Upload folder using huggingface_hub

README.md

@@ -0,0 +1,143 @@
+---
+library_name: peft
+license: llama3.1
+base_model: meta-llama/Llama-3.1-8B-Instruct
+tags:
+- generated_from_trainer
+datasets:
+- ugaoo/rephased_hf_lmharness
+model-index:
+- name: out/meta_llama_Llama_3.1_8B_Instruct_ugaoo_rephased_hf_lmharness
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.8.0.dev0`
+```yaml
+base_model: meta-llama/Llama-3.1-8B-Instruct
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+trust_remote_code: true
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+datasets:
+  - path: ugaoo/rephased_hf_lmharness
+    type: alpaca
+val_set_size: 0
+output_dir: ./out/meta_llama_Llama_3.1_8B_Instruct_ugaoo_rephased_hf_lmharness
+
+sequence_len: 4000
+sample_packing: true
+pad_to_sequence_len: true
+
+adapter: qlora
+lora_r: 256
+lora_alpha: 512
+lora_dropout: 0.05
+lora_target_linear: true
+lora_target_modules:
+  - q_proj
+  - k_proj
+  - v_proj
+  - o_proj
+  - up_proj
+  - down_proj
+  - gate_proj
+lora_modules_to_save:
+  - embed_tokens
+  - lm_head
+ 
+wandb_project: testsearch
+wandb_entity:
+wandb_watch: 
+wandb_name: meta_llama_Llama_3.1_8B_Instruct_ugaoo_rephased_hf_lmharness
+wandb_log_model:
+
+gradient_accumulation_steps: 3
+micro_batch_size: 4
+num_epochs: 6
+optimizer: adamw_torch
+lr_scheduler: cosine
+learning_rate: 5e-6
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16: false
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 100
+evals_per_epoch: 6
+eval_table_size:
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+save_total_limit: 6
+special_tokens:
+   pad_token: <|end_of_text|>
+```
+
+</details><br>
+
+# out/meta_llama_Llama_3.1_8B_Instruct_ugaoo_rephased_hf_lmharness
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the ugaoo/rephased_hf_lmharness dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 12
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 6.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.49.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -6,7 +6,7 @@
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": null,
-  "inference_mode": false,
+  "inference_mode": true,
   "init_lora_weights": true,
   "layer_replication": null,
   "layers_pattern": null,

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b70d3eda148f97aaa6ecaa1ef0763872b134c1a17dbc4575bd1b77a7c2b105a3
+size 3443586272

checkpoint-380/README.md

@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.1-8B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-380/adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-380/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70285ac403a646b7d2675c1ac41926ca99e94be27be85c5741b3948c5753f3d2
+size 3443586272

checkpoint-380/global_step378/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:206d677df67fe65c927ccff2976ada384dd51bcb2a3f0beeb514ed2f0317a1cb
+size 20661195036

checkpoint-380/global_step378/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f8c0270e88e0c60f7b00d6e54ef5cfb16e4c27d84814531acfb32462995c0d
+size 3555326649

checkpoint-380/latest

@@ -0,0 +1 @@
+global_step378

checkpoint-380/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fb4210e72e0243d76546ad8c839002c589c59d44073fd6f75416ace44652754
+size 14244

checkpoint-380/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a93097201a634931518316956d488c8df82e81f7fc29c1bde6ce7bd6033e7827
+size 1064

checkpoint-380/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-380/tokenizer.json

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

checkpoint-380/tokenizer_config.json

@@ -0,0 +1,2064 @@
+{
+  "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|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}

