": 1.838714227584658e-05,
+      "loss": 0.0621,
+      "step": 895
+    },
+    {
+      "epoch": 9.09113924050633,
+      "grad_norm": 1.2461936473846436,
+      "learning_rate": 1.8263750522357107e-05,
+      "loss": 0.0583,
+      "step": 900
+    },
+    {
+      "epoch": 9.141772151898735,
+      "grad_norm": 1.1864615678787231,
+      "learning_rate": 1.814012649798007e-05,
+      "loss": 0.0614,
+      "step": 905
+    },
+    {
+      "epoch": 9.192405063291138,
+      "grad_norm": 1.408365249633789,
+      "learning_rate": 1.8016279000649523e-05,
+      "loss": 0.0661,
+      "step": 910
+    },
+    {
+      "epoch": 9.243037974683544,
+      "grad_norm": 1.521738886833191,
+      "learning_rate": 1.7892216844203395e-05,
+      "loss": 0.0643,
+      "step": 915
+    },
+    {
+      "epoch": 9.29367088607595,
+      "grad_norm": 1.6638453006744385,
+      "learning_rate": 1.7767948857756226e-05,
+      "loss": 0.0653,
+      "step": 920
+    },
+    {
+      "epoch": 9.344303797468354,
+      "grad_norm": 1.9698224067687988,
+      "learning_rate": 1.7643483885070827e-05,
+      "loss": 0.0656,
+      "step": 925
+    },
+    {
+      "epoch": 9.39493670886076,
+      "grad_norm": 1.5151782035827637,
+      "learning_rate": 1.751883078392891e-05,
+      "loss": 0.0638,
+      "step": 930
+    },
+    {
+      "epoch": 9.445569620253165,
+      "grad_norm": 1.6791659593582153,
+      "learning_rate": 1.739399842550069e-05,
+      "loss": 0.0642,
+      "step": 935
+    },
+    {
+      "epoch": 9.496202531645569,
+      "grad_norm": 1.4712715148925781,
+      "learning_rate": 1.726899569371357e-05,
+      "loss": 0.0651,
+      "step": 940
+    },
+    {
+      "epoch": 9.546835443037974,
+      "grad_norm": 1.313909888267517,
+      "learning_rate": 1.7143831484619884e-05,
+      "loss": 0.0579,
+      "step": 945
+    },
+    {
+      "epoch": 9.59746835443038,
+      "grad_norm": 1.5802178382873535,
+      "learning_rate": 1.7018514705763804e-05,
+      "loss": 0.0655,
+      "step": 950
+    },
+    {
+      "epoch": 9.648101265822785,
+      "grad_norm": 1.674559473991394,
+      "learning_rate": 1.6893054275547407e-05,
+      "loss": 0.0633,
+      "step": 955
+    },
+    {
+      "epoch": 9.69873417721519,
+      "grad_norm": 2.3455135822296143,
+      "learning_rate": 1.6767459122595998e-05,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 9.749367088607595,
+      "grad_norm": 1.1516377925872803,
+      "learning_rate": 1.6641738185122663e-05,
+      "loss": 0.0585,
+      "step": 965
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": 1.211869478225708,
+      "learning_rate": 1.6515900410292188e-05,
+      "loss": 0.0684,
+      "step": 970
+    },
+    {
+      "epoch": 9.850632911392404,
+      "grad_norm": 1.3427664041519165,
+      "learning_rate": 1.6389954753584303e-05,
+      "loss": 0.0613,
+      "step": 975
+    },
+    {
+      "epoch": 9.90126582278481,
+      "grad_norm": 0.9951387643814087,
+      "learning_rate": 1.626391017815635e-05,
+      "loss": 0.071,
+      "step": 980
+    },
+    {
+      "epoch": 9.951898734177215,
+      "grad_norm": 2.0930867195129395,
+      "learning_rate": 1.6137775654205414e-05,
+      "loss": 0.0655,
+      "step": 985
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.7130424976348877,
+      "learning_rate": 1.601156015832993e-05,
+      "loss": 0.0622,
+      "step": 990
+    },
+    {
+      "epoch": 10.050632911392405,
+      "grad_norm": 1.5401997566223145,
+      "learning_rate": 1.5885272672890842e-05,
+      "loss": 0.0621,
+      "step": 995
+    },
+    {
+      "epoch": 10.10126582278481,
+      "grad_norm": 1.5477750301361084,
+      "learning_rate": 1.5758922185372387e-05,
+      "loss": 0.0574,
+      "step": 1000
+    },
+    {
+      "epoch": 10.151898734177216,
+      "grad_norm": 1.1239627599716187,
+      "learning_rate": 1.5632517687742438e-05,
+      "loss": 0.0599,
+      "step": 1005
+    },
+    {
+      "epoch": 10.20253164556962,
+      "grad_norm": 1.1288483142852783,
+      "learning_rate": 1.5506068175812618e-05,
+      "loss": 0.059,
+      "step": 1010
+    },
+    {
+      "epoch": 10.253164556962025,
+      "grad_norm": 1.120748519897461,
+      "learning_rate": 1.5379582648598056e-05,
+      "loss": 0.0602,
+      "step": 1015
+    },
+    {
+      "epoch": 10.30379746835443,
+      "grad_norm": 1.4478673934936523,
+      "learning_rate": 1.5253070107677006e-05,
+      "loss": 0.0609,
+      "step": 1020
+    },
+    {
+      "epoch": 10.354430379746836,
+      "grad_norm": 1.0375020503997803,
+      "learning_rate": 1.5126539556550172e-05,
+      "loss": 0.0593,
+      "step": 1025
+    },
+    {
+      "epoch": 10.405063291139241,
+      "grad_norm": 1.6543164253234863,
+      "learning_rate": 1.5e-05,
+      "loss": 0.0598,
+      "step": 1030
+    },
+    {
+      "epoch": 10.455696202531646,
+      "grad_norm": 1.5519331693649292,
+      "learning_rate": 1.4873460443449834e-05,
+      "loss": 0.0614,
+      "step": 1035
+    },
+    {
+      "epoch": 10.50632911392405,
+      "grad_norm": 1.8383262157440186,
+      "learning_rate": 1.4746929892322996e-05,
+      "loss": 0.0582,
+      "step": 1040
+    },
+    {
+      "epoch": 10.556962025316455,
+      "grad_norm": 1.509050726890564,
+      "learning_rate": 1.4620417351401945e-05,
+      "loss": 0.0646,
+      "step": 1045
+    },
+    {
+      "epoch": 10.60759493670886,
+      "grad_norm": 1.1060560941696167,
+      "learning_rate": 1.4493931824187385e-05,
+      "loss": 0.0577,
+      "step": 1050
+    },
+    {
+      "epoch": 10.658227848101266,
+      "grad_norm": 1.5542149543762207,
+      "learning_rate": 1.4367482312257564e-05,
+      "loss": 0.06,
+      "step": 1055
+    },
+    {
+      "epoch": 10.708860759493671,
+      "grad_norm": 0.8741584420204163,
+      "learning_rate": 1.4241077814627618e-05,
+      "loss": 0.0591,
+      "step": 1060
+    },
+    {
+      "epoch": 10.759493670886076,
+      "grad_norm": 1.3523668050765991,
+      "learning_rate": 1.411472732710916e-05,
+      "loss": 0.0582,
+      "step": 1065
+    },
+    {
+      "epoch": 10.810126582278482,
+      "grad_norm": 0.9250157475471497,
+      "learning_rate": 1.3988439841670075e-05,
+      "loss": 0.055,
+      "step": 1070
+    },
+    {
+      "epoch": 10.860759493670885,
+      "grad_norm": 1.4959791898727417,
+      "learning_rate": 1.3862224345794585e-05,
+      "loss": 0.0572,
+      "step": 1075
+    },
+    {
+      "epoch": 10.91139240506329,
+      "grad_norm": 1.737217664718628,
+      "learning_rate": 1.3736089821843653e-05,
+      "loss": 0.057,
+      "step": 1080
+    },
+    {
+      "epoch": 10.962025316455696,
+      "grad_norm": 1.0605052709579468,
+      "learning_rate": 1.3610045246415703e-05,
+      "loss": 0.0534,
+      "step": 1085
+    },
+    {
+      "epoch": 11.010126582278481,
+      "grad_norm": 1.4872320890426636,
+      "learning_rate": 1.3484099589707813e-05,
+      "loss": 0.0592,
+      "step": 1090
+    },
+    {
+      "epoch": 11.060759493670886,
+      "grad_norm": 1.0444155931472778,
+      "learning_rate": 1.335826181487734e-05,
+      "loss": 0.0568,
+      "step": 1095
+    },
+    {
+      "epoch": 11.111392405063292,
+      "grad_norm": 1.3047372102737427,
+      "learning_rate": 1.3232540877404e-05,
+      "loss": 0.0541,
+      "step": 1100
+    },
+    {
+      "epoch": 11.162025316455697,
+      "grad_norm": 1.697584867477417,
+      "learning_rate": 1.3106945724452592e-05,
+      "loss": 0.0569,
+      "step": 1105
+    },
+    {
+      "epoch": 11.2126582278481,
+      "grad_norm": 1.4648683071136475,
+      "learning_rate": 1.2981485294236201e-05,
+      "loss": 0.056,
+      "step": 1110
+    },
+    {
+      "epoch": 11.263291139240506,
+      "grad_norm": 0.8088081479072571,
+      "learning_rate": 1.2856168515380117e-05,
+      "loss": 0.0539,
+      "step": 1115
+    },
+    {
+      "epoch": 11.313924050632911,
+      "grad_norm": 1.1021257638931274,
+      "learning_rate": 1.2731004306286434e-05,
+      "loss": 0.0565,
+      "step": 1120
+    },
+    {
+      "epoch": 11.364556962025317,
+      "grad_norm": 1.3986896276474,
+      "learning_rate": 1.2606001574499316e-05,
+      "loss": 0.058,
+      "step": 1125
+    },
+    {
+      "epoch": 11.415189873417722,
+      "grad_norm": 0.8848942518234253,
+      "learning_rate": 1.2481169216071093e-05,
+      "loss": 0.0564,
+      "step": 1130
+    },
+    {
+      "epoch": 11.465822784810127,
+      "grad_norm": 1.2140717506408691,
+      "learning_rate": 1.2356516114929176e-05,
+      "loss": 0.057,
+      "step": 1135
+    },
+    {
+      "epoch": 11.51645569620253,
+      "grad_norm": 1.1261478662490845,
+      "learning_rate": 1.2232051142243773e-05,
+      "loss": 0.0565,
+      "step": 1140
+    },
+    {
+      "epoch": 11.567088607594936,
+      "grad_norm": 1.119118094444275,
+      "learning_rate": 1.2107783155796606e-05,
+      "loss": 0.055,
+      "step": 1145
+    },
+    {
+      "epoch": 11.617721518987342,
+      "grad_norm": 0.9958686828613281,
+      "learning_rate": 1.198372099935048e-05,
+      "loss": 0.0559,
+      "step": 1150
+    },
+    {
+      "epoch": 11.668354430379747,
+      "grad_norm": 1.2256391048431396,
+      "learning_rate": 1.1859873502019935e-05,
+      "loss": 0.0589,
+      "step": 1155
+    },
+    {
+      "epoch": 11.718987341772152,
+      "grad_norm": 1.7713159322738647,
+      "learning_rate": 1.1736249477642896e-05,
+      "loss": 0.0565,
+      "step": 1160
+    },
+    {
+      "epoch": 11.769620253164558,
+      "grad_norm": 1.1513127088546753,
+      "learning_rate": 1.1612857724153418e-05,
+      "loss": 0.06,
+      "step": 1165
+    },
+    {
+      "epoch": 11.820253164556963,
+      "grad_norm": 1.0759341716766357,
+      "learning_rate": 1.1489707022955566e-05,
+      "loss": 0.0565,
+      "step": 1170
+    },
+    {
+      "epoch": 11.870886075949366,
+      "grad_norm": 1.09992253780365,
+      "learning_rate": 1.1366806138298468e-05,
+      "loss": 0.0531,
+      "step": 1175
+    },
+    {
+      "epoch": 11.921518987341772,
+      "grad_norm": 1.2160842418670654,
+      "learning_rate": 1.1244163816652588e-05,
+      "loss": 0.0514,
+      "step": 1180
+    },
+    {
+      "epoch": 11.972151898734177,
+      "grad_norm": 0.8802081942558289,
+      "learning_rate": 1.1121788786087285e-05,
+      "loss": 0.053,
+      "step": 1185
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1960,
+  "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": 4.077498297252577e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1188/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a436d9e507a65e167f35408ec1bb674e772877bdfffc477144f5ecc24f0321
+size 7608

