Training in progress, step 516, checkpoint

checkpoint-516/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-516/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": [
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

checkpoint-516/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:242cd7d4ecbb1bdf47f4883623ee96dd647fecb44b993c9912561247bfe83df7
+size 7516349296

checkpoint-516/global_step516/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7e345d2c5d974d34fa98615d6e85b019b9b6e5858d09167236883e5c0f58c0
+size 3312262110

checkpoint-516/global_step516/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:174a2e3f72f6c156a039b712bdb6493a697d61372144c06a2de4aa60043a153b
+size 3312262110

checkpoint-516/global_step516/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:001cbeaf906f90fad3d504aeb4edb20e5bf31ec4aed3e1ec72c6aae4d36864cb
+size 3312262110

checkpoint-516/global_step516/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:a4dcdff49b64ffece6d8b620f3a96cfb37f01b7098e1361a6c04abc911991f5c
+size 3312262110

checkpoint-516/global_step516/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6181bd19519ca7652b80e7e08d78ae0d201864d37f5c3e80345aeaa2d21fa573
+size 3312262110

checkpoint-516/global_step516/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05539eea400c37e97898f774d17153b399562be4eda6daf0d48ca7fe81ffc4ff
+size 3312262110

checkpoint-516/global_step516/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:e0da2bbf01d8f7765f74af616053e50a961c6cb10780b8c77d212ebaa65ca93d
+size 3312262110

checkpoint-516/global_step516/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12615af29f415406e7fe7730d42a2300f0e730efb03a9a6705589a87c3891aa9
+size 3312262110

checkpoint-516/global_step516/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61cac308b3ac84fdd0f9677d191c4bb83da257b4e34f76398333a3961676ba62
+size 1114818

checkpoint-516/global_step516/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b9702d54d9f0206de57882a49c7556ecd306edf81bb55fa21fc1af83f3eb68
+size 1114818

checkpoint-516/global_step516/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:463cb4609cf54af210380856f54d92744a8b1389ff1feaeb6a692221f1c86842
+size 1114818

checkpoint-516/global_step516/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edfaa630f9ed60a7d763c64cda07d8217aeb886594d71748a3126d98fc66d33f
+size 1114818

checkpoint-516/global_step516/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859b4695084e83eb7f73b40e63a58b9666345f3b4359bfbf6531bb254e9a3ec3
+size 1114818

checkpoint-516/global_step516/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:199ff51791a7a598600f7c4dd8b11dac2a0eeb43738d69da8b181b7c578906e8
+size 1114818

checkpoint-516/global_step516/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:357b1c03d8a2ddc1f7976dcba6489365a1fe5b2fe3859e833daa9dcdea21f92e
+size 1114818

checkpoint-516/global_step516/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ae3e1490c8fc95c85d9ea3a97f7ea5ec36712ffe11269f8a97dcacdd61e16d
+size 1114818

checkpoint-516/latest

@@ -0,0 +1 @@
+global_step516

checkpoint-516/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d65b2c2934bb52b1a2a49ea479e75cfb9b6545c1f0b41a7e5116b990b63a70fe
+size 15984

checkpoint-516/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf760ad8ce6d15e3af64673d4a3ffb59bea46954038c09e8a90ceabce576628
+size 15984

checkpoint-516/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f8e69fff5ac28d75458e952d8e0816f50af25450d386c2a6da20a2c77210b5a
+size 15984

checkpoint-516/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52f18a6db12dc7dea8fb9589b36e983b3de8e4035dfc1acf8feeea42c8a271d3
+size 15984

checkpoint-516/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:829ef4cb7e6448cd09f973be9793de131d0412b20a902e94d88f5e95c3b6c509
+size 15984

checkpoint-516/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e326cf3544ced1ef4148a25ece770da7954d9b6b02d55f41d333ebef078540d8
+size 15984

checkpoint-516/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3d90f1457b3f2846e2835c82ccf2dc5be075e75d160ebe8ebf24b5f871c4736
+size 15984

checkpoint-516/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d741e2c9e7feddbf494acf5c78efc1ebc1848c8d3180bf194df7b150a6909e
+size 15984

checkpoint-516/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e2300a62ff8e16784d2b9e1a986b525f017b1fb7b4276207ba741dae02170d
+size 1064

checkpoint-516/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-516/tokenizer.json

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

checkpoint-516/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-516/trainer_state.json