checkpoint-380/trainer_state.json

@@ -0,0 +1,2693 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.939130434782609,
+  "eval_steps": 500,
+  "global_step": 380,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013043478260869565,
+      "grad_norm": 30.641691207885742,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 2.1951,
+      "step": 1
+    },
+    {
+      "epoch": 0.02608695652173913,
+      "grad_norm": 31.937227249145508,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 2.274,
+      "step": 2
+    },
+    {
+      "epoch": 0.0391304347826087,
+      "grad_norm": 30.902198791503906,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 2.1994,
+      "step": 3
+    },
+    {
+      "epoch": 0.05217391304347826,
+      "grad_norm": 31.316129684448242,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 2.1975,
+      "step": 4
+    },
+    {
+      "epoch": 0.06521739130434782,
+      "grad_norm": 30.678176879882812,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 2.1836,
+      "step": 5
+    },
+    {
+      "epoch": 0.0782608695652174,
+      "grad_norm": 31.651874542236328,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 2.2658,
+      "step": 6
+    },
+    {
+      "epoch": 0.09130434782608696,
+      "grad_norm": 31.49991226196289,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 2.2324,
+      "step": 7
+    },
+    {
+      "epoch": 0.10434782608695652,
+      "grad_norm": 31.158674240112305,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 2.1922,
+      "step": 8
+    },
+    {
+      "epoch": 0.11739130434782609,
+      "grad_norm": 30.786540985107422,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 2.2302,
+      "step": 9
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "grad_norm": 30.784502029418945,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 2.1845,
+      "step": 10
+    },
+    {
+      "epoch": 0.14347826086956522,
+      "grad_norm": 30.878541946411133,
+      "learning_rate": 5.5e-07,
+      "loss": 2.1471,
+      "step": 11
+    },
+    {
+      "epoch": 0.1565217391304348,
+      "grad_norm": 30.616840362548828,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.086,
+      "step": 12
+    },
+    {
+      "epoch": 0.16956521739130434,
+      "grad_norm": 29.676923751831055,
+      "learning_rate": 6.5e-07,
+      "loss": 2.0468,
+      "step": 13
+    },
+    {
+      "epoch": 0.1826086956521739,
+      "grad_norm": 30.126493453979492,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 1.9897,
+      "step": 14
+    },
+    {
+      "epoch": 0.1956521739130435,
+      "grad_norm": 30.251602172851562,
+      "learning_rate": 7.5e-07,
+      "loss": 1.9232,
+      "step": 15
+    },
+    {
+      "epoch": 0.20869565217391303,
+      "grad_norm": 30.116798400878906,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.8406,
+      "step": 16
+    },
+    {
+      "epoch": 0.2217391304347826,
+      "grad_norm": 30.881160736083984,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 1.7809,
+      "step": 17
+    },
+    {
+      "epoch": 0.23478260869565218,
+      "grad_norm": 31.951828002929688,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 1.7001,
+      "step": 18
+    },
+    {
+      "epoch": 0.24782608695652175,
+      "grad_norm": 31.537166595458984,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 1.5591,
+      "step": 19
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 32.81351852416992,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.4578,
+      "step": 20
+    },
+    {
+      "epoch": 0.27391304347826084,
+      "grad_norm": 31.268814086914062,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 1.3437,
+      "step": 21
+    },
+    {
+      "epoch": 0.28695652173913044,
+      "grad_norm": 29.851335525512695,
+      "learning_rate": 1.1e-06,
+      "loss": 1.2298,
+      "step": 22
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 25.662965774536133,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 1.0528,
+      "step": 23
+    },
+    {
+      "epoch": 0.3130434782608696,
+      "grad_norm": 26.398494720458984,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.9624,
+      "step": 24
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": 26.3111629486084,
+      "learning_rate": 1.25e-06,
+      "loss": 0.7787,
+      "step": 25
+    },
+    {
+      "epoch": 0.3391304347826087,
+      "grad_norm": 28.78609275817871,
+      "learning_rate": 1.3e-06,
+      "loss": 0.6537,
+      "step": 26
+    },
+    {
+      "epoch": 0.3521739130434783,
+      "grad_norm": 26.990314483642578,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 0.4982,
+      "step": 27
+    },
+    {
+      "epoch": 0.3652173913043478,
+      "grad_norm": 23.103364944458008,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.3761,
+      "step": 28
+    },
+    {
+      "epoch": 0.3782608695652174,
+      "grad_norm": 20.322370529174805,
+      "learning_rate": 1.45e-06,
+      "loss": 0.2816,
+      "step": 29
+    },
+    {
+      "epoch": 0.391304347826087,
+      "grad_norm": 18.134693145751953,
+      "learning_rate": 1.5e-06,
+      "loss": 0.194,
+      "step": 30
+    },
+    {
+      "epoch": 0.4043478260869565,
+      "grad_norm": 10.411937713623047,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 0.1208,
+      "step": 31
+    },
+    {
+      "epoch": 0.41739130434782606,
+      "grad_norm": 3.981872081756592,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.0885,
+      "step": 32
+    },
+    {
+      "epoch": 0.43043478260869567,
+      "grad_norm": 2.513179063796997,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 0.0827,
+      "step": 33
+    },
+    {
+      "epoch": 0.4434782608695652,
+      "grad_norm": 1.3037446737289429,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 0.0738,
+      "step": 34
+    },
+    {
+      "epoch": 0.45652173913043476,
+      "grad_norm": 1.5666987895965576,
+      "learning_rate": 1.75e-06,
+      "loss": 0.0737,
+      "step": 35
+    },
+    {
+      "epoch": 0.46956521739130436,
+      "grad_norm": 1.8724833726882935,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.0716,
+      "step": 36
+    },
+    {
+      "epoch": 0.4826086956521739,
+      "grad_norm": 1.8552911281585693,
+      "learning_rate": 1.85e-06,
+      "loss": 0.0703,
+      "step": 37
+    },
+    {
+      "epoch": 0.4956521739130435,
+      "grad_norm": 1.165390968322754,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.0665,
+      "step": 38
+    },
+    {
+      "epoch": 0.508695652173913,
+      "grad_norm": 1.1661189794540405,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.0654,
+      "step": 39
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 1.3230024576187134,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0693,
+      "step": 40
+    },
+    {
+      "epoch": 0.5347826086956522,
+      "grad_norm": 0.7362420558929443,
+      "learning_rate": 2.05e-06,
+      "loss": 0.0665,
+      "step": 41
+    },
+    {
+      "epoch": 0.5478260869565217,
+      "grad_norm": 0.6983249187469482,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 0.0695,
+      "step": 42
+    },
+    {
+      "epoch": 0.5608695652173913,
+      "grad_norm": 1.134478211402893,
+      "learning_rate": 2.15e-06,
+      "loss": 0.0638,
+      "step": 43
+    },
+    {
+      "epoch": 0.5739130434782609,
+      "grad_norm": 1.1987451314926147,
+      "learning_rate": 2.2e-06,
+      "loss": 0.0538,
+      "step": 44
+    },
+    {
+      "epoch": 0.5869565217391305,
+      "grad_norm": 0.8745909929275513,
+      "learning_rate": 2.25e-06,
+      "loss": 0.0618,
+      "step": 45
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.0686204433441162,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 0.0662,
+      "step": 46
+    },
+    {
+      "epoch": 0.6130434782608696,
+      "grad_norm": 0.6556565165519714,
+      "learning_rate": 2.35e-06,
+      "loss": 0.056,
+      "step": 47
+    },
+    {
+      "epoch": 0.6260869565217392,
+      "grad_norm": 0.7634578943252563,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.0594,
+      "step": 48
+    },
+    {
+      "epoch": 0.6391304347826087,
+      "grad_norm": 0.8059038519859314,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.0615,
+      "step": 49
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 0.5894052982330322,
+      "learning_rate": 2.5e-06,
+      "loss": 0.058,
+      "step": 50
+    },
+    {
+      "epoch": 0.6652173913043479,
+      "grad_norm": 0.5712239146232605,
+      "learning_rate": 2.55e-06,
+      "loss": 0.0589,
+      "step": 51
+    },
+    {
+      "epoch": 0.6782608695652174,
+      "grad_norm": 0.6876189708709717,
+      "learning_rate": 2.6e-06,
+      "loss": 0.0607,
+      "step": 52
+    },
+    {
+      "epoch": 0.691304347826087,
+      "grad_norm": 0.623663067817688,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 0.0576,
+      "step": 53
+    },
+    {
+      "epoch": 0.7043478260869566,
+      "grad_norm": 0.6075452566146851,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.0612,
+      "step": 54
+    },
+    {
+      "epoch": 0.717391304347826,
+      "grad_norm": 0.7780712842941284,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.0566,
+      "step": 55
+    },
+    {
+      "epoch": 0.7304347826086957,
+      "grad_norm": 0.6400704383850098,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.0603,
+      "step": 56
+    },
+    {
+      "epoch": 0.7434782608695653,
+      "grad_norm": 0.6284154653549194,
+      "learning_rate": 2.85e-06,
+      "loss": 0.0547,
+      "step": 57
+    },
+    {
+      "epoch": 0.7565217391304347,
+      "grad_norm": 0.5499616265296936,
+      "learning_rate": 2.9e-06,
+      "loss": 0.0571,
+      "step": 58
+    },
+    {
+      "epoch": 0.7695652173913043,
+      "grad_norm": 0.6163158416748047,
+      "learning_rate": 2.95e-06,
+      "loss": 0.0587,
+      "step": 59
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 0.684912919998169,
+      "learning_rate": 3e-06,
+      "loss": 0.0596,
+      "step": 60
+    },
+    {
+      "epoch": 0.7956521739130434,
+      "grad_norm": 0.7246200442314148,
+      "learning_rate": 3.05e-06,
+      "loss": 0.0493,
+      "step": 61
+    },
+    {
+      "epoch": 0.808695652173913,
+      "grad_norm": 0.7146164774894714,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.0559,
+      "step": 62
+    },
+    {
+      "epoch": 0.8217391304347826,
+      "grad_norm": 0.6179472804069519,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 0.0604,
+      "step": 63
+    },
+    {
+      "epoch": 0.8347826086956521,
+      "grad_norm": 0.7352550029754639,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.0498,
+      "step": 64
+    },
+    {
+      "epoch": 0.8478260869565217,
+      "grad_norm": 0.5682029128074646,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.0562,
+      "step": 65
+    },
+    {
+      "epoch": 0.8608695652173913,
+      "grad_norm": 0.4977523982524872,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.0534,
+      "step": 66
+    },
+    {
+      "epoch": 0.8739130434782608,
+      "grad_norm": 0.5390787124633789,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 0.0534,
+      "step": 67
+    },
+    {
+      "epoch": 0.8869565217391304,
+      "grad_norm": 0.712452232837677,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.0528,
+      "step": 68
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.5136511921882629,
+      "learning_rate": 3.45e-06,
+      "loss": 0.0529,
+      "step": 69
+    },
+    {
+      "epoch": 0.9130434782608695,
+      "grad_norm": 0.5339029431343079,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0489,
+      "step": 70
+    },
+    {
+      "epoch": 0.9260869565217391,
+      "grad_norm": 0.647507905960083,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 0.0477,
+      "step": 71
+    },
+    {
+      "epoch": 0.9391304347826087,
+      "grad_norm": 0.5351842641830444,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.0491,
+      "step": 72
+    },
+    {
+      "epoch": 0.9521739130434783,
+      "grad_norm": 0.620066225528717,
+      "learning_rate": 3.65e-06,
+      "loss": 0.0477,
+      "step": 73
+    },
+    {
+      "epoch": 0.9652173913043478,
+      "grad_norm": 0.5559766292572021,
+      "learning_rate": 3.7e-06,
+      "loss": 0.0444,
+      "step": 74
+    },
+    {
+      "epoch": 0.9782608695652174,
+      "grad_norm": 0.5821895599365234,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0484,
+      "step": 75
+    },
+    {
+      "epoch": 0.991304347826087,
+      "grad_norm": 0.6146248579025269,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.046,
+      "step": 76
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6146248579025269,
+      "learning_rate": 3.85e-06,
+      "loss": 0.0538,
+      "step": 77
+    },
+    {
+      "epoch": 1.0130434782608695,
+      "grad_norm": 1.2398924827575684,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.0512,
+      "step": 78
+    },
+    {
+      "epoch": 1.0260869565217392,
+      "grad_norm": 0.5804176330566406,
+      "learning_rate": 3.95e-06,
+      "loss": 0.046,
+      "step": 79
+    },
+    {
+      "epoch": 1.0391304347826087,
+      "grad_norm": 0.47833946347236633,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0428,
+      "step": 80
+    },
+    {
+      "epoch": 1.0521739130434782,
+      "grad_norm": 0.562652051448822,
+      "learning_rate": 4.05e-06,
+      "loss": 0.0403,
+      "step": 81
+    },
+    {
+      "epoch": 1.065217391304348,
+      "grad_norm": 0.5788324475288391,
+      "learning_rate": 4.1e-06,
+      "loss": 0.0399,
+      "step": 82
+    },
+    {
+      "epoch": 1.0782608695652174,
+      "grad_norm": 0.513817310333252,
+      "learning_rate": 4.15e-06,
+      "loss": 0.0417,
+      "step": 83
+    },
+    {
+      "epoch": 1.0913043478260869,
+      "grad_norm": 0.6000502705574036,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.042,
+      "step": 84
+    },
+    {
+      "epoch": 1.1043478260869566,
+      "grad_norm": 0.721695601940155,
+      "learning_rate": 4.25e-06,
+      "loss": 0.0472,
+      "step": 85
+    },
+    {
+      "epoch": 1.117391304347826,
+      "grad_norm": 0.7209702730178833,
+      "learning_rate": 4.3e-06,
+      "loss": 0.0371,
+      "step": 86
+    },
+    {
+      "epoch": 1.1304347826086956,
+      "grad_norm": 0.5806598663330078,
+      "learning_rate": 4.350000000000001e-06,
+      "loss": 0.0478,
+      "step": 87
+    },
+    {
+      "epoch": 1.1434782608695653,
+      "grad_norm": 0.6562755703926086,
+      "learning_rate": 4.4e-06,
+      "loss": 0.0414,
+      "step": 88
+    },
+    {
+      "epoch": 1.1565217391304348,
+      "grad_norm": 0.5621042847633362,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 0.0373,
+      "step": 89
+    },
+    {
+      "epoch": 1.1695652173913043,
+      "grad_norm": 0.6904962658882141,
+      "learning_rate": 4.5e-06,
+      "loss": 0.0481,
+      "step": 90
+    },
+    {
+      "epoch": 1.182608695652174,
+      "grad_norm": 0.5569142699241638,
+      "learning_rate": 4.5500000000000005e-06,
+      "loss": 0.0425,
+      "step": 91
+    },
+    {
+      "epoch": 1.1956521739130435,
+      "grad_norm": 0.6834372282028198,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.04,
+      "step": 92
+    },
+    {
+      "epoch": 1.208695652173913,
+      "grad_norm": 0.6567809581756592,
+      "learning_rate": 4.65e-06,
+      "loss": 0.0399,
+      "step": 93
+    },
+    {
+      "epoch": 1.2217391304347827,
+      "grad_norm": 0.5778902769088745,
+      "learning_rate": 4.7e-06,
+      "loss": 0.0337,
+      "step": 94
+    },
+    {
+      "epoch": 1.2347826086956522,
+      "grad_norm": 0.5971974730491638,
+      "learning_rate": 4.75e-06,
+      "loss": 0.0364,
+      "step": 95
+    },
+    {
+      "epoch": 1.2478260869565219,
+      "grad_norm": 0.5933169722557068,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.0357,
+      "step": 96
+    },
+    {
+      "epoch": 1.2608695652173914,
+      "grad_norm": 0.6292222142219543,
+      "learning_rate": 4.85e-06,
+      "loss": 0.031,
+      "step": 97
+    },
+    {
+      "epoch": 1.2739130434782608,
+      "grad_norm": 0.8789151906967163,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.0313,
+      "step": 98
+    },
+    {
+      "epoch": 1.2869565217391306,
+      "grad_norm": 0.6100375652313232,
+      "learning_rate": 4.95e-06,
+      "loss": 0.0343,
+      "step": 99
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.7254518866539001,
+      "learning_rate": 5e-06,
+      "loss": 0.0364,
+      "step": 100
+    },
+    {
+      "epoch": 1.3130434782608695,
+      "grad_norm": 0.6824344396591187,
+      "learning_rate": 4.999902656502973e-06,
+      "loss": 0.0297,
+      "step": 101
+    },
+    {
+      "epoch": 1.3260869565217392,
+      "grad_norm": 0.5075684785842896,
+      "learning_rate": 4.9996106335924965e-06,
+      "loss": 0.0323,
+      "step": 102
+    },
+    {
+      "epoch": 1.3391304347826087,
+      "grad_norm": 0.5161061882972717,
+      "learning_rate": 4.999123954009797e-06,
+      "loss": 0.0289,
+      "step": 103
+    },
+    {
+      "epoch": 1.3521739130434782,
+      "grad_norm": 0.5754029154777527,
+      "learning_rate": 4.998442655654946e-06,
+      "loss": 0.0333,
+      "step": 104
+    },
+    {
+      "epoch": 1.365217391304348,
+      "grad_norm": 0.7110198736190796,
+      "learning_rate": 4.997566791583916e-06,
+      "loss": 0.0304,
+      "step": 105
+    },
+    {
+      "epoch": 1.3782608695652174,
+      "grad_norm": 0.7235414385795593,
+      "learning_rate": 4.996496430004446e-06,
+      "loss": 0.0319,
+      "step": 106
+    },
+    {
+      "epoch": 1.391304347826087,
+      "grad_norm": 0.5558100342750549,
+      "learning_rate": 4.995231654270726e-06,
+      "loss": 0.0256,
+      "step": 107
+    },
+    {
+      "epoch": 1.4043478260869566,
+      "grad_norm": 0.5645644068717957,
+      "learning_rate": 4.993772562876909e-06,
+      "loss": 0.0257,
+      "step": 108
+    },
+    {
+      "epoch": 1.4173913043478261,
+      "grad_norm": 0.589040994644165,
+      "learning_rate": 4.992119269449445e-06,
+      "loss": 0.026,
+      "step": 109
+    },
+    {
+      "epoch": 1.4304347826086956,
+      "grad_norm": 0.7214376330375671,
+      "learning_rate": 4.990271902738223e-06,
+      "loss": 0.0325,
+      "step": 110
+    },
+    {
+      "epoch": 1.4434782608695653,
+      "grad_norm": 0.7478785514831543,
+      "learning_rate": 4.988230606606552e-06,
+      "loss": 0.0241,
+      "step": 111
+    },
+    {
+      "epoch": 1.4565217391304348,
+      "grad_norm": 0.9108967781066895,
+      "learning_rate": 4.985995540019956e-06,
+      "loss": 0.0242,
+      "step": 112
+    },
+    {
+      "epoch": 1.4695652173913043,
+      "grad_norm": 0.6113864779472351,
+      "learning_rate": 4.983566877033791e-06,
+      "loss": 0.0263,
+      "step": 113
+    },
+    {
+      "epoch": 1.482608695652174,
+      "grad_norm": 0.6748284101486206,
+      "learning_rate": 4.980944806779698e-06,
+      "loss": 0.0235,
+      "step": 114
+    },
+    {
+      "epoch": 1.4956521739130435,
+      "grad_norm": 0.5893757939338684,
+      "learning_rate": 4.9781295334508664e-06,
+      "loss": 0.0292,
+      "step": 115
+    },
+    {
+      "epoch": 1.508695652173913,
+      "grad_norm": 0.8105467557907104,
+      "learning_rate": 4.975121276286136e-06,
+      "loss": 0.0217,
+      "step": 116
+    },
+    {
+      "epoch": 1.5217391304347827,
+      "grad_norm": 0.5484834909439087,
+      "learning_rate": 4.9719202695529265e-06,
+      "loss": 0.0241,
+      "step": 117
+    },
+    {
+      "epoch": 1.5347826086956522,
+      "grad_norm": 0.6067440509796143,
+      "learning_rate": 4.968526762528988e-06,
+      "loss": 0.025,
+      "step": 118
+    },
+    {
+      "epoch": 1.5478260869565217,
+      "grad_norm": 0.7170385122299194,
+      "learning_rate": 4.964941019482995e-06,
+      "loss": 0.0163,
+      "step": 119
+    },
+    {
+      "epoch": 1.5608695652173914,
+      "grad_norm": 0.5389299392700195,
+      "learning_rate": 4.961163319653959e-06,
+      "loss": 0.022,
+      "step": 120
+    },
+    {
+      "epoch": 1.5739130434782609,
+      "grad_norm": 0.8852945566177368,
+      "learning_rate": 4.9571939572294914e-06,
+      "loss": 0.0202,
+      "step": 121
+    },
+    {
+      "epoch": 1.5869565217391304,
+      "grad_norm": 0.6196063756942749,
+      "learning_rate": 4.953033241322887e-06,
+      "loss": 0.0205,
+      "step": 122
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.5872839093208313,
+      "learning_rate": 4.948681495949055e-06,
+      "loss": 0.0175,
+      "step": 123
+    },
+    {
+      "epoch": 1.6130434782608696,
+      "grad_norm": 0.6874949932098389,
+      "learning_rate": 4.944139059999286e-06,
+      "loss": 0.0179,
+      "step": 124
+    },
+    {
+      "epoch": 1.626086956521739,
+      "grad_norm": 0.49811050295829773,
+      "learning_rate": 4.939406287214861e-06,
+      "loss": 0.0193,
+      "step": 125
+    },
+    {
+      "epoch": 1.6391304347826088,
+      "grad_norm": 0.6337487101554871,
+      "learning_rate": 4.9344835461595016e-06,
+      "loss": 0.0176,
+      "step": 126
+    },
+    {
+      "epoch": 1.6521739130434783,
+      "grad_norm": 0.7472748160362244,
+      "learning_rate": 4.929371220190671e-06,
+      "loss": 0.0139,
+      "step": 127
+    },
+    {
+      "epoch": 1.6652173913043478,
+      "grad_norm": 0.6550290584564209,
+      "learning_rate": 4.9240697074297205e-06,
+      "loss": 0.0161,
+      "step": 128
+    },
+    {
+      "epoch": 1.6782608695652175,
+      "grad_norm": 0.473919540643692,
+      "learning_rate": 4.918579420730884e-06,
+      "loss": 0.0163,
+      "step": 129
+    },
+    {
+      "epoch": 1.691304347826087,
+      "grad_norm": 0.5661535859107971,
+      "learning_rate": 4.912900787649124e-06,
+      "loss": 0.0183,
+      "step": 130
+    },
+    {
+      "epoch": 1.7043478260869565,
+      "grad_norm": 0.7776857018470764,
+      "learning_rate": 4.907034250406846e-06,
+      "loss": 0.0117,
+      "step": 131
+    },
+    {
+      "epoch": 1.7173913043478262,
+      "grad_norm": 0.4113011658191681,