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1188/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)

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1287/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

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1287/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": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1287/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2be28fcaf4ed9f67e69aac4107a233e3a2efb92a9894547597893d27b2a5c491
+size 671150064

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1287/latest

@@ -0,0 +1 @@
+global_step1283

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1287/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e49c4597d71ddc36eed0bc52f68877bb0f34e85116f35fb9bc3f2b5a4fb8bded
+size 14960

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1287/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ed107f0c912ba70302f5aceaddc64821853d479f8b38cb8240b62e8e45bf12
+size 14960

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1287/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41f584844843d3ff566e3cb7cf5caaae2bf5b0e447e893de4386d3e67578f87f
+size 14960

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1287/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e83ee19247eac1dab2f0c5ef96b4d580c45c3da80fc2ce56d3fff0658a52f1c
+size 14960

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1287/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d89b1f1508b75a92e8a519412eace2ed98f64e6faca5a6f3e6c844e3b0507d0
+size 1064

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1287/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|>"
+}

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1287/tokenizer.json

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

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1287/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"
+}

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1287/trainer_state.json

@@ -0,0 +1,1833 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 13.0,
+  "eval_steps": 500,
+  "global_step": 1287,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05063291139240506,
+      "grad_norm": 3.4980525970458984,
+      "learning_rate": 1.2244897959183673e-06,
+      "loss": 1.6467,
+      "step": 5
+    },
+    {
+      "epoch": 0.10126582278481013,
+      "grad_norm": 2.9643654823303223,
+      "learning_rate": 2.7551020408163266e-06,
+      "loss": 1.6536,
+      "step": 10
+    },
+    {
+      "epoch": 0.1518987341772152,
+      "grad_norm": 2.9791953563690186,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 1.666,
+      "step": 15
+    },
+    {
+      "epoch": 0.20253164556962025,
+      "grad_norm": 2.6827096939086914,
+      "learning_rate": 5.816326530612245e-06,
+      "loss": 1.5566,
+      "step": 20
+    },
+    {
+      "epoch": 0.25316455696202533,
+      "grad_norm": 2.3671700954437256,
+      "learning_rate": 7.346938775510204e-06,
+      "loss": 1.5781,
+      "step": 25
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 3.708879232406616,
+      "learning_rate": 8.877551020408163e-06,
+      "loss": 1.5619,
+      "step": 30
+    },
+    {
+      "epoch": 0.35443037974683544,
+      "grad_norm": 2.66953706741333,
+      "learning_rate": 1.0408163265306123e-05,
+      "loss": 1.4739,
+      "step": 35
+    },
+    {
+      "epoch": 0.4050632911392405,
+      "grad_norm": 3.1258773803710938,
+      "learning_rate": 1.1938775510204082e-05,
+      "loss": 1.4944,
+      "step": 40
+    },
+    {
+      "epoch": 0.45569620253164556,
+      "grad_norm": 2.905057907104492,
+      "learning_rate": 1.3469387755102042e-05,
+      "loss": 1.3855,
+      "step": 45
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "grad_norm": 2.4417102336883545,
+      "learning_rate": 1.5e-05,
+      "loss": 1.3961,
+      "step": 50
+    },
+    {
+      "epoch": 0.5569620253164557,
+      "grad_norm": 2.6814239025115967,
+      "learning_rate": 1.6530612244897957e-05,
+      "loss": 1.2905,
+      "step": 55
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 3.3076088428497314,
+      "learning_rate": 1.806122448979592e-05,
+      "loss": 1.2598,
+      "step": 60
+    },
+    {
+      "epoch": 0.6582278481012658,
+      "grad_norm": 2.7890193462371826,
+      "learning_rate": 1.9591836734693877e-05,
+      "loss": 1.2,
+      "step": 65
+    },
+    {
+      "epoch": 0.7088607594936709,
+      "grad_norm": 2.4030416011810303,
+      "learning_rate": 2.1122448979591836e-05,
+      "loss": 1.2148,
+      "step": 70
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 2.4205846786499023,
+      "learning_rate": 2.2653061224489794e-05,
+      "loss": 1.2163,
+      "step": 75
+    },
+    {
+      "epoch": 0.810126582278481,
+      "grad_norm": 2.9943370819091797,
+      "learning_rate": 2.4183673469387756e-05,
+      "loss": 1.1494,
+      "step": 80
+    },
+    {
+      "epoch": 0.8607594936708861,
+      "grad_norm": 2.5231359004974365,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 1.1404,
+      "step": 85
+    },
+    {
+      "epoch": 0.9113924050632911,
+      "grad_norm": 3.446718692779541,
+      "learning_rate": 2.7244897959183673e-05,
+      "loss": 1.0815,
+      "step": 90
+    },
+    {
+      "epoch": 0.9620253164556962,
+      "grad_norm": 3.4152660369873047,
+      "learning_rate": 2.877551020408163e-05,
+      "loss": 1.0733,
+      "step": 95
+    },
+    {
+      "epoch": 1.010126582278481,
+      "grad_norm": 4.289358615875244,
+      "learning_rate": 2.9999978649819432e-05,
+      "loss": 1.0755,
+      "step": 100
+    },
+    {
+      "epoch": 1.0607594936708862,
+      "grad_norm": 3.5033681392669678,
+      "learning_rate": 2.999923139988104e-05,
+      "loss": 1.0308,
+      "step": 105
+    },
+    {
+      "epoch": 1.111392405063291,
+      "grad_norm": 3.502793788909912,
+      "learning_rate": 2.9997416701690675e-05,
+      "loss": 0.9201,
+      "step": 110
+    },
+    {
+      "epoch": 1.1620253164556962,
+      "grad_norm": 2.977989912033081,
+      "learning_rate": 2.999453468439471e-05,
+      "loss": 0.9366,
+      "step": 115
+    },
+    {
+      "epoch": 1.2126582278481013,
+      "grad_norm": 3.385281801223755,
+      "learning_rate": 2.9990585553097278e-05,
+      "loss": 0.873,
+      "step": 120
+    },
+    {
+      "epoch": 1.2632911392405064,
+      "grad_norm": 3.4536044597625732,
+      "learning_rate": 2.9985569588845665e-05,
+      "loss": 0.9513,
+      "step": 125
+    },
+    {
+      "epoch": 1.3139240506329113,
+      "grad_norm": 3.455348253250122,
+      "learning_rate": 2.9979487148610315e-05,
+      "loss": 0.9035,
+      "step": 130
+    },
+    {
+      "epoch": 1.3645569620253164,
+      "grad_norm": 3.171076774597168,
+      "learning_rate": 2.997233866525942e-05,
+      "loss": 0.8489,
+      "step": 135
+    },
+    {
+      "epoch": 1.4151898734177215,
+      "grad_norm": 3.0069353580474854,
