Training in progress, step 512, checkpoint

checkpoint-512/README.md

@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.3-70B-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-512/adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.3-70B-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": 16,
+  "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": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

checkpoint-512/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a778af1a896b64001ccc32c47658eadf6236f2ae36db71e5099ce9d7d25e8b0
+size 7516349296

checkpoint-512/global_step512/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a5db84a3d735d37901105460e27a8bb3bb91bb366fcea2f9cae396c6cd08f01
+size 3312262110

checkpoint-512/global_step512/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d88fe8006a0636fd8ea88a146ce42039d36f47ae414bcefc7dd911ae5859def
+size 3312262110

checkpoint-512/global_step512/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3811761b68708fd5281c3675410988a4f9cb76fbab1b386c30c272042ccefdb8
+size 3312262110

checkpoint-512/global_step512/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3d6a1fc5ef044a0316bf431f824c160d059fa86e66f6e6464960dba8091d92f
+size 3312262110

checkpoint-512/global_step512/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7bcc3526dee730e6a9311daf0f1087a1bc8114d3e37e80364645ca130335e9a
+size 3312262110

checkpoint-512/global_step512/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36bcf0f59324801544f1471f955e2ee84010277a060084fc5731225b7cd1af2b
+size 3312262110

checkpoint-512/global_step512/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81078e90b503b5d4ca0efd8713d1909cd94d1904dd89fda87bf1ec31c3fef78b
+size 3312262110

checkpoint-512/global_step512/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b413dc10fba865216b3fc7c91ca794d592be9bfef8a5444d8f1a1bf85c9d1667
+size 3312262110

checkpoint-512/global_step512/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc2934770b45e1f10c1f51d3f4da6bbeeaf057f88a0da4f5f5b48804dc3b1994
+size 1120962

checkpoint-512/global_step512/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:286430da97059339ca782af2630d2aee6703400e91fffad242fe8ee792ba65a4
+size 1120962

checkpoint-512/global_step512/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02864b47c277b22ae4d0687ded1176860811b876e13d8e5faea355eb621501eb
+size 1120962

checkpoint-512/global_step512/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c3da55fa10e6f850f7a53169943c2081496cf74cb7816ccce6d1f545e26aa9
+size 1120962

checkpoint-512/global_step512/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd789d300c4c18bd0519f508e4e91517acbfb4a81f9946f29eb81e9d36b444ad
+size 1120962

checkpoint-512/global_step512/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b58e26e3dfc1129d7196d24529646a884d9ea35d447797c1704f9af7f8ca89c
+size 1120962

checkpoint-512/global_step512/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eafbda36286ce606fb5a34840e1e1e38e3d8ea4a843195db2538d11a0b4b438
+size 1120962

checkpoint-512/global_step512/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83baa75623c78d8f91c6b2e64569f308a7462b877688ee00ed0feac6f820a849
+size 1120962

checkpoint-512/latest

@@ -0,0 +1 @@
+global_step512

checkpoint-512/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d81bdf35d4a96f83d17747658fc8419a08891834a6563b21948b87add9fb04d4
+size 15984

checkpoint-512/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b2226b3baf281c1a4682d3589cca22c49c03d08ddabba4b7bf0cd8f962e763
+size 15984

checkpoint-512/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2747bc04dd2eeac95885e98e2187e3bcd4afa3a342b84be848f831df95b5a45c
+size 15984

checkpoint-512/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:748ce8f6af9ee4f71634326ef0feab2689709ba265189db14e8ad2597a6a069f
+size 15984

checkpoint-512/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a305b9ee5552eafde4144f85827de5111e284b7a80d0730305caf122ddcb1b2
+size 15984

checkpoint-512/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994783fa7f186ee1e47f58286d2fac359247ace5cf6839cc27dd9554cec8f4c3
+size 15984

checkpoint-512/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0fd9d9563c1219f3b991eb043682a89ca78359fcde7abae21bd4e3723ade958
+size 15984

checkpoint-512/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d2b56147e1688b1e0eb18ac78736638ed468c8d814b3f285be263e33b30a8f1
+size 15984

checkpoint-512/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c13d82dab2f9cabcebe9bfed01f579fd2743b456246653711702e6bb767ac220
+size 1064

checkpoint-512/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": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-512/tokenizer.json

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

checkpoint-512/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": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-512/trainer_state.json