@@ -0,0 +1,3645 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5043731778425657,
+  "eval_steps": 500,
+  "global_step": 516,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0029154518950437317,
+      "grad_norm": 1.96997298809509,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.4888,
+      "step": 1
+    },
+    {
+      "epoch": 0.0058309037900874635,
+      "grad_norm": 2.0593671952568466,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.5633,
+      "step": 2
+    },
+    {
+      "epoch": 0.008746355685131196,
+      "grad_norm": 2.0558980680243,
+      "learning_rate": 3e-06,
+      "loss": 1.4922,
+      "step": 3
+    },
+    {
+      "epoch": 0.011661807580174927,
+      "grad_norm": 2.0407653033784907,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.5552,
+      "step": 4
+    },
+    {
+      "epoch": 0.014577259475218658,
+      "grad_norm": 2.049565870762043,
+      "learning_rate": 5e-06,
+      "loss": 1.4963,
+      "step": 5
+    },
+    {
+      "epoch": 0.01749271137026239,
+      "grad_norm": 1.8921551243504868,
+      "learning_rate": 6e-06,
+      "loss": 1.4756,
+      "step": 6
+    },
+    {
+      "epoch": 0.02040816326530612,
+      "grad_norm": 1.9932142025756485,
+      "learning_rate": 7e-06,
+      "loss": 1.4733,
+      "step": 7
+    },
+    {
+      "epoch": 0.023323615160349854,
+      "grad_norm": 1.8344452830038493,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.4998,
+      "step": 8
+    },
+    {
+      "epoch": 0.026239067055393587,
+      "grad_norm": 3.1185523094664664,
+      "learning_rate": 9e-06,
+      "loss": 1.4562,
+      "step": 9
+    },
+    {
+      "epoch": 0.029154518950437316,
+      "grad_norm": 1.3193772173204783,
+      "learning_rate": 1e-05,
+      "loss": 1.4078,
+      "step": 10
+    },
+    {
+      "epoch": 0.03206997084548105,
+      "grad_norm": 1.4291215496905525,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 1.3631,
+      "step": 11
+    },
+    {
+      "epoch": 0.03498542274052478,
+      "grad_norm": 1.0345538651419202,
+      "learning_rate": 1.2e-05,
+      "loss": 1.2687,
+      "step": 12
+    },
+    {
+      "epoch": 0.037900874635568516,
+      "grad_norm": 0.8509765803387165,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 1.2788,
+      "step": 13
+    },
+    {
+      "epoch": 0.04081632653061224,
+      "grad_norm": 0.7122306203690422,
+      "learning_rate": 1.4e-05,
+      "loss": 1.2479,
+      "step": 14
+    },
+    {
+      "epoch": 0.043731778425655975,
+      "grad_norm": 0.6858784204503546,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.312,
+      "step": 15
+    },
+    {
+      "epoch": 0.04664723032069971,
+      "grad_norm": 0.8402421437953252,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.2104,
+      "step": 16
+    },
+    {
+      "epoch": 0.04956268221574344,
+      "grad_norm": 0.9216616450448899,
+      "learning_rate": 1.7e-05,
+      "loss": 1.2521,
+      "step": 17
+    },
+    {
+      "epoch": 0.052478134110787174,
+      "grad_norm": 0.9921691551642605,
+      "learning_rate": 1.8e-05,
+      "loss": 1.2179,
+      "step": 18
+    },
+    {
+      "epoch": 0.05539358600583091,
+      "grad_norm": 1.022423689479842,
+      "learning_rate": 1.9e-05,
+      "loss": 1.1792,
+      "step": 19
+    },
+    {
+      "epoch": 0.05830903790087463,
+      "grad_norm": 1.0879189463724102,
+      "learning_rate": 2e-05,
+      "loss": 1.1985,
+      "step": 20
+    },
+    {
+      "epoch": 0.061224489795918366,
+      "grad_norm": 1.0207736739226028,
+      "learning_rate": 2.1000000000000002e-05,
+      "loss": 1.2144,
+      "step": 21
+    },
+    {
+      "epoch": 0.0641399416909621,
+      "grad_norm": 0.977515728831309,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 1.2368,