+      "learning_rate": 2.996412464752812e-05,
+      "loss": 0.8202,
+      "step": 140
+    },
+    {
+      "epoch": 1.4658227848101266,
+      "grad_norm": 2.801588296890259,
+      "learning_rate": 2.995484567998229e-05,
+      "loss": 0.7959,
+      "step": 145
+    },
+    {
+      "epoch": 1.5164556962025317,
+      "grad_norm": 2.8108527660369873,
+      "learning_rate": 2.994450242297695e-05,
+      "loss": 0.7332,
+      "step": 150
+    },
+    {
+      "epoch": 1.5670886075949366,
+      "grad_norm": 3.3879706859588623,
+      "learning_rate": 2.9933095612609253e-05,
+      "loss": 0.7345,
+      "step": 155
+    },
+    {
+      "epoch": 1.6177215189873417,
+      "grad_norm": 3.4273533821105957,
+      "learning_rate": 2.992062606066612e-05,
+      "loss": 0.7658,
+      "step": 160
+    },
+    {
+      "epoch": 1.6683544303797468,
+      "grad_norm": 4.3649444580078125,
+      "learning_rate": 2.9907094654566445e-05,
+      "loss": 0.7349,
+      "step": 165
+    },
+    {
+      "epoch": 1.7189873417721517,
+      "grad_norm": 3.840703248977661,
+      "learning_rate": 2.989250235729796e-05,
+      "loss": 0.6883,
+      "step": 170
+    },
+    {
+      "epoch": 1.769620253164557,
+      "grad_norm": 3.321861743927002,
+      "learning_rate": 2.987685020734869e-05,
+      "loss": 0.6445,
+      "step": 175
+    },
+    {
+      "epoch": 1.820253164556962,
+      "grad_norm": 4.948067665100098,
+      "learning_rate": 2.986013931863306e-05,
+      "loss": 0.6853,
+      "step": 180
+    },
+    {
+      "epoch": 1.870886075949367,
+      "grad_norm": 3.2912204265594482,
+      "learning_rate": 2.984237088041259e-05,
+      "loss": 0.6809,
+      "step": 185
+    },
+    {
+      "epoch": 1.9215189873417722,
+      "grad_norm": 3.854374647140503,
+      "learning_rate": 2.9823546157211303e-05,
+      "loss": 0.6823,
+      "step": 190
+    },
+    {
+      "epoch": 1.972151898734177,
+      "grad_norm": 3.8937790393829346,
+      "learning_rate": 2.980366648872571e-05,
+      "loss": 0.6421,
+      "step": 195
+    },
+    {
+      "epoch": 2.020253164556962,
+      "grad_norm": 3.1727030277252197,
+      "learning_rate": 2.9782733289729448e-05,
+      "loss": 0.5468,
+      "step": 200
+    },
+    {
+      "epoch": 2.070886075949367,
+      "grad_norm": 3.526210308074951,
+      "learning_rate": 2.9760748049972646e-05,
+      "loss": 0.5887,
+      "step": 205
+    },
+    {
+      "epoch": 2.1215189873417724,
+      "grad_norm": 2.802851915359497,
+      "learning_rate": 2.9737712334075847e-05,
+      "loss": 0.5184,
+      "step": 210
+    },
+    {
+      "epoch": 2.1721518987341772,
+      "grad_norm": 4.610970497131348,
+      "learning_rate": 2.97136277814187e-05,
+      "loss": 0.5158,
+      "step": 215
+    },
+    {
+      "epoch": 2.222784810126582,
+      "grad_norm": 3.258543014526367,
+      "learning_rate": 2.9688496106023274e-05,
+      "loss": 0.5302,
+      "step": 220
+    },
+    {
+      "epoch": 2.2734177215189875,
+      "grad_norm": 3.7272274494171143,
+      "learning_rate": 2.966231909643208e-05,
+      "loss": 0.4942,
+      "step": 225
+    },
+    {
+      "epoch": 2.3240506329113924,
+      "grad_norm": 3.0091631412506104,
+      "learning_rate": 2.9635098615580783e-05,
+      "loss": 0.4892,
+      "step": 230
+    },
+    {
+      "epoch": 2.3746835443037977,
+      "grad_norm": 3.477494716644287,
+      "learning_rate": 2.960683660066562e-05,
+      "loss": 0.4488,
+      "step": 235
+    },
+    {
+      "epoch": 2.4253164556962026,
+      "grad_norm": 2.9678242206573486,
+      "learning_rate": 2.9577535063005555e-05,
+      "loss": 0.439,
+      "step": 240
+    },
+    {
+      "epoch": 2.4759493670886075,
+      "grad_norm": 4.674062728881836,
+      "learning_rate": 2.9547196087899116e-05,
+      "loss": 0.4748,
+      "step": 245
+    },
+    {
+      "epoch": 2.526582278481013,
+      "grad_norm": 3.2280211448669434,
+      "learning_rate": 2.9515821834475986e-05,
+      "loss": 0.4618,
+      "step": 250
+    },
+    {
+      "epoch": 2.5772151898734177,
+      "grad_norm": 4.220160484313965,
+      "learning_rate": 2.9483414535543386e-05,
+      "loss": 0.423,
+      "step": 255
+    },
+    {
+      "epoch": 2.6278481012658226,
+      "grad_norm": 3.365264415740967,
+      "learning_rate": 2.9449976497427127e-05,
+      "loss": 0.3989,
+      "step": 260
+    },
+    {
+      "epoch": 2.678481012658228,
+      "grad_norm": 3.159595251083374,
+      "learning_rate": 2.94155100998075e-05,
+      "loss": 0.4103,
+      "step": 265
+    },
+    {
+      "epoch": 2.729113924050633,
+      "grad_norm": 3.472161293029785,
+      "learning_rate": 2.938001779554991e-05,
+      "loss": 0.4164,
+      "step": 270
+    },
+    {
+      "epoch": 2.779746835443038,
+      "grad_norm": 3.7458016872406006,
+      "learning_rate": 2.9343502110530332e-05,
+      "loss": 0.3774,
+      "step": 275
+    },
+    {
+      "epoch": 2.830379746835443,
+      "grad_norm": 3.9665720462799072,
+      "learning_rate": 2.930596564345554e-05,
+      "loss": 0.3615,
+      "step": 280
+    },
+    {
+      "epoch": 2.8810126582278484,
+      "grad_norm": 3.497344732284546,
+      "learning_rate": 2.9267411065678146e-05,
+      "loss": 0.3737,
+      "step": 285
+    },
+    {
+      "epoch": 2.9316455696202532,
+      "grad_norm": 3.826024293899536,
+      "learning_rate": 2.9227841121006524e-05,
+      "loss": 0.3397,
+      "step": 290
+    },
+    {
+      "epoch": 2.982278481012658,
+      "grad_norm": 3.507917881011963,
+      "learning_rate": 2.9187258625509518e-05,
+      "loss": 0.3496,
+      "step": 295
+    },
+    {
+      "epoch": 3.030379746835443,
+      "grad_norm": 4.524459362030029,
+      "learning_rate": 2.914566646731605e-05,
+      "loss": 0.3471,
+      "step": 300
+    },
+    {
+      "epoch": 3.081012658227848,
+      "grad_norm": 3.779264211654663,
+      "learning_rate": 2.9103067606409555e-05,
+      "loss": 0.3081,
+      "step": 305
+    },
+    {
+      "epoch": 3.131645569620253,
+      "grad_norm": 3.9139416217803955,
+      "learning_rate": 2.9059465074417343e-05,
+      "loss": 0.3065,
+      "step": 310
+    },
+    {
+      "epoch": 3.1822784810126583,
+      "grad_norm": 3.71647310256958,
+      "learning_rate": 2.9014861974394856e-05,
+      "loss": 0.3024,
+      "step": 315
+    },
+    {
+      "epoch": 3.232911392405063,
+      "grad_norm": 3.003744125366211,
+      "learning_rate": 2.896926148060482e-05,
+      "loss": 0.2942,
+      "step": 320
+    },
+    {
+      "epoch": 3.2835443037974685,
+      "grad_norm": 4.5852251052856445,
+      "learning_rate": 2.892266683829135e-05,
+      "loss": 0.2626,
+      "step": 325
+    },
+    {
+      "epoch": 3.3341772151898734,
+      "grad_norm": 3.427046298980713,
+      "learning_rate": 2.887508136344899e-05,
+      "loss": 0.2565,
+      "step": 330
+    },
+    {
+      "epoch": 3.3848101265822783,
+      "grad_norm": 3.712449789047241,
+      "learning_rate": 2.882650844258672e-05,