+      "learning_rate": 4.900980265859449e-06,
+      "loss": 0.0119,
+      "step": 132
+    },
+    {
+      "epoch": 1.7304347826086957,
+      "grad_norm": 0.7155903577804565,
+      "learning_rate": 4.894739305459754e-06,
+      "loss": 0.0094,
+      "step": 133
+    },
+    {
+      "epoch": 1.7434782608695651,
+      "grad_norm": 0.7912915349006653,
+      "learning_rate": 4.88831185522129e-06,
+      "loss": 0.0169,
+      "step": 134
+    },
+    {
+      "epoch": 1.7565217391304349,
+      "grad_norm": 0.6020934581756592,
+      "learning_rate": 4.881698415680442e-06,
+      "loss": 0.0163,
+      "step": 135
+    },
+    {
+      "epoch": 1.7695652173913043,
+      "grad_norm": 0.6352165341377258,
+      "learning_rate": 4.874899501857477e-06,
+      "loss": 0.01,
+      "step": 136
+    },
+    {
+      "epoch": 1.7826086956521738,
+      "grad_norm": 0.45883336663246155,
+      "learning_rate": 4.867915643216434e-06,
+      "loss": 0.0135,
+      "step": 137
+    },
+    {
+      "epoch": 1.7956521739130435,
+      "grad_norm": 0.6866053938865662,
+      "learning_rate": 4.860747383623889e-06,
+      "loss": 0.0095,
+      "step": 138
+    },
+    {
+      "epoch": 1.808695652173913,
+      "grad_norm": 0.44558900594711304,
+      "learning_rate": 4.85339528130661e-06,
+      "loss": 0.0081,
+      "step": 139
+    },
+    {
+      "epoch": 1.8217391304347825,
+      "grad_norm": 0.47094374895095825,
+      "learning_rate": 4.845859908808074e-06,
+      "loss": 0.0095,
+      "step": 140
+    },
+    {
+      "epoch": 1.8347826086956522,
+      "grad_norm": 0.4724484086036682,
+      "learning_rate": 4.838141852943891e-06,
+      "loss": 0.0085,
+      "step": 141
+    },
+    {
+      "epoch": 1.8478260869565217,
+      "grad_norm": 0.6628655195236206,
+      "learning_rate": 4.830241714756099e-06,
+      "loss": 0.014,
+      "step": 142
+    },
+    {
+      "epoch": 1.8608695652173912,
+      "grad_norm": 0.7814735174179077,
+      "learning_rate": 4.822160109466361e-06,
+      "loss": 0.0108,
+      "step": 143
+    },
+    {
+      "epoch": 1.873913043478261,
+      "grad_norm": 0.45942002534866333,
+      "learning_rate": 4.813897666428054e-06,
+      "loss": 0.011,
+      "step": 144
+    },
+    {
+      "epoch": 1.8869565217391304,
+      "grad_norm": 0.6027839183807373,
+      "learning_rate": 4.805455029077255e-06,
+      "loss": 0.0054,
+      "step": 145
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.4727053642272949,
+      "learning_rate": 4.79683285488264e-06,
+      "loss": 0.0081,
+      "step": 146
+    },
+    {
+      "epoch": 1.9130434782608696,
+      "grad_norm": 0.6347537040710449,
+      "learning_rate": 4.788031815294282e-06,
+      "loss": 0.0058,
+      "step": 147
+    },
+    {
+      "epoch": 1.9260869565217391,
+      "grad_norm": 0.4297194480895996,
+      "learning_rate": 4.779052595691355e-06,
+      "loss": 0.0062,
+      "step": 148
+    },
+    {
+      "epoch": 1.9391304347826086,
+      "grad_norm": 0.7891242504119873,
+      "learning_rate": 4.76989589532877e-06,
+      "loss": 0.0079,
+      "step": 149
+    },
+    {
+      "epoch": 1.9521739130434783,
+      "grad_norm": 0.5888785123825073,
+      "learning_rate": 4.7605624272827125e-06,
+      "loss": 0.0046,
+      "step": 150
+    },
+    {
+      "epoch": 1.9652173913043478,
+      "grad_norm": 0.5303910970687866,
+      "learning_rate": 4.75105291839512e-06,
+      "loss": 0.0071,
+      "step": 151
+    },
+    {
+      "epoch": 1.9782608695652173,
+      "grad_norm": 0.6492812037467957,
+      "learning_rate": 4.741368109217072e-06,
+      "loss": 0.0072,
+      "step": 152
+    },
+    {
+      "epoch": 1.991304347826087,
+      "grad_norm": 0.6820566654205322,
+      "learning_rate": 4.7315087539511225e-06,
+      "loss": 0.0058,
+      "step": 153
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.4742223918437958,
+      "learning_rate": 4.721475620392567e-06,
+      "loss": 0.0078,
+      "step": 154
+    },
+    {
+      "epoch": 2.0130434782608697,
+      "grad_norm": 1.0548763275146484,
+      "learning_rate": 4.711269489869654e-06,
+      "loss": 0.0035,
+      "step": 155
+    },
+    {
+      "epoch": 2.026086956521739,
+      "grad_norm": 0.2593505382537842,
+      "learning_rate": 4.700891157182729e-06,
+      "loss": 0.0026,
+      "step": 156
+    },
+    {
+      "epoch": 2.0391304347826087,
+      "grad_norm": 0.6592870354652405,
+      "learning_rate": 4.690341430542351e-06,
+      "loss": 0.0009,
+      "step": 157
+    },
+    {
+      "epoch": 2.0521739130434784,
+      "grad_norm": 0.10995268076658249,
+      "learning_rate": 4.679621131506347e-06,
+      "loss": 0.0025,
+      "step": 158
+    },
+    {
+      "epoch": 2.0652173913043477,
+      "grad_norm": 1.0068087577819824,
+      "learning_rate": 4.668731094915835e-06,
+      "loss": 0.0016,
+      "step": 159
+    },
+    {
+      "epoch": 2.0782608695652174,
+      "grad_norm": 0.19254828989505768,
+      "learning_rate": 4.657672168830211e-06,
+      "loss": 0.0017,
+      "step": 160
+    },
+    {
+      "epoch": 2.091304347826087,
+      "grad_norm": 0.513418972492218,
+      "learning_rate": 4.646445214461105e-06,
+      "loss": 0.0032,
+      "step": 161
+    },
+    {
+      "epoch": 2.1043478260869564,
+      "grad_norm": 0.4659607410430908,
+      "learning_rate": 4.635051106105316e-06,
+      "loss": 0.0027,
+      "step": 162
+    },
+    {
+      "epoch": 2.117391304347826,
+      "grad_norm": 0.26887616515159607,
+      "learning_rate": 4.623490731076728e-06,
+      "loss": 0.0007,
+      "step": 163
+    },
+    {
+      "epoch": 2.130434782608696,
+      "grad_norm": 0.22268249094486237,
+      "learning_rate": 4.6117649896372055e-06,
+      "loss": 0.001,
+      "step": 164
+    },
+    {
+      "epoch": 2.143478260869565,
+      "grad_norm": 0.35821816325187683,
+      "learning_rate": 4.59987479492649e-06,
+      "loss": 0.0023,
+      "step": 165
+    },
+    {
+      "epoch": 2.1565217391304348,
+      "grad_norm": 0.4691464602947235,
+      "learning_rate": 4.587821072891089e-06,
+      "loss": 0.0046,
+      "step": 166
+    },
+    {
+      "epoch": 2.1695652173913045,
+      "grad_norm": 0.6060182452201843,
+      "learning_rate": 4.5756047622121665e-06,
+      "loss": 0.0024,
+      "step": 167
+    },
+    {
+      "epoch": 2.1826086956521737,
+      "grad_norm": 0.37854066491127014,
+      "learning_rate": 4.563226814232444e-06,
+      "loss": 0.0021,
+      "step": 168
+    },
+    {
+      "epoch": 2.1956521739130435,
+      "grad_norm": 0.903462827205658,
+      "learning_rate": 4.550688192882115e-06,
+      "loss": 0.001,
+      "step": 169
+    },
+    {
+      "epoch": 2.208695652173913,
+      "grad_norm": 0.5006014704704285,
+      "learning_rate": 4.53798987460378e-06,
+      "loss": 0.0034,
+      "step": 170
+    },
+    {
+      "epoch": 2.2217391304347824,
+      "grad_norm": 0.49557602405548096,
+      "learning_rate": 4.525132848276405e-06,
+      "loss": 0.0005,
+      "step": 171
+    },
+    {
+      "epoch": 2.234782608695652,
+      "grad_norm": 0.7139260768890381,
+      "learning_rate": 4.512118115138315e-06,
+      "loss": 0.0061,
+      "step": 172
+    },
+    {
+      "epoch": 2.247826086956522,
+      "grad_norm": 0.8578881025314331,
+      "learning_rate": 4.498946688709216e-06,
+      "loss": 0.0017,
+      "step": 173
+    },
+    {
+      "epoch": 2.260869565217391,
+      "grad_norm": 0.22415713965892792,
+      "learning_rate": 4.485619594711278e-06,
+      "loss": 0.0007,
+      "step": 174
+    },
+    {
+      "epoch": 2.273913043478261,
+      "grad_norm": 0.3430750072002411,
+      "learning_rate": 4.4721378709892475e-06,
+      "loss": 0.002,
+      "step": 175
+    },
+    {
+      "epoch": 2.2869565217391306,
+      "grad_norm": 0.3404991626739502,
+      "learning_rate": 4.4585025674296315e-06,
+      "loss": 0.0011,
+      "step": 176
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.45432400703430176,
+      "learning_rate": 4.444714745878936e-06,
+      "loss": 0.0012,
+      "step": 177
+    },
+    {
+      "epoch": 2.3130434782608695,
+      "grad_norm": 0.2696153223514557,
+      "learning_rate": 4.430775480060973e-06,
+      "loss": 0.0012,
+      "step": 178
+    },
+    {
+      "epoch": 2.3260869565217392,
+      "grad_norm": 0.10708807408809662,
+      "learning_rate": 4.416685855493246e-06,
+      "loss": 0.0008,
+      "step": 179
+    },
+    {
+      "epoch": 2.3391304347826085,
+      "grad_norm": 0.39214053750038147,
+      "learning_rate": 4.4024469694024194e-06,
+      "loss": 0.0019,
+      "step": 180
+    },
+    {
+      "epoch": 2.3521739130434782,
+      "grad_norm": 0.6886045336723328,
+      "learning_rate": 4.388059930638865e-06,
+      "loss": 0.0016,
+      "step": 181
+    },
+    {
+      "epoch": 2.365217391304348,
+      "grad_norm": 0.21321725845336914,
+      "learning_rate": 4.373525859590313e-06,
+      "loss": 0.0018,
+      "step": 182
+    },
+    {
+      "epoch": 2.378260869565217,
+      "grad_norm": 0.35919421911239624,
+      "learning_rate": 4.358845888094607e-06,
+      "loss": 0.0013,
+      "step": 183
+    },
+    {
+      "epoch": 2.391304347826087,
+      "grad_norm": 0.27048271894454956,
+      "learning_rate": 4.3440211593515556e-06,
+      "loss": 0.0027,
+      "step": 184
+    },
+    {
+      "epoch": 2.4043478260869566,
+      "grad_norm": 0.5377674698829651,
+      "learning_rate": 4.32905282783391e-06,
+      "loss": 0.0011,
+      "step": 185
+    },
+    {
+      "epoch": 2.417391304347826,
+      "grad_norm": 0.12088856846094131,
+      "learning_rate": 4.313942059197457e-06,
+      "loss": 0.0018,
+      "step": 186
+    },
+    {
+      "epoch": 2.4304347826086956,
+      "grad_norm": 0.4951612055301666,
+      "learning_rate": 4.298690030190247e-06,
+      "loss": 0.0006,
+      "step": 187
+    },
+    {
+      "epoch": 2.4434782608695653,
+      "grad_norm": 0.11120982468128204,
+      "learning_rate": 4.283297928560951e-06,
+      "loss": 0.0007,
+      "step": 188
+    },
+    {
+      "epoch": 2.4565217391304346,
+      "grad_norm": 0.12437040358781815,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.0004,
+      "step": 189
+    },
+    {
+      "epoch": 2.4695652173913043,
+      "grad_norm": 0.10102014243602753,
+      "learning_rate": 4.252098312878083e-06,
+      "loss": 0.0004,
+      "step": 190
+    },
+    {
+      "epoch": 2.482608695652174,
+      "grad_norm": 0.16300979256629944,
+      "learning_rate": 4.236293228488267e-06,
+      "loss": 0.0008,
+      "step": 191
+    },
+    {
+      "epoch": 2.4956521739130437,
+      "grad_norm": 0.2017083615064621,
+      "learning_rate": 4.220352930614672e-06,
+      "loss": 0.0004,
+      "step": 192
+    },
+    {
+      "epoch": 2.508695652173913,
+      "grad_norm": 0.20179031789302826,
+      "learning_rate": 4.204278660604767e-06,
+      "loss": 0.0009,
+      "step": 193
+    },
+    {
+      "epoch": 2.5217391304347827,
+      "grad_norm": 0.2158278077840805,
+      "learning_rate": 4.1880716702390764e-06,
+      "loss": 0.002,
+      "step": 194
+    },
+    {
+      "epoch": 2.534782608695652,
+      "grad_norm": 0.326331228017807,
+      "learning_rate": 4.171733221633695e-06,
+      "loss": 0.0014,
+      "step": 195
+    },
+    {
+      "epoch": 2.5478260869565217,
+      "grad_norm": 0.30759623646736145,
+      "learning_rate": 4.155264587142002e-06,
+      "loss": 0.0008,
+      "step": 196
+    },
+    {
+      "epoch": 2.5608695652173914,
+      "grad_norm": 0.3855862021446228,
+      "learning_rate": 4.138667049255574e-06,
+      "loss": 0.0003,
+      "step": 197
+    },
+    {
+      "epoch": 2.573913043478261,
+      "grad_norm": 0.05741116404533386,
+      "learning_rate": 4.121941900504316e-06,
+      "loss": 0.0001,
+      "step": 198
+    },
+    {
+      "epoch": 2.5869565217391304,
+      "grad_norm": 0.015228237956762314,
+      "learning_rate": 4.105090443355801e-06,
+      "loss": 0.0002,
+      "step": 199
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.4413849711418152,
+      "learning_rate": 4.088113990113846e-06,
+      "loss": 0.0007,
+      "step": 200
+    },
+    {
+      "epoch": 2.6130434782608694,
+      "grad_norm": 0.303357869386673,
+      "learning_rate": 4.071013862816311e-06,
+      "loss": 0.0002,
+      "step": 201
+    },
+    {
+      "epoch": 2.626086956521739,
+      "grad_norm": 0.19713574647903442,
+      "learning_rate": 4.0537913931321495e-06,
+      "loss": 0.0006,
+      "step": 202
+    },
+    {
+      "epoch": 2.639130434782609,
+      "grad_norm": 0.39923036098480225,
+      "learning_rate": 4.036447922257699e-06,
+      "loss": 0.0005,
+      "step": 203
+    },
+    {
+      "epoch": 2.6521739130434785,
+      "grad_norm": 0.13886815309524536,
+      "learning_rate": 4.018984800812248e-06,
+      "loss": 0.0003,
+      "step": 204
+    },
+    {
+      "epoch": 2.6652173913043478,
+      "grad_norm": 0.3616029620170593,
+      "learning_rate": 4.001403388732842e-06,
+      "loss": 0.0011,
+      "step": 205
+    },
+    {
+      "epoch": 2.6782608695652175,
+      "grad_norm": 0.09302274137735367,
+      "learning_rate": 3.983705055168391e-06,
+      "loss": 0.0001,
+      "step": 206
+    },
+    {
+      "epoch": 2.6913043478260867,
+      "grad_norm": 0.11136471480131149,
+      "learning_rate": 3.965891178373038e-06,
+      "loss": 0.0002,
+      "step": 207
+    },
+    {
+      "epoch": 2.7043478260869565,
+      "grad_norm": 0.030531201511621475,
+      "learning_rate": 3.947963145598833e-06,
+      "loss": 0.0001,
+      "step": 208
+    },
+    {
+      "epoch": 2.717391304347826,
+      "grad_norm": 0.07998622953891754,
+      "learning_rate": 3.929922352987702e-06,
+      "loss": 0.0012,
+      "step": 209
+    },
+    {
+      "epoch": 2.730434782608696,
+      "grad_norm": 0.24564768373966217,
+      "learning_rate": 3.911770205462717e-06,
+      "loss": 0.0001,
+      "step": 210
+    },
+    {
+      "epoch": 2.743478260869565,
+      "grad_norm": 0.3731745481491089,
+      "learning_rate": 3.8935081166186935e-06,
+      "loss": 0.0005,
+      "step": 211
+    },
+    {
+      "epoch": 2.756521739130435,
+      "grad_norm": 0.02599702961742878,
+      "learning_rate": 3.875137508612104e-06,
+      "loss": 0.0001,
+      "step": 212
+    },
+    {
+      "epoch": 2.769565217391304,
+      "grad_norm": 0.013257239945232868,
+      "learning_rate": 3.856659812050328e-06,
+      "loss": 0.0003,
+      "step": 213
+    },
+    {
+      "epoch": 2.782608695652174,
+      "grad_norm": 0.23876884579658508,
+      "learning_rate": 3.838076465880248e-06,
+      "loss": 0.0001,
+      "step": 214
+    },
+    {
+      "epoch": 2.7956521739130435,
+      "grad_norm": 0.022550106048583984,
+      "learning_rate": 3.819388917276186e-06,
+      "loss": 0.0001,
+      "step": 215
+    },
+    {
+      "epoch": 2.8086956521739133,
+      "grad_norm": 0.0803162083029747,
+      "learning_rate": 3.8005986215272056e-06,
+      "loss": 0.0001,
+      "step": 216
+    },
+    {
+      "epoch": 2.8217391304347825,
+      "grad_norm": 0.04428872838616371,
+      "learning_rate": 3.7817070419237866e-06,
+      "loss": 0.0001,
+      "step": 217
+    },
+    {
+      "epoch": 2.8347826086956522,
+      "grad_norm": 0.06828437000513077,
+      "learning_rate": 3.7627156496438686e-06,
+      "loss": 0.0001,
+      "step": 218
+    },
+    {
+      "epoch": 2.8478260869565215,
+      "grad_norm": 0.6988795399665833,
+      "learning_rate": 3.7436259236382797e-06,
+      "loss": 0.0013,
+      "step": 219
+    },
+    {
+      "epoch": 2.860869565217391,
+      "grad_norm": 0.16631139814853668,
+      "learning_rate": 3.7244393505155713e-06,
+      "loss": 0.0001,
+      "step": 220
+    },
+    {
+      "epoch": 2.873913043478261,
+      "grad_norm": 0.03770599141716957,
+      "learning_rate": 3.7051574244262412e-06,
+      "loss": 0.0,
+      "step": 221
+    },
+    {
+      "epoch": 2.8869565217391306,
+      "grad_norm": 0.012837939895689487,
+      "learning_rate": 3.6857816469463806e-06,
+      "loss": 0.0,
+      "step": 222
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.042198728770017624,
+      "learning_rate": 3.6663135269607413e-06,
+      "loss": 0.0001,
+      "step": 223
+    },
+    {
+      "epoch": 2.9130434782608696,
+      "grad_norm": 0.15300290286540985,
+      "learning_rate": 3.6467545805452266e-06,
+      "loss": 0.0004,
+      "step": 224
+    },
+    {
+      "epoch": 2.926086956521739,
+      "grad_norm": 0.592495322227478,
+      "learning_rate": 3.6271063308488298e-06,
+      "loss": 0.0004,
+      "step": 225
+    },
+    {
+      "epoch": 2.9391304347826086,
+      "grad_norm": 0.006714676506817341,
+      "learning_rate": 3.6073703079750204e-06,
+      "loss": 0.0001,
+      "step": 226
+    },
+    {
+      "epoch": 2.9521739130434783,
+      "grad_norm": 0.07667013257741928,
+      "learning_rate": 3.5875480488625847e-06,
+      "loss": 0.0,
+      "step": 227
+    },
+    {
+      "epoch": 2.965217391304348,
+      "grad_norm": 0.07356667518615723,
+      "learning_rate": 3.5676410971659404e-06,
+      "loss": 0.0,
+      "step": 228
+    },
+    {
+      "epoch": 2.9782608695652173,
+      "grad_norm": 0.08367449045181274,
+      "learning_rate": 3.547651003134921e-06,
+      "loss": 0.0002,
+      "step": 229
+    },
+    {
+      "epoch": 2.991304347826087,
+      "grad_norm": 0.10358540713787079,
+      "learning_rate": 3.527579323494055e-06,
+      "loss": 0.0001,
+      "step": 230
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.28751426935195923,
+      "learning_rate": 3.507427621321331e-06,
+      "loss": 0.0001,
+      "step": 231
+    },
+    {
+      "epoch": 3.0130434782608697,
+      "grad_norm": 0.029475737363100052,
+      "learning_rate": 3.4871974659264786e-06,
+      "loss": 0.0,
+      "step": 232
+    },
+    {
+      "epoch": 3.026086956521739,
+      "grad_norm": 0.011441878043115139,
+      "learning_rate": 3.466890432728754e-06,
+      "loss": 0.0,
+      "step": 233
+    },
+    {
+      "epoch": 3.0391304347826087,
+      "grad_norm": 0.06686944514513016,
+      "learning_rate": 3.446508103134259e-06,
+      "loss": 0.0001,
+      "step": 234
+    },
+    {
+      "epoch": 3.0521739130434784,
+      "grad_norm": 0.06711216270923615,
+      "learning_rate": 3.426052064412785e-06,
+      "loss": 0.0001,
+      "step": 235
+    },
+    {
+      "epoch": 3.0652173913043477,
+      "grad_norm": 0.49988555908203125,
+      "learning_rate": 3.4055239095742067e-06,
+      "loss": 0.0004,
+      "step": 236
+    },
+    {
+      "epoch": 3.0782608695652174,
+      "grad_norm": 0.028451934456825256,
+      "learning_rate": 3.3849252372444295e-06,
+      "loss": 0.0,
+      "step": 237
+    },
+    {
+      "epoch": 3.091304347826087,
+      "grad_norm": 1.1554491519927979,
+      "learning_rate": 3.364257651540891e-06,
+      "loss": 0.0002,
+      "step": 238
+    },
+    {
+      "epoch": 3.1043478260869564,
+      "grad_norm": 0.013896522112190723,
+      "learning_rate": 3.343522761947646e-06,
+      "loss": 0.0,
+      "step": 239
+    },
+    {
+      "epoch": 3.117391304347826,
+      "grad_norm": 0.31346824765205383,
+      "learning_rate": 3.322722183190025e-06,
+      "loss": 0.0001,
+      "step": 240
+    },
+    {
+      "epoch": 3.130434782608696,
+      "grad_norm": 0.025106234475970268,
+      "learning_rate": 3.3018575351088894e-06,
+      "loss": 0.0,
+      "step": 241
+    },
+    {
+      "epoch": 3.143478260869565,
+      "grad_norm": 0.011471948586404324,
+      "learning_rate": 3.280930442534486e-06,
+      "loss": 0.0,
+      "step": 242
+    },
+    {
+      "epoch": 3.1565217391304348,
+      "grad_norm": 0.002863516565412283,
+      "learning_rate": 3.2599425351599136e-06,
+      "loss": 0.0,
+      "step": 243
+    },
+    {
+      "epoch": 3.1695652173913045,
+      "grad_norm": 0.028560644015669823,
+      "learning_rate": 3.238895447414211e-06,
+      "loss": 0.0,
+      "step": 244
+    },
+    {
+      "epoch": 3.1826086956521737,
+      "grad_norm": 0.011418928392231464,
+      "learning_rate": 3.217790818335077e-06,
+      "loss": 0.0,
+      "step": 245
+    },
+    {
+      "epoch": 3.1956521739130435,
+      "grad_norm": 0.0024322019889950752,
+      "learning_rate": 3.196630291441231e-06,
+      "loss": 0.0,
+      "step": 246
+    },
+    {
+      "epoch": 3.208695652173913,
+      "grad_norm": 0.004240074194967747,
+      "learning_rate": 3.175415514604422e-06,
+      "loss": 0.0,
+      "step": 247
+    },
+    {
+      "epoch": 3.2217391304347824,
+      "grad_norm": 0.0032878071069717407,
+      "learning_rate": 3.154148139921102e-06,
+      "loss": 0.0,
+      "step": 248
+    },
+    {
+      "epoch": 3.234782608695652,
+      "grad_norm": 0.004318348132073879,
+      "learning_rate": 3.132829823583771e-06,
+      "loss": 0.0,
+      "step": 249
+    },
+    {
+      "epoch": 3.247826086956522,
+      "grad_norm": 0.03787163272500038,
+      "learning_rate": 3.1114622257520004e-06,
+      "loss": 0.0,
+      "step": 250
+    },
+    {
+      "epoch": 3.260869565217391,
+      "grad_norm": 0.006955282762646675,
+      "learning_rate": 3.0900470104231456e-06,
+      "loss": 0.0,
+      "step": 251
+    },
+    {
+      "epoch": 3.273913043478261,
+      "grad_norm": 0.0021230122074484825,
+      "learning_rate": 3.0685858453027668e-06,
+      "loss": 0.0,
+      "step": 252
+    },
+    {
+      "epoch": 3.2869565217391306,
+      "grad_norm": 0.004325004294514656,
+      "learning_rate": 3.047080401674754e-06,
+      "loss": 0.0,
+      "step": 253
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 0.006688334047794342,
+      "learning_rate": 3.0255323542711784e-06,
+      "loss": 0.0,
+      "step": 254
+    },
+    {
+      "epoch": 3.3130434782608695,
+      "grad_norm": 0.08411774784326553,
+      "learning_rate": 3.00394338114187e-06,
+      "loss": 0.0001,
+      "step": 255
+    },
+    {
+      "epoch": 3.3260869565217392,
+      "grad_norm": 0.008930100128054619,
+      "learning_rate": 2.9823151635237424e-06,
+      "loss": 0.0,
+      "step": 256
+    },
+    {
+      "epoch": 3.3391304347826085,
+      "grad_norm": 0.0022701190318912268,