+      "step": 22
+    },
+    {
+      "epoch": 0.06705539358600583,
+      "grad_norm": 0.8388691896742322,
+      "learning_rate": 2.3e-05,
+      "loss": 1.1545,
+      "step": 23
+    },
+    {
+      "epoch": 0.06997084548104957,
+      "grad_norm": 0.7188235107709924,
+      "learning_rate": 2.4e-05,
+      "loss": 1.2304,
+      "step": 24
+    },
+    {
+      "epoch": 0.0728862973760933,
+      "grad_norm": 0.6257931373002115,
+      "learning_rate": 2.5e-05,
+      "loss": 1.1733,
+      "step": 25
+    },
+    {
+      "epoch": 0.07580174927113703,
+      "grad_norm": 0.5237685387486158,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 1.1693,
+      "step": 26
+    },
+    {
+      "epoch": 0.07871720116618076,
+      "grad_norm": 0.5989713165204653,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 1.2331,
+      "step": 27
+    },
+    {
+      "epoch": 0.08163265306122448,
+      "grad_norm": 0.5869524805948223,
+      "learning_rate": 2.8e-05,
+      "loss": 1.2142,
+      "step": 28
+    },
+    {
+      "epoch": 0.08454810495626822,
+      "grad_norm": 0.6720149885989607,
+      "learning_rate": 2.9e-05,
+      "loss": 1.1472,
+      "step": 29
+    },
+    {
+      "epoch": 0.08746355685131195,
+      "grad_norm": 0.73864045163312,
+      "learning_rate": 3.0000000000000004e-05,
+      "loss": 1.1908,
+      "step": 30
+    },
+    {
+      "epoch": 0.09037900874635568,
+      "grad_norm": 0.6759314678600088,
+      "learning_rate": 3.1e-05,
+      "loss": 1.1971,
+      "step": 31
+    },
+    {
+      "epoch": 0.09329446064139942,
+      "grad_norm": 0.7251126641398837,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 1.1809,
+      "step": 32
+    },
+    {
+      "epoch": 0.09620991253644315,
+      "grad_norm": 0.6691450174305634,
+      "learning_rate": 3.3e-05,
+      "loss": 1.1753,
+      "step": 33
+    },
+    {
+      "epoch": 0.09912536443148688,
+      "grad_norm": 0.5339684032344343,
+      "learning_rate": 3.4e-05,
+      "loss": 1.1597,
+      "step": 34
+    },
+    {
+      "epoch": 0.10204081632653061,
+      "grad_norm": 0.4919690310909855,
+      "learning_rate": 3.5000000000000004e-05,
+      "loss": 1.1721,
+      "step": 35
+    },
+    {
+      "epoch": 0.10495626822157435,
+      "grad_norm": 0.42018891979017214,
+      "learning_rate": 3.6e-05,
+      "loss": 1.1644,
+      "step": 36
+    },
+    {
+      "epoch": 0.10787172011661808,
+      "grad_norm": 0.5490256316108622,
+      "learning_rate": 3.7000000000000005e-05,
+      "loss": 1.2463,
+      "step": 37
+    },
+    {
+      "epoch": 0.11078717201166181,
+      "grad_norm": 0.5427250875445369,
+      "learning_rate": 3.8e-05,
+      "loss": 1.1137,
+      "step": 38
+    },
+    {
+      "epoch": 0.11370262390670553,
+      "grad_norm": 0.5778225846177277,
+      "learning_rate": 3.9e-05,
+      "loss": 1.2072,
+      "step": 39
+    },
+    {
+      "epoch": 0.11661807580174927,
+      "grad_norm": 0.693680585719681,
+      "learning_rate": 4e-05,
+      "loss": 1.1519,
+      "step": 40
+    },
+    {
+      "epoch": 0.119533527696793,
+      "grad_norm": 0.6127902830311082,
+      "learning_rate": 3.999976349852511e-05,
+      "loss": 1.1104,
+      "step": 41
+    },
+    {
+      "epoch": 0.12244897959183673,
+      "grad_norm": 0.6799487970334515,
+      "learning_rate": 3.999905399969373e-05,
+      "loss": 1.1175,
+      "step": 42
+    },
+    {
+      "epoch": 0.12536443148688048,
+      "grad_norm": 0.5367363097182918,
+      "learning_rate": 3.999787152028561e-05,
+      "loss": 1.1483,
+      "step": 43
+    },
+    {
+      "epoch": 0.1282798833819242,
+      "grad_norm": 0.4524657560624909,
+      "learning_rate": 3.999621608826657e-05,
+      "loss": 1.138,
+      "step": 44
+    },