+      "loss": 0.2455,
+      "step": 335
+    },
+    {
+      "epoch": 3.4354430379746836,
+      "grad_norm": 3.4680449962615967,
+      "learning_rate": 2.877695153248697e-05,
+      "loss": 0.2485,
+      "step": 340
+    },
+    {
+      "epoch": 3.4860759493670885,
+      "grad_norm": 3.1136488914489746,
+      "learning_rate": 2.8726414159959585e-05,
+      "loss": 0.2724,
+      "step": 345
+    },
+    {
+      "epoch": 3.536708860759494,
+      "grad_norm": 3.908705234527588,
+      "learning_rate": 2.867489992159086e-05,
+      "loss": 0.2657,
+      "step": 350
+    },
+    {
+      "epoch": 3.5873417721518988,
+      "grad_norm": 4.278017044067383,
+      "learning_rate": 2.8622412483487553e-05,
+      "loss": 0.2669,
+      "step": 355
+    },
+    {
+      "epoch": 3.6379746835443036,
+      "grad_norm": 3.4697976112365723,
+      "learning_rate": 2.8568955581016003e-05,
+      "loss": 0.2427,
+      "step": 360
+    },
+    {
+      "epoch": 3.688607594936709,
+      "grad_norm": 3.08229398727417,
+      "learning_rate": 2.8514533018536286e-05,
+      "loss": 0.2494,
+      "step": 365
+    },
+    {
+      "epoch": 3.739240506329114,
+      "grad_norm": 3.35378098487854,
+      "learning_rate": 2.8459148669131476e-05,
+      "loss": 0.2383,
+      "step": 370
+    },
+    {
+      "epoch": 3.7898734177215188,
+      "grad_norm": 3.133762836456299,
+      "learning_rate": 2.8402806474331994e-05,
+      "loss": 0.2387,
+      "step": 375
+    },
+    {
+      "epoch": 3.840506329113924,
+      "grad_norm": 3.7151851654052734,
+      "learning_rate": 2.8345510443835116e-05,
+      "loss": 0.2373,
+      "step": 380
+    },
+    {
+      "epoch": 3.891139240506329,
+      "grad_norm": 3.03208327293396,
+      "learning_rate": 2.828726465521963e-05,
+      "loss": 0.2159,
+      "step": 385
+    },
+    {
+      "epoch": 3.9417721518987343,
+      "grad_norm": 3.15083646774292,
+      "learning_rate": 2.8228073253655608e-05,
+      "loss": 0.2152,
+      "step": 390
+    },
+    {
+      "epoch": 3.992405063291139,
+      "grad_norm": 3.210649013519287,
+      "learning_rate": 2.8167940451609444e-05,
+      "loss": 0.2213,
+      "step": 395
+    },
+    {
+      "epoch": 4.040506329113924,
+      "grad_norm": 3.083118200302124,
+      "learning_rate": 2.8106870528544044e-05,
+      "loss": 0.1842,
+      "step": 400
+    },
+    {
+      "epoch": 4.091139240506329,
+      "grad_norm": 3.1503756046295166,
+      "learning_rate": 2.804486783061428e-05,
+      "loss": 0.1861,
+      "step": 405
+    },
+    {
+      "epoch": 4.141772151898734,
+      "grad_norm": 2.813202381134033,
+      "learning_rate": 2.798193677035768e-05,
+      "loss": 0.1755,
+      "step": 410
+    },
+    {
+      "epoch": 4.192405063291139,
+      "grad_norm": 3.875789165496826,
+      "learning_rate": 2.7918081826380428e-05,
+      "loss": 0.1762,
+      "step": 415
+    },
+    {
+      "epoch": 4.243037974683545,
+      "grad_norm": 3.8627779483795166,
+      "learning_rate": 2.785330754303858e-05,
+      "loss": 0.1723,
+      "step": 420
+    },
+    {
+      "epoch": 4.293670886075949,
+      "grad_norm": 2.6941754817962646,
+      "learning_rate": 2.7787618530114724e-05,
+      "loss": 0.1606,
+      "step": 425
+    },
+    {
+      "epoch": 4.3443037974683545,
+      "grad_norm": 3.605570077896118,
+      "learning_rate": 2.7721019462489862e-05,
+      "loss": 0.17,
+      "step": 430
+    },
+    {
+      "epoch": 4.39493670886076,
+      "grad_norm": 2.771569013595581,
+      "learning_rate": 2.7653515079810744e-05,
+      "loss": 0.1738,
+      "step": 435
+    },
+    {
+      "epoch": 4.445569620253164,
+      "grad_norm": 3.381185531616211,
+      "learning_rate": 2.758511018615254e-05,
+      "loss": 0.1645,
+      "step": 440
+    },
+    {
+      "epoch": 4.49620253164557,
+      "grad_norm": 2.929736375808716,
+      "learning_rate": 2.751580964967699e-05,
+      "loss": 0.1758,
+      "step": 445
+    },
+    {
+      "epoch": 4.546835443037975,
+      "grad_norm": 4.251176357269287,
+      "learning_rate": 2.7445618402285894e-05,
+      "loss": 0.1675,
+      "step": 450
+    },
+    {
+      "epoch": 4.597468354430379,
+      "grad_norm": 3.2119245529174805,
+      "learning_rate": 2.7374541439270174e-05,
+      "loss": 0.1662,
+      "step": 455
+    },
+    {
+      "epoch": 4.648101265822785,
+      "grad_norm": 3.273690700531006,
+      "learning_rate": 2.730258381895434e-05,
+      "loss": 0.1649,
+      "step": 460
+    },
+    {
+      "epoch": 4.69873417721519,
+      "grad_norm": 2.8210129737854004,
+      "learning_rate": 2.722975066233653e-05,
+      "loss": 0.1471,
+      "step": 465
+    },
+    {
+      "epoch": 4.749367088607595,
+      "grad_norm": 3.1151881217956543,
+      "learning_rate": 2.7156047152724046e-05,
+      "loss": 0.1519,
+      "step": 470
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 3.13199782371521,
+      "learning_rate": 2.7081478535364496e-05,
+      "loss": 0.1537,
+      "step": 475
+    },
+    {
+      "epoch": 4.850632911392405,
+      "grad_norm": 2.7968389987945557,
+      "learning_rate": 2.700605011707248e-05,
+      "loss": 0.1447,
+      "step": 480
+    },
+    {
+      "epoch": 4.9012658227848105,
+      "grad_norm": 3.166747570037842,
+      "learning_rate": 2.692976726585194e-05,
+      "loss": 0.1426,
+      "step": 485
+    },
+    {
+      "epoch": 4.951898734177215,
+      "grad_norm": 3.1832809448242188,
+      "learning_rate": 2.6852635410514125e-05,
+      "loss": 0.1386,
+      "step": 490
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.532459735870361,
+      "learning_rate": 2.6774660040291257e-05,
+      "loss": 0.1481,
+      "step": 495
+    },
+    {
+      "epoch": 5.050632911392405,
+      "grad_norm": 2.8513097763061523,
+      "learning_rate": 2.6695846704445842e-05,
+      "loss": 0.1118,
+      "step": 500
+    },
+    {
+      "epoch": 5.10126582278481,
+      "grad_norm": 2.8358778953552246,
+      "learning_rate": 2.6616201011875792e-05,
+      "loss": 0.1259,
+      "step": 505
+    },
+    {
+      "epoch": 5.151898734177215,
+      "grad_norm": 2.5484566688537598,
+      "learning_rate": 2.6535728630715228e-05,
+      "loss": 0.1108,
+      "step": 510
+    },
+    {
+      "epoch": 5.2025316455696204,
+      "grad_norm": 2.7051589488983154,
+      "learning_rate": 2.645443528793111e-05,
+      "loss": 0.1196,
+      "step": 515
+    },
+    {
+      "epoch": 5.253164556962025,
+      "grad_norm": 2.469198226928711,
+      "learning_rate": 2.6372326768915658e-05,
+      "loss": 0.1255,
+      "step": 520
+    },
+    {
+      "epoch": 5.30379746835443,
+      "grad_norm": 2.5851681232452393,
+      "learning_rate": 2.628940891707462e-05,
+      "loss": 0.1204,
+      "step": 525
+    },
+    {
+      "epoch": 5.3544303797468356,
+      "grad_norm": 2.605705499649048,
+      "learning_rate": 2.6205687633411445e-05,
+      "loss": 0.1127,
+      "step": 530
+    },