+      "learning_rate": 2.9606493857098657e-06,
+      "loss": 0.0,
+      "step": 257
+    },
+    {
+      "epoch": 3.3521739130434782,
+      "grad_norm": 0.01467288751155138,
+      "learning_rate": 2.938947734918302e-06,
+      "loss": 0.0,
+      "step": 258
+    },
+    {
+      "epoch": 3.365217391304348,
+      "grad_norm": 0.003942245151847601,
+      "learning_rate": 2.9172119011607153e-06,
+      "loss": 0.0,
+      "step": 259
+    },
+    {
+      "epoch": 3.378260869565217,
+      "grad_norm": 0.03254281356930733,
+      "learning_rate": 2.8954435771107604e-06,
+      "loss": 0.0,
+      "step": 260
+    },
+    {
+      "epoch": 3.391304347826087,
+      "grad_norm": 0.004211796913295984,
+      "learning_rate": 2.8736444579722665e-06,
+      "loss": 0.0,
+      "step": 261
+    },
+    {
+      "epoch": 3.4043478260869566,
+      "grad_norm": 0.002981652272865176,
+      "learning_rate": 2.8518162413472266e-06,
+      "loss": 0.0,
+      "step": 262
+    },
+    {
+      "epoch": 3.417391304347826,
+      "grad_norm": 0.004685316234827042,
+      "learning_rate": 2.8299606271035913e-06,
+      "loss": 0.0,
+      "step": 263
+    },
+    {
+      "epoch": 3.4304347826086956,
+      "grad_norm": 0.0022689092438668013,
+      "learning_rate": 2.8080793172428965e-06,
+      "loss": 0.0,
+      "step": 264
+    },
+    {
+      "epoch": 3.4434782608695653,
+      "grad_norm": 0.06723912060260773,
+      "learning_rate": 2.786174015767721e-06,
+      "loss": 0.0,
+      "step": 265
+    },
+    {
+      "epoch": 3.4565217391304346,
+      "grad_norm": 0.002560825552791357,
+      "learning_rate": 2.764246428548983e-06,
+      "loss": 0.0,
+      "step": 266
+    },
+    {
+      "epoch": 3.4695652173913043,
+      "grad_norm": 0.0016798798460513353,
+      "learning_rate": 2.742298263193099e-06,
+      "loss": 0.0,
+      "step": 267
+    },
+    {
+      "epoch": 3.482608695652174,
+      "grad_norm": 0.0021493195090442896,
+      "learning_rate": 2.720331228909005e-06,
+      "loss": 0.0,
+      "step": 268
+    },
+    {
+      "epoch": 3.4956521739130437,
+      "grad_norm": 0.004216059111058712,
+      "learning_rate": 2.6983470363750497e-06,
+      "loss": 0.0,
+      "step": 269
+    },
+    {
+      "epoch": 3.508695652173913,
+      "grad_norm": 0.0076387436129152775,
+      "learning_rate": 2.6763473976057776e-06,
+      "loss": 0.0,
+      "step": 270
+    },
+    {
+      "epoch": 3.5217391304347827,
+      "grad_norm": 0.005549773573875427,
+      "learning_rate": 2.6543340258186063e-06,
+      "loss": 0.0,
+      "step": 271
+    },
+    {
+      "epoch": 3.534782608695652,
+      "grad_norm": 0.00346516165882349,
+      "learning_rate": 2.6323086353004077e-06,
+      "loss": 0.0,
+      "step": 272
+    },
+    {
+      "epoch": 3.5478260869565217,
+      "grad_norm": 0.0031406464986503124,
+      "learning_rate": 2.610272941274012e-06,
+      "loss": 0.0,
+      "step": 273
+    },
+    {
+      "epoch": 3.5608695652173914,
+      "grad_norm": 0.0028460270259529352,
+      "learning_rate": 2.588228659764632e-06,
+      "loss": 0.0,
+      "step": 274
+    },
+    {
+      "epoch": 3.573913043478261,
+      "grad_norm": 0.002545596333220601,
+      "learning_rate": 2.5661775074662276e-06,
+      "loss": 0.0,
+      "step": 275
+    },
+    {
+      "epoch": 3.5869565217391304,
+      "grad_norm": 0.003621069248765707,
+      "learning_rate": 2.544121201607822e-06,
+      "loss": 0.0,
+      "step": 276
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 0.005747300107032061,
+      "learning_rate": 2.5220614598197708e-06,
+      "loss": 0.0,
+      "step": 277
+    },
+    {
+      "epoch": 3.6130434782608694,
+      "grad_norm": 0.0030976571142673492,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0,
+      "step": 278
+    },
+    {
+      "epoch": 3.626086956521739,
+      "grad_norm": 0.0016673463396728039,
+      "learning_rate": 2.477938540180231e-06,
+      "loss": 0.0,
+      "step": 279
+    },
+    {
+      "epoch": 3.639130434782609,
+      "grad_norm": 0.002529913792386651,
+      "learning_rate": 2.455878798392179e-06,
+      "loss": 0.0,
+      "step": 280
+    },
+    {
+      "epoch": 3.6521739130434785,
+      "grad_norm": 0.002386297332122922,
+      "learning_rate": 2.433822492533774e-06,
+      "loss": 0.0,
+      "step": 281
+    },
+    {
+      "epoch": 3.6652173913043478,
+      "grad_norm": 0.0032285265624523163,
+      "learning_rate": 2.411771340235369e-06,
+      "loss": 0.0,
+      "step": 282
+    },
+    {
+      "epoch": 3.6782608695652175,
+      "grad_norm": 0.0029606029856950045,
+      "learning_rate": 2.389727058725989e-06,
+      "loss": 0.0,
+      "step": 283
+    },
+    {
+      "epoch": 3.6913043478260867,
+      "grad_norm": 0.0039359270595014095,
+      "learning_rate": 2.3676913646995923e-06,
+      "loss": 0.0,
+      "step": 284
+    },
+    {
+      "epoch": 3.7043478260869565,
+      "grad_norm": 0.0026253967080265284,
+      "learning_rate": 2.3456659741813945e-06,
+      "loss": 0.0,
+      "step": 285
+    },
+    {
+      "epoch": 3.717391304347826,
+      "grad_norm": 0.00597747415304184,
+      "learning_rate": 2.3236526023942224e-06,
+      "loss": 0.0,
+      "step": 286
+    },
+    {
+      "epoch": 3.730434782608696,
+      "grad_norm": 0.003086534794420004,
+      "learning_rate": 2.301652963624951e-06,
+      "loss": 0.0,
+      "step": 287
+    },
+    {
+      "epoch": 3.743478260869565,
+      "grad_norm": 0.0029124680440872908,
+      "learning_rate": 2.2796687710909966e-06,
+      "loss": 0.0,
+      "step": 288
+    },
+    {
+      "epoch": 3.756521739130435,
+      "grad_norm": 0.010468163527548313,
+      "learning_rate": 2.2577017368069017e-06,
+      "loss": 0.0,
+      "step": 289
+    },
+    {
+      "epoch": 3.769565217391304,
+      "grad_norm": 0.004169187508523464,
+      "learning_rate": 2.235753571451018e-06,
+      "loss": 0.0,
+      "step": 290
+    },
+    {
+      "epoch": 3.782608695652174,
+      "grad_norm": 0.0022279575932770967,
+      "learning_rate": 2.2138259842322794e-06,
+      "loss": 0.0,
+      "step": 291
+    },
+    {
+      "epoch": 3.7956521739130435,
+      "grad_norm": 0.002126251347362995,
+      "learning_rate": 2.191920682757104e-06,
+      "loss": 0.0,
+      "step": 292
+    },
+    {
+      "epoch": 3.8086956521739133,
+      "grad_norm": 0.0013267571339383721,
+      "learning_rate": 2.170039372896409e-06,
+      "loss": 0.0,
+      "step": 293
+    },
+    {
+      "epoch": 3.8217391304347825,
+      "grad_norm": 0.002595380414277315,
+      "learning_rate": 2.148183758652774e-06,
+      "loss": 0.0,
+      "step": 294
+    },
+    {
+      "epoch": 3.8347826086956522,
+      "grad_norm": 0.004983303602784872,
+      "learning_rate": 2.126355542027734e-06,
+      "loss": 0.0,
+      "step": 295
+    },
+    {
+      "epoch": 3.8478260869565215,
+      "grad_norm": 0.002446365775540471,
+      "learning_rate": 2.1045564228892404e-06,
+      "loss": 0.0,
+      "step": 296
+    },
+    {
+      "epoch": 3.860869565217391,
+      "grad_norm": 0.002043728018179536,
+      "learning_rate": 2.0827880988392856e-06,
+      "loss": 0.0,
+      "step": 297
+    },
+    {
+      "epoch": 3.873913043478261,
+      "grad_norm": 0.010027135722339153,
+      "learning_rate": 2.0610522650816985e-06,
+      "loss": 0.0,
+      "step": 298
+    },
+    {
+      "epoch": 3.8869565217391306,
+      "grad_norm": 0.01416314672678709,
+      "learning_rate": 2.0393506142901347e-06,
+      "loss": 0.0,
+      "step": 299
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 0.003061251249164343,
+      "learning_rate": 2.017684836476258e-06,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 3.9130434782608696,
+      "grad_norm": 0.0023156912066042423,
+      "learning_rate": 1.9960566188581306e-06,
+      "loss": 0.0,
+      "step": 301
+    },
+    {
+      "epoch": 3.926086956521739,
+      "grad_norm": 0.0034826321061700583,
+      "learning_rate": 1.9744676457288225e-06,
+      "loss": 0.0,
+      "step": 302
+    },
+    {
+      "epoch": 3.9391304347826086,
+      "grad_norm": 0.001995071768760681,
+      "learning_rate": 1.952919598325247e-06,
+      "loss": 0.0,
+      "step": 303
+    },
+    {
+      "epoch": 3.9521739130434783,
+      "grad_norm": 0.00404984038323164,
+      "learning_rate": 1.9314141546972345e-06,
+      "loss": 0.0,
+      "step": 304
+    },
+    {
+      "epoch": 3.965217391304348,
+      "grad_norm": 0.0019303123699501157,
+      "learning_rate": 1.9099529895768552e-06,
+      "loss": 0.0,
+      "step": 305
+    },
+    {
+      "epoch": 3.9782608695652173,
+      "grad_norm": 0.0014716465957462788,
+      "learning_rate": 1.8885377742480005e-06,
+      "loss": 0.0,
+      "step": 306
+    },
+    {
+      "epoch": 3.991304347826087,
+      "grad_norm": 0.0028718914836645126,
+      "learning_rate": 1.8671701764162287e-06,
+      "loss": 0.0,
+      "step": 307
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.0028718914836645126,
+      "learning_rate": 1.8458518600788988e-06,
+      "loss": 0.0,
+      "step": 308
+    },
+    {
+      "epoch": 4.01304347826087,
+      "grad_norm": 0.01034778356552124,
+      "learning_rate": 1.8245844853955786e-06,
+      "loss": 0.0,
+      "step": 309
+    },
+    {
+      "epoch": 4.026086956521739,
+      "grad_norm": 0.001763720065355301,
+      "learning_rate": 1.8033697085587698e-06,
+      "loss": 0.0,
+      "step": 310
+    },
+    {
+      "epoch": 4.039130434782609,
+      "grad_norm": 0.0014494823990389705,
+      "learning_rate": 1.782209181664924e-06,
+      "loss": 0.0,
+      "step": 311
+    },
+    {
+      "epoch": 4.052173913043478,
+      "grad_norm": 0.0013845040230080485,
+      "learning_rate": 1.7611045525857902e-06,
+      "loss": 0.0,
+      "step": 312
+    },
+    {
+      "epoch": 4.065217391304348,
+      "grad_norm": 0.0025538592599332333,
+      "learning_rate": 1.740057464840088e-06,
+      "loss": 0.0,
+      "step": 313
+    },
+    {
+      "epoch": 4.078260869565217,
+      "grad_norm": 0.0015924959443509579,
+      "learning_rate": 1.7190695574655147e-06,
+      "loss": 0.0,
+      "step": 314
+    },
+    {
+      "epoch": 4.091304347826087,
+      "grad_norm": 0.0016162138199433684,
+      "learning_rate": 1.6981424648911112e-06,
+      "loss": 0.0,
+      "step": 315
+    },
+    {
+      "epoch": 4.104347826086957,
+      "grad_norm": 0.0015241021756082773,
+      "learning_rate": 1.677277816809975e-06,
+      "loss": 0.0,
+      "step": 316
+    },
+    {
+      "epoch": 4.1173913043478265,
+      "grad_norm": 0.0010168206645175815,
+      "learning_rate": 1.6564772380523546e-06,
+      "loss": 0.0,
+      "step": 317
+    },
+    {
+      "epoch": 4.130434782608695,
+      "grad_norm": 0.012456579133868217,
+      "learning_rate": 1.635742348459109e-06,
+      "loss": 0.0,
+      "step": 318
+    },
+    {
+      "epoch": 4.143478260869565,
+      "grad_norm": 0.00380521547049284,
+      "learning_rate": 1.6150747627555713e-06,
+      "loss": 0.0,
+      "step": 319
+    },
+    {
+      "epoch": 4.156521739130435,
+      "grad_norm": 0.0036846757866442204,
+      "learning_rate": 1.5944760904257944e-06,
+      "loss": 0.0,
+      "step": 320
+    },
+    {
+      "epoch": 4.1695652173913045,
+      "grad_norm": 0.0013467305107042193,
+      "learning_rate": 1.5739479355872162e-06,
+      "loss": 0.0,
+      "step": 321
+    },
+    {
+      "epoch": 4.182608695652174,
+      "grad_norm": 0.0018101097084581852,
+      "learning_rate": 1.5534918968657423e-06,
+      "loss": 0.0,
+      "step": 322
+    },
+    {
+      "epoch": 4.195652173913044,
+      "grad_norm": 0.001617030007764697,
+      "learning_rate": 1.5331095672712463e-06,
+      "loss": 0.0,
+      "step": 323
+    },
+    {
+      "epoch": 4.208695652173913,
+      "grad_norm": 0.00144918670412153,
+      "learning_rate": 1.5128025340735223e-06,
+      "loss": 0.0,
+      "step": 324
+    },
+    {
+      "epoch": 4.221739130434782,
+      "grad_norm": 0.0011092445347458124,
+      "learning_rate": 1.4925723786786691e-06,
+      "loss": 0.0,
+      "step": 325
+    },
+    {
+      "epoch": 4.234782608695652,
+      "grad_norm": 0.0028281533159315586,
+      "learning_rate": 1.4724206765059456e-06,
+      "loss": 0.0,
+      "step": 326
+    },
+    {
+      "epoch": 4.247826086956522,
+      "grad_norm": 0.0014354493468999863,
+      "learning_rate": 1.4523489968650795e-06,
+      "loss": 0.0,
+      "step": 327
+    },
+    {
+      "epoch": 4.260869565217392,
+      "grad_norm": 0.0017186496406793594,
+      "learning_rate": 1.4323589028340598e-06,
+      "loss": 0.0,
+      "step": 328
+    },
+    {
+      "epoch": 4.273913043478261,
+      "grad_norm": 0.0020970606710761786,
+      "learning_rate": 1.4124519511374158e-06,
+      "loss": 0.0,
+      "step": 329
+    },
+    {
+      "epoch": 4.28695652173913,
+      "grad_norm": 0.0015501041198149323,
+      "learning_rate": 1.3926296920249796e-06,
+      "loss": 0.0,
+      "step": 330
+    },
+    {
+      "epoch": 4.3,
+      "grad_norm": 0.0027128765359520912,
+      "learning_rate": 1.3728936691511704e-06,
+      "loss": 0.0,
+      "step": 331
+    },
+    {
+      "epoch": 4.3130434782608695,
+      "grad_norm": 0.0018941819434985518,
+      "learning_rate": 1.3532454194547734e-06,
+      "loss": 0.0,
+      "step": 332
+    },
+    {
+      "epoch": 4.326086956521739,
+      "grad_norm": 0.0018062669551,
+      "learning_rate": 1.3336864730392587e-06,
+      "loss": 0.0,
+      "step": 333
+    },
+    {
+      "epoch": 4.339130434782609,
+      "grad_norm": 0.002639364218339324,
+      "learning_rate": 1.314218353053619e-06,
+      "loss": 0.0,
+      "step": 334
+    },
+    {
+      "epoch": 4.352173913043479,
+      "grad_norm": 0.0031710860785096884,
+      "learning_rate": 1.2948425755737592e-06,
+      "loss": 0.0,
+      "step": 335
+    },
+    {
+      "epoch": 4.3652173913043475,
+      "grad_norm": 0.005298961885273457,
+      "learning_rate": 1.2755606494844294e-06,
+      "loss": 0.0,
+      "step": 336
+    },
+    {
+      "epoch": 4.378260869565217,
+      "grad_norm": 0.002524756360799074,
+      "learning_rate": 1.2563740763617198e-06,
+      "loss": 0.0,
+      "step": 337
+    },
+    {
+      "epoch": 4.391304347826087,
+      "grad_norm": 0.008356565609574318,
+      "learning_rate": 1.2372843503561318e-06,
+      "loss": 0.0,
+      "step": 338
+    },
+    {
+      "epoch": 4.404347826086957,
+      "grad_norm": 0.0027493846137076616,
+      "learning_rate": 1.218292958076213e-06,
+      "loss": 0.0,
+      "step": 339
+    },
+    {
+      "epoch": 4.417391304347826,
+      "grad_norm": 0.0022872223053127527,
+      "learning_rate": 1.1994013784727948e-06,
+      "loss": 0.0,
+      "step": 340
+    },
+    {
+      "epoch": 4.430434782608696,
+      "grad_norm": 0.0015215649036690593,
+      "learning_rate": 1.180611082723814e-06,
+      "loss": 0.0,
+      "step": 341
+    },
+    {
+      "epoch": 4.443478260869565,
+      "grad_norm": 0.002822963520884514,
+      "learning_rate": 1.161923534119752e-06,
+      "loss": 0.0,
+      "step": 342
+    },
+    {
+      "epoch": 4.456521739130435,
+      "grad_norm": 0.001620918745175004,
+      "learning_rate": 1.1433401879496723e-06,
+      "loss": 0.0,
+      "step": 343
+    },
+    {
+      "epoch": 4.469565217391304,
+      "grad_norm": 0.0026848018169403076,
+      "learning_rate": 1.1248624913878966e-06,
+      "loss": 0.0,
+      "step": 344
+    },
+    {
+      "epoch": 4.482608695652174,
+      "grad_norm": 0.002241417532786727,
+      "learning_rate": 1.1064918833813073e-06,
+      "loss": 0.0,
+      "step": 345
+    },
+    {
+      "epoch": 4.495652173913044,
+      "grad_norm": 0.001455339603126049,
+      "learning_rate": 1.088229794537283e-06,
+      "loss": 0.0,
+      "step": 346
+    },
+    {
+      "epoch": 4.5086956521739125,
+      "grad_norm": 0.001374992891214788,
+      "learning_rate": 1.0700776470122981e-06,
+      "loss": 0.0,
+      "step": 347
+    },
+    {
+      "epoch": 4.521739130434782,
+      "grad_norm": 0.0020591497886925936,
+      "learning_rate": 1.0520368544011661e-06,
+      "loss": 0.0,
+      "step": 348
+    },
+    {
+      "epoch": 4.534782608695652,
+      "grad_norm": 0.001313328742980957,
+      "learning_rate": 1.0341088216269625e-06,
+      "loss": 0.0,
+      "step": 349
+    },
+    {
+      "epoch": 4.547826086956522,
+      "grad_norm": 0.002054040553048253,
+      "learning_rate": 1.0162949448316089e-06,
+      "loss": 0.0,
+      "step": 350
+    },
+    {
+      "epoch": 4.560869565217391,
+      "grad_norm": 0.0022192494943737984,
+      "learning_rate": 9.98596611267158e-07,
+      "loss": 0.0,
+      "step": 351
+    },
+    {
+      "epoch": 4.573913043478261,
+      "grad_norm": 0.0027549685910344124,
+      "learning_rate": 9.81015199187753e-07,
+      "loss": 0.0,
+      "step": 352
+    },
+    {
+      "epoch": 4.586956521739131,
+      "grad_norm": 0.0015397547977045178,
+      "learning_rate": 9.63552077742301e-07,
+      "loss": 0.0,
+      "step": 353
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 0.002905682660639286,
+      "learning_rate": 9.462086068678519e-07,
+      "loss": 0.0,
+      "step": 354
+    },
+    {
+      "epoch": 4.613043478260869,
+      "grad_norm": 0.0014848869759589434,
+      "learning_rate": 9.289861371836886e-07,
+      "loss": 0.0,
+      "step": 355
+    },
+    {
+      "epoch": 4.626086956521739,
+      "grad_norm": 0.002772193867713213,
+      "learning_rate": 9.118860098861538e-07,
+      "loss": 0.0,
+      "step": 356
+    },
+    {
+      "epoch": 4.639130434782609,
+      "grad_norm": 0.001796722412109375,
+      "learning_rate": 8.949095566441985e-07,
+      "loss": 0.0,
+      "step": 357
+    },
+    {
+      "epoch": 4.6521739130434785,
+      "grad_norm": 0.0016671266639605165,
+      "learning_rate": 8.78058099495685e-07,
+      "loss": 0.0,
+      "step": 358
+    },
+    {
+      "epoch": 4.665217391304348,
+      "grad_norm": 0.0016365941846743226,
+      "learning_rate": 8.613329507444274e-07,
+      "loss": 0.0,
+      "step": 359
+    },
+    {
+      "epoch": 4.678260869565217,
+      "grad_norm": 0.0023541823029518127,
+      "learning_rate": 8.44735412857999e-07,
+      "loss": 0.0,
+      "step": 360
+    },
+    {
+      "epoch": 4.691304347826087,
+      "grad_norm": 0.0020769701804965734,
+      "learning_rate": 8.282667783663056e-07,
+      "loss": 0.0,
+      "step": 361
+    },
+    {
+      "epoch": 4.7043478260869565,
+      "grad_norm": 0.0018430390628054738,
+      "learning_rate": 8.119283297609238e-07,
+      "loss": 0.0,
+      "step": 362
+    },
+    {
+      "epoch": 4.717391304347826,
+      "grad_norm": 0.002417508512735367,
+      "learning_rate": 7.957213393952335e-07,
+      "loss": 0.0,
+      "step": 363
+    },
+    {
+      "epoch": 4.730434782608696,
+      "grad_norm": 0.001239007106050849,
+      "learning_rate": 7.796470693853281e-07,
+      "loss": 0.0,
+      "step": 364
+    },
+    {
+      "epoch": 4.743478260869566,
+      "grad_norm": 0.002612160984426737,
+      "learning_rate": 7.637067715117327e-07,
+      "loss": 0.0,
+      "step": 365
+    },
+    {
+      "epoch": 4.756521739130434,
+      "grad_norm": 0.002720440039411187,
+      "learning_rate": 7.479016871219174e-07,
+      "loss": 0.0,
+      "step": 366
+    },
+    {
+      "epoch": 4.769565217391304,
+      "grad_norm": 0.0030755773186683655,
+      "learning_rate": 7.322330470336314e-07,
+      "loss": 0.0,
+      "step": 367
+    },
+    {
+      "epoch": 4.782608695652174,
+      "grad_norm": 0.0019342007581144571,
+      "learning_rate": 7.167020714390502e-07,
+      "loss": 0.0,
+      "step": 368
+    },
+    {
+      "epoch": 4.7956521739130435,
+      "grad_norm": 0.002000426407903433,
+      "learning_rate": 7.013099698097539e-07,
+      "loss": 0.0,
+      "step": 369
+    },
+    {
+      "epoch": 4.808695652173913,
+      "grad_norm": 0.0011657639406621456,
+      "learning_rate": 6.860579408025436e-07,
+      "loss": 0.0,
+      "step": 370
+    },
+    {
+      "epoch": 4.821739130434783,
+      "grad_norm": 0.0016806419007480145,
+      "learning_rate": 6.709471721660904e-07,
+      "loss": 0.0,
+      "step": 371
+    },
+    {
+      "epoch": 4.834782608695652,
+      "grad_norm": 0.002683436032384634,
+      "learning_rate": 6.559788406484446e-07,
+      "loss": 0.0,
+      "step": 372
+    },
+    {
+      "epoch": 4.8478260869565215,
+      "grad_norm": 0.0020458789076656103,
+      "learning_rate": 6.41154111905393e-07,
+      "loss": 0.0,
+      "step": 373
+    },
+    {
+      "epoch": 4.860869565217391,
+      "grad_norm": 0.0017730394611135125,
+      "learning_rate": 6.264741404096875e-07,
+      "loss": 0.0,
+      "step": 374
+    },
+    {
+      "epoch": 4.873913043478261,
+      "grad_norm": 0.0016303405864164233,
+      "learning_rate": 6.119400693611358e-07,
+      "loss": 0.0,
+      "step": 375
+    },
+    {
+      "epoch": 4.886956521739131,
+      "grad_norm": 0.0013037021271884441,
+      "learning_rate": 5.975530305975808e-07,
+      "loss": 0.0,
+      "step": 376
+    },
+    {
+      "epoch": 4.9,
+      "grad_norm": 0.0019095903262495995,
+      "learning_rate": 5.833141445067541e-07,
+      "loss": 0.0,
+      "step": 377
+    },
+    {
+      "epoch": 4.913043478260869,
+      "grad_norm": 0.0017560195410624146,
+      "learning_rate": 5.692245199390281e-07,
+      "loss": 0.0001,
+      "step": 378
+    },
+    {
+      "epoch": 4.926086956521739,
+      "grad_norm": 0.08021274209022522,
+      "learning_rate": 5.552852541210651e-07,
+      "loss": 0.0,
+      "step": 379
+    },
+    {
+      "epoch": 4.939130434782609,
+      "grad_norm": 0.0026719518937170506,
+      "learning_rate": 5.414974325703687e-07,
+      "loss": 0.0,
+      "step": 380
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 456,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 76,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.55473380549591e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-380/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:134c4e3177c4f1e743e7e4ec30e3972d5f92595dfa94ae653b40c6765b255d01
+size 8056