+    {
+      "epoch": 0.13119533527696792,
+      "grad_norm": 0.41206360481350807,
+      "learning_rate": 3.999408774278781e-05,
+      "loss": 1.1245,
+      "step": 45
+    },
+    {
+      "epoch": 0.13411078717201166,
+      "grad_norm": 0.47061852405012233,
+      "learning_rate": 3.999148653418503e-05,
+      "loss": 1.1603,
+      "step": 46
+    },
+    {
+      "epoch": 0.13702623906705538,
+      "grad_norm": 0.5047699458420934,
+      "learning_rate": 3.998841252397718e-05,
+      "loss": 1.087,
+      "step": 47
+    },
+    {
+      "epoch": 0.13994169096209913,
+      "grad_norm": 0.45543822046591975,
+      "learning_rate": 3.998486578486507e-05,
+      "loss": 1.1162,
+      "step": 48
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.5145420477808398,
+      "learning_rate": 3.998084640072959e-05,
+      "loss": 1.1669,
+      "step": 49
+    },
+    {
+      "epoch": 0.1457725947521866,
+      "grad_norm": 0.44889190383338007,
+      "learning_rate": 3.997635446662978e-05,
+      "loss": 1.0908,
+      "step": 50
+    },
+    {
+      "epoch": 0.14868804664723032,
+      "grad_norm": 0.448875120724629,
+      "learning_rate": 3.997139008880053e-05,
+      "loss": 1.1508,
+      "step": 51
+    },
+    {
+      "epoch": 0.15160349854227406,
+      "grad_norm": 0.4559094928660873,
+      "learning_rate": 3.996595338465012e-05,
+      "loss": 1.0421,
+      "step": 52
+    },
+    {
+      "epoch": 0.15451895043731778,
+      "grad_norm": 0.41039500403883783,
+      "learning_rate": 3.9960044482757406e-05,
+      "loss": 1.0969,
+      "step": 53
+    },
+    {
+      "epoch": 0.15743440233236153,
+      "grad_norm": 2.195181984076079,
+      "learning_rate": 3.995366352286878e-05,
+      "loss": 1.1174,
+      "step": 54
+    },
+    {
+      "epoch": 0.16034985422740525,
+      "grad_norm": 0.45015457594488156,
+      "learning_rate": 3.994681065589489e-05,
+      "loss": 1.1393,
+      "step": 55
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 0.41283257576743904,
+      "learning_rate": 3.993948604390704e-05,
+      "loss": 1.1162,
+      "step": 56
+    },
+    {
+      "epoch": 0.1661807580174927,
+      "grad_norm": 0.469276947594031,
+      "learning_rate": 3.99316898601334e-05,
+      "loss": 1.1258,
+      "step": 57
+    },
+    {
+      "epoch": 0.16909620991253643,
+      "grad_norm": 0.8079999817536038,
+      "learning_rate": 3.992342228895486e-05,
+      "loss": 1.127,
+      "step": 58
+    },
+    {
+      "epoch": 0.17201166180758018,
+      "grad_norm": 0.4553362658754828,
+      "learning_rate": 3.991468352590069e-05,
+      "loss": 1.0919,
+      "step": 59
+    },
+    {
+      "epoch": 0.1749271137026239,
+      "grad_norm": 0.4361094059704535,
+      "learning_rate": 3.990547377764394e-05,
+      "loss": 1.1087,
+      "step": 60
+    },
+    {
+      "epoch": 0.17784256559766765,
+      "grad_norm": 0.41551312925162287,
+      "learning_rate": 3.9895793261996506e-05,
+      "loss": 1.101,
+      "step": 61
+    },
+    {
+      "epoch": 0.18075801749271136,
+      "grad_norm": 0.3955618751805837,
+      "learning_rate": 3.9885642207904004e-05,
+      "loss": 1.0936,
+      "step": 62
+    },
+    {
+      "epoch": 0.1836734693877551,
+      "grad_norm": 0.43720530414654624,
+      "learning_rate": 3.9875020855440374e-05,
+      "loss": 1.133,
+      "step": 63
+    },
+    {
+      "epoch": 0.18658892128279883,
+      "grad_norm": 0.4347111246810371,
+      "learning_rate": 3.986392945580216e-05,
+      "loss": 1.1389,
+      "step": 64
+    },
+    {
+      "epoch": 0.18950437317784258,
+      "grad_norm": 0.44850787138923726,
+      "learning_rate": 3.9852368271302604e-05,
+      "loss": 1.1137,
+      "step": 65
+    },
+    {
+      "epoch": 0.1924198250728863,