@@ -0,0 +1,3617 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 512,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001953125,
+      "grad_norm": 2.2842363876082494,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.7076,
+      "step": 1
+    },
+    {
+      "epoch": 0.00390625,
+      "grad_norm": 2.317015212334916,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.6296,
+      "step": 2
+    },
+    {
+      "epoch": 0.005859375,
+      "grad_norm": 2.0835939653262883,
+      "learning_rate": 3e-06,
+      "loss": 1.5593,
+      "step": 3
+    },
+    {
+      "epoch": 0.0078125,
+      "grad_norm": 2.1357657121975797,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.6713,
+      "step": 4
+    },
+    {
+      "epoch": 0.009765625,
+      "grad_norm": 2.0362735997756847,
+      "learning_rate": 5e-06,
+      "loss": 1.5327,
+      "step": 5
+    },
+    {
+      "epoch": 0.01171875,
+      "grad_norm": 2.1597413317388523,
+      "learning_rate": 6e-06,
+      "loss": 1.6435,
+      "step": 6
+    },
+    {
+      "epoch": 0.013671875,
+      "grad_norm": 2.1354234831872616,
+      "learning_rate": 7e-06,
+      "loss": 1.539,
+      "step": 7
+    },
+    {
+      "epoch": 0.015625,
+      "grad_norm": 2.0222980997885682,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.491,
+      "step": 8
+    },
+    {
+      "epoch": 0.017578125,
+      "grad_norm": 1.8336578914749888,
+      "learning_rate": 9e-06,
+      "loss": 1.567,
+      "step": 9
+    },
+    {
+      "epoch": 0.01953125,
+      "grad_norm": 1.7535364548043673,
+      "learning_rate": 1e-05,
+      "loss": 1.5181,
+      "step": 10
+    },
+    {
+      "epoch": 0.021484375,
+      "grad_norm": 1.348232072077207,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 1.4633,
+      "step": 11
+    },
+    {
+      "epoch": 0.0234375,
+      "grad_norm": 1.079057032053978,
+      "learning_rate": 1.2e-05,
+      "loss": 1.36,
+      "step": 12
+    },
+    {
+      "epoch": 0.025390625,
+      "grad_norm": 0.7143765277543237,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 1.3195,
+      "step": 13
+    },
+    {
+      "epoch": 0.02734375,
+      "grad_norm": 0.8120880164824964,
+      "learning_rate": 1.4e-05,
+      "loss": 1.3469,
+      "step": 14
+    },
+    {
+      "epoch": 0.029296875,
+      "grad_norm": 0.6746494578904082,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.3626,
+      "step": 15
+    },
+    {
+      "epoch": 0.03125,
+      "grad_norm": 0.9663545707089416,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.2772,
+      "step": 16
+    },
+    {
+      "epoch": 0.033203125,
+      "grad_norm": 0.961439588523319,
+      "learning_rate": 1.7e-05,
+      "loss": 1.2911,
+      "step": 17
+    },
+    {
+      "epoch": 0.03515625,
+      "grad_norm": 1.1738444068957379,
+      "learning_rate": 1.8e-05,
+      "loss": 1.3346,
+      "step": 18
+    },
+    {
+      "epoch": 0.037109375,
+      "grad_norm": 1.2332387671295317,
+      "learning_rate": 1.9e-05,
+      "loss": 1.3761,
+      "step": 19
+    },
+    {
+      "epoch": 0.0390625,
+      "grad_norm": 1.268714744941341,
+      "learning_rate": 2e-05,
+      "loss": 1.3042,
+      "step": 20
+    },
+    {
+      "epoch": 0.041015625,
+      "grad_norm": 1.078415802927275,
+      "learning_rate": 2.1000000000000002e-05,
+      "loss": 1.2102,
+      "step": 21
+    },
+    {
+      "epoch": 0.04296875,
+      "grad_norm": 1.330999136602917,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 1.2755,
+      "step": 22
+    },
+    {
+      "epoch": 0.044921875,
+      "grad_norm": 0.7130882289363479,
+      "learning_rate": 2.3e-05,
+      "loss": 1.1706,
+      "step": 23
+    },
+    {
+      "epoch": 0.046875,
+      "grad_norm": 0.5729960230193528,
+      "learning_rate": 2.4e-05,
+      "loss": 1.3215,
+      "step": 24
+    },
+    {
+      "epoch": 0.048828125,
+      "grad_norm": 0.6125271472968751,
+      "learning_rate": 2.5e-05,
+      "loss": 1.3213,
+      "step": 25
+    },
+    {
+      "epoch": 0.05078125,
+      "grad_norm": 0.6108864130655043,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 1.2865,
+      "step": 26
+    },
+    {
+      "epoch": 0.052734375,
+      "grad_norm": 0.6479528408256864,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 1.3383,
+      "step": 27
+    },
+    {
+      "epoch": 0.0546875,
+      "grad_norm": 0.8412108818700305,
+      "learning_rate": 2.8e-05,
+      "loss": 1.2763,
+      "step": 28
+    },
+    {
+      "epoch": 0.056640625,
+      "grad_norm": 0.8629612077288169,
+      "learning_rate": 2.9e-05,
+      "loss": 1.3045,
+      "step": 29
+    },
+    {
+      "epoch": 0.05859375,
+      "grad_norm": 0.7600858737745863,
+      "learning_rate": 3.0000000000000004e-05,
+      "loss": 1.2352,
+      "step": 30
+    },
+    {
+      "epoch": 0.060546875,
+      "grad_norm": 0.7130629485255873,
+      "learning_rate": 3.1e-05,
+      "loss": 1.2299,
+      "step": 31
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 0.5912964724458128,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 1.2234,
+      "step": 32
+    },
+    {
+      "epoch": 0.064453125,
+      "grad_norm": 0.5368820032381596,
+      "learning_rate": 3.3e-05,
+      "loss": 1.1934,
+      "step": 33
+    },
+    {
+      "epoch": 0.06640625,
+      "grad_norm": 0.5570421986755116,
+      "learning_rate": 3.4e-05,
+      "loss": 1.2581,
+      "step": 34
+    },
+    {
+      "epoch": 0.068359375,
+      "grad_norm": 0.46598864760360764,
+      "learning_rate": 3.5000000000000004e-05,
+      "loss": 1.2535,
+      "step": 35
+    },
+    {
+      "epoch": 0.0703125,
+      "grad_norm": 0.6392299897042107,
+      "learning_rate": 3.6e-05,
+      "loss": 1.2331,
+      "step": 36
+    },
+    {
+      "epoch": 0.072265625,
+      "grad_norm": 0.49983937474417145,
+      "learning_rate": 3.7000000000000005e-05,
+      "loss": 1.2432,
+      "step": 37
+    },
+    {
+      "epoch": 0.07421875,
+      "grad_norm": 0.652858138736506,
+      "learning_rate": 3.8e-05,
+      "loss": 1.2759,
+      "step": 38
+    },
+    {
+      "epoch": 0.076171875,
+      "grad_norm": 0.5926189930170476,
+      "learning_rate": 3.9e-05,
+      "loss": 1.3016,
+      "step": 39
+    },
+    {
+      "epoch": 0.078125,
+      "grad_norm": 0.6646763351870284,
+      "learning_rate": 4e-05,
+      "loss": 1.344,
+      "step": 40
+    },
+    {
+      "epoch": 0.080078125,
+      "grad_norm": 0.6228429864196855,
+      "learning_rate": 3.99998980683206e-05,
+      "loss": 1.2794,
+      "step": 41
+    },
+    {
+      "epoch": 0.08203125,
+      "grad_norm": 0.5633101870154669,
+      "learning_rate": 3.9999592274321385e-05,
+      "loss": 1.2931,
+      "step": 42
+    },
+    {
+      "epoch": 0.083984375,
+      "grad_norm": 0.6866774046182069,
+      "learning_rate": 3.999908262111937e-05,
+      "loss": 1.2647,
+      "step": 43
+    },
+    {
+      "epoch": 0.0859375,
+      "grad_norm": 0.5312790576505163,
+      "learning_rate": 3.9998369113909555e-05,
+      "loss": 1.2255,
+      "step": 44
+    },
+    {
+      "epoch": 0.087890625,
+      "grad_norm": 0.5694229658922494,
+      "learning_rate": 3.999745175996481e-05,
+      "loss": 1.3104,
+      "step": 45
+    },
+    {
+      "epoch": 0.08984375,
+      "grad_norm": 0.5068013674566277,
+      "learning_rate": 3.999633056863589e-05,
+      "loss": 1.1771,
+      "step": 46
+    },
+    {
+      "epoch": 0.091796875,
+      "grad_norm": 0.5428027277075501,
+      "learning_rate": 3.999500555135129e-05,
+      "loss": 1.3508,
+      "step": 47
+    },
+    {
+      "epoch": 0.09375,
+      "grad_norm": 0.4792441915562371,
+      "learning_rate": 3.999347672161713e-05,
+      "loss": 1.1144,
+      "step": 48
+    },
+    {
+      "epoch": 0.095703125,
+      "grad_norm": 0.5033945174929487,
+      "learning_rate": 3.999174409501703e-05,
+      "loss": 1.1474,
+      "step": 49
+    },
+    {
+      "epoch": 0.09765625,
+      "grad_norm": 0.5609150975698594,
+      "learning_rate": 3.9989807689211946e-05,
+      "loss": 1.2558,
+      "step": 50
+    },
+    {
+      "epoch": 0.099609375,
+      "grad_norm": 0.5558707293914855,
+      "learning_rate": 3.998766752393998e-05,
+      "loss": 1.1411,
+      "step": 51
+    },
+    {
+      "epoch": 0.1015625,
+      "grad_norm": 0.4429585853749615,
+      "learning_rate": 3.99853236210162e-05,
+      "loss": 1.1715,
+      "step": 52
+    },
+    {
+      "epoch": 0.103515625,
+      "grad_norm": 0.5064052852591816,
+      "learning_rate": 3.998277600433241e-05,
+      "loss": 1.2018,
+      "step": 53
+    },
+    {
+      "epoch": 0.10546875,
+      "grad_norm": 0.526020419983389,
+      "learning_rate": 3.998002469985688e-05,
+      "loss": 1.1164,
+      "step": 54
+    },
+    {
+      "epoch": 0.107421875,
+      "grad_norm": 0.504222879676158,
+      "learning_rate": 3.997706973563413e-05,
+      "loss": 1.191,
+      "step": 55
+    },
+    {
+      "epoch": 0.109375,
+      "grad_norm": 0.5614145336635687,
+      "learning_rate": 3.9973911141784605e-05,
+      "loss": 1.3011,
+      "step": 56
+    },
+    {
+      "epoch": 0.111328125,
+      "grad_norm": 0.4391770801146478,
+      "learning_rate": 3.997054895050437e-05,
+      "loss": 1.2535,
+      "step": 57
+    },
+    {
+      "epoch": 0.11328125,
+      "grad_norm": 0.5583307267784473,
+      "learning_rate": 3.996698319606482e-05,
+      "loss": 1.153,
+      "step": 58
+    },
+    {
+      "epoch": 0.115234375,
+      "grad_norm": 0.4576133947689655,
+      "learning_rate": 3.996321391481229e-05,
+      "loss": 1.1564,
+      "step": 59
+    },
+    {
+      "epoch": 0.1171875,
+      "grad_norm": 0.41970646962377184,
+      "learning_rate": 3.995924114516769e-05,
+      "loss": 1.1935,
+      "step": 60
+    },
+    {
+      "epoch": 0.119140625,
+      "grad_norm": 0.44805324266797203,
+      "learning_rate": 3.995506492762613e-05,
+      "loss": 1.1339,
+      "step": 61
+    },
+    {
+      "epoch": 0.12109375,
+      "grad_norm": 0.5208068893189155,
+      "learning_rate": 3.9950685304756494e-05,
+      "loss": 1.2092,
+      "step": 62
+    },
+    {
+      "epoch": 0.123046875,
+      "grad_norm": 0.44195618774115664,
+      "learning_rate": 3.994610232120101e-05,
+      "loss": 1.1292,
+      "step": 63
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.4514887790554273,
+      "learning_rate": 3.994131602367481e-05,
+      "loss": 1.1658,
+      "step": 64
+    },
+    {
+      "epoch": 0.126953125,
+      "grad_norm": 0.5908686231033371,
+      "learning_rate": 3.9936326460965423e-05,
+      "loss": 1.2076,
+      "step": 65
+    },
+    {
+      "epoch": 0.12890625,
+      "grad_norm": 0.46799815417666174,
+      "learning_rate": 3.99311336839323e-05,
+      "loss": 1.1889,
+      "step": 66
+    },
+    {
+      "epoch": 0.130859375,
+      "grad_norm": 0.45939729407525115,
+      "learning_rate": 3.992573774550629e-05,
+      "loss": 1.1704,
+      "step": 67
+    },
+    {
+      "epoch": 0.1328125,
+      "grad_norm": 0.4142175477343616,
+      "learning_rate": 3.9920138700689095e-05,
+      "loss": 1.1848,
+      "step": 68
+    },
+    {
+      "epoch": 0.134765625,
+      "grad_norm": 0.37685838553537837,
+      "learning_rate": 3.991433660655273e-05,
+      "loss": 1.1041,
+      "step": 69
+    },
+    {
+      "epoch": 0.13671875,
+      "grad_norm": 0.39832807246827023,
+      "learning_rate": 3.99083315222389e-05,
+      "loss": 1.2002,
+      "step": 70
+    },
+    {
+      "epoch": 0.138671875,
+      "grad_norm": 0.43218323629933336,
+      "learning_rate": 3.990212350895845e-05,
+      "loss": 1.1487,
+      "step": 71
+    },
+    {
+      "epoch": 0.140625,
+      "grad_norm": 0.43302460007599547,
+      "learning_rate": 3.98957126299907e-05,
+      "loss": 1.1638,
+      "step": 72
+    },
+    {
+      "epoch": 0.142578125,
+      "grad_norm": 0.41150363252077565,
+      "learning_rate": 3.988909895068281e-05,
+      "loss": 1.1353,
+      "step": 73
+    },
+    {
+      "epoch": 0.14453125,
+      "grad_norm": 0.4362254605938381,
+      "learning_rate": 3.988228253844913e-05,
+      "loss": 1.2202,
+      "step": 74
+    },
+    {
+      "epoch": 0.146484375,
+      "grad_norm": 0.4696684841153936,
+      "learning_rate": 3.987526346277049e-05,
+      "loss": 1.1722,
+      "step": 75
+    },
+    {
+      "epoch": 0.1484375,
+      "grad_norm": 0.42274900639715757,
+      "learning_rate": 3.9868041795193505e-05,
+      "loss": 1.179,
+      "step": 76
+    },
+    {
+      "epoch": 0.150390625,
+      "grad_norm": 0.47381294364503707,
+      "learning_rate": 3.9860617609329856e-05,