checkpoint-380/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)

checkpoint-456/README.md

@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.1-8B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-456/adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-456/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b70d3eda148f97aaa6ecaa1ef0763872b134c1a17dbc4575bd1b77a7c2b105a3
+size 3443586272

checkpoint-456/global_step454/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e3047af85d2b2b573ae3598a6f61d26de0ff9f2cd895950499952766c3f2013
+size 20661195036

checkpoint-456/global_step454/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62ffd836444d279d3d30bf636a3e29aee447f98b786b71c2e44e663f8b4992d
+size 3555326649

checkpoint-456/latest

@@ -0,0 +1 @@
+global_step454

checkpoint-456/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93913c01877c7c78522e3d57a1be18f34f0ca3e012fe9f7169bafad7d4c21154
+size 14244

checkpoint-456/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d66926c4ac15decb077b4dbb5f19bd97f260580bc86874cdab12fa28d20a3d96
+size 1064

checkpoint-456/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-456/tokenizer.json

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

checkpoint-456/tokenizer_config.json

@@ -0,0 +1,2064 @@
+{
+  "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|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}

checkpoint-456/trainer_state.json

@@ -0,0 +1,3225 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.926086956521739,
+  "eval_steps": 500,
+  "global_step": 456,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013043478260869565,
+      "grad_norm": 30.641691207885742,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 2.1951,
+      "step": 1
+    },
+    {
+      "epoch": 0.02608695652173913,
+      "grad_norm": 31.937227249145508,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 2.274,
+      "step": 2
+    },
+    {
+      "epoch": 0.0391304347826087,
+      "grad_norm": 30.902198791503906,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 2.1994,
+      "step": 3
+    },
+    {
+      "epoch": 0.05217391304347826,
+      "grad_norm": 31.316129684448242,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 2.1975,
+      "step": 4
+    },
+    {
+      "epoch": 0.06521739130434782,
+      "grad_norm": 30.678176879882812,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 2.1836,
+      "step": 5
+    },
+    {
+      "epoch": 0.0782608695652174,
+      "grad_norm": 31.651874542236328,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 2.2658,
+      "step": 6
+    },
+    {
+      "epoch": 0.09130434782608696,
+      "grad_norm": 31.49991226196289,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 2.2324,
+      "step": 7
+    },
+    {
+      "epoch": 0.10434782608695652,
+      "grad_norm": 31.158674240112305,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 2.1922,
+      "step": 8
+    },
+    {
+      "epoch": 0.11739130434782609,
+      "grad_norm": 30.786540985107422,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 2.2302,
+      "step": 9
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "grad_norm": 30.784502029418945,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 2.1845,
+      "step": 10
+    },
+    {
+      "epoch": 0.14347826086956522,
+      "grad_norm": 30.878541946411133,
+      "learning_rate": 5.5e-07,
+      "loss": 2.1471,
+      "step": 11
+    },
+    {
+      "epoch": 0.1565217391304348,
+      "grad_norm": 30.616840362548828,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.086,
+      "step": 12
+    },
+    {
+      "epoch": 0.16956521739130434,
+      "grad_norm": 29.676923751831055,
+      "learning_rate": 6.5e-07,
+      "loss": 2.0468,
+      "step": 13
+    },
+    {
+      "epoch": 0.1826086956521739,
+      "grad_norm": 30.126493453979492,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 1.9897,
+      "step": 14
+    },
+    {
+      "epoch": 0.1956521739130435,
+      "grad_norm": 30.251602172851562,
+      "learning_rate": 7.5e-07,
+      "loss": 1.9232,
+      "step": 15
+    },
+    {
+      "epoch": 0.20869565217391303,
+      "grad_norm": 30.116798400878906,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.8406,
+      "step": 16
+    },
+    {
+      "epoch": 0.2217391304347826,
+      "grad_norm": 30.881160736083984,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 1.7809,
+      "step": 17
+    },
+    {
+      "epoch": 0.23478260869565218,
+      "grad_norm": 31.951828002929688,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 1.7001,
+      "step": 18
+    },
+    {
+      "epoch": 0.24782608695652175,
+      "grad_norm": 31.537166595458984,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 1.5591,
+      "step": 19
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 32.81351852416992,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.4578,
+      "step": 20
+    },
+    {
+      "epoch": 0.27391304347826084,
+      "grad_norm": 31.268814086914062,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 1.3437,
+      "step": 21
+    },
+    {
+      "epoch": 0.28695652173913044,
+      "grad_norm": 29.851335525512695,
+      "learning_rate": 1.1e-06,
+      "loss": 1.2298,
+      "step": 22
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 25.662965774536133,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 1.0528,
+      "step": 23
+    },
+    {
+      "epoch": 0.3130434782608696,
+      "grad_norm": 26.398494720458984,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.9624,
+      "step": 24
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": 26.3111629486084,
+      "learning_rate": 1.25e-06,
+      "loss": 0.7787,
+      "step": 25
+    },
+    {
+      "epoch": 0.3391304347826087,
+      "grad_norm": 28.78609275817871,
+      "learning_rate": 1.3e-06,
+      "loss": 0.6537,
+      "step": 26
+    },
+    {
+      "epoch": 0.3521739130434783,
+      "grad_norm": 26.990314483642578,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 0.4982,
+      "step": 27
+    },
+    {
+      "epoch": 0.3652173913043478,
+      "grad_norm": 23.103364944458008,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.3761,
+      "step": 28
+    },
+    {
+      "epoch": 0.3782608695652174,
+      "grad_norm": 20.322370529174805,
+      "learning_rate": 1.45e-06,
+      "loss": 0.2816,
+      "step": 29
+    },
+    {
+      "epoch": 0.391304347826087,
+      "grad_norm": 18.134693145751953,
+      "learning_rate": 1.5e-06,
+      "loss": 0.194,
+      "step": 30
+    },
+    {
+      "epoch": 0.4043478260869565,
+      "grad_norm": 10.411937713623047,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 0.1208,
+      "step": 31
+    },
+    {
+      "epoch": 0.41739130434782606,
+      "grad_norm": 3.981872081756592,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.0885,
+      "step": 32
+    },
+    {
+      "epoch": 0.43043478260869567,
+      "grad_norm": 2.513179063796997,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 0.0827,
+      "step": 33
+    },
+    {
+      "epoch": 0.4434782608695652,
+      "grad_norm": 1.3037446737289429,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 0.0738,
+      "step": 34
+    },
+    {
+      "epoch": 0.45652173913043476,
+      "grad_norm": 1.5666987895965576,
+      "learning_rate": 1.75e-06,
+      "loss": 0.0737,
+      "step": 35
+    },
+    {
+      "epoch": 0.46956521739130436,
+      "grad_norm": 1.8724833726882935,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.0716,
+      "step": 36
+    },
+    {
+      "epoch": 0.4826086956521739,
+      "grad_norm": 1.8552911281585693,
+      "learning_rate": 1.85e-06,
+      "loss": 0.0703,
+      "step": 37
+    },
+    {
+      "epoch": 0.4956521739130435,
+      "grad_norm": 1.165390968322754,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.0665,
+      "step": 38
+    },
+    {
+      "epoch": 0.508695652173913,
+      "grad_norm": 1.1661189794540405,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.0654,
+      "step": 39
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 1.3230024576187134,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0693,
+      "step": 40
+    },
+    {
+      "epoch": 0.5347826086956522,
+      "grad_norm": 0.7362420558929443,
+      "learning_rate": 2.05e-06,
+      "loss": 0.0665,
+      "step": 41
+    },
+    {
+      "epoch": 0.5478260869565217,
+      "grad_norm": 0.6983249187469482,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 0.0695,
+      "step": 42
+    },
+    {
+      "epoch": 0.5608695652173913,
+      "grad_norm": 1.134478211402893,
+      "learning_rate": 2.15e-06,
+      "loss": 0.0638,
+      "step": 43
+    },
+    {
+      "epoch": 0.5739130434782609,
+      "grad_norm": 1.1987451314926147,
+      "learning_rate": 2.2e-06,
+      "loss": 0.0538,
+      "step": 44
+    },
+    {
+      "epoch": 0.5869565217391305,
+      "grad_norm": 0.8745909929275513,
+      "learning_rate": 2.25e-06,
+      "loss": 0.0618,
+      "step": 45
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.0686204433441162,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 0.0662,
+      "step": 46
+    },
+    {
+      "epoch": 0.6130434782608696,
+      "grad_norm": 0.6556565165519714,
+      "learning_rate": 2.35e-06,
+      "loss": 0.056,
+      "step": 47
+    },
+    {
+      "epoch": 0.6260869565217392,
+      "grad_norm": 0.7634578943252563,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.0594,
+      "step": 48
+    },
+    {
+      "epoch": 0.6391304347826087,
+      "grad_norm": 0.8059038519859314,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.0615,
+      "step": 49
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 0.5894052982330322,
+      "learning_rate": 2.5e-06,
+      "loss": 0.058,
+      "step": 50
+    },
+    {
+      "epoch": 0.6652173913043479,
+      "grad_norm": 0.5712239146232605,
+      "learning_rate": 2.55e-06,
+      "loss": 0.0589,
+      "step": 51
+    },
+    {
+      "epoch": 0.6782608695652174,
+      "grad_norm": 0.6876189708709717,
+      "learning_rate": 2.6e-06,
+      "loss": 0.0607,
+      "step": 52
+    },
+    {
+      "epoch": 0.691304347826087,
+      "grad_norm": 0.623663067817688,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 0.0576,
+      "step": 53
+    },
+    {
+      "epoch": 0.7043478260869566,
+      "grad_norm": 0.6075452566146851,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.0612,
+      "step": 54
+    },
+    {
+      "epoch": 0.717391304347826,
+      "grad_norm": 0.7780712842941284,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.0566,
+      "step": 55
+    },
+    {
+      "epoch": 0.7304347826086957,
+      "grad_norm": 0.6400704383850098,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.0603,
+      "step": 56
+    },
+    {
+      "epoch": 0.7434782608695653,
+      "grad_norm": 0.6284154653549194,
+      "learning_rate": 2.85e-06,
+      "loss": 0.0547,
+      "step": 57
+    },
+    {
+      "epoch": 0.7565217391304347,
+      "grad_norm": 0.5499616265296936,
+      "learning_rate": 2.9e-06,
+      "loss": 0.0571,
+      "step": 58
+    },
+    {
+      "epoch": 0.7695652173913043,
+      "grad_norm": 0.6163158416748047,
+      "learning_rate": 2.95e-06,
+      "loss": 0.0587,
+      "step": 59
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 0.684912919998169,
+      "learning_rate": 3e-06,
+      "loss": 0.0596,
+      "step": 60
+    },
+    {
+      "epoch": 0.7956521739130434,
+      "grad_norm": 0.7246200442314148,
+      "learning_rate": 3.05e-06,
+      "loss": 0.0493,
+      "step": 61
+    },
+    {
+      "epoch": 0.808695652173913,
+      "grad_norm": 0.7146164774894714,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.0559,
+      "step": 62
+    },
+    {
+      "epoch": 0.8217391304347826,
+      "grad_norm": 0.6179472804069519,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 0.0604,
+      "step": 63
+    },
+    {
+      "epoch": 0.8347826086956521,
+      "grad_norm": 0.7352550029754639,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.0498,
+      "step": 64
+    },
+    {
+      "epoch": 0.8478260869565217,
+      "grad_norm": 0.5682029128074646,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.0562,
+      "step": 65
+    },
+    {
+      "epoch": 0.8608695652173913,
+      "grad_norm": 0.4977523982524872,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.0534,
+      "step": 66
+    },
+    {
+      "epoch": 0.8739130434782608,
+      "grad_norm": 0.5390787124633789,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 0.0534,
+      "step": 67
+    },
+    {
+      "epoch": 0.8869565217391304,
+      "grad_norm": 0.712452232837677,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.0528,
+      "step": 68
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.5136511921882629,
+      "learning_rate": 3.45e-06,
+      "loss": 0.0529,
+      "step": 69
+    },
+    {
+      "epoch": 0.9130434782608695,
+      "grad_norm": 0.5339029431343079,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0489,
+      "step": 70
+    },
+    {
+      "epoch": 0.9260869565217391,
+      "grad_norm": 0.647507905960083,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 0.0477,
+      "step": 71
+    },
+    {
+      "epoch": 0.9391304347826087,
+      "grad_norm": 0.5351842641830444,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.0491,
+      "step": 72
+    },
+    {
+      "epoch": 0.9521739130434783,
+      "grad_norm": 0.620066225528717,
+      "learning_rate": 3.65e-06,
+      "loss": 0.0477,
+      "step": 73
+    },
+    {
+      "epoch": 0.9652173913043478,
+      "grad_norm": 0.5559766292572021,
+      "learning_rate": 3.7e-06,
+      "loss": 0.0444,
+      "step": 74
+    },
+    {
+      "epoch": 0.9782608695652174,
+      "grad_norm": 0.5821895599365234,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0484,
+      "step": 75
+    },
+    {
+      "epoch": 0.991304347826087,
+      "grad_norm": 0.6146248579025269,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.046,
+      "step": 76
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6146248579025269,
+      "learning_rate": 3.85e-06,
+      "loss": 0.0538,
+      "step": 77
+    },
+    {
+      "epoch": 1.0130434782608695,
+      "grad_norm": 1.2398924827575684,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.0512,
+      "step": 78
+    },
+    {
+      "epoch": 1.0260869565217392,
+      "grad_norm": 0.5804176330566406,
+      "learning_rate": 3.95e-06,
+      "loss": 0.046,
+      "step": 79
+    },
+    {
+      "epoch": 1.0391304347826087,
+      "grad_norm": 0.47833946347236633,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0428,
+      "step": 80
+    },
+    {
+      "epoch": 1.0521739130434782,
+      "grad_norm": 0.562652051448822,
+      "learning_rate": 4.05e-06,
+      "loss": 0.0403,
+      "step": 81
+    },
+    {
+      "epoch": 1.065217391304348,
+      "grad_norm": 0.5788324475288391,
+      "learning_rate": 4.1e-06,
+      "loss": 0.0399,
+      "step": 82
+    },
+    {
+      "epoch": 1.0782608695652174,
+      "grad_norm": 0.513817310333252,
+      "learning_rate": 4.15e-06,
+      "loss": 0.0417,
+      "step": 83
+    },
+    {
+      "epoch": 1.0913043478260869,
+      "grad_norm": 0.6000502705574036,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.042,
+      "step": 84
+    },
+    {
+      "epoch": 1.1043478260869566,
+      "grad_norm": 0.721695601940155,
+      "learning_rate": 4.25e-06,
+      "loss": 0.0472,
+      "step": 85
+    },
+    {
+      "epoch": 1.117391304347826,
+      "grad_norm": 0.7209702730178833,
+      "learning_rate": 4.3e-06,
+      "loss": 0.0371,
+      "step": 86
+    },
+    {
+      "epoch": 1.1304347826086956,
+      "grad_norm": 0.5806598663330078,
+      "learning_rate": 4.350000000000001e-06,
+      "loss": 0.0478,
+      "step": 87
+    },
+    {
+      "epoch": 1.1434782608695653,
+      "grad_norm": 0.6562755703926086,
+      "learning_rate": 4.4e-06,
+      "loss": 0.0414,
+      "step": 88
+    },
+    {
+      "epoch": 1.1565217391304348,
+      "grad_norm": 0.5621042847633362,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 0.0373,
+      "step": 89
+    },
+    {
+      "epoch": 1.1695652173913043,
+      "grad_norm": 0.6904962658882141,
+      "learning_rate": 4.5e-06,
+      "loss": 0.0481,
+      "step": 90
+    },
+    {
+      "epoch": 1.182608695652174,
+      "grad_norm": 0.5569142699241638,
+      "learning_rate": 4.5500000000000005e-06,
+      "loss": 0.0425,
+      "step": 91
+    },
+    {
+      "epoch": 1.1956521739130435,
+      "grad_norm": 0.6834372282028198,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.04,
+      "step": 92
+    },
+    {
+      "epoch": 1.208695652173913,
+      "grad_norm": 0.6567809581756592,
+      "learning_rate": 4.65e-06,
+      "loss": 0.0399,
+      "step": 93
+    },
+    {
+      "epoch": 1.2217391304347827,
+      "grad_norm": 0.5778902769088745,
+      "learning_rate": 4.7e-06,
+      "loss": 0.0337,
+      "step": 94
+    },
+    {
+      "epoch": 1.2347826086956522,
+      "grad_norm": 0.5971974730491638,
+      "learning_rate": 4.75e-06,
+      "loss": 0.0364,
+      "step": 95
+    },
+    {
+      "epoch": 1.2478260869565219,
+      "grad_norm": 0.5933169722557068,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.0357,
+      "step": 96
+    },
+    {
+      "epoch": 1.2608695652173914,
+      "grad_norm": 0.6292222142219543,
+      "learning_rate": 4.85e-06,
+      "loss": 0.031,
+      "step": 97
+    },
+    {
+      "epoch": 1.2739130434782608,
+      "grad_norm": 0.8789151906967163,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.0313,
+      "step": 98
+    },
+    {
+      "epoch": 1.2869565217391306,
+      "grad_norm": 0.6100375652313232,
+      "learning_rate": 4.95e-06,
+      "loss": 0.0343,
+      "step": 99
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.7254518866539001,
+      "learning_rate": 5e-06,
+      "loss": 0.0364,
+      "step": 100
+    },
+    {
+      "epoch": 1.3130434782608695,
+      "grad_norm": 0.6824344396591187,
+      "learning_rate": 4.999902656502973e-06,
+      "loss": 0.0297,
+      "step": 101
+    },
+    {
+      "epoch": 1.3260869565217392,
+      "grad_norm": 0.5075684785842896,
+      "learning_rate": 4.9996106335924965e-06,
+      "loss": 0.0323,
+      "step": 102
+    },
+    {
+      "epoch": 1.3391304347826087,
+      "grad_norm": 0.5161061882972717,
+      "learning_rate": 4.999123954009797e-06,
+      "loss": 0.0289,
+      "step": 103
+    },
+    {
+      "epoch": 1.3521739130434782,
+      "grad_norm": 0.5754029154777527,
+      "learning_rate": 4.998442655654946e-06,
+      "loss": 0.0333,
+      "step": 104
+    },
+    {
+      "epoch": 1.365217391304348,
+      "grad_norm": 0.7110198736190796,
+      "learning_rate": 4.997566791583916e-06,
+      "loss": 0.0304,
+      "step": 105
+    },
+    {
+      "epoch": 1.3782608695652174,
+      "grad_norm": 0.7235414385795593,
+      "learning_rate": 4.996496430004446e-06,
+      "loss": 0.0319,
+      "step": 106
+    },
+    {
+      "epoch": 1.391304347826087,
+      "grad_norm": 0.5558100342750549,
+      "learning_rate": 4.995231654270726e-06,
+      "loss": 0.0256,
+      "step": 107
+    },
+    {
+      "epoch": 1.4043478260869566,
+      "grad_norm": 0.5645644068717957,
+      "learning_rate": 4.993772562876909e-06,
+      "loss": 0.0257,
+      "step": 108
+    },
+    {
+      "epoch": 1.4173913043478261,
+      "grad_norm": 0.589040994644165,
+      "learning_rate": 4.992119269449445e-06,
+      "loss": 0.026,
+      "step": 109
+    },
+    {
+      "epoch": 1.4304347826086956,
+      "grad_norm": 0.7214376330375671,
+      "learning_rate": 4.990271902738223e-06,
+      "loss": 0.0325,
+      "step": 110
+    },
+    {
+      "epoch": 1.4434782608695653,
+      "grad_norm": 0.7478785514831543,
+      "learning_rate": 4.988230606606552e-06,
+      "loss": 0.0241,
+      "step": 111
+    },
+    {
+      "epoch": 1.4565217391304348,
+      "grad_norm": 0.9108967781066895,
+      "learning_rate": 4.985995540019956e-06,
+      "loss": 0.0242,
+      "step": 112
+    },
+    {
+      "epoch": 1.4695652173913043,
+      "grad_norm": 0.6113864779472351,
+      "learning_rate": 4.983566877033791e-06,
+      "loss": 0.0263,
+      "step": 113
+    },
+    {
+      "epoch": 1.482608695652174,