+      "grad_norm": 0.38905578160555143,
+      "learning_rate": 3.984033757536542e-05,
+      "loss": 1.1007,
+      "step": 66
+    },
+    {
+      "epoch": 0.19533527696793002,
+      "grad_norm": 0.4073765119693394,
+      "learning_rate": 3.982783765251834e-05,
+      "loss": 1.0624,
+      "step": 67
+    },
+    {
+      "epoch": 0.19825072886297376,
+      "grad_norm": 0.4520768326268948,
+      "learning_rate": 3.981486879838639e-05,
+      "loss": 1.1307,
+      "step": 68
+    },
+    {
+      "epoch": 0.20116618075801748,
+      "grad_norm": 0.4766094918337742,
+      "learning_rate": 3.980143131968488e-05,
+      "loss": 1.1057,
+      "step": 69
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 0.3857556379543063,
+      "learning_rate": 3.978752553421216e-05,
+      "loss": 1.0811,
+      "step": 70
+    },
+    {
+      "epoch": 0.20699708454810495,
+      "grad_norm": 0.4117513969256482,
+      "learning_rate": 3.977315177084211e-05,
+      "loss": 1.1368,
+      "step": 71
+    },
+    {
+      "epoch": 0.2099125364431487,
+      "grad_norm": 0.4331294683046506,
+      "learning_rate": 3.975831036951635e-05,
+      "loss": 1.1067,
+      "step": 72
+    },
+    {
+      "epoch": 0.21282798833819241,
+      "grad_norm": 0.4181099883703104,
+      "learning_rate": 3.974300168123622e-05,
+      "loss": 1.1078,
+      "step": 73
+    },
+    {
+      "epoch": 0.21574344023323616,
+      "grad_norm": 0.5193623846316575,
+      "learning_rate": 3.972722606805445e-05,
+      "loss": 1.0217,
+      "step": 74
+    },
+    {
+      "epoch": 0.21865889212827988,
+      "grad_norm": 0.42748682578145775,
+      "learning_rate": 3.9710983903066616e-05,
+      "loss": 1.1183,
+      "step": 75
+    },
+    {
+      "epoch": 0.22157434402332363,
+      "grad_norm": 0.40340255468232195,
+      "learning_rate": 3.9694275570402316e-05,
+      "loss": 1.0175,
+      "step": 76
+    },
+    {
+      "epoch": 0.22448979591836735,
+      "grad_norm": 0.6901116231810781,
+      "learning_rate": 3.9677101465216085e-05,
+      "loss": 1.1436,
+      "step": 77
+    },
+    {
+      "epoch": 0.22740524781341107,
+      "grad_norm": 0.4470827057095483,
+      "learning_rate": 3.965946199367804e-05,
+      "loss": 1.1026,
+      "step": 78
+    },
+    {
+      "epoch": 0.2303206997084548,
+      "grad_norm": 1.4507030226182656,
+      "learning_rate": 3.964135757296428e-05,
+      "loss": 1.0932,
+      "step": 79
+    },
+    {
+      "epoch": 0.23323615160349853,
+      "grad_norm": 0.40183625780568555,
+      "learning_rate": 3.9622788631247045e-05,
+      "loss": 1.1108,
+      "step": 80
+    },
+    {
+      "epoch": 0.23615160349854228,
+      "grad_norm": 0.4083797606486713,
+      "learning_rate": 3.960375560768452e-05,
+      "loss": 1.1263,
+      "step": 81
+    },
+    {
+      "epoch": 0.239067055393586,
+      "grad_norm": 0.3982498098365359,
+      "learning_rate": 3.958425895241054e-05,
+      "loss": 1.1237,
+      "step": 82
+    },
+    {
+      "epoch": 0.24198250728862974,
+      "grad_norm": 0.4059963555050571,
+      "learning_rate": 3.9564299126523867e-05,
+      "loss": 1.068,
+      "step": 83
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": 0.38793892556447224,
+      "learning_rate": 3.954387660207733e-05,
+      "loss": 1.1354,
+      "step": 84
+    },
+    {
+      "epoch": 0.2478134110787172,
+      "grad_norm": 0.3941774269738573,
+      "learning_rate": 3.952299186206664e-05,
+      "loss": 1.0097,
+      "step": 85
+    },
+    {
+      "epoch": 0.25072886297376096,
+      "grad_norm": 0.43220005658120336,
+      "learning_rate": 3.950164540041898e-05,
+      "loss": 1.0977,
+      "step": 86
+    },
+    {
+      "epoch": 0.2536443148688047,
+      "grad_norm": 0.36583877050224667,