+      "loss": 1.1978,
+      "step": 77
+    },
+    {
+      "epoch": 0.15234375,
+      "grad_norm": 0.448192967722078,
+      "learning_rate": 3.9852990980855505e-05,
+      "loss": 1.2042,
+      "step": 78
+    },
+    {
+      "epoch": 0.154296875,
+      "grad_norm": 0.388483486919693,
+      "learning_rate": 3.984516198750997e-05,
+      "loss": 1.148,
+      "step": 79
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 0.4057112657252388,
+      "learning_rate": 3.9837130709095475e-05,
+      "loss": 1.1267,
+      "step": 80
+    },
+    {
+      "epoch": 0.158203125,
+      "grad_norm": 0.5111257616377479,
+      "learning_rate": 3.982889722747621e-05,
+      "loss": 1.1992,
+      "step": 81
+    },
+    {
+      "epoch": 0.16015625,
+      "grad_norm": 0.42800919524357695,
+      "learning_rate": 3.9820461626577426e-05,
+      "loss": 1.2214,
+      "step": 82
+    },
+    {
+      "epoch": 0.162109375,
+      "grad_norm": 0.6604320971658805,
+      "learning_rate": 3.981182399238462e-05,
+      "loss": 1.1046,
+      "step": 83
+    },
+    {
+      "epoch": 0.1640625,
+      "grad_norm": 0.4650529995861808,
+      "learning_rate": 3.980298441294265e-05,
+      "loss": 1.1485,
+      "step": 84
+    },
+    {
+      "epoch": 0.166015625,
+      "grad_norm": 0.8247014006092652,
+      "learning_rate": 3.9793942978354835e-05,
+      "loss": 1.2345,
+      "step": 85
+    },
+    {
+      "epoch": 0.16796875,
+      "grad_norm": 0.5111463246016623,
+      "learning_rate": 3.978469978078203e-05,
+      "loss": 1.1406,
+      "step": 86
+    },
+    {
+      "epoch": 0.169921875,
+      "grad_norm": 0.3980549366997817,
+      "learning_rate": 3.977525491444171e-05,
+      "loss": 1.138,
+      "step": 87
+    },
+    {
+      "epoch": 0.171875,
+      "grad_norm": 0.4500013345653544,
+      "learning_rate": 3.976560847560697e-05,
+      "loss": 1.1803,
+      "step": 88
+    },
+    {
+      "epoch": 0.173828125,
+      "grad_norm": 0.6144879263096161,
+      "learning_rate": 3.975576056260559e-05,
+      "loss": 1.376,
+      "step": 89
+    },
+    {
+      "epoch": 0.17578125,
+      "grad_norm": 0.45250166677505255,
+      "learning_rate": 3.974571127581901e-05,
+      "loss": 1.2616,
+      "step": 90
+    },
+    {
+      "epoch": 0.177734375,
+      "grad_norm": 0.7260361194779941,
+      "learning_rate": 3.973546071768128e-05,
+      "loss": 1.207,
+      "step": 91
+    },
+    {
+      "epoch": 0.1796875,
+      "grad_norm": 0.40590569325939646,
+      "learning_rate": 3.972500899267807e-05,
+      "loss": 1.1857,
+      "step": 92
+    },
+    {
+      "epoch": 0.181640625,
+      "grad_norm": 0.7059204956983739,
+      "learning_rate": 3.971435620734557e-05,
+      "loss": 1.1629,
+      "step": 93
+    },
+    {
+      "epoch": 0.18359375,
+      "grad_norm": 0.4166494769492577,
+      "learning_rate": 3.97035024702694e-05,
+      "loss": 1.2105,
+      "step": 94
+    },
+    {
+      "epoch": 0.185546875,
+      "grad_norm": 0.4708428232528331,
+      "learning_rate": 3.969244789208354e-05,
+      "loss": 1.2074,
+      "step": 95
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 0.46187395897944283,
+      "learning_rate": 3.9681192585469146e-05,
+      "loss": 1.2411,
+      "step": 96
+    },
+    {
+      "epoch": 0.189453125,
+      "grad_norm": 0.40887786827875044,
+      "learning_rate": 3.9669736665153455e-05,
+      "loss": 1.181,
+      "step": 97
+    },
+    {
+      "epoch": 0.19140625,
+      "grad_norm": 0.5783677933870661,
+      "learning_rate": 3.96580802479086e-05,
+      "loss": 1.2412,
+      "step": 98
+    },
+    {
+      "epoch": 0.193359375,
+      "grad_norm": 0.46098155681455955,
+      "learning_rate": 3.9646223452550374e-05,
+      "loss": 1.0478,
+      "step": 99
+    },
+    {
+      "epoch": 0.1953125,
+      "grad_norm": 0.4421189367731534,
+      "learning_rate": 3.9634166399937104e-05,
+      "loss": 1.1528,
+      "step": 100
+    },
+    {
+      "epoch": 0.197265625,
+      "grad_norm": 0.44208897843282735,
+      "learning_rate": 3.962190921296834e-05,
+      "loss": 1.1294,
+      "step": 101
+    },
+    {
+      "epoch": 0.19921875,
+      "grad_norm": 0.41115810620405063,
+      "learning_rate": 3.9609452016583654e-05,
+      "loss": 1.0787,
+      "step": 102
+    },
+    {
+      "epoch": 0.201171875,
+      "grad_norm": 0.4592703963732682,
+      "learning_rate": 3.959679493776134e-05,
+      "loss": 1.2084,
+      "step": 103
+    },
+    {
+      "epoch": 0.203125,
+      "grad_norm": 0.46514364761525706,
+      "learning_rate": 3.9583938105517127e-05,
+      "loss": 1.169,
+      "step": 104
+    },
+    {
+      "epoch": 0.205078125,
+      "grad_norm": 0.5044144386089332,
+      "learning_rate": 3.957088165090287e-05,
+      "loss": 1.121,
+      "step": 105
+    },
+    {
+      "epoch": 0.20703125,
+      "grad_norm": 0.4160320267546915,
+      "learning_rate": 3.9557625707005185e-05,
+      "loss": 1.1133,
+      "step": 106
+    },
+    {
+      "epoch": 0.208984375,
+      "grad_norm": 0.46611013560363507,
+      "learning_rate": 3.954417040894416e-05,
+      "loss": 1.0846,
+      "step": 107
+    },
+    {
+      "epoch": 0.2109375,
+      "grad_norm": 0.494489354902747,
+      "learning_rate": 3.953051589387189e-05,
+      "loss": 1.1762,
+      "step": 108
+    },
+    {
+      "epoch": 0.212890625,
+      "grad_norm": 0.4226200871032249,
+      "learning_rate": 3.951666230097115e-05,
+      "loss": 1.0346,
+      "step": 109
+    },
+    {
+      "epoch": 0.21484375,
+      "grad_norm": 0.4032354878018358,
+      "learning_rate": 3.9502609771453934e-05,
+      "loss": 1.1223,
+      "step": 110
+    },
+    {
+      "epoch": 0.216796875,
+      "grad_norm": 0.4148468151686513,
+      "learning_rate": 3.948835844856004e-05,
+      "loss": 1.1581,
+      "step": 111
+    },
+    {
+      "epoch": 0.21875,
+      "grad_norm": 0.4655201875464092,
+      "learning_rate": 3.947390847755559e-05,
+      "loss": 1.141,
+      "step": 112
+    },
+    {
+      "epoch": 0.220703125,
+      "grad_norm": 0.44131202754652804,
+      "learning_rate": 3.945926000573156e-05,
+      "loss": 1.228,
+      "step": 113
+    },
+    {
+      "epoch": 0.22265625,
+      "grad_norm": 0.4878464713519324,
+      "learning_rate": 3.94444131824023e-05,
+      "loss": 1.2023,
+      "step": 114
+    },
+    {
+      "epoch": 0.224609375,
+      "grad_norm": 0.4433704308856408,
+      "learning_rate": 3.942936815890396e-05,
+      "loss": 1.2479,
+      "step": 115
+    },
+    {
+      "epoch": 0.2265625,
+      "grad_norm": 0.4848454824446459,
+      "learning_rate": 3.941412508859299e-05,
+      "loss": 1.1269,
+      "step": 116
+    },
+    {
+      "epoch": 0.228515625,
+      "grad_norm": 0.419630467357436,
+      "learning_rate": 3.939868412684458e-05,
+      "loss": 1.1806,
+      "step": 117
+    },
+    {
+      "epoch": 0.23046875,
+      "grad_norm": 0.39683375502836515,
+      "learning_rate": 3.938304543105104e-05,
+      "loss": 1.1054,
+      "step": 118
+    },
+    {
+      "epoch": 0.232421875,
+      "grad_norm": 0.4832371787668091,
+      "learning_rate": 3.936720916062022e-05,
+      "loss": 1.1174,
+      "step": 119
+    },
+    {
+      "epoch": 0.234375,
+      "grad_norm": 0.5986867637436046,
+      "learning_rate": 3.935117547697387e-05,
+      "loss": 1.1791,
+      "step": 120
+    },
+    {
+      "epoch": 0.236328125,
+      "grad_norm": 0.4150490343483682,
+      "learning_rate": 3.933494454354605e-05,
+      "loss": 1.2129,
+      "step": 121
+    },
+    {
+      "epoch": 0.23828125,
+      "grad_norm": 0.4215588087170942,
+      "learning_rate": 3.931851652578137e-05,
+      "loss": 1.1414,
+      "step": 122
+    },
+    {
+      "epoch": 0.240234375,
+      "grad_norm": 0.42515318009071157,
+      "learning_rate": 3.9301891591133377e-05,
+      "loss": 1.0854,
+      "step": 123
+    },
+    {
+      "epoch": 0.2421875,
+      "grad_norm": 0.4488701042494301,
+      "learning_rate": 3.928506990906282e-05,
+      "loss": 1.0725,
+      "step": 124
+    },
+    {
+      "epoch": 0.244140625,
+      "grad_norm": 0.41531581194897543,
+      "learning_rate": 3.9268051651035944e-05,
+      "loss": 1.0746,
+      "step": 125
+    },
+    {
+      "epoch": 0.24609375,
+      "grad_norm": 0.46204021714125687,
+      "learning_rate": 3.9250836990522685e-05,
+      "loss": 1.2164,
+      "step": 126
+    },
+    {
+      "epoch": 0.248046875,
+      "grad_norm": 0.6677384727690392,
+      "learning_rate": 3.923342610299499e-05,
+      "loss": 1.1834,
+      "step": 127
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.4961785465516465,
+      "learning_rate": 3.9215819165924956e-05,
+      "loss": 1.2178,
+      "step": 128
+    },
+    {
+      "epoch": 0.251953125,
+      "grad_norm": 0.4651476735438144,
+      "learning_rate": 3.919801635878305e-05,
+      "loss": 1.1005,
+      "step": 129
+    },
+    {
+      "epoch": 0.25390625,
+      "grad_norm": 0.49434332973849215,
+      "learning_rate": 3.918001786303627e-05,
+      "loss": 1.1922,
+      "step": 130
+    },
+    {
+      "epoch": 0.255859375,
+      "grad_norm": 0.45671514667179935,
+      "learning_rate": 3.9161823862146297e-05,
+      "loss": 1.0617,
+      "step": 131
+    },
+    {
+      "epoch": 0.2578125,
+      "grad_norm": 0.49674226929417115,
+      "learning_rate": 3.9143434541567654e-05,
+      "loss": 1.2203,
+      "step": 132
+    },
+    {
+      "epoch": 0.259765625,
+      "grad_norm": 0.5208683235687923,
+      "learning_rate": 3.912485008874577e-05,
+      "loss": 1.1587,
+      "step": 133
+    },
+    {
+      "epoch": 0.26171875,
+      "grad_norm": 0.517022288962491,
+      "learning_rate": 3.9106070693115087e-05,
+      "loss": 1.1427,
+      "step": 134
+    },
+    {
+      "epoch": 0.263671875,
+      "grad_norm": 0.38942661826422087,
+      "learning_rate": 3.908709654609715e-05,
+      "loss": 1.0629,
+      "step": 135
+    },
+    {
+      "epoch": 0.265625,
+      "grad_norm": 0.4564236281556844,
+      "learning_rate": 3.9067927841098614e-05,
+      "loss": 1.0919,
+      "step": 136
+    },
+    {
+      "epoch": 0.267578125,
+      "grad_norm": 0.4929559987928741,
+      "learning_rate": 3.9048564773509314e-05,
+      "loss": 1.1502,
+      "step": 137
+    },
+    {
+      "epoch": 0.26953125,
+      "grad_norm": 0.48513251932309925,
+      "learning_rate": 3.902900754070025e-05,
+      "loss": 1.1158,
+      "step": 138
+    },
+    {
+      "epoch": 0.271484375,
+      "grad_norm": 0.5349569441078609,
+      "learning_rate": 3.900925634202158e-05,
+      "loss": 1.1279,
+      "step": 139
+    },
+    {
+      "epoch": 0.2734375,
+      "grad_norm": 0.47177459620840684,
+      "learning_rate": 3.898931137880059e-05,
+      "loss": 1.1595,
+      "step": 140
+    },
+    {
+      "epoch": 0.275390625,
+      "grad_norm": 0.4904546697998669,
+      "learning_rate": 3.896917285433964e-05,
+      "loss": 1.2615,
+      "step": 141
+    },
+    {
+      "epoch": 0.27734375,
+      "grad_norm": 0.5768180408665089,
+      "learning_rate": 3.894884097391409e-05,
+      "loss": 1.1688,
+      "step": 142
+    },
+    {
+      "epoch": 0.279296875,
+      "grad_norm": 0.4362108519904031,
+      "learning_rate": 3.892831594477021e-05,
+      "loss": 1.0983,
+      "step": 143
+    },
+    {
+      "epoch": 0.28125,
+      "grad_norm": 0.4570710320413065,
+      "learning_rate": 3.890759797612307e-05,
+      "loss": 1.3706,
+      "step": 144
+    },
+    {
+      "epoch": 0.283203125,
+      "grad_norm": 0.4465318663671251,
+      "learning_rate": 3.888668727915441e-05,
+      "loss": 1.1377,
+      "step": 145
+    },
+    {
+      "epoch": 0.28515625,
+      "grad_norm": 0.5047852656660148,
+      "learning_rate": 3.886558406701046e-05,
+      "loss": 1.0747,
+      "step": 146
+    },
+    {
+      "epoch": 0.287109375,
+      "grad_norm": 0.4412295789497703,
+      "learning_rate": 3.884428855479983e-05,
+      "loss": 1.1261,
+      "step": 147
+    },
+    {
+      "epoch": 0.2890625,
+      "grad_norm": 0.4476476539228374,
+      "learning_rate": 3.8822800959591236e-05,
+      "loss": 1.1769,
+      "step": 148
+    },
+    {
+      "epoch": 0.291015625,
+      "grad_norm": 0.45924117326794117,
+      "learning_rate": 3.880112150041134e-05,
+      "loss": 1.1564,
+      "step": 149
+    },
+    {
+      "epoch": 0.29296875,
+      "grad_norm": 0.43931168833110684,
+      "learning_rate": 3.877925039824253e-05,
+      "loss": 1.1682,
+      "step": 150
+    },
+    {
+      "epoch": 0.294921875,
+      "grad_norm": 0.5438637955362605,
+      "learning_rate": 3.8757187876020603e-05,
+      "loss": 1.1448,