+      "grad_norm": 0.6748284101486206,
+      "learning_rate": 4.980944806779698e-06,
+      "loss": 0.0235,
+      "step": 114
+    },
+    {
+      "epoch": 1.4956521739130435,
+      "grad_norm": 0.5893757939338684,
+      "learning_rate": 4.9781295334508664e-06,
+      "loss": 0.0292,
+      "step": 115
+    },
+    {
+      "epoch": 1.508695652173913,
+      "grad_norm": 0.8105467557907104,
+      "learning_rate": 4.975121276286136e-06,
+      "loss": 0.0217,
+      "step": 116
+    },
+    {
+      "epoch": 1.5217391304347827,
+      "grad_norm": 0.5484834909439087,
+      "learning_rate": 4.9719202695529265e-06,
+      "loss": 0.0241,
+      "step": 117
+    },
+    {
+      "epoch": 1.5347826086956522,
+      "grad_norm": 0.6067440509796143,
+      "learning_rate": 4.968526762528988e-06,
+      "loss": 0.025,
+      "step": 118
+    },
+    {
+      "epoch": 1.5478260869565217,
+      "grad_norm": 0.7170385122299194,
+      "learning_rate": 4.964941019482995e-06,
+      "loss": 0.0163,
+      "step": 119
+    },
+    {
+      "epoch": 1.5608695652173914,
+      "grad_norm": 0.5389299392700195,
+      "learning_rate": 4.961163319653959e-06,
+      "loss": 0.022,
+      "step": 120
+    },
+    {
+      "epoch": 1.5739130434782609,
+      "grad_norm": 0.8852945566177368,
+      "learning_rate": 4.9571939572294914e-06,
+      "loss": 0.0202,
+      "step": 121
+    },
+    {
+      "epoch": 1.5869565217391304,
+      "grad_norm": 0.6196063756942749,
+      "learning_rate": 4.953033241322887e-06,
+      "loss": 0.0205,
+      "step": 122
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.5872839093208313,
+      "learning_rate": 4.948681495949055e-06,
+      "loss": 0.0175,
+      "step": 123
+    },
+    {
+      "epoch": 1.6130434782608696,
+      "grad_norm": 0.6874949932098389,
+      "learning_rate": 4.944139059999286e-06,
+      "loss": 0.0179,
+      "step": 124
+    },
+    {
+      "epoch": 1.626086956521739,
+      "grad_norm": 0.49811050295829773,
+      "learning_rate": 4.939406287214861e-06,
+      "loss": 0.0193,
+      "step": 125
+    },
+    {
+      "epoch": 1.6391304347826088,
+      "grad_norm": 0.6337487101554871,
+      "learning_rate": 4.9344835461595016e-06,
+      "loss": 0.0176,
+      "step": 126
+    },
+    {
+      "epoch": 1.6521739130434783,
+      "grad_norm": 0.7472748160362244,
+      "learning_rate": 4.929371220190671e-06,
+      "loss": 0.0139,
+      "step": 127
+    },
+    {
+      "epoch": 1.6652173913043478,
+      "grad_norm": 0.6550290584564209,
+      "learning_rate": 4.9240697074297205e-06,
+      "loss": 0.0161,
+      "step": 128
+    },
+    {
+      "epoch": 1.6782608695652175,
+      "grad_norm": 0.473919540643692,
+      "learning_rate": 4.918579420730884e-06,
+      "loss": 0.0163,
+      "step": 129
+    },
+    {
+      "epoch": 1.691304347826087,
+      "grad_norm": 0.5661535859107971,
+      "learning_rate": 4.912900787649124e-06,
+      "loss": 0.0183,
+      "step": 130
+    },
+    {
+      "epoch": 1.7043478260869565,
+      "grad_norm": 0.7776857018470764,
+      "learning_rate": 4.907034250406846e-06,
+      "loss": 0.0117,
+      "step": 131
+    },
+    {
+      "epoch": 1.7173913043478262,
+      "grad_norm": 0.4113011658191681,
+      "learning_rate": 4.900980265859449e-06,
+      "loss": 0.0119,
+      "step": 132
+    },
+    {
+      "epoch": 1.7304347826086957,
+      "grad_norm": 0.7155903577804565,
+      "learning_rate": 4.894739305459754e-06,
+      "loss": 0.0094,
+      "step": 133
+    },
+    {
+      "epoch": 1.7434782608695651,
+      "grad_norm": 0.7912915349006653,
+      "learning_rate": 4.88831185522129e-06,
+      "loss": 0.0169,
+      "step": 134
+    },
+    {
+      "epoch": 1.7565217391304349,
+      "grad_norm": 0.6020934581756592,
+      "learning_rate": 4.881698415680442e-06,
+      "loss": 0.0163,
+      "step": 135
+    },
+    {
+      "epoch": 1.7695652173913043,
+      "grad_norm": 0.6352165341377258,
+      "learning_rate": 4.874899501857477e-06,
+      "loss": 0.01,
+      "step": 136
+    },
+    {
+      "epoch": 1.7826086956521738,
+      "grad_norm": 0.45883336663246155,
+      "learning_rate": 4.867915643216434e-06,
+      "loss": 0.0135,
+      "step": 137
+    },
+    {
+      "epoch": 1.7956521739130435,
+      "grad_norm": 0.6866053938865662,
+      "learning_rate": 4.860747383623889e-06,
+      "loss": 0.0095,
+      "step": 138
+    },
+    {
+      "epoch": 1.808695652173913,
+      "grad_norm": 0.44558900594711304,
+      "learning_rate": 4.85339528130661e-06,
+      "loss": 0.0081,
+      "step": 139
+    },
+    {
+      "epoch": 1.8217391304347825,
+      "grad_norm": 0.47094374895095825,
+      "learning_rate": 4.845859908808074e-06,
+      "loss": 0.0095,
+      "step": 140
+    },
+    {
+      "epoch": 1.8347826086956522,
+      "grad_norm": 0.4724484086036682,
+      "learning_rate": 4.838141852943891e-06,
+      "loss": 0.0085,
+      "step": 141
+    },
+    {
+      "epoch": 1.8478260869565217,
+      "grad_norm": 0.6628655195236206,
+      "learning_rate": 4.830241714756099e-06,
+      "loss": 0.014,
+      "step": 142
+    },
+    {
+      "epoch": 1.8608695652173912,
+      "grad_norm": 0.7814735174179077,
+      "learning_rate": 4.822160109466361e-06,
+      "loss": 0.0108,
+      "step": 143
+    },
+    {
+      "epoch": 1.873913043478261,
+      "grad_norm": 0.45942002534866333,
+      "learning_rate": 4.813897666428054e-06,
+      "loss": 0.011,
+      "step": 144
+    },
+    {
+      "epoch": 1.8869565217391304,
+      "grad_norm": 0.6027839183807373,
+      "learning_rate": 4.805455029077255e-06,
+      "loss": 0.0054,
+      "step": 145
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.4727053642272949,
+      "learning_rate": 4.79683285488264e-06,
+      "loss": 0.0081,
+      "step": 146
+    },
+    {
+      "epoch": 1.9130434782608696,
+      "grad_norm": 0.6347537040710449,
+      "learning_rate": 4.788031815294282e-06,
+      "loss": 0.0058,
+      "step": 147
+    },
+    {
+      "epoch": 1.9260869565217391,
+      "grad_norm": 0.4297194480895996,
+      "learning_rate": 4.779052595691355e-06,
+      "loss": 0.0062,
+      "step": 148
+    },
+    {
+      "epoch": 1.9391304347826086,
+      "grad_norm": 0.7891242504119873,
+      "learning_rate": 4.76989589532877e-06,
+      "loss": 0.0079,
+      "step": 149
+    },
+    {
+      "epoch": 1.9521739130434783,
+      "grad_norm": 0.5888785123825073,
+      "learning_rate": 4.7605624272827125e-06,
+      "loss": 0.0046,
+      "step": 150
+    },
+    {
+      "epoch": 1.9652173913043478,
+      "grad_norm": 0.5303910970687866,
+      "learning_rate": 4.75105291839512e-06,
+      "loss": 0.0071,
+      "step": 151
+    },
+    {
+      "epoch": 1.9782608695652173,
+      "grad_norm": 0.6492812037467957,
+      "learning_rate": 4.741368109217072e-06,
+      "loss": 0.0072,
+      "step": 152
+    },
+    {
+      "epoch": 1.991304347826087,
+      "grad_norm": 0.6820566654205322,
+      "learning_rate": 4.7315087539511225e-06,
+      "loss": 0.0058,
+      "step": 153
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.4742223918437958,
+      "learning_rate": 4.721475620392567e-06,
+      "loss": 0.0078,
+      "step": 154
+    },
+    {
+      "epoch": 2.0130434782608697,
+      "grad_norm": 1.0548763275146484,
+      "learning_rate": 4.711269489869654e-06,
+      "loss": 0.0035,
+      "step": 155
+    },
+    {
+      "epoch": 2.026086956521739,
+      "grad_norm": 0.2593505382537842,
+      "learning_rate": 4.700891157182729e-06,
+      "loss": 0.0026,
+      "step": 156
+    },
+    {
+      "epoch": 2.0391304347826087,
+      "grad_norm": 0.6592870354652405,
+      "learning_rate": 4.690341430542351e-06,
+      "loss": 0.0009,
+      "step": 157
+    },
+    {
+      "epoch": 2.0521739130434784,
+      "grad_norm": 0.10995268076658249,
+      "learning_rate": 4.679621131506347e-06,
+      "loss": 0.0025,
+      "step": 158
+    },
+    {
+      "epoch": 2.0652173913043477,
+      "grad_norm": 1.0068087577819824,
+      "learning_rate": 4.668731094915835e-06,
+      "loss": 0.0016,
+      "step": 159
+    },
+    {
+      "epoch": 2.0782608695652174,
+      "grad_norm": 0.19254828989505768,
+      "learning_rate": 4.657672168830211e-06,
+      "loss": 0.0017,
+      "step": 160
+    },
+    {
+      "epoch": 2.091304347826087,
+      "grad_norm": 0.513418972492218,
+      "learning_rate": 4.646445214461105e-06,
+      "loss": 0.0032,
+      "step": 161
+    },
+    {
+      "epoch": 2.1043478260869564,
+      "grad_norm": 0.4659607410430908,
+      "learning_rate": 4.635051106105316e-06,
+      "loss": 0.0027,
+      "step": 162
+    },
+    {
+      "epoch": 2.117391304347826,
+      "grad_norm": 0.26887616515159607,
+      "learning_rate": 4.623490731076728e-06,
+      "loss": 0.0007,
+      "step": 163
+    },
+    {
+      "epoch": 2.130434782608696,
+      "grad_norm": 0.22268249094486237,
+      "learning_rate": 4.6117649896372055e-06,
+      "loss": 0.001,
+      "step": 164
+    },
+    {
+      "epoch": 2.143478260869565,
+      "grad_norm": 0.35821816325187683,
+      "learning_rate": 4.59987479492649e-06,
+      "loss": 0.0023,
+      "step": 165
+    },
+    {
+      "epoch": 2.1565217391304348,
+      "grad_norm": 0.4691464602947235,
+      "learning_rate": 4.587821072891089e-06,
+      "loss": 0.0046,
+      "step": 166
+    },
+    {
+      "epoch": 2.1695652173913045,
+      "grad_norm": 0.6060182452201843,
+      "learning_rate": 4.5756047622121665e-06,
+      "loss": 0.0024,
+      "step": 167
+    },
+    {
+      "epoch": 2.1826086956521737,
+      "grad_norm": 0.37854066491127014,
+      "learning_rate": 4.563226814232444e-06,
+      "loss": 0.0021,
+      "step": 168
+    },
+    {
+      "epoch": 2.1956521739130435,
+      "grad_norm": 0.903462827205658,
+      "learning_rate": 4.550688192882115e-06,
+      "loss": 0.001,
+      "step": 169
+    },
+    {
+      "epoch": 2.208695652173913,
+      "grad_norm": 0.5006014704704285,
+      "learning_rate": 4.53798987460378e-06,
+      "loss": 0.0034,
+      "step": 170
+    },
+    {
+      "epoch": 2.2217391304347824,
+      "grad_norm": 0.49557602405548096,
+      "learning_rate": 4.525132848276405e-06,
+      "loss": 0.0005,
+      "step": 171
+    },
+    {
+      "epoch": 2.234782608695652,
+      "grad_norm": 0.7139260768890381,
+      "learning_rate": 4.512118115138315e-06,
+      "loss": 0.0061,
+      "step": 172
+    },
+    {
+      "epoch": 2.247826086956522,
+      "grad_norm": 0.8578881025314331,
+      "learning_rate": 4.498946688709216e-06,
+      "loss": 0.0017,
+      "step": 173
+    },
+    {
+      "epoch": 2.260869565217391,
+      "grad_norm": 0.22415713965892792,
+      "learning_rate": 4.485619594711278e-06,
+      "loss": 0.0007,
+      "step": 174
+    },
+    {
+      "epoch": 2.273913043478261,
+      "grad_norm": 0.3430750072002411,
+      "learning_rate": 4.4721378709892475e-06,
+      "loss": 0.002,
+      "step": 175
+    },
+    {
+      "epoch": 2.2869565217391306,
+      "grad_norm": 0.3404991626739502,
+      "learning_rate": 4.4585025674296315e-06,
+      "loss": 0.0011,
+      "step": 176
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.45432400703430176,
+      "learning_rate": 4.444714745878936e-06,
+      "loss": 0.0012,
+      "step": 177
+    },
+    {
+      "epoch": 2.3130434782608695,
+      "grad_norm": 0.2696153223514557,
+      "learning_rate": 4.430775480060973e-06,
+      "loss": 0.0012,
+      "step": 178
+    },
+    {
+      "epoch": 2.3260869565217392,
+      "grad_norm": 0.10708807408809662,
+      "learning_rate": 4.416685855493246e-06,
+      "loss": 0.0008,
+      "step": 179
+    },
+    {
+      "epoch": 2.3391304347826085,
+      "grad_norm": 0.39214053750038147,
+      "learning_rate": 4.4024469694024194e-06,
+      "loss": 0.0019,
+      "step": 180
+    },
+    {
+      "epoch": 2.3521739130434782,
+      "grad_norm": 0.6886045336723328,
+      "learning_rate": 4.388059930638865e-06,
+      "loss": 0.0016,
+      "step": 181
+    },
+    {
+      "epoch": 2.365217391304348,
+      "grad_norm": 0.21321725845336914,
+      "learning_rate": 4.373525859590313e-06,
+      "loss": 0.0018,
+      "step": 182
+    },
+    {
+      "epoch": 2.378260869565217,
+      "grad_norm": 0.35919421911239624,
+      "learning_rate": 4.358845888094607e-06,
+      "loss": 0.0013,
+      "step": 183
+    },
+    {
+      "epoch": 2.391304347826087,
+      "grad_norm": 0.27048271894454956,
+      "learning_rate": 4.3440211593515556e-06,
+      "loss": 0.0027,
+      "step": 184
+    },
+    {
+      "epoch": 2.4043478260869566,
+      "grad_norm": 0.5377674698829651,
+      "learning_rate": 4.32905282783391e-06,
+      "loss": 0.0011,
+      "step": 185
+    },
+    {
+      "epoch": 2.417391304347826,
+      "grad_norm": 0.12088856846094131,
+      "learning_rate": 4.313942059197457e-06,
+      "loss": 0.0018,
+      "step": 186
+    },
+    {
+      "epoch": 2.4304347826086956,
+      "grad_norm": 0.4951612055301666,
+      "learning_rate": 4.298690030190247e-06,
+      "loss": 0.0006,
+      "step": 187
+    },
+    {
+      "epoch": 2.4434782608695653,
+      "grad_norm": 0.11120982468128204,
+      "learning_rate": 4.283297928560951e-06,
+      "loss": 0.0007,
+      "step": 188
+    },
+    {
+      "epoch": 2.4565217391304346,
+      "grad_norm": 0.12437040358781815,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.0004,
+      "step": 189
+    },
+    {
+      "epoch": 2.4695652173913043,
+      "grad_norm": 0.10102014243602753,
+      "learning_rate": 4.252098312878083e-06,
+      "loss": 0.0004,
+      "step": 190
+    },
+    {
+      "epoch": 2.482608695652174,
+      "grad_norm": 0.16300979256629944,
+      "learning_rate": 4.236293228488267e-06,
+      "loss": 0.0008,
+      "step": 191
+    },
+    {
+      "epoch": 2.4956521739130437,
+      "grad_norm": 0.2017083615064621,
+      "learning_rate": 4.220352930614672e-06,
+      "loss": 0.0004,
+      "step": 192
+    },
+    {
+      "epoch": 2.508695652173913,
+      "grad_norm": 0.20179031789302826,
+      "learning_rate": 4.204278660604767e-06,
+      "loss": 0.0009,
+      "step": 193
+    },
+    {
+      "epoch": 2.5217391304347827,
+      "grad_norm": 0.2158278077840805,
+      "learning_rate": 4.1880716702390764e-06,
+      "loss": 0.002,
+      "step": 194
+    },
+    {
+      "epoch": 2.534782608695652,
+      "grad_norm": 0.326331228017807,
+      "learning_rate": 4.171733221633695e-06,
+      "loss": 0.0014,
+      "step": 195
+    },
+    {
+      "epoch": 2.5478260869565217,
+      "grad_norm": 0.30759623646736145,
+      "learning_rate": 4.155264587142002e-06,
+      "loss": 0.0008,
+      "step": 196
+    },
+    {
+      "epoch": 2.5608695652173914,
+      "grad_norm": 0.3855862021446228,
+      "learning_rate": 4.138667049255574e-06,
+      "loss": 0.0003,
+      "step": 197
+    },
+    {
+      "epoch": 2.573913043478261,
+      "grad_norm": 0.05741116404533386,
+      "learning_rate": 4.121941900504316e-06,
+      "loss": 0.0001,
+      "step": 198
+    },
+    {
+      "epoch": 2.5869565217391304,
+      "grad_norm": 0.015228237956762314,
+      "learning_rate": 4.105090443355801e-06,
+      "loss": 0.0002,
+      "step": 199
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.4413849711418152,
+      "learning_rate": 4.088113990113846e-06,
+      "loss": 0.0007,
+      "step": 200
+    },
+    {
+      "epoch": 2.6130434782608694,
+      "grad_norm": 0.303357869386673,
+      "learning_rate": 4.071013862816311e-06,
+      "loss": 0.0002,
+      "step": 201
+    },
+    {
+      "epoch": 2.626086956521739,
+      "grad_norm": 0.19713574647903442,
+      "learning_rate": 4.0537913931321495e-06,
+      "loss": 0.0006,
+      "step": 202
+    },
+    {
+      "epoch": 2.639130434782609,
+      "grad_norm": 0.39923036098480225,
+      "learning_rate": 4.036447922257699e-06,
+      "loss": 0.0005,
+      "step": 203
+    },
+    {
+      "epoch": 2.6521739130434785,
+      "grad_norm": 0.13886815309524536,
+      "learning_rate": 4.018984800812248e-06,
+      "loss": 0.0003,
+      "step": 204
+    },
+    {
+      "epoch": 2.6652173913043478,
+      "grad_norm": 0.3616029620170593,
+      "learning_rate": 4.001403388732842e-06,
+      "loss": 0.0011,
+      "step": 205
+    },
+    {
+      "epoch": 2.6782608695652175,
+      "grad_norm": 0.09302274137735367,
+      "learning_rate": 3.983705055168391e-06,
+      "loss": 0.0001,
+      "step": 206
+    },
+    {
+      "epoch": 2.6913043478260867,
+      "grad_norm": 0.11136471480131149,
+      "learning_rate": 3.965891178373038e-06,
+      "loss": 0.0002,
+      "step": 207
+    },
+    {
+      "epoch": 2.7043478260869565,
+      "grad_norm": 0.030531201511621475,
+      "learning_rate": 3.947963145598833e-06,
+      "loss": 0.0001,
+      "step": 208
+    },
+    {
+      "epoch": 2.717391304347826,
+      "grad_norm": 0.07998622953891754,
+      "learning_rate": 3.929922352987702e-06,
+      "loss": 0.0012,
+      "step": 209
+    },
+    {
+      "epoch": 2.730434782608696,
+      "grad_norm": 0.24564768373966217,
+      "learning_rate": 3.911770205462717e-06,
+      "loss": 0.0001,
+      "step": 210
+    },
+    {
+      "epoch": 2.743478260869565,
+      "grad_norm": 0.3731745481491089,
+      "learning_rate": 3.8935081166186935e-06,
+      "loss": 0.0005,
+      "step": 211
+    },
+    {
+      "epoch": 2.756521739130435,
+      "grad_norm": 0.02599702961742878,
+      "learning_rate": 3.875137508612104e-06,
+      "loss": 0.0001,
+      "step": 212
+    },
+    {
+      "epoch": 2.769565217391304,
+      "grad_norm": 0.013257239945232868,
+      "learning_rate": 3.856659812050328e-06,
+      "loss": 0.0003,
+      "step": 213
+    },
+    {
+      "epoch": 2.782608695652174,
+      "grad_norm": 0.23876884579658508,
+      "learning_rate": 3.838076465880248e-06,
+      "loss": 0.0001,
+      "step": 214
+    },
+    {
+      "epoch": 2.7956521739130435,
+      "grad_norm": 0.022550106048583984,
+      "learning_rate": 3.819388917276186e-06,
+      "loss": 0.0001,
+      "step": 215
+    },
+    {
+      "epoch": 2.8086956521739133,
+      "grad_norm": 0.0803162083029747,
+      "learning_rate": 3.8005986215272056e-06,
+      "loss": 0.0001,
+      "step": 216
+    },
+    {
+      "epoch": 2.8217391304347825,
+      "grad_norm": 0.04428872838616371,
+      "learning_rate": 3.7817070419237866e-06,
+      "loss": 0.0001,
+      "step": 217
+    },
+    {
+      "epoch": 2.8347826086956522,
+      "grad_norm": 0.06828437000513077,
+      "learning_rate": 3.7627156496438686e-06,
+      "loss": 0.0001,
+      "step": 218
+    },
+    {
+      "epoch": 2.8478260869565215,
+      "grad_norm": 0.6988795399665833,
+      "learning_rate": 3.7436259236382797e-06,
+      "loss": 0.0013,
+      "step": 219
+    },
+    {
+      "epoch": 2.860869565217391,
+      "grad_norm": 0.16631139814853668,
+      "learning_rate": 3.7244393505155713e-06,
+      "loss": 0.0001,
+      "step": 220
+    },
+    {
+      "epoch": 2.873913043478261,
+      "grad_norm": 0.03770599141716957,
+      "learning_rate": 3.7051574244262412e-06,
+      "loss": 0.0,
+      "step": 221
+    },
+    {
+      "epoch": 2.8869565217391306,
+      "grad_norm": 0.012837939895689487,
+      "learning_rate": 3.6857816469463806e-06,
+      "loss": 0.0,
+      "step": 222
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.042198728770017624,
+      "learning_rate": 3.6663135269607413e-06,
+      "loss": 0.0001,
+      "step": 223
+    },
+    {
+      "epoch": 2.9130434782608696,
+      "grad_norm": 0.15300290286540985,
+      "learning_rate": 3.6467545805452266e-06,
+      "loss": 0.0004,
+      "step": 224
+    },
+    {
+      "epoch": 2.926086956521739,
+      "grad_norm": 0.592495322227478,
+      "learning_rate": 3.6271063308488298e-06,
+      "loss": 0.0004,
+      "step": 225
+    },
+    {
+      "epoch": 2.9391304347826086,
+      "grad_norm": 0.006714676506817341,
+      "learning_rate": 3.6073703079750204e-06,
+      "loss": 0.0001,
+      "step": 226
+    },
+    {
+      "epoch": 2.9521739130434783,
+      "grad_norm": 0.07667013257741928,
+      "learning_rate": 3.5875480488625847e-06,
+      "loss": 0.0,
+      "step": 227
+    },
+    {
+      "epoch": 2.965217391304348,
+      "grad_norm": 0.07356667518615723,
+      "learning_rate": 3.5676410971659404e-06,
+      "loss": 0.0,
+      "step": 228