+      "learning_rate": 3.9479837721981315e-05,
+      "loss": 1.0613,
+      "step": 87
+    },
+    {
+      "epoch": 0.2565597667638484,
+      "grad_norm": 0.3968503378403748,
+      "learning_rate": 3.9457569342508474e-05,
+      "loss": 1.1081,
+      "step": 88
+    },
+    {
+      "epoch": 0.2594752186588921,
+      "grad_norm": 0.36657514937570074,
+      "learning_rate": 3.943484078865089e-05,
+      "loss": 1.0638,
+      "step": 89
+    },
+    {
+      "epoch": 0.26239067055393583,
+      "grad_norm": 0.3990173761473332,
+      "learning_rate": 3.9411652597942224e-05,
+      "loss": 1.1051,
+      "step": 90
+    },
+    {
+      "epoch": 0.2653061224489796,
+      "grad_norm": 0.41741218758949744,
+      "learning_rate": 3.938800531878661e-05,
+      "loss": 1.0402,
+      "step": 91
+    },
+    {
+      "epoch": 0.26822157434402333,
+      "grad_norm": 0.35100087055896617,
+      "learning_rate": 3.936389951044569e-05,
+      "loss": 1.036,
+      "step": 92
+    },
+    {
+      "epoch": 0.27113702623906705,
+      "grad_norm": 0.3939910877708907,
+      "learning_rate": 3.933933574302538e-05,
+      "loss": 1.0915,
+      "step": 93
+    },
+    {
+      "epoch": 0.27405247813411077,
+      "grad_norm": 0.48903634568290555,
+      "learning_rate": 3.93143145974624e-05,
+      "loss": 1.1166,
+      "step": 94
+    },
+    {
+      "epoch": 0.27696793002915454,
+      "grad_norm": 0.47943406165195734,
+      "learning_rate": 3.928883666551054e-05,
+      "loss": 1.0421,
+      "step": 95
+    },
+    {
+      "epoch": 0.27988338192419826,
+      "grad_norm": 0.4240913146011234,
+      "learning_rate": 3.926290254972665e-05,
+      "loss": 1.0877,
+      "step": 96
+    },
+    {
+      "epoch": 0.282798833819242,
+      "grad_norm": 0.417735312873443,
+      "learning_rate": 3.923651286345638e-05,
+      "loss": 1.0495,
+      "step": 97
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.4027791781208716,
+      "learning_rate": 3.920966823081972e-05,
+      "loss": 1.11,
+      "step": 98
+    },
+    {
+      "epoch": 0.2886297376093295,
+      "grad_norm": 0.4021123805362925,
+      "learning_rate": 3.9182369286696185e-05,
+      "loss": 1.0656,
+      "step": 99
+    },
+    {
+      "epoch": 0.2915451895043732,
+      "grad_norm": 0.41657372958369593,
+      "learning_rate": 3.915461667670982e-05,
+      "loss": 1.0953,
+      "step": 100
+    },
+    {
+      "epoch": 0.2944606413994169,
+      "grad_norm": 0.4549189185164727,
+      "learning_rate": 3.9126411057213954e-05,
+      "loss": 1.0427,
+      "step": 101
+    },
+    {
+      "epoch": 0.29737609329446063,
+      "grad_norm": 0.3909314378908402,
+      "learning_rate": 3.909775309527564e-05,
+      "loss": 1.0578,
+      "step": 102
+    },
+    {
+      "epoch": 0.30029154518950435,
+      "grad_norm": 0.40901980161241175,
+      "learning_rate": 3.906864346865992e-05,
+      "loss": 1.0074,
+      "step": 103
+    },
+    {
+      "epoch": 0.3032069970845481,
+      "grad_norm": 0.4009430285161083,
+      "learning_rate": 3.903908286581374e-05,
+      "loss": 1.0633,
+      "step": 104
+    },
+    {
+      "epoch": 0.30612244897959184,
+      "grad_norm": 0.4413234724998126,
+      "learning_rate": 3.900907198584974e-05,
+      "loss": 1.0645,
+      "step": 105
+    },
+    {
+      "epoch": 0.30903790087463556,
+      "grad_norm": 0.4146515624534,
+      "learning_rate": 3.8978611538529626e-05,
+      "loss": 1.0773,
+      "step": 106
+    },
+    {
+      "epoch": 0.3119533527696793,
+      "grad_norm": 0.39991789210919104,
+      "learning_rate": 3.8947702244247485e-05,
+      "loss": 1.0766,
+      "step": 107
+    },
+    {
+      "epoch": 0.31486880466472306,
+      "grad_norm": 0.4296757215583828,
+      "learning_rate": 3.8916344834012695e-05,