+      "step": 151
+    },
+    {
+      "epoch": 0.296875,
+      "grad_norm": 0.42928963297461137,
+      "learning_rate": 3.873493415863256e-05,
+      "loss": 1.2078,
+      "step": 152
+    },
+    {
+      "epoch": 0.298828125,
+      "grad_norm": 0.4381709802123583,
+      "learning_rate": 3.8712489472914286e-05,
+      "loss": 1.0604,
+      "step": 153
+    },
+    {
+      "epoch": 0.30078125,
+      "grad_norm": 0.4988490117613772,
+      "learning_rate": 3.8689854047648224e-05,
+      "loss": 1.1424,
+      "step": 154
+    },
+    {
+      "epoch": 0.302734375,
+      "grad_norm": 0.4257038437137218,
+      "learning_rate": 3.866702811356107e-05,
+      "loss": 1.0955,
+      "step": 155
+    },
+    {
+      "epoch": 0.3046875,
+      "grad_norm": 0.4893472968930594,
+      "learning_rate": 3.86440119033214e-05,
+      "loss": 1.1854,
+      "step": 156
+    },
+    {
+      "epoch": 0.306640625,
+      "grad_norm": 0.5731240348991923,
+      "learning_rate": 3.862080565153731e-05,
+      "loss": 1.2505,
+      "step": 157
+    },
+    {
+      "epoch": 0.30859375,
+      "grad_norm": 0.4594995644663965,
+      "learning_rate": 3.8597409594754025e-05,
+      "loss": 1.1047,
+      "step": 158
+    },
+    {
+      "epoch": 0.310546875,
+      "grad_norm": 0.3898970756217597,
+      "learning_rate": 3.857382397145148e-05,
+      "loss": 1.1728,
+      "step": 159
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.5165759238716673,
+      "learning_rate": 3.85500490220419e-05,
+      "loss": 1.1232,
+      "step": 160
+    },
+    {
+      "epoch": 0.314453125,
+      "grad_norm": 0.42169317869735606,
+      "learning_rate": 3.852608498886732e-05,
+      "loss": 1.1087,
+      "step": 161
+    },
+    {
+      "epoch": 0.31640625,
+      "grad_norm": 0.4831766592421198,
+      "learning_rate": 3.850193211619718e-05,
+      "loss": 1.0902,
+      "step": 162
+    },
+    {
+      "epoch": 0.318359375,
+      "grad_norm": 0.5168422003190449,
+      "learning_rate": 3.8477590650225735e-05,
+      "loss": 1.1979,
+      "step": 163
+    },
+    {
+      "epoch": 0.3203125,
+      "grad_norm": 0.44267326014624,
+      "learning_rate": 3.845306083906967e-05,
+      "loss": 1.1311,
+      "step": 164
+    },
+    {
+      "epoch": 0.322265625,
+      "grad_norm": 0.42634229457641887,
+      "learning_rate": 3.842834293276545e-05,
+      "loss": 1.1729,
+      "step": 165
+    },
+    {
+      "epoch": 0.32421875,
+      "grad_norm": 0.40628491116146026,
+      "learning_rate": 3.8403437183266834e-05,
+      "loss": 1.0984,
+      "step": 166
+    },
+    {
+      "epoch": 0.326171875,
+      "grad_norm": 0.4159045672550255,
+      "learning_rate": 3.8378343844442344e-05,
+      "loss": 1.1731,
+      "step": 167
+    },
+    {
+      "epoch": 0.328125,
+      "grad_norm": 0.5968785135150301,
+      "learning_rate": 3.8353063172072564e-05,
+      "loss": 1.0247,
+      "step": 168
+    },
+    {
+      "epoch": 0.330078125,
+      "grad_norm": 0.4649591605790638,
+      "learning_rate": 3.8327595423847645e-05,
+      "loss": 1.139,
+      "step": 169
+    },
+    {
+      "epoch": 0.33203125,
+      "grad_norm": 0.48079030109724175,
+      "learning_rate": 3.830194085936463e-05,
+      "loss": 1.1268,
+      "step": 170
+    },
+    {
+      "epoch": 0.333984375,
+      "grad_norm": 0.46348618416181137,
+      "learning_rate": 3.8276099740124794e-05,
+      "loss": 1.2004,
+      "step": 171
+    },
+    {
+      "epoch": 0.3359375,
+      "grad_norm": 0.4832617358199499,
+      "learning_rate": 3.8250072329531004e-05,
+      "loss": 1.0743,
+      "step": 172
+    },
+    {
+      "epoch": 0.337890625,
+      "grad_norm": 0.4420229534375586,
+      "learning_rate": 3.822385889288503e-05,
+      "loss": 1.141,
+      "step": 173
+    },
+    {
+      "epoch": 0.33984375,
+      "grad_norm": 0.39752191495545935,
+      "learning_rate": 3.819745969738484e-05,
+      "loss": 1.0972,
+      "step": 174
+    },
+    {
+      "epoch": 0.341796875,
+      "grad_norm": 0.4411421700040708,
+      "learning_rate": 3.817087501212185e-05,
+      "loss": 1.0233,
+      "step": 175
+    },
+    {
+      "epoch": 0.34375,
+      "grad_norm": 0.4017237336736879,
+      "learning_rate": 3.8144105108078246e-05,
+      "loss": 1.1563,
+      "step": 176
+    },
+    {
+      "epoch": 0.345703125,
+      "grad_norm": 0.686922962042273,
+      "learning_rate": 3.8117150258124134e-05,
+      "loss": 1.147,
+      "step": 177
+    },
+    {
+      "epoch": 0.34765625,
+      "grad_norm": 0.4294357539370898,
+      "learning_rate": 3.8090010737014836e-05,
+      "loss": 1.1116,
+      "step": 178
+    },
+    {
+      "epoch": 0.349609375,
+      "grad_norm": 0.41962832297995667,
+      "learning_rate": 3.806268682138805e-05,
+      "loss": 1.0827,
+      "step": 179
+    },
+    {
+      "epoch": 0.3515625,
+      "grad_norm": 0.4413195950046206,
+      "learning_rate": 3.803517878976103e-05,
+      "loss": 1.0814,
+      "step": 180
+    },
+    {
+      "epoch": 0.353515625,
+      "grad_norm": 0.45365068157119814,
+      "learning_rate": 3.8007486922527774e-05,
+      "loss": 1.0599,
+      "step": 181
+    },
+    {
+      "epoch": 0.35546875,
+      "grad_norm": 0.5286445380979327,
+      "learning_rate": 3.7979611501956124e-05,
+      "loss": 1.2251,
+      "step": 182
+    },
+    {
+      "epoch": 0.357421875,
+      "grad_norm": 0.38599209970455534,
+      "learning_rate": 3.795155281218493e-05,
+      "loss": 1.1676,
+      "step": 183
+    },
+    {
+      "epoch": 0.359375,
+      "grad_norm": 0.44025531979392435,
+      "learning_rate": 3.7923311139221114e-05,
+      "loss": 1.0514,
+      "step": 184
+    },
+    {
+      "epoch": 0.361328125,
+      "grad_norm": 0.42167205583593925,
+      "learning_rate": 3.789488677093681e-05,
+      "loss": 1.1002,
+      "step": 185
+    },
+    {
+      "epoch": 0.36328125,
+      "grad_norm": 0.4466402130651366,
+      "learning_rate": 3.786627999706638e-05,
+      "loss": 1.1013,
+      "step": 186
+    },
+    {
+      "epoch": 0.365234375,
+      "grad_norm": 0.496760952886551,
+      "learning_rate": 3.783749110920345e-05,
+      "loss": 1.1465,
+      "step": 187
+    },
+    {
+      "epoch": 0.3671875,
+      "grad_norm": 0.4367613213432748,
+      "learning_rate": 3.780852040079802e-05,
+      "loss": 1.0657,
+      "step": 188
+    },
+    {
+      "epoch": 0.369140625,
+      "grad_norm": 0.41447069424638583,
+      "learning_rate": 3.777936816715336e-05,
+      "loss": 1.116,
+      "step": 189
+    },
+    {
+      "epoch": 0.37109375,
+      "grad_norm": 0.4361134375016492,
+      "learning_rate": 3.7750034705423095e-05,
+      "loss": 1.2767,
+      "step": 190
+    },
+    {
+      "epoch": 0.373046875,
+      "grad_norm": 0.4066150259484398,
+      "learning_rate": 3.772052031460812e-05,
+      "loss": 1.0785,
+      "step": 191
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.40407841923262816,
+      "learning_rate": 3.769082529555359e-05,
+      "loss": 1.1644,
+      "step": 192
+    },
+    {
+      "epoch": 0.376953125,
+      "grad_norm": 0.44561296429853814,
+      "learning_rate": 3.766094995094581e-05,
+      "loss": 1.0663,
+      "step": 193
+    },
+    {
+      "epoch": 0.37890625,
+      "grad_norm": 0.5352430776738828,
+      "learning_rate": 3.7630894585309195e-05,
+      "loss": 1.0209,
+      "step": 194
+    },
+    {
+      "epoch": 0.380859375,
+      "grad_norm": 0.43636357529723163,
+      "learning_rate": 3.7600659505003125e-05,
+      "loss": 1.0621,
+      "step": 195
+    },
+    {
+      "epoch": 0.3828125,
+      "grad_norm": 0.4264879021475797,
+      "learning_rate": 3.757024501821885e-05,
+      "loss": 1.1336,
+      "step": 196
+    },
+    {
+      "epoch": 0.384765625,
+      "grad_norm": 0.3873402520476977,
+      "learning_rate": 3.753965143497635e-05,
+      "loss": 1.1378,
+      "step": 197
+    },
+    {
+      "epoch": 0.38671875,
+      "grad_norm": 0.40092066811193233,
+      "learning_rate": 3.750887906712115e-05,
+      "loss": 1.0685,
+      "step": 198
+    },
+    {
+      "epoch": 0.388671875,
+      "grad_norm": 0.43572366333630774,
+      "learning_rate": 3.747792822832117e-05,
+      "loss": 1.1723,
+      "step": 199
+    },
+    {
+      "epoch": 0.390625,
+      "grad_norm": 0.37730662296410905,
+      "learning_rate": 3.744679923406351e-05,
+      "loss": 1.0823,
+      "step": 200
+    },
+    {
+      "epoch": 0.392578125,
+      "grad_norm": 0.4578098403628755,
+      "learning_rate": 3.741549240165122e-05,
+      "loss": 1.1354,
+      "step": 201
+    },
+    {
+      "epoch": 0.39453125,
+      "grad_norm": 0.4402925550279655,
+      "learning_rate": 3.738400805020011e-05,
+      "loss": 1.0921,
+      "step": 202
+    },
+    {
+      "epoch": 0.396484375,
+      "grad_norm": 0.3814506298253285,
+      "learning_rate": 3.7352346500635466e-05,
+      "loss": 1.0813,
+      "step": 203
+    },
+    {
+      "epoch": 0.3984375,
+      "grad_norm": 0.5352313284178145,
+      "learning_rate": 3.732050807568878e-05,
+      "loss": 1.2286,
+      "step": 204
+    },
+    {
+      "epoch": 0.400390625,
+      "grad_norm": 0.4394941726895711,
+      "learning_rate": 3.728849309989445e-05,
+      "loss": 1.1362,
+      "step": 205
+    },
+    {
+      "epoch": 0.40234375,
+      "grad_norm": 0.40009193940161264,
+      "learning_rate": 3.7256301899586524e-05,
+      "loss": 1.014,
+      "step": 206
+    },
+    {
+      "epoch": 0.404296875,
+      "grad_norm": 0.4093033957375515,
+      "learning_rate": 3.7223934802895294e-05,
+      "loss": 1.0731,
+      "step": 207
+    },
+    {
+      "epoch": 0.40625,
+      "grad_norm": 0.47801078784248796,
+      "learning_rate": 3.719139213974403e-05,
+      "loss": 1.2081,
+      "step": 208
+    },
+    {
+      "epoch": 0.408203125,
+      "grad_norm": 0.5965083454407833,
+      "learning_rate": 3.715867424184554e-05,
+      "loss": 1.1495,
+      "step": 209
+    },
+    {
+      "epoch": 0.41015625,
+      "grad_norm": 0.43672026913516004,
+      "learning_rate": 3.712578144269887e-05,
+      "loss": 1.1201,
+      "step": 210
+    },
+    {
+      "epoch": 0.412109375,
+      "grad_norm": 0.5253144641112631,
+      "learning_rate": 3.7092714077585836e-05,
+      "loss": 1.2268,
+      "step": 211
+    },
+    {
+      "epoch": 0.4140625,
+      "grad_norm": 0.4738073414405108,
+      "learning_rate": 3.705947248356765e-05,
+      "loss": 1.1188,
+      "step": 212
+    },
+    {
+      "epoch": 0.416015625,
+      "grad_norm": 0.4477140058126639,
+      "learning_rate": 3.7026056999481464e-05,
+      "loss": 1.0571,
+      "step": 213
+    },
+    {
+      "epoch": 0.41796875,
+      "grad_norm": 0.4471574730565842,
+      "learning_rate": 3.699246796593692e-05,
+      "loss": 1.0847,
+      "step": 214
+    },
+    {
+      "epoch": 0.419921875,
+      "grad_norm": 0.41405988952981876,
+      "learning_rate": 3.6958705725312655e-05,
+      "loss": 1.1401,
+      "step": 215
+    },
+    {
+      "epoch": 0.421875,
+      "grad_norm": 0.49370245896699827,
+      "learning_rate": 3.692477062175289e-05,
+      "loss": 1.0703,
+      "step": 216
+    },
+    {
+      "epoch": 0.423828125,
+      "grad_norm": 0.4406399072344879,
+      "learning_rate": 3.689066300116381e-05,
+      "loss": 1.1793,
+      "step": 217
+    },
+    {
+      "epoch": 0.42578125,
+      "grad_norm": 0.43483619180179833,
+      "learning_rate": 3.6856383211210134e-05,
+      "loss": 1.1305,
+      "step": 218
+    },
+    {
+      "epoch": 0.427734375,
+      "grad_norm": 0.43256055966703133,
+      "learning_rate": 3.682193160131152e-05,
+      "loss": 1.0943,
+      "step": 219
+    },
+    {
+      "epoch": 0.4296875,
+      "grad_norm": 0.5598257236379292,
+      "learning_rate": 3.678730852263901e-05,
+      "loss": 1.2309,
+      "step": 220
+    },
+    {
+      "epoch": 0.431640625,
+      "grad_norm": 0.39045352547405415,
+      "learning_rate": 3.675251432811144e-05,
+      "loss": 1.0047,
+      "step": 221
+    },
+    {
+      "epoch": 0.43359375,
+      "grad_norm": 0.44912102512870905,
+      "learning_rate": 3.671754937239191e-05,
+      "loss": 1.1087,
+      "step": 222
+    },
+    {
+      "epoch": 0.435546875,
+      "grad_norm": 0.4174420596478436,
+      "learning_rate": 3.668241401188407e-05,
+      "loss": 1.0313,
+      "step": 223
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 0.36458359932139156,
+      "learning_rate": 3.6647108604728546e-05,
+      "loss": 0.9782,
+      "step": 224
+    },
+    {
+      "epoch": 0.439453125,
+      "grad_norm": 0.4419635662052487,
+      "learning_rate": 3.661163351079929e-05,