+    {
+      "epoch": 5.405063291139241,
+      "grad_norm": 2.959566593170166,
+      "learning_rate": 2.6121168876107274e-05,
+      "loss": 0.1158,
+      "step": 535
+    },
+    {
+      "epoch": 5.455696202531645,
+      "grad_norm": 2.3968331813812256,
+      "learning_rate": 2.6035858660096975e-05,
+      "loss": 0.1249,
+      "step": 540
+    },
+    {
+      "epoch": 5.506329113924051,
+      "grad_norm": 4.327753067016602,
+      "learning_rate": 2.594976305664103e-05,
+      "loss": 0.1169,
+      "step": 545
+    },
+    {
+      "epoch": 5.556962025316456,
+      "grad_norm": 2.5143179893493652,
+      "learning_rate": 2.586288819289349e-05,
+      "loss": 0.1149,
+      "step": 550
+    },
+    {
+      "epoch": 5.6075949367088604,
+      "grad_norm": 2.9387834072113037,
+      "learning_rate": 2.5775240251465914e-05,
+      "loss": 0.1173,
+      "step": 555
+    },
+    {
+      "epoch": 5.658227848101266,
+      "grad_norm": 2.727640390396118,
+      "learning_rate": 2.568682546998738e-05,
+      "loss": 0.1069,
+      "step": 560
+    },
+    {
+      "epoch": 5.708860759493671,
+      "grad_norm": 2.930460214614868,
+      "learning_rate": 2.5597650140660555e-05,
+      "loss": 0.1096,
+      "step": 565
+    },
+    {
+      "epoch": 5.759493670886076,
+      "grad_norm": 2.747501850128174,
+      "learning_rate": 2.5507720609813928e-05,
+      "loss": 0.105,
+      "step": 570
+    },
+    {
+      "epoch": 5.810126582278481,
+      "grad_norm": 2.5990662574768066,
+      "learning_rate": 2.541704327745013e-05,
+      "loss": 0.1147,
+      "step": 575
+    },
+    {
+      "epoch": 5.860759493670886,
+      "grad_norm": 2.7866060733795166,
+      "learning_rate": 2.5325624596790486e-05,
+      "loss": 0.1134,
+      "step": 580
+    },
+    {
+      "epoch": 5.911392405063291,
+      "grad_norm": 2.9491360187530518,
+      "learning_rate": 2.523347107381576e-05,
+      "loss": 0.1039,
+      "step": 585
+    },
+    {
+      "epoch": 5.962025316455696,
+      "grad_norm": 2.775834321975708,
+      "learning_rate": 2.514058926680312e-05,
+      "loss": 0.109,
+      "step": 590
+    },
+    {
+      "epoch": 6.010126582278481,
+      "grad_norm": 3.1889455318450928,
+      "learning_rate": 2.5046985785859453e-05,
+      "loss": 0.1048,
+      "step": 595
+    },
+    {
+      "epoch": 6.060759493670886,
+      "grad_norm": 2.762517213821411,
+      "learning_rate": 2.4952667292450887e-05,
+      "loss": 0.0884,
+      "step": 600
+    },
+    {
+      "epoch": 6.111392405063291,
+      "grad_norm": 1.801896095275879,
+      "learning_rate": 2.4857640498928756e-05,
+      "loss": 0.0907,
+      "step": 605
+    },
+    {
+      "epoch": 6.162025316455696,
+      "grad_norm": 2.1080682277679443,
+      "learning_rate": 2.4761912168051903e-05,
+      "loss": 0.0892,
+      "step": 610
+    },
+    {
+      "epoch": 6.2126582278481015,
+      "grad_norm": 2.79091215133667,
+      "learning_rate": 2.4665489112505372e-05,
+      "loss": 0.0936,
+      "step": 615
+    },
+    {
+      "epoch": 6.263291139240506,
+      "grad_norm": 2.5198278427124023,
+      "learning_rate": 2.4568378194415583e-05,
+      "loss": 0.0973,
+      "step": 620
+    },
+    {
+      "epoch": 6.313924050632911,
+      "grad_norm": 2.038583278656006,
+      "learning_rate": 2.447058632486197e-05,
+      "loss": 0.0915,
+      "step": 625
+    },
+    {
+      "epoch": 6.364556962025317,
+      "grad_norm": 3.310605049133301,
+      "learning_rate": 2.4372120463385167e-05,
+      "loss": 0.0936,
+      "step": 630
+    },
+    {
+      "epoch": 6.415189873417722,
+      "grad_norm": 2.2550792694091797,
+      "learning_rate": 2.427298761749168e-05,
+      "loss": 0.1016,
+      "step": 635
+    },
+    {
+      "epoch": 6.465822784810126,
+      "grad_norm": 2.7243216037750244,
+      "learning_rate": 2.4173194842155208e-05,
+      "loss": 0.0888,
+      "step": 640
+    },
+    {
+      "epoch": 6.516455696202532,
+      "grad_norm": 2.442253351211548,
+      "learning_rate": 2.4072749239314565e-05,
+      "loss": 0.0901,
+      "step": 645
+    },
+    {
+      "epoch": 6.567088607594937,
+      "grad_norm": 2.2244441509246826,
+      "learning_rate": 2.397165795736824e-05,
+      "loss": 0.0919,
+      "step": 650
+    },
+    {
+      "epoch": 6.6177215189873415,
+      "grad_norm": 2.14775013923645,
+      "learning_rate": 2.386992819066569e-05,
+      "loss": 0.0903,
+      "step": 655
+    },
+    {
+      "epoch": 6.668354430379747,
+      "grad_norm": 2.5285158157348633,
+      "learning_rate": 2.3767567178995323e-05,
+      "loss": 0.0899,
+      "step": 660
+    },
+    {
+      "epoch": 6.718987341772152,
+      "grad_norm": 2.9994752407073975,
+      "learning_rate": 2.366458220706928e-05,
+      "loss": 0.095,
+      "step": 665
+    },
+    {
+      "epoch": 6.769620253164557,
+      "grad_norm": 2.355753183364868,
+      "learning_rate": 2.3560980604004977e-05,
+      "loss": 0.0866,
+      "step": 670
+    },
+    {
+      "epoch": 6.820253164556962,
+      "grad_norm": 2.467966318130493,
+      "learning_rate": 2.345676974280355e-05,
+      "loss": 0.0841,
+      "step": 675
+    },
+    {
+      "epoch": 6.870886075949367,
+      "grad_norm": 2.32102632522583,
+      "learning_rate": 2.335195703982513e-05,
+      "loss": 0.0879,
+      "step": 680
+    },
+    {
+      "epoch": 6.921518987341772,
+      "grad_norm": 2.34090518951416,
+      "learning_rate": 2.324654995426102e-05,
+      "loss": 0.0892,
+      "step": 685
+    },
+    {
+      "epoch": 6.972151898734177,
+      "grad_norm": 2.4923956394195557,
+      "learning_rate": 2.3140555987602886e-05,
+      "loss": 0.0861,
+      "step": 690
+    },
+    {
+      "epoch": 7.020253164556962,
+      "grad_norm": 2.2103333473205566,
+      "learning_rate": 2.3033982683108867e-05,
+      "loss": 0.0792,
+      "step": 695
+    },
+    {
+      "epoch": 7.0708860759493675,
+      "grad_norm": 2.5478057861328125,
+      "learning_rate": 2.2926837625266776e-05,
+      "loss": 0.074,
+      "step": 700
+    },
+    {
+      "epoch": 7.121518987341772,
+      "grad_norm": 2.4020633697509766,
+      "learning_rate": 2.281912843925429e-05,
+      "loss": 0.0729,
+      "step": 705
+    },
+    {
+      "epoch": 7.172151898734177,
+      "grad_norm": 1.8848402500152588,
+      "learning_rate": 2.2710862790396353e-05,
+      "loss": 0.0707,
+      "step": 710
+    },
+    {
+      "epoch": 7.222784810126583,
+      "grad_norm": 2.636121988296509,
+      "learning_rate": 2.26020483836196e-05,
+      "loss": 0.0847,
+      "step": 715
+    },
+    {
+      "epoch": 7.273417721518987,
+      "grad_norm": 2.489856719970703,
+      "learning_rate": 2.249269296290405e-05,
+      "loss": 0.0789,
+      "step": 720
+    },
+    {
+      "epoch": 7.324050632911392,
+      "grad_norm": 2.441281795501709,
+      "learning_rate": 2.238280431073199e-05,
+      "loss": 0.0815,
+      "step": 725
+    },
+    {
+      "epoch": 7.374683544303798,