+    },
+    {
+      "epoch": 2.9782608695652173,
+      "grad_norm": 0.08367449045181274,
+      "learning_rate": 3.547651003134921e-06,
+      "loss": 0.0002,
+      "step": 229
+    },
+    {
+      "epoch": 2.991304347826087,
+      "grad_norm": 0.10358540713787079,
+      "learning_rate": 3.527579323494055e-06,
+      "loss": 0.0001,
+      "step": 230
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.28751426935195923,
+      "learning_rate": 3.507427621321331e-06,
+      "loss": 0.0001,
+      "step": 231
+    },
+    {
+      "epoch": 3.0130434782608697,
+      "grad_norm": 0.029475737363100052,
+      "learning_rate": 3.4871974659264786e-06,
+      "loss": 0.0,
+      "step": 232
+    },
+    {
+      "epoch": 3.026086956521739,
+      "grad_norm": 0.011441878043115139,
+      "learning_rate": 3.466890432728754e-06,
+      "loss": 0.0,
+      "step": 233
+    },
+    {
+      "epoch": 3.0391304347826087,
+      "grad_norm": 0.06686944514513016,
+      "learning_rate": 3.446508103134259e-06,
+      "loss": 0.0001,
+      "step": 234
+    },
+    {
+      "epoch": 3.0521739130434784,
+      "grad_norm": 0.06711216270923615,
+      "learning_rate": 3.426052064412785e-06,
+      "loss": 0.0001,
+      "step": 235
+    },
+    {
+      "epoch": 3.0652173913043477,
+      "grad_norm": 0.49988555908203125,
+      "learning_rate": 3.4055239095742067e-06,
+      "loss": 0.0004,
+      "step": 236
+    },
+    {
+      "epoch": 3.0782608695652174,
+      "grad_norm": 0.028451934456825256,
+      "learning_rate": 3.3849252372444295e-06,
+      "loss": 0.0,
+      "step": 237
+    },
+    {
+      "epoch": 3.091304347826087,
+      "grad_norm": 1.1554491519927979,
+      "learning_rate": 3.364257651540891e-06,
+      "loss": 0.0002,
+      "step": 238
+    },
+    {
+      "epoch": 3.1043478260869564,
+      "grad_norm": 0.013896522112190723,
+      "learning_rate": 3.343522761947646e-06,
+      "loss": 0.0,
+      "step": 239
+    },
+    {
+      "epoch": 3.117391304347826,
+      "grad_norm": 0.31346824765205383,
+      "learning_rate": 3.322722183190025e-06,
+      "loss": 0.0001,
+      "step": 240
+    },
+    {
+      "epoch": 3.130434782608696,
+      "grad_norm": 0.025106234475970268,
+      "learning_rate": 3.3018575351088894e-06,
+      "loss": 0.0,
+      "step": 241
+    },
+    {
+      "epoch": 3.143478260869565,
+      "grad_norm": 0.011471948586404324,
+      "learning_rate": 3.280930442534486e-06,
+      "loss": 0.0,
+      "step": 242
+    },
+    {
+      "epoch": 3.1565217391304348,
+      "grad_norm": 0.002863516565412283,
+      "learning_rate": 3.2599425351599136e-06,
+      "loss": 0.0,
+      "step": 243
+    },
+    {
+      "epoch": 3.1695652173913045,
+      "grad_norm": 0.028560644015669823,
+      "learning_rate": 3.238895447414211e-06,
+      "loss": 0.0,
+      "step": 244
+    },
+    {
+      "epoch": 3.1826086956521737,
+      "grad_norm": 0.011418928392231464,
+      "learning_rate": 3.217790818335077e-06,
+      "loss": 0.0,
+      "step": 245
+    },
+    {
+      "epoch": 3.1956521739130435,
+      "grad_norm": 0.0024322019889950752,
+      "learning_rate": 3.196630291441231e-06,
+      "loss": 0.0,
+      "step": 246
+    },
+    {
+      "epoch": 3.208695652173913,
+      "grad_norm": 0.004240074194967747,
+      "learning_rate": 3.175415514604422e-06,
+      "loss": 0.0,
+      "step": 247
+    },
+    {
+      "epoch": 3.2217391304347824,
+      "grad_norm": 0.0032878071069717407,
+      "learning_rate": 3.154148139921102e-06,
+      "loss": 0.0,
+      "step": 248
+    },
+    {
+      "epoch": 3.234782608695652,
+      "grad_norm": 0.004318348132073879,
+      "learning_rate": 3.132829823583771e-06,
+      "loss": 0.0,
+      "step": 249
+    },
+    {
+      "epoch": 3.247826086956522,
+      "grad_norm": 0.03787163272500038,
+      "learning_rate": 3.1114622257520004e-06,
+      "loss": 0.0,
+      "step": 250
+    },
+    {
+      "epoch": 3.260869565217391,
+      "grad_norm": 0.006955282762646675,
+      "learning_rate": 3.0900470104231456e-06,
+      "loss": 0.0,
+      "step": 251
+    },
+    {
+      "epoch": 3.273913043478261,
+      "grad_norm": 0.0021230122074484825,
+      "learning_rate": 3.0685858453027668e-06,
+      "loss": 0.0,
+      "step": 252
+    },
+    {
+      "epoch": 3.2869565217391306,
+      "grad_norm": 0.004325004294514656,
+      "learning_rate": 3.047080401674754e-06,
+      "loss": 0.0,
+      "step": 253
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 0.006688334047794342,
+      "learning_rate": 3.0255323542711784e-06,
+      "loss": 0.0,
+      "step": 254
+    },
+    {
+      "epoch": 3.3130434782608695,
+      "grad_norm": 0.08411774784326553,
+      "learning_rate": 3.00394338114187e-06,
+      "loss": 0.0001,
+      "step": 255
+    },
+    {
+      "epoch": 3.3260869565217392,
+      "grad_norm": 0.008930100128054619,
+      "learning_rate": 2.9823151635237424e-06,
+      "loss": 0.0,
+      "step": 256
+    },
+    {
+      "epoch": 3.3391304347826085,
+      "grad_norm": 0.0022701190318912268,
+      "learning_rate": 2.9606493857098657e-06,
+      "loss": 0.0,
+      "step": 257
+    },
+    {
+      "epoch": 3.3521739130434782,
+      "grad_norm": 0.01467288751155138,
+      "learning_rate": 2.938947734918302e-06,
+      "loss": 0.0,
+      "step": 258
+    },
+    {
+      "epoch": 3.365217391304348,
+      "grad_norm": 0.003942245151847601,
+      "learning_rate": 2.9172119011607153e-06,
+      "loss": 0.0,
+      "step": 259
+    },
+    {
+      "epoch": 3.378260869565217,
+      "grad_norm": 0.03254281356930733,
+      "learning_rate": 2.8954435771107604e-06,
+      "loss": 0.0,
+      "step": 260
+    },
+    {
+      "epoch": 3.391304347826087,
+      "grad_norm": 0.004211796913295984,
+      "learning_rate": 2.8736444579722665e-06,
+      "loss": 0.0,
+      "step": 261
+    },
+    {
+      "epoch": 3.4043478260869566,
+      "grad_norm": 0.002981652272865176,
+      "learning_rate": 2.8518162413472266e-06,
+      "loss": 0.0,
+      "step": 262
+    },
+    {
+      "epoch": 3.417391304347826,
+      "grad_norm": 0.004685316234827042,
+      "learning_rate": 2.8299606271035913e-06,
+      "loss": 0.0,
+      "step": 263
+    },
+    {
+      "epoch": 3.4304347826086956,
+      "grad_norm": 0.0022689092438668013,
+      "learning_rate": 2.8080793172428965e-06,
+      "loss": 0.0,
+      "step": 264
+    },
+    {
+      "epoch": 3.4434782608695653,
+      "grad_norm": 0.06723912060260773,
+      "learning_rate": 2.786174015767721e-06,
+      "loss": 0.0,
+      "step": 265
+    },
+    {
+      "epoch": 3.4565217391304346,
+      "grad_norm": 0.002560825552791357,
+      "learning_rate": 2.764246428548983e-06,
+      "loss": 0.0,
+      "step": 266
+    },
+    {
+      "epoch": 3.4695652173913043,
+      "grad_norm": 0.0016798798460513353,
+      "learning_rate": 2.742298263193099e-06,
+      "loss": 0.0,
+      "step": 267
+    },
+    {
+      "epoch": 3.482608695652174,
+      "grad_norm": 0.0021493195090442896,
+      "learning_rate": 2.720331228909005e-06,
+      "loss": 0.0,
+      "step": 268
+    },
+    {
+      "epoch": 3.4956521739130437,
+      "grad_norm": 0.004216059111058712,
+      "learning_rate": 2.6983470363750497e-06,
+      "loss": 0.0,
+      "step": 269
+    },
+    {
+      "epoch": 3.508695652173913,
+      "grad_norm": 0.0076387436129152775,
+      "learning_rate": 2.6763473976057776e-06,
+      "loss": 0.0,
+      "step": 270
+    },
+    {
+      "epoch": 3.5217391304347827,
+      "grad_norm": 0.005549773573875427,
+      "learning_rate": 2.6543340258186063e-06,
+      "loss": 0.0,
+      "step": 271
+    },
+    {
+      "epoch": 3.534782608695652,
+      "grad_norm": 0.00346516165882349,
+      "learning_rate": 2.6323086353004077e-06,
+      "loss": 0.0,
+      "step": 272
+    },
+    {
+      "epoch": 3.5478260869565217,
+      "grad_norm": 0.0031406464986503124,
+      "learning_rate": 2.610272941274012e-06,
+      "loss": 0.0,
+      "step": 273
+    },
+    {
+      "epoch": 3.5608695652173914,
+      "grad_norm": 0.0028460270259529352,
+      "learning_rate": 2.588228659764632e-06,
+      "loss": 0.0,
+      "step": 274
+    },
+    {
+      "epoch": 3.573913043478261,
+      "grad_norm": 0.002545596333220601,
+      "learning_rate": 2.5661775074662276e-06,
+      "loss": 0.0,
+      "step": 275
+    },
+    {
+      "epoch": 3.5869565217391304,
+      "grad_norm": 0.003621069248765707,
+      "learning_rate": 2.544121201607822e-06,
+      "loss": 0.0,
+      "step": 276
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 0.005747300107032061,
+      "learning_rate": 2.5220614598197708e-06,
+      "loss": 0.0,
+      "step": 277
+    },
+    {
+      "epoch": 3.6130434782608694,
+      "grad_norm": 0.0030976571142673492,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0,
+      "step": 278
+    },
+    {
+      "epoch": 3.626086956521739,
+      "grad_norm": 0.0016673463396728039,
+      "learning_rate": 2.477938540180231e-06,
+      "loss": 0.0,
+      "step": 279
+    },
+    {
+      "epoch": 3.639130434782609,
+      "grad_norm": 0.002529913792386651,
+      "learning_rate": 2.455878798392179e-06,
+      "loss": 0.0,
+      "step": 280
+    },
+    {
+      "epoch": 3.6521739130434785,
+      "grad_norm": 0.002386297332122922,
+      "learning_rate": 2.433822492533774e-06,
+      "loss": 0.0,
+      "step": 281
+    },
+    {
+      "epoch": 3.6652173913043478,
+      "grad_norm": 0.0032285265624523163,
+      "learning_rate": 2.411771340235369e-06,
+      "loss": 0.0,
+      "step": 282
+    },
+    {
+      "epoch": 3.6782608695652175,
+      "grad_norm": 0.0029606029856950045,
+      "learning_rate": 2.389727058725989e-06,
+      "loss": 0.0,
+      "step": 283
+    },
+    {
+      "epoch": 3.6913043478260867,
+      "grad_norm": 0.0039359270595014095,
+      "learning_rate": 2.3676913646995923e-06,
+      "loss": 0.0,
+      "step": 284
+    },
+    {
+      "epoch": 3.7043478260869565,
+      "grad_norm": 0.0026253967080265284,
+      "learning_rate": 2.3456659741813945e-06,
+      "loss": 0.0,
+      "step": 285
+    },
+    {
+      "epoch": 3.717391304347826,
+      "grad_norm": 0.00597747415304184,
+      "learning_rate": 2.3236526023942224e-06,
+      "loss": 0.0,
+      "step": 286
+    },
+    {
+      "epoch": 3.730434782608696,
+      "grad_norm": 0.003086534794420004,
+      "learning_rate": 2.301652963624951e-06,
+      "loss": 0.0,
+      "step": 287
+    },
+    {
+      "epoch": 3.743478260869565,
+      "grad_norm": 0.0029124680440872908,
+      "learning_rate": 2.2796687710909966e-06,
+      "loss": 0.0,
+      "step": 288
+    },
+    {
+      "epoch": 3.756521739130435,
+      "grad_norm": 0.010468163527548313,
+      "learning_rate": 2.2577017368069017e-06,
+      "loss": 0.0,
+      "step": 289
+    },
+    {
+      "epoch": 3.769565217391304,
+      "grad_norm": 0.004169187508523464,
+      "learning_rate": 2.235753571451018e-06,
+      "loss": 0.0,
+      "step": 290
+    },
+    {
+      "epoch": 3.782608695652174,
+      "grad_norm": 0.0022279575932770967,
+      "learning_rate": 2.2138259842322794e-06,
+      "loss": 0.0,
+      "step": 291
+    },
+    {
+      "epoch": 3.7956521739130435,
+      "grad_norm": 0.002126251347362995,
+      "learning_rate": 2.191920682757104e-06,
+      "loss": 0.0,
+      "step": 292
+    },
+    {
+      "epoch": 3.8086956521739133,
+      "grad_norm": 0.0013267571339383721,
+      "learning_rate": 2.170039372896409e-06,
+      "loss": 0.0,
+      "step": 293
+    },
+    {
+      "epoch": 3.8217391304347825,
+      "grad_norm": 0.002595380414277315,
+      "learning_rate": 2.148183758652774e-06,
+      "loss": 0.0,
+      "step": 294
+    },
+    {
+      "epoch": 3.8347826086956522,
+      "grad_norm": 0.004983303602784872,
+      "learning_rate": 2.126355542027734e-06,
+      "loss": 0.0,
+      "step": 295
+    },
+    {
+      "epoch": 3.8478260869565215,
+      "grad_norm": 0.002446365775540471,
+      "learning_rate": 2.1045564228892404e-06,
+      "loss": 0.0,
+      "step": 296
+    },
+    {
+      "epoch": 3.860869565217391,
+      "grad_norm": 0.002043728018179536,
+      "learning_rate": 2.0827880988392856e-06,
+      "loss": 0.0,
+      "step": 297
+    },
+    {
+      "epoch": 3.873913043478261,
+      "grad_norm": 0.010027135722339153,
+      "learning_rate": 2.0610522650816985e-06,
+      "loss": 0.0,
+      "step": 298
+    },
+    {
+      "epoch": 3.8869565217391306,
+      "grad_norm": 0.01416314672678709,
+      "learning_rate": 2.0393506142901347e-06,
+      "loss": 0.0,
+      "step": 299
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 0.003061251249164343,
+      "learning_rate": 2.017684836476258e-06,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 3.9130434782608696,
+      "grad_norm": 0.0023156912066042423,
+      "learning_rate": 1.9960566188581306e-06,
+      "loss": 0.0,
+      "step": 301
+    },
+    {
+      "epoch": 3.926086956521739,
+      "grad_norm": 0.0034826321061700583,
+      "learning_rate": 1.9744676457288225e-06,
+      "loss": 0.0,
+      "step": 302
+    },
+    {
+      "epoch": 3.9391304347826086,
+      "grad_norm": 0.001995071768760681,
+      "learning_rate": 1.952919598325247e-06,
+      "loss": 0.0,
+      "step": 303
+    },
+    {
+      "epoch": 3.9521739130434783,
+      "grad_norm": 0.00404984038323164,
+      "learning_rate": 1.9314141546972345e-06,
+      "loss": 0.0,
+      "step": 304
+    },
+    {
+      "epoch": 3.965217391304348,
+      "grad_norm": 0.0019303123699501157,
+      "learning_rate": 1.9099529895768552e-06,
+      "loss": 0.0,
+      "step": 305
+    },
+    {
+      "epoch": 3.9782608695652173,
+      "grad_norm": 0.0014716465957462788,
+      "learning_rate": 1.8885377742480005e-06,
+      "loss": 0.0,
+      "step": 306
+    },
+    {
+      "epoch": 3.991304347826087,
+      "grad_norm": 0.0028718914836645126,
+      "learning_rate": 1.8671701764162287e-06,
+      "loss": 0.0,
+      "step": 307
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.0028718914836645126,
+      "learning_rate": 1.8458518600788988e-06,
+      "loss": 0.0,
+      "step": 308
+    },
+    {
+      "epoch": 4.01304347826087,
+      "grad_norm": 0.01034778356552124,
+      "learning_rate": 1.8245844853955786e-06,
+      "loss": 0.0,
+      "step": 309
+    },
+    {
+      "epoch": 4.026086956521739,
+      "grad_norm": 0.001763720065355301,
+      "learning_rate": 1.8033697085587698e-06,
+      "loss": 0.0,
+      "step": 310
+    },
+    {
+      "epoch": 4.039130434782609,
+      "grad_norm": 0.0014494823990389705,
+      "learning_rate": 1.782209181664924e-06,
+      "loss": 0.0,
+      "step": 311
+    },
+    {
+      "epoch": 4.052173913043478,
+      "grad_norm": 0.0013845040230080485,
+      "learning_rate": 1.7611045525857902e-06,
+      "loss": 0.0,
+      "step": 312
+    },
+    {
+      "epoch": 4.065217391304348,
+      "grad_norm": 0.0025538592599332333,
+      "learning_rate": 1.740057464840088e-06,
+      "loss": 0.0,
+      "step": 313
+    },
+    {
+      "epoch": 4.078260869565217,
+      "grad_norm": 0.0015924959443509579,
+      "learning_rate": 1.7190695574655147e-06,
+      "loss": 0.0,
+      "step": 314
+    },
+    {
+      "epoch": 4.091304347826087,
+      "grad_norm": 0.0016162138199433684,
+      "learning_rate": 1.6981424648911112e-06,
+      "loss": 0.0,
+      "step": 315
+    },
+    {
+      "epoch": 4.104347826086957,
+      "grad_norm": 0.0015241021756082773,
+      "learning_rate": 1.677277816809975e-06,
+      "loss": 0.0,
+      "step": 316
+    },
+    {
+      "epoch": 4.1173913043478265,
+      "grad_norm": 0.0010168206645175815,
+      "learning_rate": 1.6564772380523546e-06,
+      "loss": 0.0,
+      "step": 317
+    },
+    {
+      "epoch": 4.130434782608695,
+      "grad_norm": 0.012456579133868217,
+      "learning_rate": 1.635742348459109e-06,
+      "loss": 0.0,
+      "step": 318
+    },
+    {
+      "epoch": 4.143478260869565,
+      "grad_norm": 0.00380521547049284,
+      "learning_rate": 1.6150747627555713e-06,
+      "loss": 0.0,
+      "step": 319
+    },
+    {
+      "epoch": 4.156521739130435,
+      "grad_norm": 0.0036846757866442204,
+      "learning_rate": 1.5944760904257944e-06,
+      "loss": 0.0,
+      "step": 320
+    },
+    {
+      "epoch": 4.1695652173913045,
+      "grad_norm": 0.0013467305107042193,
+      "learning_rate": 1.5739479355872162e-06,
+      "loss": 0.0,
+      "step": 321
+    },
+    {
+      "epoch": 4.182608695652174,
+      "grad_norm": 0.0018101097084581852,
+      "learning_rate": 1.5534918968657423e-06,
+      "loss": 0.0,
+      "step": 322
+    },
+    {
+      "epoch": 4.195652173913044,
+      "grad_norm": 0.001617030007764697,
+      "learning_rate": 1.5331095672712463e-06,
+      "loss": 0.0,
+      "step": 323
+    },
+    {
+      "epoch": 4.208695652173913,
+      "grad_norm": 0.00144918670412153,
+      "learning_rate": 1.5128025340735223e-06,
+      "loss": 0.0,
+      "step": 324
+    },
+    {
+      "epoch": 4.221739130434782,
+      "grad_norm": 0.0011092445347458124,
+      "learning_rate": 1.4925723786786691e-06,
+      "loss": 0.0,
+      "step": 325
+    },
+    {
+      "epoch": 4.234782608695652,
+      "grad_norm": 0.0028281533159315586,
+      "learning_rate": 1.4724206765059456e-06,
+      "loss": 0.0,
+      "step": 326
+    },
+    {
+      "epoch": 4.247826086956522,
+      "grad_norm": 0.0014354493468999863,
+      "learning_rate": 1.4523489968650795e-06,
+      "loss": 0.0,
+      "step": 327
+    },
+    {
+      "epoch": 4.260869565217392,
+      "grad_norm": 0.0017186496406793594,
+      "learning_rate": 1.4323589028340598e-06,
+      "loss": 0.0,
+      "step": 328
+    },
+    {
+      "epoch": 4.273913043478261,
+      "grad_norm": 0.0020970606710761786,
+      "learning_rate": 1.4124519511374158e-06,
+      "loss": 0.0,
+      "step": 329
+    },
+    {
+      "epoch": 4.28695652173913,
+      "grad_norm": 0.0015501041198149323,
+      "learning_rate": 1.3926296920249796e-06,
+      "loss": 0.0,
+      "step": 330
+    },
+    {
+      "epoch": 4.3,
+      "grad_norm": 0.0027128765359520912,
+      "learning_rate": 1.3728936691511704e-06,
+      "loss": 0.0,
+      "step": 331
+    },
+    {
+      "epoch": 4.3130434782608695,
+      "grad_norm": 0.0018941819434985518,
+      "learning_rate": 1.3532454194547734e-06,
+      "loss": 0.0,
+      "step": 332
+    },
+    {
+      "epoch": 4.326086956521739,
+      "grad_norm": 0.0018062669551,
+      "learning_rate": 1.3336864730392587e-06,
+      "loss": 0.0,
+      "step": 333
+    },
+    {
+      "epoch": 4.339130434782609,
+      "grad_norm": 0.002639364218339324,
+      "learning_rate": 1.314218353053619e-06,
+      "loss": 0.0,
+      "step": 334
+    },
+    {
+      "epoch": 4.352173913043479,
+      "grad_norm": 0.0031710860785096884,
+      "learning_rate": 1.2948425755737592e-06,
+      "loss": 0.0,
+      "step": 335
+    },
+    {
+      "epoch": 4.3652173913043475,
+      "grad_norm": 0.005298961885273457,
+      "learning_rate": 1.2755606494844294e-06,
+      "loss": 0.0,
+      "step": 336
+    },
+    {
+      "epoch": 4.378260869565217,
+      "grad_norm": 0.002524756360799074,
+      "learning_rate": 1.2563740763617198e-06,
+      "loss": 0.0,
+      "step": 337
+    },
+    {
+      "epoch": 4.391304347826087,
+      "grad_norm": 0.008356565609574318,
+      "learning_rate": 1.2372843503561318e-06,
+      "loss": 0.0,
+      "step": 338
+    },
+    {
+      "epoch": 4.404347826086957,
+      "grad_norm": 0.0027493846137076616,
+      "learning_rate": 1.218292958076213e-06,
+      "loss": 0.0,
+      "step": 339
+    },
+    {
+      "epoch": 4.417391304347826,
+      "grad_norm": 0.0022872223053127527,
+      "learning_rate": 1.1994013784727948e-06,
+      "loss": 0.0,
+      "step": 340
+    },
+    {
+      "epoch": 4.430434782608696,
+      "grad_norm": 0.0015215649036690593,
+      "learning_rate": 1.180611082723814e-06,
+      "loss": 0.0,
+      "step": 341
+    },
+    {
+      "epoch": 4.443478260869565,
+      "grad_norm": 0.002822963520884514,
+      "learning_rate": 1.161923534119752e-06,
+      "loss": 0.0,
+      "step": 342
+    },
+    {
+      "epoch": 4.456521739130435,
+      "grad_norm": 0.001620918745175004,
+      "learning_rate": 1.1433401879496723e-06,
+      "loss": 0.0,
+      "step": 343
+    },
+    {