+      "loss": 1.1076,
+      "step": 225
+    },
+    {
+      "epoch": 0.44140625,
+      "grad_norm": 0.4537093691655119,
+      "learning_rate": 3.6575989091699895e-05,
+      "loss": 1.1265,
+      "step": 226
+    },
+    {
+      "epoch": 0.443359375,
+      "grad_norm": 0.4515222234083662,
+      "learning_rate": 3.65401757107599e-05,
+      "loss": 1.124,
+      "step": 227
+    },
+    {
+      "epoch": 0.4453125,
+      "grad_norm": 0.4509933735945529,
+      "learning_rate": 3.650419373303112e-05,
+      "loss": 1.2212,
+      "step": 228
+    },
+    {
+      "epoch": 0.447265625,
+      "grad_norm": 0.39315970041656184,
+      "learning_rate": 3.646804352528389e-05,
+      "loss": 1.1003,
+      "step": 229
+    },
+    {
+      "epoch": 0.44921875,
+      "grad_norm": 0.583897939706095,
+      "learning_rate": 3.643172545600336e-05,
+      "loss": 1.0984,
+      "step": 230
+    },
+    {
+      "epoch": 0.451171875,
+      "grad_norm": 0.5164803615434137,
+      "learning_rate": 3.63952398953857e-05,
+      "loss": 1.0738,
+      "step": 231
+    },
+    {
+      "epoch": 0.453125,
+      "grad_norm": 0.4070265753872102,
+      "learning_rate": 3.6358587215334355e-05,
+      "loss": 1.034,
+      "step": 232
+    },
+    {
+      "epoch": 0.455078125,
+      "grad_norm": 0.4101472350679783,
+      "learning_rate": 3.632176778945626e-05,
+      "loss": 1.1234,
+      "step": 233
+    },
+    {
+      "epoch": 0.45703125,
+      "grad_norm": 0.410956088362877,
+      "learning_rate": 3.628478199305799e-05,
+      "loss": 1.1062,
+      "step": 234
+    },
+    {
+      "epoch": 0.458984375,
+      "grad_norm": 0.42181972355385416,
+      "learning_rate": 3.624763020314199e-05,
+      "loss": 1.1848,
+      "step": 235
+    },
+    {
+      "epoch": 0.4609375,
+      "grad_norm": 0.4069735981570203,
+      "learning_rate": 3.62103127984027e-05,
+      "loss": 1.1203,
+      "step": 236
+    },
+    {
+      "epoch": 0.462890625,
+      "grad_norm": 0.4142934678480609,
+      "learning_rate": 3.617283015922268e-05,
+      "loss": 1.1044,
+      "step": 237
+    },
+    {
+      "epoch": 0.46484375,
+      "grad_norm": 0.4697374307040272,
+      "learning_rate": 3.6135182667668764e-05,
+      "loss": 1.1947,
+      "step": 238
+    },
+    {
+      "epoch": 0.466796875,
+      "grad_norm": 0.3985058819632944,
+      "learning_rate": 3.6097370707488175e-05,
+      "loss": 1.0906,
+      "step": 239
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 0.40215610602620183,
+      "learning_rate": 3.6059394664104554e-05,
+      "loss": 1.1607,
+      "step": 240
+    },
+    {
+      "epoch": 0.470703125,
+      "grad_norm": 0.3985665062059567,
+      "learning_rate": 3.60212549246141e-05,
+      "loss": 1.0787,
+      "step": 241
+    },
+    {
+      "epoch": 0.47265625,
+      "grad_norm": 0.43711415007382576,
+      "learning_rate": 3.598295187778158e-05,
+      "loss": 1.1554,
+      "step": 242
+    },
+    {
+      "epoch": 0.474609375,
+      "grad_norm": 0.4382023321095773,
+      "learning_rate": 3.5944485914036384e-05,
+      "loss": 1.0126,
+      "step": 243
+    },
+    {
+      "epoch": 0.4765625,
+      "grad_norm": 0.37488265505774904,
+      "learning_rate": 3.590585742546853e-05,
+      "loss": 1.1054,
+      "step": 244
+    },
+    {
+      "epoch": 0.478515625,
+      "grad_norm": 0.40930451172856447,
+      "learning_rate": 3.586706680582471e-05,
+      "loss": 1.0321,
+      "step": 245
+    },
+    {
+      "epoch": 0.48046875,
+      "grad_norm": 0.5059310227059168,
+      "learning_rate": 3.5828114450504205e-05,
+      "loss": 1.1239,
+      "step": 246
+    },
+    {
+      "epoch": 0.482421875,
+      "grad_norm": 0.45898297435796365,
+      "learning_rate": 3.5789000756554927e-05,
+      "loss": 1.0467,
+      "step": 247
+    },
+    {
+      "epoch": 0.484375,
+      "grad_norm": 0.42551550838444063,
+      "learning_rate": 3.5749726122669316e-05,
+      "loss": 1.051,
+      "step": 248
+    },
+    {
+      "epoch": 0.486328125,
+      "grad_norm": 0.4451344613451106,
+      "learning_rate": 3.5710290949180325e-05,
+      "loss": 1.1036,
+      "step": 249
+    },
+    {
+      "epoch": 0.48828125,
+      "grad_norm": 0.43151805025113255,
+      "learning_rate": 3.5670695638057285e-05,
+      "loss": 1.1906,
+      "step": 250
+    },
+    {
+      "epoch": 0.490234375,
+      "grad_norm": 0.492114391902568,
+      "learning_rate": 3.563094059290186e-05,
+      "loss": 1.1629,
+      "step": 251
+    },
+    {
+      "epoch": 0.4921875,
+      "grad_norm": 0.4144331093915329,
+      "learning_rate": 3.5591026218943905e-05,
+      "loss": 1.1485,
+      "step": 252
+    },
+    {
+      "epoch": 0.494140625,
+      "grad_norm": 0.4201461662795515,
+      "learning_rate": 3.5550952923037337e-05,
+      "loss": 1.1451,
+      "step": 253
+    },
+    {
+      "epoch": 0.49609375,
+      "grad_norm": 0.41132936789582963,
+      "learning_rate": 3.551072111365598e-05,
+      "loss": 1.1216,
+      "step": 254
+    },
+    {
+      "epoch": 0.498046875,
+      "grad_norm": 0.40892606177310264,
+      "learning_rate": 3.547033120088943e-05,
+      "loss": 1.0282,
+      "step": 255
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.39721649148962185,
+      "learning_rate": 3.5429783596438864e-05,
+      "loss": 1.113,
+      "step": 256
+    },
+    {
+      "epoch": 0.501953125,
+      "grad_norm": 0.41766348101220013,
+      "learning_rate": 3.5389078713612806e-05,
+      "loss": 1.0074,
+      "step": 257
+    },
+    {
+      "epoch": 0.50390625,
+      "grad_norm": 0.4167567256329769,
+      "learning_rate": 3.534821696732296e-05,
+      "loss": 1.1494,
+      "step": 258
+    },
+    {
+      "epoch": 0.505859375,
+      "grad_norm": 0.40290815531080393,
+      "learning_rate": 3.5307198774079986e-05,
+      "loss": 1.1173,
+      "step": 259
+    },
+    {
+      "epoch": 0.5078125,
+      "grad_norm": 0.3993720783667527,
+      "learning_rate": 3.52660245519892e-05,
+      "loss": 1.0752,
+      "step": 260
+    },
+    {
+      "epoch": 0.509765625,
+      "grad_norm": 0.42545000522760734,
+      "learning_rate": 3.522469472074638e-05,
+      "loss": 0.9948,
+      "step": 261
+    },
+    {
+      "epoch": 0.51171875,
+      "grad_norm": 0.37379510205589955,
+      "learning_rate": 3.518320970163341e-05,
+      "loss": 1.0816,
+      "step": 262
+    },
+    {
+      "epoch": 0.513671875,
+      "grad_norm": 0.38633279486112854,
+      "learning_rate": 3.514156991751409e-05,
+      "loss": 1.0954,
+      "step": 263
+    },
+    {
+      "epoch": 0.515625,
+      "grad_norm": 0.40389091982968633,
+      "learning_rate": 3.509977579282971e-05,
+      "loss": 1.133,
+      "step": 264
+    },
+    {
+      "epoch": 0.517578125,
+      "grad_norm": 0.4804041926173668,
+      "learning_rate": 3.50578277535948e-05,
+      "loss": 1.0541,
+      "step": 265
+    },
+    {
+      "epoch": 0.51953125,
+      "grad_norm": 0.4012148619394628,
+      "learning_rate": 3.501572622739278e-05,
+      "loss": 1.1555,
+      "step": 266
+    },
+    {
+      "epoch": 0.521484375,
+      "grad_norm": 0.3696526763975506,
+      "learning_rate": 3.497347164337158e-05,
+      "loss": 1.0857,
+      "step": 267
+    },
+    {
+      "epoch": 0.5234375,
+      "grad_norm": 0.655745451392472,
+      "learning_rate": 3.4931064432239256e-05,
+      "loss": 1.1313,
+      "step": 268
+    },
+    {
+      "epoch": 0.525390625,
+      "grad_norm": 0.37063711320152914,
+      "learning_rate": 3.4888505026259644e-05,
+      "loss": 1.0493,
+      "step": 269
+    },
+    {
+      "epoch": 0.52734375,
+      "grad_norm": 0.6053650660031528,
+      "learning_rate": 3.484579385924791e-05,
+      "loss": 1.228,
+      "step": 270
+    },
+    {
+      "epoch": 0.529296875,
+      "grad_norm": 0.4395843614703912,
+      "learning_rate": 3.480293136656617e-05,
+      "loss": 1.0371,
+      "step": 271
+    },
+    {
+      "epoch": 0.53125,
+      "grad_norm": 0.4253433992305504,
+      "learning_rate": 3.475991798511899e-05,
+      "loss": 1.1542,
+      "step": 272
+    },
+    {
+      "epoch": 0.533203125,
+      "grad_norm": 0.4192169579593461,
+      "learning_rate": 3.471675415334899e-05,
+      "loss": 1.119,
+      "step": 273
+    },
+    {
+      "epoch": 0.53515625,
+      "grad_norm": 0.5125507615260523,
+      "learning_rate": 3.467344031123237e-05,
+      "loss": 1.0975,
+      "step": 274
+    },
+    {
+      "epoch": 0.537109375,
+      "grad_norm": 0.4409386727934208,
+      "learning_rate": 3.4629976900274396e-05,
+      "loss": 1.0797,
+      "step": 275
+    },
+    {
+      "epoch": 0.5390625,
+      "grad_norm": 0.4433870652840288,
+      "learning_rate": 3.45863643635049e-05,
+      "loss": 1.0765,
+      "step": 276
+    },
+    {
+      "epoch": 0.541015625,
+      "grad_norm": 0.4369641917579842,
+      "learning_rate": 3.454260314547381e-05,
+      "loss": 1.1345,
+      "step": 277
+    },
+    {
+      "epoch": 0.54296875,
+      "grad_norm": 0.4569220638166111,
+      "learning_rate": 3.449869369224656e-05,
+      "loss": 1.0484,
+      "step": 278
+    },
+    {
+      "epoch": 0.544921875,
+      "grad_norm": 0.39807678444867833,
+      "learning_rate": 3.445463645139959e-05,
+      "loss": 1.1421,
+      "step": 279
+    },
+    {
+      "epoch": 0.546875,
+      "grad_norm": 0.4053891646377848,
+      "learning_rate": 3.441043187201574e-05,
+      "loss": 1.0423,
+      "step": 280
+    },
+    {
+      "epoch": 0.548828125,
+      "grad_norm": 0.3906910516461102,
+      "learning_rate": 3.436608040467973e-05,
+      "loss": 1.1273,
+      "step": 281
+    },
+    {
+      "epoch": 0.55078125,
+      "grad_norm": 0.41346781105113967,
+      "learning_rate": 3.432158250147351e-05,
+      "loss": 1.0668,
+      "step": 282
+    },
+    {
+      "epoch": 0.552734375,
+      "grad_norm": 0.4124283498849353,
+      "learning_rate": 3.4276938615971664e-05,
+      "loss": 1.0927,
+      "step": 283
+    },
+    {
+      "epoch": 0.5546875,
+      "grad_norm": 0.43815431152188694,
+      "learning_rate": 3.4232149203236836e-05,
+      "loss": 1.1899,
+      "step": 284
+    },
+    {
+      "epoch": 0.556640625,
+      "grad_norm": 0.3884560347509617,
+      "learning_rate": 3.418721471981502e-05,
+      "loss": 1.0609,
+      "step": 285
+    },
+    {
+      "epoch": 0.55859375,
+      "grad_norm": 0.4232084968596145,
+      "learning_rate": 3.4142135623730954e-05,
+      "loss": 1.1084,
+      "step": 286
+    },
+    {
+      "epoch": 0.560546875,
+      "grad_norm": 0.6358397558455653,
+      "learning_rate": 3.409691237448343e-05,
+      "loss": 1.029,
+      "step": 287
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 0.45992194648645957,
+      "learning_rate": 3.405154543304065e-05,
+      "loss": 1.0849,
+      "step": 288
+    },
+    {
+      "epoch": 0.564453125,
+      "grad_norm": 0.4818812993346098,
+      "learning_rate": 3.400603526183542e-05,
+      "loss": 0.943,
+      "step": 289
+    },
+    {
+      "epoch": 0.56640625,
+      "grad_norm": 0.3765252982516796,
+      "learning_rate": 3.3960382324760596e-05,
+      "loss": 0.9954,
+      "step": 290
+    },
+    {
+      "epoch": 0.568359375,
+      "grad_norm": 0.46990214773068983,
+      "learning_rate": 3.391458708716422e-05,
+      "loss": 1.0926,
+      "step": 291
+    },
+    {
+      "epoch": 0.5703125,
+      "grad_norm": 0.3917178675223708,
+      "learning_rate": 3.3868650015844835e-05,
+      "loss": 1.0707,
+      "step": 292
+    },
+    {
+      "epoch": 0.572265625,
+      "grad_norm": 0.41696024883927335,
+      "learning_rate": 3.382257157904674e-05,
+      "loss": 1.0687,
+      "step": 293
+    },
+    {
+      "epoch": 0.57421875,
+      "grad_norm": 0.38807035050695815,
+      "learning_rate": 3.377635224645515e-05,
+      "loss": 1.1126,
+      "step": 294
+    },
+    {
+      "epoch": 0.576171875,
+      "grad_norm": 0.406255734326262,
+      "learning_rate": 3.3729992489191514e-05,
+      "loss": 1.1278,
+      "step": 295
+    },
+    {
+      "epoch": 0.578125,
+      "grad_norm": 0.39143009407102003,
+      "learning_rate": 3.368349277980861e-05,
+      "loss": 1.1409,
+      "step": 296
+    },
+    {
+      "epoch": 0.580078125,
+      "grad_norm": 0.39325912719226885,
+      "learning_rate": 3.363685359228579e-05,
+      "loss": 1.0673,
+      "step": 297
+    },
+    {
+      "epoch": 0.58203125,
+      "grad_norm": 0.4080744357399852,
+      "learning_rate": 3.359007540202412e-05,
+      "loss": 1.0569,
+      "step": 298
+    },
+    {
+      "epoch": 0.583984375,
+      "grad_norm": 0.41221286181985456,
+      "learning_rate": 3.354315868584155e-05,