+      "grad_norm": 2.4158310890197754,
+      "learning_rate": 2.2272390247534127e-05,
+      "loss": 0.0767,
+      "step": 730
+    },
+    {
+      "epoch": 7.425316455696202,
+      "grad_norm": 1.5769174098968506,
+      "learning_rate": 2.2161458631133e-05,
+      "loss": 0.0758,
+      "step": 735
+    },
+    {
+      "epoch": 7.4759493670886075,
+      "grad_norm": 2.136112928390503,
+      "learning_rate": 2.2050017356183806e-05,
+      "loss": 0.0805,
+      "step": 740
+    },
+    {
+      "epoch": 7.526582278481013,
+      "grad_norm": 2.3461337089538574,
+      "learning_rate": 2.1938074353612533e-05,
+      "loss": 0.0831,
+      "step": 745
+    },
+    {
+      "epoch": 7.577215189873417,
+      "grad_norm": 2.017784833908081,
+      "learning_rate": 2.182563759005155e-05,
+      "loss": 0.0769,
+      "step": 750
+    },
+    {
+      "epoch": 7.627848101265823,
+      "grad_norm": 1.7009460926055908,
+      "learning_rate": 2.1712715067272655e-05,
+      "loss": 0.0743,
+      "step": 755
+    },
+    {
+      "epoch": 7.678481012658228,
+      "grad_norm": 1.948912262916565,
+      "learning_rate": 2.1599314821617598e-05,
+      "loss": 0.0769,
+      "step": 760
+    },
+    {
+      "epoch": 7.729113924050633,
+      "grad_norm": 1.9673391580581665,
+      "learning_rate": 2.1485444923426167e-05,
+      "loss": 0.081,
+      "step": 765
+    },
+    {
+      "epoch": 7.779746835443038,
+      "grad_norm": 2.3732705116271973,
+      "learning_rate": 2.1371113476461855e-05,
+      "loss": 0.0773,
+      "step": 770
+    },
+    {
+      "epoch": 7.830379746835443,
+      "grad_norm": 1.866337776184082,
+      "learning_rate": 2.1256328617335124e-05,
+      "loss": 0.0759,
+      "step": 775
+    },
+    {
+      "epoch": 7.881012658227848,
+      "grad_norm": 2.141129970550537,
+      "learning_rate": 2.1141098514924367e-05,
+      "loss": 0.0733,
+      "step": 780
+    },
+    {
+      "epoch": 7.931645569620253,
+      "grad_norm": 2.2540833950042725,
+      "learning_rate": 2.1025431369794546e-05,
+      "loss": 0.0749,
+      "step": 785
+    },
+    {
+      "epoch": 7.982278481012658,
+      "grad_norm": 1.980592966079712,
+      "learning_rate": 2.0909335413613563e-05,
+      "loss": 0.0717,
+      "step": 790
+    },
+    {
+      "epoch": 8.030379746835443,
+      "grad_norm": 2.3790063858032227,
+      "learning_rate": 2.079281890856648e-05,
+      "loss": 0.071,
+      "step": 795
+    },
+    {
+      "epoch": 8.081012658227849,
+      "grad_norm": 1.9786341190338135,
+      "learning_rate": 2.067589014676749e-05,
+      "loss": 0.0671,
+      "step": 800
+    },
+    {
+      "epoch": 8.131645569620254,
+      "grad_norm": 1.850415825843811,
+      "learning_rate": 2.0558557449669818e-05,
+      "loss": 0.0706,
+      "step": 805
+    },
+    {
+      "epoch": 8.182278481012657,
+      "grad_norm": 1.740311622619629,
+      "learning_rate": 2.0440829167473486e-05,
+      "loss": 0.0696,
+      "step": 810
+    },
+    {
+      "epoch": 8.232911392405063,
+      "grad_norm": 1.6912726163864136,
+      "learning_rate": 2.0322713678531067e-05,
+      "loss": 0.0737,
+      "step": 815
+    },
+    {
+      "epoch": 8.283544303797468,
+      "grad_norm": 1.9001421928405762,
+      "learning_rate": 2.020421938875143e-05,
+      "loss": 0.0662,
+      "step": 820
+    },
+    {
+      "epoch": 8.334177215189873,
+      "grad_norm": 1.8828890323638916,
+      "learning_rate": 2.0085354731001502e-05,
+      "loss": 0.0703,
+      "step": 825
+    },
+    {
+      "epoch": 8.384810126582279,
+      "grad_norm": 1.4946229457855225,
+      "learning_rate": 1.9966128164506153e-05,
+      "loss": 0.0691,
+      "step": 830
+    },
+    {
+      "epoch": 8.435443037974684,
+      "grad_norm": 2.7881011962890625,
+      "learning_rate": 1.9846548174246144e-05,
+      "loss": 0.0727,
+      "step": 835
+    },
+    {
+      "epoch": 8.48607594936709,
+      "grad_norm": 1.8071367740631104,
+      "learning_rate": 1.9726623270354314e-05,
+      "loss": 0.0657,
+      "step": 840
+    },
+    {
+      "epoch": 8.536708860759493,
+      "grad_norm": 1.4970042705535889,
+      "learning_rate": 1.9606361987509905e-05,
+      "loss": 0.0698,
+      "step": 845
+    },
+    {
+      "epoch": 8.587341772151898,
+      "grad_norm": 1.7957663536071777,
+      "learning_rate": 1.9485772884331215e-05,
+      "loss": 0.0698,
+      "step": 850
+    },
+    {
+      "epoch": 8.637974683544304,
+      "grad_norm": 1.6136796474456787,
+      "learning_rate": 1.936486454276647e-05,
+      "loss": 0.0716,
+      "step": 855
+    },
+    {
+      "epoch": 8.688607594936709,
+      "grad_norm": 1.5621618032455444,
+      "learning_rate": 1.9243645567483096e-05,
+      "loss": 0.0675,
+      "step": 860
+    },
+    {
+      "epoch": 8.739240506329114,
+      "grad_norm": 1.7963391542434692,
+      "learning_rate": 1.9122124585255348e-05,
+      "loss": 0.0681,
+      "step": 865
+    },
+    {
+      "epoch": 8.78987341772152,
+      "grad_norm": 2.201146364212036,
+      "learning_rate": 1.900031024435037e-05,
+      "loss": 0.0717,
+      "step": 870
+    },
+    {
+      "epoch": 8.840506329113925,
+      "grad_norm": 1.4939143657684326,
+      "learning_rate": 1.887821121391272e-05,
+      "loss": 0.0713,
+      "step": 875
+    },
+    {
+      "epoch": 8.891139240506329,
+      "grad_norm": 1.4898556470870972,
+      "learning_rate": 1.8755836183347416e-05,
+      "loss": 0.0646,
+      "step": 880
+    },
+    {
+      "epoch": 8.941772151898734,
+      "grad_norm": 1.6174167394638062,
+      "learning_rate": 1.863319386170154e-05,
+      "loss": 0.0645,
+      "step": 885
+    },
+    {
+      "epoch": 8.99240506329114,
+      "grad_norm": 1.5976531505584717,
+      "learning_rate": 1.8510292977044434e-05,
+      "loss": 0.0688,
+      "step": 890
+    },
+    {
+      "epoch": 9.040506329113924,
+      "grad_norm": 1.7708168029785156,
+      "learning_rate": 1.838714227584658e-05,
+      "loss": 0.0621,
+      "step": 895
+    },
+    {
+      "epoch": 9.09113924050633,
+      "grad_norm": 1.2461936473846436,
+      "learning_rate": 1.8263750522357107e-05,
+      "loss": 0.0583,
+      "step": 900
+    },
+    {
+      "epoch": 9.141772151898735,
+      "grad_norm": 1.1864615678787231,
+      "learning_rate": 1.814012649798007e-05,
+      "loss": 0.0614,
+      "step": 905
+    },
+    {
+      "epoch": 9.192405063291138,
+      "grad_norm": 1.408365249633789,
+      "learning_rate": 1.8016279000649523e-05,
+      "loss": 0.0661,
+      "step": 910
+    },
+    {
+      "epoch": 9.243037974683544,
+      "grad_norm": 1.521738886833191,
+      "learning_rate": 1.7892216844203395e-05,
+      "loss": 0.0643,
+      "step": 915
+    },
+    {
+      "epoch": 9.29367088607595,
+      "grad_norm": 1.6638453006744385,
+      "learning_rate": 1.7767948857756226e-05,
+      "loss": 0.0653,
+      "step": 920
+    },
+    {
+      "epoch": 9.344303797468354,