+      "loss": 1.0449,
+      "step": 108
+    },
+    {
+      "epoch": 0.3177842565597668,
+      "grad_norm": 0.40497448422268767,
+      "learning_rate": 3.8884540049432626e-05,
+      "loss": 1.0504,
+      "step": 109
+    },
+    {
+      "epoch": 0.3206997084548105,
+      "grad_norm": 0.42461898148240107,
+      "learning_rate": 3.885228864269511e-05,
+      "loss": 1.046,
+      "step": 110
+    },
+    {
+      "epoch": 0.3236151603498542,
+      "grad_norm": 0.388986879558302,
+      "learning_rate": 3.88195913765507e-05,
+      "loss": 1.0737,
+      "step": 111
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 0.3941352715173726,
+      "learning_rate": 3.878644902429454e-05,
+      "loss": 1.0322,
+      "step": 112
+    },
+    {
+      "epoch": 0.3294460641399417,
+      "grad_norm": 0.42215837837057424,
+      "learning_rate": 3.875286236974816e-05,
+      "loss": 1.0645,
+      "step": 113
+    },
+    {
+      "epoch": 0.3323615160349854,
+      "grad_norm": 0.4610458683962393,
+      "learning_rate": 3.871883220724089e-05,
+      "loss": 1.0884,
+      "step": 114
+    },
+    {
+      "epoch": 0.33527696793002915,
+      "grad_norm": 0.4346091661281081,
+      "learning_rate": 3.868435934159109e-05,
+      "loss": 1.1111,
+      "step": 115
+    },
+    {
+      "epoch": 0.33819241982507287,
+      "grad_norm": 0.37427705436326664,
+      "learning_rate": 3.864944458808712e-05,
+      "loss": 1.0629,
+      "step": 116
+    },
+    {
+      "epoch": 0.34110787172011664,
+      "grad_norm": 0.4316114239509569,
+      "learning_rate": 3.8614088772468055e-05,
+      "loss": 1.0964,
+      "step": 117
+    },
+    {
+      "epoch": 0.34402332361516036,
+      "grad_norm": 0.4597612055828575,
+      "learning_rate": 3.857829273090414e-05,
+      "loss": 1.0467,
+      "step": 118
+    },
+    {
+      "epoch": 0.3469387755102041,
+      "grad_norm": 0.41631549856597405,
+      "learning_rate": 3.854205730997704e-05,
+      "loss": 1.0786,
+      "step": 119
+    },
+    {
+      "epoch": 0.3498542274052478,
+      "grad_norm": 0.3829026297223422,
+      "learning_rate": 3.850538336665981e-05,
+      "loss": 1.045,
+      "step": 120
+    },
+    {
+      "epoch": 0.35276967930029157,
+      "grad_norm": 0.4046975211753129,
+      "learning_rate": 3.846827176829662e-05,
+      "loss": 1.0549,
+      "step": 121
+    },
+    {
+      "epoch": 0.3556851311953353,
+      "grad_norm": 0.406694717694253,
+      "learning_rate": 3.843072339258223e-05,
+      "loss": 1.0579,
+      "step": 122
+    },
+    {
+      "epoch": 0.358600583090379,
+      "grad_norm": 0.3868374046092744,
+      "learning_rate": 3.839273912754128e-05,
+      "loss": 1.0588,
+      "step": 123
+    },
+    {
+      "epoch": 0.36151603498542273,
+      "grad_norm": 0.399700910407372,
+      "learning_rate": 3.8354319871507224e-05,
+      "loss": 1.0572,
+      "step": 124
+    },
+    {
+      "epoch": 0.36443148688046645,
+      "grad_norm": 0.4404105487294615,
+      "learning_rate": 3.8315466533101154e-05,
+      "loss": 1.0646,
+      "step": 125
+    },
+    {
+      "epoch": 0.3673469387755102,
+      "grad_norm": 0.38113631041534785,
+      "learning_rate": 3.827618003121023e-05,
+      "loss": 1.0137,
+      "step": 126
+    },
+    {
+      "epoch": 0.37026239067055394,
+      "grad_norm": 0.4572696347195023,
+      "learning_rate": 3.823646129496604e-05,
+      "loss": 1.0825,
+      "step": 127
+    },
+    {
+      "epoch": 0.37317784256559766,
+      "grad_norm": 0.44338604907070756,
+      "learning_rate": 3.8196311263722545e-05,
+      "loss": 1.0494,
+      "step": 128
+    },
+    {
+      "epoch": 0.3760932944606414,
+      "grad_norm": 0.38848719927969894,
+      "learning_rate": 3.8155730887033895e-05,
+      "loss": 1.0524,