+      "loss": 1.0345,
+      "step": 299
+    },
+    {
+      "epoch": 0.5859375,
+      "grad_norm": 0.408899231590681,
+      "learning_rate": 3.349610392196804e-05,
+      "loss": 1.1531,
+      "step": 300
+    },
+    {
+      "epoch": 0.587890625,
+      "grad_norm": 0.40782751081372265,
+      "learning_rate": 3.344891159004072e-05,
+      "loss": 1.1214,
+      "step": 301
+    },
+    {
+      "epoch": 0.58984375,
+      "grad_norm": 0.41491986698901345,
+      "learning_rate": 3.340158217109895e-05,
+      "loss": 1.102,
+      "step": 302
+    },
+    {
+      "epoch": 0.591796875,
+      "grad_norm": 0.43560034237218315,
+      "learning_rate": 3.335411614757942e-05,
+      "loss": 1.0563,
+      "step": 303
+    },
+    {
+      "epoch": 0.59375,
+      "grad_norm": 0.39300089945853034,
+      "learning_rate": 3.3306514003311305e-05,
+      "loss": 1.0941,
+      "step": 304
+    },
+    {
+      "epoch": 0.595703125,
+      "grad_norm": 0.3993080209023848,
+      "learning_rate": 3.3258776223511254e-05,
+      "loss": 1.061,
+      "step": 305
+    },
+    {
+      "epoch": 0.59765625,
+      "grad_norm": 0.4403361997874876,
+      "learning_rate": 3.3210903294778476e-05,
+      "loss": 1.059,
+      "step": 306
+    },
+    {
+      "epoch": 0.599609375,
+      "grad_norm": 0.40839699507220767,
+      "learning_rate": 3.3162895705089755e-05,
+      "loss": 1.0646,
+      "step": 307
+    },
+    {
+      "epoch": 0.6015625,
+      "grad_norm": 0.45190381917447386,
+      "learning_rate": 3.311475394379454e-05,
+      "loss": 1.0537,
+      "step": 308
+    },
+    {
+      "epoch": 0.603515625,
+      "grad_norm": 0.4029154813389833,
+      "learning_rate": 3.306647850160986e-05,
+      "loss": 1.0964,
+      "step": 309
+    },
+    {
+      "epoch": 0.60546875,
+      "grad_norm": 0.4202106517061233,
+      "learning_rate": 3.301806987061543e-05,
+      "loss": 1.0978,
+      "step": 310
+    },
+    {
+      "epoch": 0.607421875,
+      "grad_norm": 0.4668232017003024,
+      "learning_rate": 3.296952854424854e-05,
+      "loss": 1.0437,
+      "step": 311
+    },
+    {
+      "epoch": 0.609375,
+      "grad_norm": 0.39673723899015667,
+      "learning_rate": 3.292085501729909e-05,
+      "loss": 1.1046,
+      "step": 312
+    },
+    {
+      "epoch": 0.611328125,
+      "grad_norm": 0.44958313468143707,
+      "learning_rate": 3.287204978590451e-05,
+      "loss": 1.1186,
+      "step": 313
+    },
+    {
+      "epoch": 0.61328125,
+      "grad_norm": 0.4836454614853554,
+      "learning_rate": 3.282311334754473e-05,
+      "loss": 1.0877,
+      "step": 314
+    },
+    {
+      "epoch": 0.615234375,
+      "grad_norm": 0.42606585670317537,
+      "learning_rate": 3.277404620103707e-05,
+      "loss": 1.1295,
+      "step": 315
+    },
+    {
+      "epoch": 0.6171875,
+      "grad_norm": 0.390307353492261,
+      "learning_rate": 3.27248488465312e-05,
+      "loss": 1.1007,
+      "step": 316
+    },
+    {
+      "epoch": 0.619140625,
+      "grad_norm": 0.3805925300751237,
+      "learning_rate": 3.267552178550401e-05,
+      "loss": 1.1001,
+      "step": 317
+    },
+    {
+      "epoch": 0.62109375,
+      "grad_norm": 0.4035790500067785,
+      "learning_rate": 3.262606552075454e-05,
+      "loss": 1.1128,
+      "step": 318
+    },
+    {
+      "epoch": 0.623046875,
+      "grad_norm": 0.4722955312249792,
+      "learning_rate": 3.2576480556398786e-05,
+      "loss": 1.1137,
+      "step": 319
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.44165761079295995,
+      "learning_rate": 3.2526767397864614e-05,
+      "loss": 1.1454,
+      "step": 320
+    },
+    {
+      "epoch": 0.626953125,
+      "grad_norm": 0.39553753160419564,
+      "learning_rate": 3.2476926551886606e-05,
+      "loss": 1.1166,
+      "step": 321
+    },
+    {
+      "epoch": 0.62890625,
+      "grad_norm": 0.403965297853274,
+      "learning_rate": 3.2426958526500865e-05,
+      "loss": 1.0781,
+      "step": 322
+    },
+    {
+      "epoch": 0.630859375,
+      "grad_norm": 0.3903234152596363,
+      "learning_rate": 3.237686383103988e-05,
+      "loss": 1.0549,
+      "step": 323
+    },
+    {
+      "epoch": 0.6328125,
+      "grad_norm": 0.3927744347727879,
+      "learning_rate": 3.232664297612727e-05,
+      "loss": 1.1046,
+      "step": 324
+    },
+    {
+      "epoch": 0.634765625,
+      "grad_norm": 0.3812149147814974,
+      "learning_rate": 3.227629647367268e-05,
+      "loss": 1.1601,
+      "step": 325
+    },
+    {
+      "epoch": 0.63671875,
+      "grad_norm": 0.38396424698024334,
+      "learning_rate": 3.2225824836866436e-05,
+      "loss": 1.0004,
+      "step": 326
+    },
+    {
+      "epoch": 0.638671875,
+      "grad_norm": 0.47563674580569204,
+      "learning_rate": 3.217522858017442e-05,
+      "loss": 1.0227,
+      "step": 327
+    },
+    {
+      "epoch": 0.640625,
+      "grad_norm": 0.3935678660654307,
+      "learning_rate": 3.212450821933277e-05,
+      "loss": 1.0778,
+      "step": 328
+    },
+    {
+      "epoch": 0.642578125,
+      "grad_norm": 0.37644343966319804,
+      "learning_rate": 3.207366427134264e-05,
+      "loss": 1.0786,
+      "step": 329
+    },
+    {
+      "epoch": 0.64453125,
+      "grad_norm": 0.3901117853270985,
+      "learning_rate": 3.2022697254464926e-05,
+      "loss": 1.0559,
+      "step": 330
+    },
+    {
+      "epoch": 0.646484375,
+      "grad_norm": 0.38427110510469054,
+      "learning_rate": 3.1971607688215005e-05,
+      "loss": 1.0164,
+      "step": 331
+    },
+    {
+      "epoch": 0.6484375,
+      "grad_norm": 0.42177940077749226,
+      "learning_rate": 3.19203960933574e-05,
+      "loss": 1.0411,
+      "step": 332
+    },
+    {
+      "epoch": 0.650390625,
+      "grad_norm": 0.4528297229069142,
+      "learning_rate": 3.1869062991900496e-05,
+      "loss": 1.1706,
+      "step": 333
+    },
+    {
+      "epoch": 0.65234375,
+      "grad_norm": 0.3803445217139758,
+      "learning_rate": 3.1817608907091216e-05,
+      "loss": 1.0699,
+      "step": 334
+    },
+    {
+      "epoch": 0.654296875,
+      "grad_norm": 0.41347538149417745,
+      "learning_rate": 3.176603436340969e-05,
+      "loss": 1.1955,
+      "step": 335
+    },
+    {
+      "epoch": 0.65625,
+      "grad_norm": 0.3694910871081213,
+      "learning_rate": 3.1714339886563896e-05,
+      "loss": 0.9668,
+      "step": 336
+    },
+    {
+      "epoch": 0.658203125,
+      "grad_norm": 0.3817019926131847,
+      "learning_rate": 3.1662526003484336e-05,
+      "loss": 0.9349,
+      "step": 337
+    },
+    {
+      "epoch": 0.66015625,
+      "grad_norm": 0.4366158667650914,
+      "learning_rate": 3.16105932423186e-05,
+      "loss": 1.0995,
+      "step": 338
+    },
+    {
+      "epoch": 0.662109375,
+      "grad_norm": 0.41958839201127524,
+      "learning_rate": 3.155854213242606e-05,
+      "loss": 0.9731,
+      "step": 339
+    },
+    {
+      "epoch": 0.6640625,
+      "grad_norm": 0.47402698673401783,
+      "learning_rate": 3.1506373204372414e-05,
+      "loss": 1.147,
+      "step": 340
+    },
+    {
+      "epoch": 0.666015625,
+      "grad_norm": 0.4827624577661964,
+      "learning_rate": 3.145408698992431e-05,
+      "loss": 1.0264,
+      "step": 341
+    },
+    {
+      "epoch": 0.66796875,
+      "grad_norm": 0.4263534871906621,
+      "learning_rate": 3.140168402204391e-05,
+      "loss": 1.1036,
+      "step": 342
+    },
+    {
+      "epoch": 0.669921875,
+      "grad_norm": 0.40773201005922843,
+      "learning_rate": 3.134916483488347e-05,
+      "loss": 1.0361,
+      "step": 343
+    },
+    {
+      "epoch": 0.671875,
+      "grad_norm": 0.4066940928998629,
+      "learning_rate": 3.129652996377987e-05,
+      "loss": 1.1271,
+      "step": 344
+    },
+    {
+      "epoch": 0.673828125,
+      "grad_norm": 0.4241747622419329,
+      "learning_rate": 3.124377994524921e-05,
+      "loss": 1.1259,
+      "step": 345
+    },
+    {
+      "epoch": 0.67578125,
+      "grad_norm": 0.39662513220486106,
+      "learning_rate": 3.1190915316981285e-05,
+      "loss": 1.0236,
+      "step": 346
+    },
+    {
+      "epoch": 0.677734375,
+      "grad_norm": 0.43948866331025493,
+      "learning_rate": 3.1137936617834116e-05,
+      "loss": 1.1076,
+      "step": 347
+    },
+    {
+      "epoch": 0.6796875,
+      "grad_norm": 0.36237602577817707,
+      "learning_rate": 3.10848443878285e-05,
+      "loss": 1.033,
+      "step": 348
+    },
+    {
+      "epoch": 0.681640625,
+      "grad_norm": 0.40357619022841135,
+      "learning_rate": 3.103163916814243e-05,
+      "loss": 1.1313,
+      "step": 349
+    },
+    {
+      "epoch": 0.68359375,
+      "grad_norm": 0.4555883501566975,
+      "learning_rate": 3.0978321501105666e-05,
+      "loss": 1.0808,
+      "step": 350
+    },
+    {
+      "epoch": 0.685546875,
+      "grad_norm": 0.35792704349676846,
+      "learning_rate": 3.0924891930194135e-05,
+      "loss": 1.0395,
+      "step": 351
+    },
+    {
+      "epoch": 0.6875,
+      "grad_norm": 0.593623473361786,
+      "learning_rate": 3.0871351000024425e-05,
+      "loss": 1.0712,
+      "step": 352
+    },
+    {
+      "epoch": 0.689453125,
+      "grad_norm": 0.4074422748367139,
+      "learning_rate": 3.0817699256348225e-05,
+      "loss": 0.9527,
+      "step": 353
+    },
+    {
+      "epoch": 0.69140625,
+      "grad_norm": 0.4127817442760279,
+      "learning_rate": 3.076393724604678e-05,
+      "loss": 1.1954,
+      "step": 354
+    },
+    {
+      "epoch": 0.693359375,
+      "grad_norm": 0.4946890107161909,
+      "learning_rate": 3.071006551712528e-05,
+      "loss": 1.0985,
+      "step": 355
+    },
+    {
+      "epoch": 0.6953125,
+      "grad_norm": 0.44421056915788415,
+      "learning_rate": 3.065608461870731e-05,
+      "loss": 1.1738,
+      "step": 356
+    },
+    {
+      "epoch": 0.697265625,
+      "grad_norm": 0.4556022988192606,
+      "learning_rate": 3.0601995101029234e-05,
+      "loss": 1.0996,
+      "step": 357
+    },
+    {
+      "epoch": 0.69921875,
+      "grad_norm": 0.4589330478948055,
+      "learning_rate": 3.054779751543459e-05,
+      "loss": 1.1462,
+      "step": 358
+    },
+    {
+      "epoch": 0.701171875,
+      "grad_norm": 0.8222210487787517,
+      "learning_rate": 3.0493492414368467e-05,
+      "loss": 1.0775,
+      "step": 359
+    },
+    {
+      "epoch": 0.703125,
+      "grad_norm": 0.4588728539488581,
+      "learning_rate": 3.0439080351371875e-05,
+      "loss": 1.0424,
+      "step": 360
+    },
+    {
+      "epoch": 0.705078125,
+      "grad_norm": 0.44719999962538626,
+      "learning_rate": 3.0384561881076117e-05,
+      "loss": 1.0759,
+      "step": 361
+    },
+    {
+      "epoch": 0.70703125,
+      "grad_norm": 0.46357553715630206,
+      "learning_rate": 3.0329937559197115e-05,
+      "loss": 1.2382,
+      "step": 362
+    },
+    {
+      "epoch": 0.708984375,
+      "grad_norm": 0.40336861309256355,
+      "learning_rate": 3.0275207942529756e-05,
+      "loss": 1.1079,
+      "step": 363
+    },
+    {
+      "epoch": 0.7109375,
+      "grad_norm": 0.5144680446514719,
+      "learning_rate": 3.022037358894221e-05,
+      "loss": 1.0465,
+      "step": 364
+    },
+    {
+      "epoch": 0.712890625,
+      "grad_norm": 0.4921289653271309,
+      "learning_rate": 3.0165435057370263e-05,
+      "loss": 1.0311,
+      "step": 365
+    },
+    {
+      "epoch": 0.71484375,
+      "grad_norm": 0.4320225158526767,
+      "learning_rate": 3.011039290781158e-05,
+      "loss": 1.0595,
+      "step": 366
+    },
+    {
+      "epoch": 0.716796875,
+      "grad_norm": 0.3810201922042623,
+      "learning_rate": 3.005524770132004e-05,
+      "loss": 0.9803,
+      "step": 367
+    },
+    {
+      "epoch": 0.71875,
+      "grad_norm": 0.4495492407985583,
+      "learning_rate": 3.0000000000000004e-05,
+      "loss": 1.0729,
+      "step": 368
+    },
+    {
+      "epoch": 0.720703125,
+      "grad_norm": 0.4152518634185682,
+      "learning_rate": 2.9944650367000556e-05,
+      "loss": 1.164,
+      "step": 369
+    },
+    {
+      "epoch": 0.72265625,
+      "grad_norm": 0.46481518081956474,
+      "learning_rate": 2.9889199366509807e-05,
+      "loss": 1.0677,
+      "step": 370
+    },
+    {
+      "epoch": 0.724609375,
+      "grad_norm": 0.36687791333329894,
+      "learning_rate": 2.983364756374912e-05,
+      "loss": 1.097,
+      "step": 371
+    },
+    {
+      "epoch": 0.7265625,
+      "grad_norm": 0.4609623092360792,
+      "learning_rate": 2.977799552496734e-05,
+      "loss": 1.0742,
+      "step": 372
+    },
+    {
+      "epoch": 0.728515625,
+      "grad_norm": 0.43485629130468156,