+      "grad_norm": 1.9698224067687988,
+      "learning_rate": 1.7643483885070827e-05,
+      "loss": 0.0656,
+      "step": 925
+    },
+    {
+      "epoch": 9.39493670886076,
+      "grad_norm": 1.5151782035827637,
+      "learning_rate": 1.751883078392891e-05,
+      "loss": 0.0638,
+      "step": 930
+    },
+    {
+      "epoch": 9.445569620253165,
+      "grad_norm": 1.6791659593582153,
+      "learning_rate": 1.739399842550069e-05,
+      "loss": 0.0642,
+      "step": 935
+    },
+    {
+      "epoch": 9.496202531645569,
+      "grad_norm": 1.4712715148925781,
+      "learning_rate": 1.726899569371357e-05,
+      "loss": 0.0651,
+      "step": 940
+    },
+    {
+      "epoch": 9.546835443037974,
+      "grad_norm": 1.313909888267517,
+      "learning_rate": 1.7143831484619884e-05,
+      "loss": 0.0579,
+      "step": 945
+    },
+    {
+      "epoch": 9.59746835443038,
+      "grad_norm": 1.5802178382873535,
+      "learning_rate": 1.7018514705763804e-05,
+      "loss": 0.0655,
+      "step": 950
+    },
+    {
+      "epoch": 9.648101265822785,
+      "grad_norm": 1.674559473991394,
+      "learning_rate": 1.6893054275547407e-05,
+      "loss": 0.0633,
+      "step": 955
+    },
+    {
+      "epoch": 9.69873417721519,
+      "grad_norm": 2.3455135822296143,
+      "learning_rate": 1.6767459122595998e-05,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 9.749367088607595,
+      "grad_norm": 1.1516377925872803,
+      "learning_rate": 1.6641738185122663e-05,
+      "loss": 0.0585,
+      "step": 965
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": 1.211869478225708,
+      "learning_rate": 1.6515900410292188e-05,
+      "loss": 0.0684,
+      "step": 970
+    },
+    {
+      "epoch": 9.850632911392404,
+      "grad_norm": 1.3427664041519165,
+      "learning_rate": 1.6389954753584303e-05,
+      "loss": 0.0613,
+      "step": 975
+    },
+    {
+      "epoch": 9.90126582278481,
+      "grad_norm": 0.9951387643814087,
+      "learning_rate": 1.626391017815635e-05,
+      "loss": 0.071,
+      "step": 980
+    },
+    {
+      "epoch": 9.951898734177215,
+      "grad_norm": 2.0930867195129395,
+      "learning_rate": 1.6137775654205414e-05,
+      "loss": 0.0655,
+      "step": 985
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.7130424976348877,
+      "learning_rate": 1.601156015832993e-05,
+      "loss": 0.0622,
+      "step": 990
+    },
+    {
+      "epoch": 10.050632911392405,
+      "grad_norm": 1.5401997566223145,
+      "learning_rate": 1.5885272672890842e-05,
+      "loss": 0.0621,
+      "step": 995
+    },
+    {
+      "epoch": 10.10126582278481,
+      "grad_norm": 1.5477750301361084,
+      "learning_rate": 1.5758922185372387e-05,
+      "loss": 0.0574,
+      "step": 1000
+    },
+    {
+      "epoch": 10.151898734177216,
+      "grad_norm": 1.1239627599716187,
+      "learning_rate": 1.5632517687742438e-05,
+      "loss": 0.0599,
+      "step": 1005
+    },
+    {
+      "epoch": 10.20253164556962,
+      "grad_norm": 1.1288483142852783,
+      "learning_rate": 1.5506068175812618e-05,
+      "loss": 0.059,
+      "step": 1010
+    },
+    {
+      "epoch": 10.253164556962025,
+      "grad_norm": 1.120748519897461,
+      "learning_rate": 1.5379582648598056e-05,
+      "loss": 0.0602,
+      "step": 1015
+    },
+    {
+      "epoch": 10.30379746835443,
+      "grad_norm": 1.4478673934936523,
+      "learning_rate": 1.5253070107677006e-05,
+      "loss": 0.0609,
+      "step": 1020
+    },
+    {
+      "epoch": 10.354430379746836,
+      "grad_norm": 1.0375020503997803,
+      "learning_rate": 1.5126539556550172e-05,
+      "loss": 0.0593,
+      "step": 1025
+    },
+    {
+      "epoch": 10.405063291139241,
+      "grad_norm": 1.6543164253234863,
+      "learning_rate": 1.5e-05,
+      "loss": 0.0598,
+      "step": 1030
+    },
+    {
+      "epoch": 10.455696202531646,
+      "grad_norm": 1.5519331693649292,
+      "learning_rate": 1.4873460443449834e-05,
+      "loss": 0.0614,
+      "step": 1035
+    },
+    {
+      "epoch": 10.50632911392405,
+      "grad_norm": 1.8383262157440186,
+      "learning_rate": 1.4746929892322996e-05,
+      "loss": 0.0582,
+      "step": 1040
+    },
+    {
+      "epoch": 10.556962025316455,
+      "grad_norm": 1.509050726890564,
+      "learning_rate": 1.4620417351401945e-05,
+      "loss": 0.0646,
+      "step": 1045
+    },
+    {
+      "epoch": 10.60759493670886,
+      "grad_norm": 1.1060560941696167,
+      "learning_rate": 1.4493931824187385e-05,
+      "loss": 0.0577,
+      "step": 1050
+    },
+    {
+      "epoch": 10.658227848101266,
+      "grad_norm": 1.5542149543762207,
+      "learning_rate": 1.4367482312257564e-05,
+      "loss": 0.06,
+      "step": 1055
+    },
+    {
+      "epoch": 10.708860759493671,
+      "grad_norm": 0.8741584420204163,
+      "learning_rate": 1.4241077814627618e-05,
+      "loss": 0.0591,
+      "step": 1060
+    },
+    {
+      "epoch": 10.759493670886076,
+      "grad_norm": 1.3523668050765991,
+      "learning_rate": 1.411472732710916e-05,
+      "loss": 0.0582,
+      "step": 1065
+    },
+    {
+      "epoch": 10.810126582278482,
+      "grad_norm": 0.9250157475471497,
+      "learning_rate": 1.3988439841670075e-05,
+      "loss": 0.055,
+      "step": 1070
+    },
+    {
+      "epoch": 10.860759493670885,
+      "grad_norm": 1.4959791898727417,
+      "learning_rate": 1.3862224345794585e-05,
+      "loss": 0.0572,
+      "step": 1075
+    },
+    {
+      "epoch": 10.91139240506329,
+      "grad_norm": 1.737217664718628,
+      "learning_rate": 1.3736089821843653e-05,
+      "loss": 0.057,
+      "step": 1080
+    },
+    {
+      "epoch": 10.962025316455696,
+      "grad_norm": 1.0605052709579468,
+      "learning_rate": 1.3610045246415703e-05,
+      "loss": 0.0534,
+      "step": 1085
+    },
+    {
+      "epoch": 11.010126582278481,
+      "grad_norm": 1.4872320890426636,
+      "learning_rate": 1.3484099589707813e-05,
+      "loss": 0.0592,
+      "step": 1090
+    },
+    {
+      "epoch": 11.060759493670886,
+      "grad_norm": 1.0444155931472778,
+      "learning_rate": 1.335826181487734e-05,
+      "loss": 0.0568,
+      "step": 1095
+    },
+    {
+      "epoch": 11.111392405063292,
+      "grad_norm": 1.3047372102737427,
+      "learning_rate": 1.3232540877404e-05,
+      "loss": 0.0541,
+      "step": 1100
+    },
+    {
+      "epoch": 11.162025316455697,
+      "grad_norm": 1.697584867477417,
+      "learning_rate": 1.3106945724452592e-05,
+      "loss": 0.0569,
+      "step": 1105
+    },
+    {
+      "epoch": 11.2126582278481,
+      "grad_norm": 1.4648683071136475,
+      "learning_rate": 1.2981485294236201e-05,
+      "loss": 0.056,
+      "step": 1110
+    },
+    {
+      "epoch": 11.263291139240506,
+      "grad_norm": 0.8088081479072571,
+      "learning_rate": 1.2856168515380117e-05,
+      "loss": 0.0539,
+      "step": 1115
+    },
+    {
+      "epoch": 11.313924050632911,
+      "grad_norm": 1.1021257638931274,