+      "epoch": 4.469565217391304,
+      "grad_norm": 0.0026848018169403076,
+      "learning_rate": 1.1248624913878966e-06,
+      "loss": 0.0,
+      "step": 344
+    },
+    {
+      "epoch": 4.482608695652174,
+      "grad_norm": 0.002241417532786727,
+      "learning_rate": 1.1064918833813073e-06,
+      "loss": 0.0,
+      "step": 345
+    },
+    {
+      "epoch": 4.495652173913044,
+      "grad_norm": 0.001455339603126049,
+      "learning_rate": 1.088229794537283e-06,
+      "loss": 0.0,
+      "step": 346
+    },
+    {
+      "epoch": 4.5086956521739125,
+      "grad_norm": 0.001374992891214788,
+      "learning_rate": 1.0700776470122981e-06,
+      "loss": 0.0,
+      "step": 347
+    },
+    {
+      "epoch": 4.521739130434782,
+      "grad_norm": 0.0020591497886925936,
+      "learning_rate": 1.0520368544011661e-06,
+      "loss": 0.0,
+      "step": 348
+    },
+    {
+      "epoch": 4.534782608695652,
+      "grad_norm": 0.001313328742980957,
+      "learning_rate": 1.0341088216269625e-06,
+      "loss": 0.0,
+      "step": 349
+    },
+    {
+      "epoch": 4.547826086956522,
+      "grad_norm": 0.002054040553048253,
+      "learning_rate": 1.0162949448316089e-06,
+      "loss": 0.0,
+      "step": 350
+    },
+    {
+      "epoch": 4.560869565217391,
+      "grad_norm": 0.0022192494943737984,
+      "learning_rate": 9.98596611267158e-07,
+      "loss": 0.0,
+      "step": 351
+    },
+    {
+      "epoch": 4.573913043478261,
+      "grad_norm": 0.0027549685910344124,
+      "learning_rate": 9.81015199187753e-07,
+      "loss": 0.0,
+      "step": 352
+    },
+    {
+      "epoch": 4.586956521739131,
+      "grad_norm": 0.0015397547977045178,
+      "learning_rate": 9.63552077742301e-07,
+      "loss": 0.0,
+      "step": 353
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 0.002905682660639286,
+      "learning_rate": 9.462086068678519e-07,
+      "loss": 0.0,
+      "step": 354
+    },
+    {
+      "epoch": 4.613043478260869,
+      "grad_norm": 0.0014848869759589434,
+      "learning_rate": 9.289861371836886e-07,
+      "loss": 0.0,
+      "step": 355
+    },
+    {
+      "epoch": 4.626086956521739,
+      "grad_norm": 0.002772193867713213,
+      "learning_rate": 9.118860098861538e-07,
+      "loss": 0.0,
+      "step": 356
+    },
+    {
+      "epoch": 4.639130434782609,
+      "grad_norm": 0.001796722412109375,
+      "learning_rate": 8.949095566441985e-07,
+      "loss": 0.0,
+      "step": 357
+    },
+    {
+      "epoch": 4.6521739130434785,
+      "grad_norm": 0.0016671266639605165,
+      "learning_rate": 8.78058099495685e-07,
+      "loss": 0.0,
+      "step": 358
+    },
+    {
+      "epoch": 4.665217391304348,
+      "grad_norm": 0.0016365941846743226,
+      "learning_rate": 8.613329507444274e-07,
+      "loss": 0.0,
+      "step": 359
+    },
+    {
+      "epoch": 4.678260869565217,
+      "grad_norm": 0.0023541823029518127,
+      "learning_rate": 8.44735412857999e-07,
+      "loss": 0.0,
+      "step": 360
+    },
+    {
+      "epoch": 4.691304347826087,
+      "grad_norm": 0.0020769701804965734,
+      "learning_rate": 8.282667783663056e-07,
+      "loss": 0.0,
+      "step": 361
+    },
+    {
+      "epoch": 4.7043478260869565,
+      "grad_norm": 0.0018430390628054738,
+      "learning_rate": 8.119283297609238e-07,
+      "loss": 0.0,
+      "step": 362
+    },
+    {
+      "epoch": 4.717391304347826,
+      "grad_norm": 0.002417508512735367,
+      "learning_rate": 7.957213393952335e-07,
+      "loss": 0.0,
+      "step": 363
+    },
+    {
+      "epoch": 4.730434782608696,
+      "grad_norm": 0.001239007106050849,
+      "learning_rate": 7.796470693853281e-07,
+      "loss": 0.0,
+      "step": 364
+    },
+    {
+      "epoch": 4.743478260869566,
+      "grad_norm": 0.002612160984426737,
+      "learning_rate": 7.637067715117327e-07,
+      "loss": 0.0,
+      "step": 365
+    },
+    {
+      "epoch": 4.756521739130434,
+      "grad_norm": 0.002720440039411187,
+      "learning_rate": 7.479016871219174e-07,
+      "loss": 0.0,
+      "step": 366
+    },
+    {
+      "epoch": 4.769565217391304,
+      "grad_norm": 0.0030755773186683655,
+      "learning_rate": 7.322330470336314e-07,
+      "loss": 0.0,
+      "step": 367
+    },
+    {
+      "epoch": 4.782608695652174,
+      "grad_norm": 0.0019342007581144571,
+      "learning_rate": 7.167020714390502e-07,
+      "loss": 0.0,
+      "step": 368
+    },
+    {
+      "epoch": 4.7956521739130435,
+      "grad_norm": 0.002000426407903433,
+      "learning_rate": 7.013099698097539e-07,
+      "loss": 0.0,
+      "step": 369
+    },
+    {
+      "epoch": 4.808695652173913,
+      "grad_norm": 0.0011657639406621456,
+      "learning_rate": 6.860579408025436e-07,
+      "loss": 0.0,
+      "step": 370
+    },
+    {
+      "epoch": 4.821739130434783,
+      "grad_norm": 0.0016806419007480145,
+      "learning_rate": 6.709471721660904e-07,
+      "loss": 0.0,
+      "step": 371
+    },
+    {
+      "epoch": 4.834782608695652,
+      "grad_norm": 0.002683436032384634,
+      "learning_rate": 6.559788406484446e-07,
+      "loss": 0.0,
+      "step": 372
+    },
+    {
+      "epoch": 4.8478260869565215,
+      "grad_norm": 0.0020458789076656103,
+      "learning_rate": 6.41154111905393e-07,
+      "loss": 0.0,
+      "step": 373
+    },
+    {
+      "epoch": 4.860869565217391,
+      "grad_norm": 0.0017730394611135125,
+      "learning_rate": 6.264741404096875e-07,
+      "loss": 0.0,
+      "step": 374
+    },
+    {
+      "epoch": 4.873913043478261,
+      "grad_norm": 0.0016303405864164233,
+      "learning_rate": 6.119400693611358e-07,
+      "loss": 0.0,
+      "step": 375
+    },
+    {
+      "epoch": 4.886956521739131,
+      "grad_norm": 0.0013037021271884441,
+      "learning_rate": 5.975530305975808e-07,
+      "loss": 0.0,
+      "step": 376
+    },
+    {
+      "epoch": 4.9,
+      "grad_norm": 0.0019095903262495995,
+      "learning_rate": 5.833141445067541e-07,
+      "loss": 0.0,
+      "step": 377
+    },
+    {
+      "epoch": 4.913043478260869,
+      "grad_norm": 0.0017560195410624146,
+      "learning_rate": 5.692245199390281e-07,
+      "loss": 0.0001,
+      "step": 378
+    },
+    {
+      "epoch": 4.926086956521739,
+      "grad_norm": 0.08021274209022522,
+      "learning_rate": 5.552852541210651e-07,
+      "loss": 0.0,
+      "step": 379
+    },
+    {
+      "epoch": 4.939130434782609,
+      "grad_norm": 0.0026719518937170506,
+      "learning_rate": 5.414974325703687e-07,
+      "loss": 0.0,
+      "step": 380
+    },
+    {
+      "epoch": 4.952173913043478,
+      "grad_norm": 0.0017763073556125164,
+      "learning_rate": 5.278621290107533e-07,
+      "loss": 0.0,
+      "step": 381
+    },
+    {
+      "epoch": 4.965217391304348,
+      "grad_norm": 0.0016084731323644519,
+      "learning_rate": 5.143804052887228e-07,
+      "loss": 0.0,
+      "step": 382
+    },
+    {
+      "epoch": 4.978260869565218,
+      "grad_norm": 0.0017133202636614442,
+      "learning_rate": 5.010533112907845e-07,
+      "loss": 0.0,
+      "step": 383
+    },
+    {
+      "epoch": 4.9913043478260875,
+      "grad_norm": 0.001300052274018526,
+      "learning_rate": 4.878818848616861e-07,
+      "loss": 0.0,
+      "step": 384
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.0027902189176529646,
+      "learning_rate": 4.748671517235948e-07,
+      "loss": 0.0,
+      "step": 385
+    },
+    {
+      "epoch": 5.01304347826087,
+      "grad_norm": 0.011486860923469067,
+      "learning_rate": 4.620101253962206e-07,
+      "loss": 0.0,
+      "step": 386
+    },
+    {
+      "epoch": 5.026086956521739,
+      "grad_norm": 0.0009154711733572185,
+      "learning_rate": 4.4931180711788537e-07,
+      "loss": 0.0,
+      "step": 387
+    },
+    {
+      "epoch": 5.039130434782609,
+      "grad_norm": 0.002004265086725354,
+      "learning_rate": 4.3677318576755693e-07,
+      "loss": 0.0,
+      "step": 388
+    },
+    {
+      "epoch": 5.052173913043478,
+      "grad_norm": 0.0016135271871462464,
+      "learning_rate": 4.243952377878338e-07,
+      "loss": 0.0,
+      "step": 389
+    },
+    {
+      "epoch": 5.065217391304348,
+      "grad_norm": 0.0018086008494719863,
+      "learning_rate": 4.1217892710891134e-07,
+      "loss": 0.0,
+      "step": 390
+    },
+    {
+      "epoch": 5.078260869565217,
+      "grad_norm": 0.0037798560224473476,
+      "learning_rate": 4.001252050735102e-07,
+      "loss": 0.0,
+      "step": 391
+    },
+    {
+      "epoch": 5.091304347826087,
+      "grad_norm": 0.0011360564967617393,
+      "learning_rate": 3.882350103627952e-07,
+      "loss": 0.0,
+      "step": 392
+    },
+    {
+      "epoch": 5.104347826086957,
+      "grad_norm": 0.0013740825233981013,
+      "learning_rate": 3.7650926892327297e-07,
+      "loss": 0.0,
+      "step": 393
+    },
+    {
+      "epoch": 5.1173913043478265,
+      "grad_norm": 0.0032870906870812178,
+      "learning_rate": 3.649488938946844e-07,
+      "loss": 0.0,
+      "step": 394
+    },
+    {
+      "epoch": 5.130434782608695,
+      "grad_norm": 0.0029629303608089685,
+      "learning_rate": 3.5355478553889626e-07,
+      "loss": 0.0,
+      "step": 395
+    },
+    {
+      "epoch": 5.143478260869565,
+      "grad_norm": 0.0016408413648605347,
+      "learning_rate": 3.4232783116978976e-07,
+      "loss": 0.0,
+      "step": 396
+    },
+    {
+      "epoch": 5.156521739130435,
+      "grad_norm": 0.000968664709944278,
+      "learning_rate": 3.312689050841658e-07,
+      "loss": 0.0,
+      "step": 397
+    },
+    {
+      "epoch": 5.1695652173913045,
+      "grad_norm": 0.0020472989417612553,
+      "learning_rate": 3.203788684936535e-07,
+      "loss": 0.0,
+      "step": 398
+    },
+    {
+      "epoch": 5.182608695652174,
+      "grad_norm": 0.0058404686860740185,
+      "learning_rate": 3.096585694576498e-07,
+      "loss": 0.0,
+      "step": 399
+    },
+    {
+      "epoch": 5.195652173913044,
+      "grad_norm": 0.002077893353998661,
+      "learning_rate": 2.9910884281727225e-07,
+      "loss": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 5.208695652173913,
+      "grad_norm": 0.001151588628999889,
+      "learning_rate": 2.8873051013034695e-07,
+      "loss": 0.0,
+      "step": 401
+    },
+    {
+      "epoch": 5.221739130434782,
+      "grad_norm": 0.0014998423866927624,
+      "learning_rate": 2.785243796074333e-07,
+      "loss": 0.0,
+      "step": 402
+    },
+    {
+      "epoch": 5.234782608695652,
+      "grad_norm": 0.0022406023927032948,
+      "learning_rate": 2.6849124604887836e-07,
+      "loss": 0.0,
+      "step": 403
+    },
+    {
+      "epoch": 5.247826086956522,
+      "grad_norm": 0.0014261951437219977,
+      "learning_rate": 2.5863189078292913e-07,
+      "loss": 0.0,
+      "step": 404
+    },
+    {
+      "epoch": 5.260869565217392,
+      "grad_norm": 0.0016519747441634536,
+      "learning_rate": 2.489470816048806e-07,
+      "loss": 0.0,
+      "step": 405
+    },
+    {
+      "epoch": 5.273913043478261,
+      "grad_norm": 0.0016760436119511724,
+      "learning_rate": 2.3943757271728816e-07,
+      "loss": 0.0,
+      "step": 406
+    },
+    {
+      "epoch": 5.28695652173913,
+      "grad_norm": 0.0022172159515321255,
+      "learning_rate": 2.30104104671231e-07,
+      "loss": 0.0,
+      "step": 407
+    },
+    {
+      "epoch": 5.3,
+      "grad_norm": 0.0016910339472815394,
+      "learning_rate": 2.2094740430864569e-07,
+      "loss": 0.0,
+      "step": 408
+    },
+    {
+      "epoch": 5.3130434782608695,
+      "grad_norm": 0.0012156476732343435,
+      "learning_rate": 2.119681847057184e-07,
+      "loss": 0.0,
+      "step": 409
+    },
+    {
+      "epoch": 5.326086956521739,
+      "grad_norm": 0.0022703667636960745,
+      "learning_rate": 2.0316714511736002e-07,
+      "loss": 0.0,
+      "step": 410
+    },
+    {
+      "epoch": 5.339130434782609,
+      "grad_norm": 0.0021776454523205757,
+      "learning_rate": 1.9454497092274565e-07,
+      "loss": 0.0,
+      "step": 411
+    },
+    {
+      "epoch": 5.352173913043479,
+      "grad_norm": 0.0013432299019768834,
+      "learning_rate": 1.861023335719475e-07,
+      "loss": 0.0,
+      "step": 412
+    },
+    {
+      "epoch": 5.3652173913043475,
+      "grad_norm": 0.001742590800859034,
+      "learning_rate": 1.7783989053363926e-07,
+      "loss": 0.0,
+      "step": 413
+    },
+    {
+      "epoch": 5.378260869565217,
+      "grad_norm": 0.001307090511545539,
+      "learning_rate": 1.6975828524390116e-07,
+      "loss": 0.0,
+      "step": 414
+    },
+    {
+      "epoch": 5.391304347826087,
+      "grad_norm": 0.001631222665309906,
+      "learning_rate": 1.6185814705610926e-07,
+      "loss": 0.0,
+      "step": 415
+    },
+    {
+      "epoch": 5.404347826086957,
+      "grad_norm": 0.0028114933520555496,
+      "learning_rate": 1.5414009119192635e-07,
+      "loss": 0.0,
+      "step": 416
+    },
+    {
+      "epoch": 5.417391304347826,
+      "grad_norm": 0.001492610783316195,
+      "learning_rate": 1.4660471869339056e-07,
+      "loss": 0.0,
+      "step": 417
+    },
+    {
+      "epoch": 5.430434782608696,
+      "grad_norm": 0.0016285318415611982,
+      "learning_rate": 1.392526163761107e-07,
+      "loss": 0.0,
+      "step": 418
+    },
+    {
+      "epoch": 5.443478260869565,
+      "grad_norm": 0.0008480209507979453,
+      "learning_rate": 1.3208435678356612e-07,
+      "loss": 0.0,
+      "step": 419
+    },
+    {
+      "epoch": 5.456521739130435,
+      "grad_norm": 0.00366847007535398,
+      "learning_rate": 1.2510049814252302e-07,
+      "loss": 0.0,
+      "step": 420
+    },
+    {
+      "epoch": 5.469565217391304,
+      "grad_norm": 0.001310039428062737,
+      "learning_rate": 1.1830158431955841e-07,
+      "loss": 0.0,
+      "step": 421
+    },
+    {
+      "epoch": 5.482608695652174,
+      "grad_norm": 0.0014891099417582154,
+      "learning_rate": 1.1168814477871132e-07,
+      "loss": 0.0,
+      "step": 422
+    },
+    {
+      "epoch": 5.495652173913044,
+      "grad_norm": 0.0017748738173395395,
+      "learning_rate": 1.0526069454024651e-07,
+      "loss": 0.0,
+      "step": 423
+    },
+    {
+      "epoch": 5.5086956521739125,
+      "grad_norm": 0.0029161018319427967,
+      "learning_rate": 9.901973414055188e-08,
+      "loss": 0.0,
+      "step": 424
+    },
+    {
+      "epoch": 5.521739130434782,
+      "grad_norm": 0.0016620843671262264,
+      "learning_rate": 9.296574959315464e-08,
+      "loss": 0.0,
+      "step": 425
+    },
+    {
+      "epoch": 5.534782608695652,
+      "grad_norm": 0.0022197188809514046,
+      "learning_rate": 8.709921235087598e-08,
+      "loss": 0.0,
+      "step": 426
+    },
+    {
+      "epoch": 5.547826086956522,
+      "grad_norm": 0.0011936837108805776,
+      "learning_rate": 8.142057926911722e-08,
+      "loss": 0.0,
+      "step": 427
+    },
+    {
+      "epoch": 5.560869565217391,
+      "grad_norm": 0.0016476701712235808,
+      "learning_rate": 7.593029257027956e-08,
+      "loss": 0.0,
+      "step": 428
+    },
+    {
+      "epoch": 5.573913043478261,
+      "grad_norm": 0.0025552220176905394,
+      "learning_rate": 7.062877980932914e-08,
+      "loss": 0.0,
+      "step": 429
+    },
+    {
+      "epoch": 5.586956521739131,
+      "grad_norm": 0.0014675466809421778,
+      "learning_rate": 6.551645384049898e-08,
+      "loss": 0.0,
+      "step": 430
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 0.0015081793535500765,
+      "learning_rate": 6.059371278513942e-08,
+      "loss": 0.0,
+      "step": 431
+    },
+    {
+      "epoch": 5.613043478260869,
+      "grad_norm": 0.001078072702512145,
+      "learning_rate": 5.5860940000714016e-08,
+      "loss": 0.0,
+      "step": 432
+    },
+    {
+      "epoch": 5.626086956521739,
+      "grad_norm": 0.0021398630924522877,
+      "learning_rate": 5.131850405094535e-08,
+      "loss": 0.0,
+      "step": 433
+    },
+    {
+      "epoch": 5.639130434782609,
+      "grad_norm": 0.004267909564077854,
+      "learning_rate": 4.6966758677113865e-08,
+      "loss": 0.0,
+      "step": 434
+    },
+    {
+      "epoch": 5.6521739130434785,
+      "grad_norm": 0.001567747793160379,
+      "learning_rate": 4.280604277050932e-08,
+      "loss": 0.0,
+      "step": 435
+    },
+    {
+      "epoch": 5.665217391304348,
+      "grad_norm": 0.0011814325116574764,
+      "learning_rate": 3.88366803460416e-08,
+      "loss": 0.0,
+      "step": 436
+    },
+    {
+      "epoch": 5.678260869565217,
+      "grad_norm": 0.0012217245530337095,
+      "learning_rate": 3.505898051700596e-08,
+      "loss": 0.0,
+      "step": 437
+    },
+    {
+      "epoch": 5.691304347826087,
+      "grad_norm": 0.0015993325505405664,
+      "learning_rate": 3.147323747101222e-08,
+      "loss": 0.0,
+      "step": 438
+    },
+    {
+      "epoch": 5.7043478260869565,
+      "grad_norm": 0.0011081008706241846,
+      "learning_rate": 2.8079730447073685e-08,
+      "loss": 0.0,
+      "step": 439
+    },
+    {
+      "epoch": 5.717391304347826,
+      "grad_norm": 0.0020945158321410418,
+      "learning_rate": 2.487872371386424e-08,
+      "loss": 0.0,
+      "step": 440
+    },
+    {
+      "epoch": 5.730434782608696,
+      "grad_norm": 0.0014333524741232395,
+      "learning_rate": 2.187046654913455e-08,
+      "loss": 0.0,
+      "step": 441
+    },
+    {
+      "epoch": 5.743478260869566,
+      "grad_norm": 0.0008574423263780773,
+      "learning_rate": 1.9055193220302582e-08,
+      "loss": 0.0,
+      "step": 442
+    },
+    {
+      "epoch": 5.756521739130434,
+      "grad_norm": 0.00152776506729424,
+      "learning_rate": 1.6433122966209303e-08,
+      "loss": 0.0,
+      "step": 443
+    },
+    {
+      "epoch": 5.769565217391304,
+      "grad_norm": 0.001546284998767078,
+      "learning_rate": 1.4004459980045127e-08,
+      "loss": 0.0,
+      "step": 444
+    },
+    {
+      "epoch": 5.782608695652174,
+      "grad_norm": 0.0014010363956913352,
+      "learning_rate": 1.1769393393448459e-08,
+      "loss": 0.0,
+      "step": 445
+    },
+    {
+      "epoch": 5.7956521739130435,
+      "grad_norm": 0.00130969169549644,
+      "learning_rate": 9.728097261777202e-09,
+      "loss": 0.0,
+      "step": 446
+    },
+    {
+      "epoch": 5.808695652173913,
+      "grad_norm": 0.0017989901825785637,
+      "learning_rate": 7.88073055055516e-09,
+      "loss": 0.0,
+      "step": 447
+    },
+    {
+      "epoch": 5.821739130434783,
+      "grad_norm": 0.0016501746140420437,
+      "learning_rate": 6.2274371230905405e-09,
+      "loss": 0.0,
+      "step": 448
+    },
+    {
+      "epoch": 5.834782608695652,
+      "grad_norm": 0.0010283251758664846,
+      "learning_rate": 4.7683457292743705e-09,
+      "loss": 0.0,
+      "step": 449
+    },
+    {
+      "epoch": 5.8478260869565215,
+      "grad_norm": 0.0011717312736436725,
+      "learning_rate": 3.503569995554068e-09,
+      "loss": 0.0,
+      "step": 450
+    },
+    {
+      "epoch": 5.860869565217391,
+      "grad_norm": 0.0016135338228195906,
+      "learning_rate": 2.4332084160835766e-09,
+      "loss": 0.0,
+      "step": 451
+    },
+    {
+      "epoch": 5.873913043478261,
+      "grad_norm": 0.001525578205473721,
+      "learning_rate": 1.5573443450545012e-09,
+      "loss": 0.0,
+      "step": 452
+    },
+    {
+      "epoch": 5.886956521739131,
+      "grad_norm": 0.0014873399632051587,
+      "learning_rate": 8.760459902037998e-10,
+      "loss": 0.0,
+      "step": 453
+    },
+    {
+      "epoch": 5.9,
+      "grad_norm": 0.002902277745306492,
+      "learning_rate": 3.8936640750358856e-10,
+      "loss": 0.0,
+      "step": 454
+    },
+    {
+      "epoch": 5.913043478260869,
+      "grad_norm": 0.001912617706693709,
+      "learning_rate": 9.734349702722468e-11,
+      "loss": 0.0,
+      "step": 455
+    },
+    {
+      "epoch": 5.926086956521739,
+      "grad_norm": 0.0018534486880525947,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 456
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 456,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 76,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1463996542130586e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-456/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:134c4e3177c4f1e743e7e4ec30e3972d5f92595dfa94ae653b40c6765b255d01
+size 8056

checkpoint-456/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)