+      "learning_rate": 2.9722243817435057e-05,
+      "loss": 1.0596,
+      "step": 373
+    },
+    {
+      "epoch": 0.73046875,
+      "grad_norm": 0.4308785423786187,
+      "learning_rate": 2.9666393009438778e-05,
+      "loss": 1.1025,
+      "step": 374
+    },
+    {
+      "epoch": 0.732421875,
+      "grad_norm": 0.41425216636311923,
+      "learning_rate": 2.9610443670275177e-05,
+      "loss": 1.033,
+      "step": 375
+    },
+    {
+      "epoch": 0.734375,
+      "grad_norm": 0.5209374726966056,
+      "learning_rate": 2.955439637024526e-05,
+      "loss": 1.0744,
+      "step": 376
+    },
+    {
+      "epoch": 0.736328125,
+      "grad_norm": 0.7038228729760657,
+      "learning_rate": 2.9498251680648572e-05,
+      "loss": 1.0699,
+      "step": 377
+    },
+    {
+      "epoch": 0.73828125,
+      "grad_norm": 0.38639106447314064,
+      "learning_rate": 2.9442010173777355e-05,
+      "loss": 1.0536,
+      "step": 378
+    },
+    {
+      "epoch": 0.740234375,
+      "grad_norm": 0.5464755744132558,
+      "learning_rate": 2.9385672422910746e-05,
+      "loss": 1.1398,
+      "step": 379
+    },
+    {
+      "epoch": 0.7421875,
+      "grad_norm": 0.37413132931711773,
+      "learning_rate": 2.932923900230889e-05,
+      "loss": 1.0285,
+      "step": 380
+    },
+    {
+      "epoch": 0.744140625,
+      "grad_norm": 0.5155456583703741,
+      "learning_rate": 2.9272710487207123e-05,
+      "loss": 1.0657,
+      "step": 381
+    },
+    {
+      "epoch": 0.74609375,
+      "grad_norm": 0.42610802775582945,
+      "learning_rate": 2.92160874538101e-05,
+      "loss": 1.0751,
+      "step": 382
+    },
+    {
+      "epoch": 0.748046875,
+      "grad_norm": 0.37312053203898266,
+      "learning_rate": 2.91593704792859e-05,
+      "loss": 1.1236,
+      "step": 383
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.3865778900367502,
+      "learning_rate": 2.9102560141760178e-05,
+      "loss": 1.0783,
+      "step": 384
+    },
+    {
+      "epoch": 0.751953125,
+      "grad_norm": 0.44181257585885864,
+      "learning_rate": 2.9045657020310245e-05,
+      "loss": 1.096,
+      "step": 385
+    },
+    {
+      "epoch": 0.75390625,
+      "grad_norm": 0.4355612014896031,
+      "learning_rate": 2.898866169495916e-05,
+      "loss": 1.1355,
+      "step": 386
+    },
+    {
+      "epoch": 0.755859375,
+      "grad_norm": 0.43570244826557325,
+      "learning_rate": 2.8931574746669865e-05,
+      "loss": 0.979,
+      "step": 387
+    },
+    {
+      "epoch": 0.7578125,
+      "grad_norm": 0.4624097023644056,
+      "learning_rate": 2.8874396757339197e-05,
+      "loss": 1.1244,
+      "step": 388
+    },
+    {
+      "epoch": 0.759765625,
+      "grad_norm": 0.43243927150243583,
+      "learning_rate": 2.881712830979201e-05,
+      "loss": 1.2005,
+      "step": 389
+    },
+    {
+      "epoch": 0.76171875,
+      "grad_norm": 0.39334103281716926,
+      "learning_rate": 2.875976998777521e-05,
+      "loss": 1.1406,
+      "step": 390
+    },
+    {
+      "epoch": 0.763671875,
+      "grad_norm": 0.41626592809859797,
+      "learning_rate": 2.8702322375951808e-05,
+      "loss": 1.0462,
+      "step": 391
+    },
+    {
+      "epoch": 0.765625,
+      "grad_norm": 0.37844113633007853,
+      "learning_rate": 2.864478605989494e-05,
+      "loss": 0.9938,
+      "step": 392
+    },
+    {
+      "epoch": 0.767578125,
+      "grad_norm": 0.38237298412290605,
+      "learning_rate": 2.8587161626081963e-05,
+      "loss": 1.1152,
+      "step": 393
+    },
+    {
+      "epoch": 0.76953125,
+      "grad_norm": 0.457773179175426,
+      "learning_rate": 2.8529449661888397e-05,
+      "loss": 1.0211,
+      "step": 394
+    },
+    {
+      "epoch": 0.771484375,
+      "grad_norm": 0.5451142296439877,
+      "learning_rate": 2.8471650755581982e-05,
+      "loss": 1.0347,
+      "step": 395
+    },
+    {
+      "epoch": 0.7734375,
+      "grad_norm": 0.3748054383861272,
+      "learning_rate": 2.8413765496316682e-05,
+      "loss": 1.0349,
+      "step": 396
+    },
+    {
+      "epoch": 0.775390625,
+      "grad_norm": 0.40348473462322654,
+      "learning_rate": 2.8355794474126673e-05,
+      "loss": 1.0827,
+      "step": 397
+    },
+    {
+      "epoch": 0.77734375,
+      "grad_norm": 0.45778728826184956,
+      "learning_rate": 2.8297738279920302e-05,
+      "loss": 1.08,
+      "step": 398
+    },
+    {
+      "epoch": 0.779296875,
+      "grad_norm": 0.416175722341481,
+      "learning_rate": 2.8239597505474123e-05,
+      "loss": 1.1477,
+      "step": 399
+    },
+    {
+      "epoch": 0.78125,
+      "grad_norm": 0.4762205014497946,
+      "learning_rate": 2.8181372743426805e-05,
+      "loss": 1.1281,
+      "step": 400
+    },
+    {
+      "epoch": 0.783203125,
+      "grad_norm": 0.38963452597451154,
+      "learning_rate": 2.8123064587273123e-05,
+      "loss": 1.1001,
+      "step": 401
+    },
+    {
+      "epoch": 0.78515625,
+      "grad_norm": 0.37143930094659405,
+      "learning_rate": 2.8064673631357914e-05,
+      "loss": 1.1031,
+      "step": 402
+    },
+    {
+      "epoch": 0.787109375,
+      "grad_norm": 0.37217736788218464,
+      "learning_rate": 2.8006200470869996e-05,
+      "loss": 1.0837,
+      "step": 403
+    },
+    {
+      "epoch": 0.7890625,
+      "grad_norm": 0.4976469620168046,
+      "learning_rate": 2.794764570183611e-05,
+      "loss": 1.1485,
+      "step": 404
+    },
+    {
+      "epoch": 0.791015625,
+      "grad_norm": 0.4118640178274368,
+      "learning_rate": 2.788900992111485e-05,
+      "loss": 1.0149,
+      "step": 405
+    },
+    {
+      "epoch": 0.79296875,
+      "grad_norm": 0.4876334794131612,
+      "learning_rate": 2.7830293726390584e-05,
+      "loss": 1.0814,
+      "step": 406
+    },
+    {
+      "epoch": 0.794921875,
+      "grad_norm": 0.39552602320591645,
+      "learning_rate": 2.7771497716167334e-05,
+      "loss": 1.0316,
+      "step": 407
+    },
+    {
+      "epoch": 0.796875,
+      "grad_norm": 0.3666660618337925,
+      "learning_rate": 2.771262248976272e-05,
+      "loss": 1.1006,
+      "step": 408
+    },
+    {
+      "epoch": 0.798828125,
+      "grad_norm": 0.4084835818544231,
+      "learning_rate": 2.7653668647301797e-05,
+      "loss": 1.1573,
+      "step": 409
+    },
+    {
+      "epoch": 0.80078125,
+      "grad_norm": 0.42026908788757056,
+      "learning_rate": 2.7594636789710992e-05,
+      "loss": 1.1005,
+      "step": 410
+    },
+    {
+      "epoch": 0.802734375,
+      "grad_norm": 0.4260753401631911,
+      "learning_rate": 2.753552751871195e-05,
+      "loss": 1.0693,
+      "step": 411
+    },
+    {
+      "epoch": 0.8046875,
+      "grad_norm": 0.3638242310551269,
+      "learning_rate": 2.7476341436815377e-05,
+      "loss": 1.0464,
+      "step": 412
+    },
+    {
+      "epoch": 0.806640625,
+      "grad_norm": 0.3709057452758752,
+      "learning_rate": 2.7417079147314965e-05,
+      "loss": 1.0302,
+      "step": 413
+    },
+    {
+      "epoch": 0.80859375,
+      "grad_norm": 0.3881489168967299,
+      "learning_rate": 2.735774125428117e-05,
+      "loss": 1.0273,
+      "step": 414
+    },
+    {
+      "epoch": 0.810546875,
+      "grad_norm": 0.3540248781421392,
+      "learning_rate": 2.729832836255511e-05,
+      "loss": 1.0526,
+      "step": 415
+    },
+    {
+      "epoch": 0.8125,
+      "grad_norm": 0.4031356501380205,
+      "learning_rate": 2.723884107774236e-05,
+      "loss": 1.0392,
+      "step": 416
+    },
+    {
+      "epoch": 0.814453125,
+      "grad_norm": 0.4213724427608797,
+      "learning_rate": 2.717928000620681e-05,
+      "loss": 1.1335,
+      "step": 417
+    },
+    {
+      "epoch": 0.81640625,
+      "grad_norm": 0.38457290513987724,
+      "learning_rate": 2.7119645755064468e-05,
+      "loss": 1.1109,
+      "step": 418
+    },
+    {
+      "epoch": 0.818359375,
+      "grad_norm": 0.3970191569510665,
+      "learning_rate": 2.7059938932177264e-05,
+      "loss": 1.1087,
+      "step": 419
+    },
+    {
+      "epoch": 0.8203125,
+      "grad_norm": 0.42376486272155184,
+      "learning_rate": 2.700016014614687e-05,
+      "loss": 1.108,
+      "step": 420
+    },
+    {
+      "epoch": 0.822265625,
+      "grad_norm": 0.4648805287473145,
+      "learning_rate": 2.6940310006308502e-05,
+      "loss": 1.1895,
+      "step": 421
+    },
+    {
+      "epoch": 0.82421875,
+      "grad_norm": 0.4219670118710678,
+      "learning_rate": 2.688038912272468e-05,
+      "loss": 1.1492,
+      "step": 422
+    },
+    {
+      "epoch": 0.826171875,
+      "grad_norm": 0.41710413834658855,
+      "learning_rate": 2.682039810617903e-05,
+      "loss": 1.1072,
+      "step": 423
+    },
+    {
+      "epoch": 0.828125,
+      "grad_norm": 0.41979400770447894,
+      "learning_rate": 2.6760337568170056e-05,
+      "loss": 1.0904,
+      "step": 424
+    },
+    {
+      "epoch": 0.830078125,
+      "grad_norm": 0.6395242461570778,
+      "learning_rate": 2.6700208120904925e-05,
+      "loss": 0.9924,
+      "step": 425
+    },
+    {
+      "epoch": 0.83203125,
+      "grad_norm": 0.3633335504856954,
+      "learning_rate": 2.6640010377293174e-05,
+      "loss": 1.014,
+      "step": 426
+    },
+    {
+      "epoch": 0.833984375,
+      "grad_norm": 0.4464511956431912,
+      "learning_rate": 2.6579744950940514e-05,
+      "loss": 1.0734,
+      "step": 427
+    },
+    {
+      "epoch": 0.8359375,
+      "grad_norm": 0.4687781979743879,
+      "learning_rate": 2.6519412456142572e-05,
+      "loss": 1.0249,
+      "step": 428
+    },
+    {
+      "epoch": 0.837890625,
+      "grad_norm": 0.49738564921372447,
+      "learning_rate": 2.6459013507878588e-05,
+      "loss": 1.0612,
+      "step": 429
+    },
+    {
+      "epoch": 0.83984375,
+      "grad_norm": 0.4494079640359484,
+      "learning_rate": 2.639854872180518e-05,
+      "loss": 1.026,
+      "step": 430
+    },
+    {
+      "epoch": 0.841796875,
+      "grad_norm": 0.39318026641514375,
+      "learning_rate": 2.6338018714250084e-05,
+      "loss": 0.9957,
+      "step": 431
+    },
+    {
+      "epoch": 0.84375,
+      "grad_norm": 0.4142115852538159,
+      "learning_rate": 2.6277424102205817e-05,
+      "loss": 1.0505,
+      "step": 432
+    },
+    {
+      "epoch": 0.845703125,
+      "grad_norm": 0.5472076626281186,
+      "learning_rate": 2.6216765503323444e-05,
+      "loss": 1.0888,
+      "step": 433
+    },
+    {
+      "epoch": 0.84765625,
+      "grad_norm": 0.45879911363611803,
+      "learning_rate": 2.615604353590625e-05,
+      "loss": 1.2271,
+      "step": 434
+    },
+    {
+      "epoch": 0.849609375,
+      "grad_norm": 0.3879148923020066,
+      "learning_rate": 2.6095258818903443e-05,
+      "loss": 1.0789,
+      "step": 435
+    },
+    {
+      "epoch": 0.8515625,
+      "grad_norm": 0.3623048445133421,
+      "learning_rate": 2.603441197190385e-05,
+      "loss": 1.1001,
+      "step": 436
+    },
+    {
+      "epoch": 0.853515625,
+      "grad_norm": 0.4034291862610704,
+      "learning_rate": 2.5973503615129607e-05,
+      "loss": 1.0657,
+      "step": 437
+    },
+    {
+      "epoch": 0.85546875,
+      "grad_norm": 0.40641069832633525,
+      "learning_rate": 2.591253436942982e-05,
+      "loss": 1.0971,
+      "step": 438
+    },
+    {
+      "epoch": 0.857421875,
+      "grad_norm": 0.4203758291885779,
+      "learning_rate": 2.5851504856274252e-05,
+      "loss": 1.0488,
+      "step": 439
+    },
+    {
+      "epoch": 0.859375,
+      "grad_norm": 0.4126884109160508,
+      "learning_rate": 2.5790415697746976e-05,
+      "loss": 1.0095,
+      "step": 440
+    },
+    {
+      "epoch": 0.861328125,
+      "grad_norm": 0.4078387530750107,
+      "learning_rate": 2.572926751654005e-05,
+      "loss": 1.0758,
+      "step": 441
+    },
+    {
+      "epoch": 0.86328125,
+      "grad_norm": 0.3817629694236213,
+      "learning_rate": 2.5668060935947144e-05,
+      "loss": 1.1348,
+      "step": 442
+    },
+    {
+      "epoch": 0.865234375,
+      "grad_norm": 0.409692718707719,
+      "learning_rate": 2.5606796579857223e-05,
+      "loss": 1.0567,
+      "step": 443
+    },
+    {
+      "epoch": 0.8671875,
+      "grad_norm": 0.4701176256570698,
+      "learning_rate": 2.554547507274816e-05,
+      "loss": 1.0535,
+      "step": 444
+    },
+    {
+      "epoch": 0.869140625,
+      "grad_norm": 0.4055365903869681,
+      "learning_rate": 2.5484097039680364e-05,
+      "loss": 1.0327,
+      "step": 445
+    },
+    {
+      "epoch": 0.87109375,
+      "grad_norm": 0.4185308510496096,
+      "learning_rate": 2.5422663106290446e-05,
+      "loss": 1.0917,
+      "step": 446
+    },
+    {
+      "epoch": 0.873046875,