+      "learning_rate": 1.2731004306286434e-05,
+      "loss": 0.0565,
+      "step": 1120
+    },
+    {
+      "epoch": 11.364556962025317,
+      "grad_norm": 1.3986896276474,
+      "learning_rate": 1.2606001574499316e-05,
+      "loss": 0.058,
+      "step": 1125
+    },
+    {
+      "epoch": 11.415189873417722,
+      "grad_norm": 0.8848942518234253,
+      "learning_rate": 1.2481169216071093e-05,
+      "loss": 0.0564,
+      "step": 1130
+    },
+    {
+      "epoch": 11.465822784810127,
+      "grad_norm": 1.2140717506408691,
+      "learning_rate": 1.2356516114929176e-05,
+      "loss": 0.057,
+      "step": 1135
+    },
+    {
+      "epoch": 11.51645569620253,
+      "grad_norm": 1.1261478662490845,
+      "learning_rate": 1.2232051142243773e-05,
+      "loss": 0.0565,
+      "step": 1140
+    },
+    {
+      "epoch": 11.567088607594936,
+      "grad_norm": 1.119118094444275,
+      "learning_rate": 1.2107783155796606e-05,
+      "loss": 0.055,
+      "step": 1145
+    },
+    {
+      "epoch": 11.617721518987342,
+      "grad_norm": 0.9958686828613281,
+      "learning_rate": 1.198372099935048e-05,
+      "loss": 0.0559,
+      "step": 1150
+    },
+    {
+      "epoch": 11.668354430379747,
+      "grad_norm": 1.2256391048431396,
+      "learning_rate": 1.1859873502019935e-05,
+      "loss": 0.0589,
+      "step": 1155
+    },
+    {
+      "epoch": 11.718987341772152,
+      "grad_norm": 1.7713159322738647,
+      "learning_rate": 1.1736249477642896e-05,
+      "loss": 0.0565,
+      "step": 1160
+    },
+    {
+      "epoch": 11.769620253164558,
+      "grad_norm": 1.1513127088546753,
+      "learning_rate": 1.1612857724153418e-05,
+      "loss": 0.06,
+      "step": 1165
+    },
+    {
+      "epoch": 11.820253164556963,
+      "grad_norm": 1.0759341716766357,
+      "learning_rate": 1.1489707022955566e-05,
+      "loss": 0.0565,
+      "step": 1170
+    },
+    {
+      "epoch": 11.870886075949366,
+      "grad_norm": 1.09992253780365,
+      "learning_rate": 1.1366806138298468e-05,
+      "loss": 0.0531,
+      "step": 1175
+    },
+    {
+      "epoch": 11.921518987341772,
+      "grad_norm": 1.2160842418670654,
+      "learning_rate": 1.1244163816652588e-05,
+      "loss": 0.0514,
+      "step": 1180
+    },
+    {
+      "epoch": 11.972151898734177,
+      "grad_norm": 0.8802081942558289,
+      "learning_rate": 1.1121788786087285e-05,
+      "loss": 0.053,
+      "step": 1185
+    },
+    {
+      "epoch": 12.020253164556962,
+      "grad_norm": 0.9346157312393188,
+      "learning_rate": 1.0999689755649628e-05,
+      "loss": 0.0564,
+      "step": 1190
+    },
+    {
+      "epoch": 12.070886075949367,
+      "grad_norm": 0.8724172711372375,
+      "learning_rate": 1.0877875414744653e-05,
+      "loss": 0.054,
+      "step": 1195
+    },
+    {
+      "epoch": 12.121518987341773,
+      "grad_norm": 0.9368230104446411,
+      "learning_rate": 1.075635443251691e-05,
+      "loss": 0.0531,
+      "step": 1200
+    },
+    {
+      "epoch": 12.172151898734176,
+      "grad_norm": 1.0073076486587524,
+      "learning_rate": 1.0635135457233533e-05,
+      "loss": 0.0539,
+      "step": 1205
+    },
+    {
+      "epoch": 12.222784810126582,
+      "grad_norm": 0.8466517925262451,
+      "learning_rate": 1.051422711566879e-05,
+      "loss": 0.0503,
+      "step": 1210
+    },
+    {
+      "epoch": 12.273417721518987,
+      "grad_norm": 0.873408854007721,
+      "learning_rate": 1.0393638012490094e-05,
+      "loss": 0.0548,
+      "step": 1215
+    },
+    {
+      "epoch": 12.324050632911392,
+      "grad_norm": 0.8608399629592896,
+      "learning_rate": 1.027337672964569e-05,
+      "loss": 0.0561,
+      "step": 1220
+    },
+    {
+      "epoch": 12.374683544303798,
+      "grad_norm": 1.132765531539917,
+      "learning_rate": 1.015345182575386e-05,
+      "loss": 0.0541,
+      "step": 1225
+    },
+    {
+      "epoch": 12.425316455696203,
+      "grad_norm": 0.8618867993354797,
+      "learning_rate": 1.0033871835493848e-05,
+      "loss": 0.0501,
+      "step": 1230
+    },
+    {
+      "epoch": 12.475949367088608,
+      "grad_norm": 0.8279222846031189,
+      "learning_rate": 9.914645268998497e-06,
+      "loss": 0.0514,
+      "step": 1235
+    },
+    {
+      "epoch": 12.526582278481012,
+      "grad_norm": 0.641146183013916,
+      "learning_rate": 9.795780611248572e-06,
+      "loss": 0.0537,
+      "step": 1240
+    },
+    {
+      "epoch": 12.577215189873417,
+      "grad_norm": 0.7527780532836914,
+      "learning_rate": 9.677286321468937e-06,
+      "loss": 0.0521,
+      "step": 1245
+    },
+    {
+      "epoch": 12.627848101265823,
+      "grad_norm": 0.8106662631034851,
+      "learning_rate": 9.559170832526518e-06,
+      "loss": 0.0506,
+      "step": 1250
+    },
+    {
+      "epoch": 12.678481012658228,
+      "grad_norm": 1.0697318315505981,
+      "learning_rate": 9.441442550330181e-06,
+      "loss": 0.0594,
+      "step": 1255
+    },
+    {
+      "epoch": 12.729113924050633,
+      "grad_norm": 0.49909257888793945,
+      "learning_rate": 9.32410985323251e-06,
+      "loss": 0.0537,
+      "step": 1260
+    },
+    {
+      "epoch": 12.779746835443039,
+      "grad_norm": 1.3684509992599487,
+      "learning_rate": 9.20718109143352e-06,
+      "loss": 0.0533,
+      "step": 1265
+    },
+    {
+      "epoch": 12.830379746835444,
+      "grad_norm": 1.0380228757858276,
+      "learning_rate": 9.090664586386441e-06,
+      "loss": 0.0529,
+      "step": 1270
+    },
+    {
+      "epoch": 12.881012658227847,
+      "grad_norm": 0.7564946413040161,
+      "learning_rate": 8.974568630205462e-06,
+      "loss": 0.0518,
+      "step": 1275
+    },
+    {
+      "epoch": 12.931645569620253,
+      "grad_norm": 0.8710391521453857,
+      "learning_rate": 8.858901485075632e-06,
+      "loss": 0.0516,
+      "step": 1280
+    },
+    {
+      "epoch": 12.982278481012658,
+      "grad_norm": 0.6873605251312256,
+      "learning_rate": 8.743671382664876e-06,
+      "loss": 0.0488,
+      "step": 1285
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1960,
+  "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": 4.418581180920627e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1287/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a436d9e507a65e167f35408ec1bb674e772877bdfffc477144f5ecc24f0321
+size 7608

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1287/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)

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1386/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

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1386/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": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1386/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c958daab69fc083dcf14f80a8e79ae22f560eb5ad4d9f70434edbedff8f7dd6a
+size 671150064

rank_128/group_size_117/layer_full/1024/base/0_128_e20_3e-5/checkpoint-1386/latest

@@ -0,0 +1 @@
+global_step1382