+      "grad_norm": 0.35436315376257477,
+      "learning_rate": 2.5361173898784793e-05,
+      "loss": 0.9629,
+      "step": 447
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.40368860473897683,
+      "learning_rate": 2.529963004393324e-05,
+      "loss": 1.1186,
+      "step": 448
+    },
+    {
+      "epoch": 0.876953125,
+      "grad_norm": 0.41933105267599274,
+      "learning_rate": 2.5238032169062615e-05,
+      "loss": 1.0612,
+      "step": 449
+    },
+    {
+      "epoch": 0.87890625,
+      "grad_norm": 0.3920136702588332,
+      "learning_rate": 2.5176380902050418e-05,
+      "loss": 1.0218,
+      "step": 450
+    },
+    {
+      "epoch": 0.880859375,
+      "grad_norm": 0.3924826056587098,
+      "learning_rate": 2.511467687131836e-05,
+      "loss": 1.0235,
+      "step": 451
+    },
+    {
+      "epoch": 0.8828125,
+      "grad_norm": 0.3713296557429479,
+      "learning_rate": 2.505292070582599e-05,
+      "loss": 1.031,
+      "step": 452
+    },
+    {
+      "epoch": 0.884765625,
+      "grad_norm": 0.4144024885541483,
+      "learning_rate": 2.4991113035064275e-05,
+      "loss": 1.1098,
+      "step": 453
+    },
+    {
+      "epoch": 0.88671875,
+      "grad_norm": 0.3953030954711052,
+      "learning_rate": 2.492925448904919e-05,
+      "loss": 1.0298,
+      "step": 454
+    },
+    {
+      "epoch": 0.888671875,
+      "grad_norm": 0.40979901345360326,
+      "learning_rate": 2.4867345698315264e-05,
+      "loss": 1.087,
+      "step": 455
+    },
+    {
+      "epoch": 0.890625,
+      "grad_norm": 0.42099406843050524,
+      "learning_rate": 2.4805387293909214e-05,
+      "loss": 1.0307,
+      "step": 456
+    },
+    {
+      "epoch": 0.892578125,
+      "grad_norm": 0.4824392395386347,
+      "learning_rate": 2.4743379907383466e-05,
+      "loss": 1.0751,
+      "step": 457
+    },
+    {
+      "epoch": 0.89453125,
+      "grad_norm": 0.43303194714488125,
+      "learning_rate": 2.46813241707897e-05,
+      "loss": 1.0852,
+      "step": 458
+    },
+    {
+      "epoch": 0.896484375,
+      "grad_norm": 0.42139104734956734,
+      "learning_rate": 2.4619220716672487e-05,
+      "loss": 1.0121,
+      "step": 459
+    },
+    {
+      "epoch": 0.8984375,
+      "grad_norm": 0.4037004594251964,
+      "learning_rate": 2.4557070178062755e-05,
+      "loss": 1.1123,
+      "step": 460
+    },
+    {
+      "epoch": 0.900390625,
+      "grad_norm": 0.43814766094211854,
+      "learning_rate": 2.4494873188471378e-05,
+      "loss": 1.0854,
+      "step": 461
+    },
+    {
+      "epoch": 0.90234375,
+      "grad_norm": 0.37549428576364635,
+      "learning_rate": 2.443263038188272e-05,
+      "loss": 1.021,
+      "step": 462
+    },
+    {
+      "epoch": 0.904296875,
+      "grad_norm": 0.4601484439948765,
+      "learning_rate": 2.437034239274816e-05,
+      "loss": 1.0255,
+      "step": 463
+    },
+    {
+      "epoch": 0.90625,
+      "grad_norm": 0.408442323524795,
+      "learning_rate": 2.430800985597963e-05,
+      "loss": 1.1535,
+      "step": 464
+    },
+    {
+      "epoch": 0.908203125,
+      "grad_norm": 0.3770639784598037,
+      "learning_rate": 2.4245633406943146e-05,
+      "loss": 1.0092,
+      "step": 465
+    },
+    {
+      "epoch": 0.91015625,
+      "grad_norm": 0.39632696571553727,
+      "learning_rate": 2.418321368145234e-05,
+      "loss": 1.0392,
+      "step": 466
+    },
+    {
+      "epoch": 0.912109375,
+      "grad_norm": 0.3900617301120619,
+      "learning_rate": 2.412075131576194e-05,
+      "loss": 0.9926,
+      "step": 467
+    },
+    {
+      "epoch": 0.9140625,
+      "grad_norm": 0.3942202959616746,
+      "learning_rate": 2.4058246946561337e-05,
+      "loss": 0.9972,
+      "step": 468
+    },
+    {
+      "epoch": 0.916015625,
+      "grad_norm": 0.3509404351888746,
+      "learning_rate": 2.3995701210968068e-05,
+      "loss": 0.988,
+      "step": 469
+    },
+    {
+      "epoch": 0.91796875,
+      "grad_norm": 0.4168690258420827,
+      "learning_rate": 2.393311474652131e-05,
+      "loss": 1.1025,
+      "step": 470
+    },
+    {
+      "epoch": 0.919921875,
+      "grad_norm": 0.46200933426792423,
+      "learning_rate": 2.3870488191175413e-05,
+      "loss": 1.0633,
+      "step": 471
+    },
+    {
+      "epoch": 0.921875,
+      "grad_norm": 0.35711987014827834,
+      "learning_rate": 2.380782218329337e-05,
+      "loss": 1.0525,
+      "step": 472
+    },
+    {
+      "epoch": 0.923828125,
+      "grad_norm": 0.4031204434850072,
+      "learning_rate": 2.3745117361640328e-05,
+      "loss": 1.1179,
+      "step": 473
+    },
+    {
+      "epoch": 0.92578125,
+      "grad_norm": 0.38258772862694423,
+      "learning_rate": 2.3682374365377055e-05,
+      "loss": 1.1029,
+      "step": 474
+    },
+    {
+      "epoch": 0.927734375,
+      "grad_norm": 0.4045956763131697,
+      "learning_rate": 2.361959383405346e-05,
+      "loss": 1.1135,
+      "step": 475
+    },
+    {
+      "epoch": 0.9296875,
+      "grad_norm": 0.39473113885867483,
+      "learning_rate": 2.3556776407602038e-05,
+      "loss": 0.9916,
+      "step": 476
+    },
+    {
+      "epoch": 0.931640625,
+      "grad_norm": 0.38643556532939677,
+      "learning_rate": 2.349392272633136e-05,
+      "loss": 1.0741,
+      "step": 477
+    },
+    {
+      "epoch": 0.93359375,
+      "grad_norm": 0.42567439419557046,
+      "learning_rate": 2.343103343091957e-05,
+      "loss": 0.9976,
+      "step": 478
+    },
+    {
+      "epoch": 0.935546875,
+      "grad_norm": 0.3885877057479704,
+      "learning_rate": 2.3368109162407802e-05,
+      "loss": 1.0954,
+      "step": 479
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.3684575524697125,
+      "learning_rate": 2.33051505621937e-05,
+      "loss": 1.1091,
+      "step": 480
+    },
+    {
+      "epoch": 0.939453125,
+      "grad_norm": 0.4053221637918515,
+      "learning_rate": 2.3242158272024852e-05,
+      "loss": 1.0335,
+      "step": 481
+    },
+    {
+      "epoch": 0.94140625,
+      "grad_norm": 0.3769352607947545,
+      "learning_rate": 2.3179132933992247e-05,
+      "loss": 1.0159,
+      "step": 482
+    },
+    {
+      "epoch": 0.943359375,
+      "grad_norm": 0.3985369025141676,
+      "learning_rate": 2.3116075190523736e-05,
+      "loss": 1.09,
+      "step": 483
+    },
+    {
+      "epoch": 0.9453125,
+      "grad_norm": 0.3935123859622257,
+      "learning_rate": 2.305298568437749e-05,
+      "loss": 0.9963,
+      "step": 484
+    },
+    {
+      "epoch": 0.947265625,
+      "grad_norm": 0.4196014578008531,
+      "learning_rate": 2.2989865058635452e-05,
+      "loss": 1.0499,
+      "step": 485
+    },
+    {
+      "epoch": 0.94921875,
+      "grad_norm": 0.419476500729373,
+      "learning_rate": 2.2926713956696745e-05,
+      "loss": 1.0371,
+      "step": 486
+    },
+    {
+      "epoch": 0.951171875,
+      "grad_norm": 0.3808077428531366,
+      "learning_rate": 2.2863533022271162e-05,
+      "loss": 1.1248,
+      "step": 487
+    },
+    {
+      "epoch": 0.953125,
+      "grad_norm": 0.3999093853366225,
+      "learning_rate": 2.2800322899372586e-05,
+      "loss": 1.064,
+      "step": 488
+    },
+    {
+      "epoch": 0.955078125,
+      "grad_norm": 0.40587143499383244,
+      "learning_rate": 2.2737084232312405e-05,
+      "loss": 1.0637,
+      "step": 489
+    },
+    {
+      "epoch": 0.95703125,
+      "grad_norm": 0.3789458557177568,
+      "learning_rate": 2.267381766569297e-05,
+      "loss": 0.9901,
+      "step": 490
+    },
+    {
+      "epoch": 0.958984375,
+      "grad_norm": 0.3888268213746482,
+      "learning_rate": 2.261052384440104e-05,
+      "loss": 1.1481,
+      "step": 491
+    },
+    {
+      "epoch": 0.9609375,
+      "grad_norm": 0.3560941746806575,
+      "learning_rate": 2.254720341360114e-05,
+      "loss": 1.0011,
+      "step": 492
+    },
+    {
+      "epoch": 0.962890625,
+      "grad_norm": 0.4117369944130386,
+      "learning_rate": 2.2483857018729066e-05,
+      "loss": 1.0988,
+      "step": 493
+    },
+    {
+      "epoch": 0.96484375,
+      "grad_norm": 0.3603669115916744,
+      "learning_rate": 2.2420485305485264e-05,
+      "loss": 1.0564,
+      "step": 494
+    },
+    {
+      "epoch": 0.966796875,
+      "grad_norm": 0.45357516371473544,
+      "learning_rate": 2.2357088919828243e-05,
+      "loss": 1.1119,
+      "step": 495
+    },
+    {
+      "epoch": 0.96875,
+      "grad_norm": 0.37884120057564985,
+      "learning_rate": 2.2293668507968015e-05,
+      "loss": 1.0883,
+      "step": 496
+    },
+    {
+      "epoch": 0.970703125,
+      "grad_norm": 0.8383895359995993,
+      "learning_rate": 2.2230224716359482e-05,
+      "loss": 1.0815,
+      "step": 497
+    },
+    {
+      "epoch": 0.97265625,
+      "grad_norm": 0.38866465119590105,
+      "learning_rate": 2.2166758191695866e-05,
+      "loss": 1.0174,
+      "step": 498
+    },
+    {
+      "epoch": 0.974609375,
+      "grad_norm": 0.5709670798963341,
+      "learning_rate": 2.210326958090212e-05,
+      "loss": 1.0009,
+      "step": 499
+    },
+    {
+      "epoch": 0.9765625,
+      "grad_norm": 0.3660396139993819,
+      "learning_rate": 2.203975953112831e-05,
+      "loss": 1.095,
+      "step": 500
+    },
+    {
+      "epoch": 0.978515625,
+      "grad_norm": 0.3674603706471189,
+      "learning_rate": 2.1976228689743044e-05,
+      "loss": 0.9867,
+      "step": 501
+    },
+    {
+      "epoch": 0.98046875,
+      "grad_norm": 0.9419848479362365,
+      "learning_rate": 2.1912677704326847e-05,
+      "loss": 1.2754,
+      "step": 502
+    },
+    {
+      "epoch": 0.982421875,
+      "grad_norm": 0.3969899221243403,
+      "learning_rate": 2.18491072226656e-05,
+      "loss": 1.0077,
+      "step": 503
+    },
+    {
+      "epoch": 0.984375,
+      "grad_norm": 0.4124566542707438,
+      "learning_rate": 2.1785517892743887e-05,
+      "loss": 1.0525,
+      "step": 504
+    },
+    {
+      "epoch": 0.986328125,
+      "grad_norm": 0.41362237633561144,
+      "learning_rate": 2.1721910362738438e-05,
+      "loss": 1.0197,
+      "step": 505
+    },
+    {
+      "epoch": 0.98828125,
+      "grad_norm": 0.4476968790164685,
+      "learning_rate": 2.165828528101148e-05,
+      "loss": 0.9919,
+      "step": 506
+    },
+    {
+      "epoch": 0.990234375,
+      "grad_norm": 0.6290964144760007,
+      "learning_rate": 2.1594643296104157e-05,
+      "loss": 1.0917,
+      "step": 507
+    },
+    {
+      "epoch": 0.9921875,
+      "grad_norm": 0.3973126449794871,
+      "learning_rate": 2.153098505672992e-05,
+      "loss": 1.1005,
+      "step": 508
+    },
+    {
+      "epoch": 0.994140625,
+      "grad_norm": 0.4323540168560289,
+      "learning_rate": 2.1467311211767873e-05,
+      "loss": 1.0063,
+      "step": 509
+    },
+    {
+      "epoch": 0.99609375,
+      "grad_norm": 0.5809974059109054,
+      "learning_rate": 2.140362241025623e-05,
+      "loss": 1.145,
+      "step": 510
+    },
+    {
+      "epoch": 0.998046875,
+      "grad_norm": 0.38472241580582794,
+      "learning_rate": 2.1339919301385636e-05,
+      "loss": 0.9965,
+      "step": 511
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4053721417966819,
+      "learning_rate": 2.1276202534492566e-05,
+      "loss": 1.0342,
+      "step": 512
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1024,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 256,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1062128232431616.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-512/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcbfa469b9202a5ee04539c5e32b6e52ff3ea81414f858ea729dd1dfc1c96091
+size 8248

checkpoint-512/zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/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 . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import json
+from tqdm import tqdm
+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 tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
+        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_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               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_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``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
+    """
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        state_dict_split = split_torch_state_dict_into_shards(state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+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_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    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_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)