+      "step": 129
+    },
+    {
+      "epoch": 0.37900874635568516,
+      "grad_norm": 0.7734150201362632,
+      "learning_rate": 3.8114721124631994e-05,
+      "loss": 0.996,
+      "step": 130
+    },
+    {
+      "epoch": 0.3819241982507289,
+      "grad_norm": 0.4333233633929747,
+      "learning_rate": 3.8073282946403774e-05,
+      "loss": 1.0789,
+      "step": 131
+    },
+    {
+      "epoch": 0.3848396501457726,
+      "grad_norm": 0.392992047366071,
+      "learning_rate": 3.803141733236826e-05,
+      "loss": 1.0326,
+      "step": 132
+    },
+    {
+      "epoch": 0.3877551020408163,
+      "grad_norm": 0.48279560465143584,
+      "learning_rate": 3.798912527265339e-05,
+      "loss": 1.1128,
+      "step": 133
+    },
+    {
+      "epoch": 0.39067055393586003,
+      "grad_norm": 0.4560757196728328,
+      "learning_rate": 3.794640776747262e-05,
+      "loss": 1.0439,
+      "step": 134
+    },
+    {
+      "epoch": 0.3935860058309038,
+      "grad_norm": 0.4445942243776014,
+      "learning_rate": 3.790326582710125e-05,
+      "loss": 1.0763,
+      "step": 135
+    },
+    {
+      "epoch": 0.3965014577259475,
+      "grad_norm": 0.4140118456428661,
+      "learning_rate": 3.785970047185253e-05,
+      "loss": 1.038,
+      "step": 136
+    },
+    {
+      "epoch": 0.39941690962099125,
+      "grad_norm": 0.3965741184815775,
+      "learning_rate": 3.781571273205354e-05,
+      "loss": 1.0569,
+      "step": 137
+    },
+    {
+      "epoch": 0.40233236151603496,
+      "grad_norm": 0.43946120665541893,
+      "learning_rate": 3.777130364802081e-05,
+      "loss": 1.0645,
+      "step": 138
+    },
+    {
+      "epoch": 0.40524781341107874,
+      "grad_norm": 0.428032341240665,
+      "learning_rate": 3.772647427003573e-05,
+      "loss": 1.0923,
+      "step": 139
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 0.4135938868702008,
+      "learning_rate": 3.76812256583197e-05,
+      "loss": 1.0019,
+      "step": 140
+    },
+    {
+      "epoch": 0.4110787172011662,
+      "grad_norm": 0.42079943542215226,
+      "learning_rate": 3.763555888300906e-05,
+      "loss": 1.0245,
+      "step": 141
+    },
+    {
+      "epoch": 0.4139941690962099,
+      "grad_norm": 0.4104835573072325,
+      "learning_rate": 3.758947502412978e-05,
+      "loss": 1.0125,
+      "step": 142
+    },
+    {
+      "epoch": 0.41690962099125367,
+      "grad_norm": 0.4999660587761059,
+      "learning_rate": 3.754297517157193e-05,
+      "loss": 1.0287,
+      "step": 143
+    },
+    {
+      "epoch": 0.4198250728862974,
+      "grad_norm": 0.45879131535359835,
+      "learning_rate": 3.749606042506387e-05,
+      "loss": 0.9914,
+      "step": 144
+    },
+    {
+      "epoch": 0.4227405247813411,
+      "grad_norm": 0.4356982931966008,
+      "learning_rate": 3.744873189414627e-05,
+      "loss": 1.062,
+      "step": 145
+    },
+    {
+      "epoch": 0.42565597667638483,
+      "grad_norm": 0.39205637695442735,
+      "learning_rate": 3.740099069814588e-05,
+      "loss": 1.0553,
+      "step": 146
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.39862366256178505,
+      "learning_rate": 3.735283796614903e-05,
+      "loss": 1.0295,
+      "step": 147
+    },
+    {
+      "epoch": 0.4314868804664723,
+      "grad_norm": 0.4565309577821647,
+      "learning_rate": 3.730427483697491e-05,
+      "loss": 0.994,
+      "step": 148
+    },
+    {
+      "epoch": 0.43440233236151604,
+      "grad_norm": 0.37911610010778896,
+      "learning_rate": 3.725530245914871e-05,
+      "loss": 0.988,
+      "step": 149
+    },
+    {
+      "epoch": 0.43731778425655976,
+      "grad_norm": 0.38802243711360784,
+      "learning_rate": 3.7205921990874375e-05,
+      "loss": 1.0003,
+      "step": 150
+    },
+    {
+      "epoch": 0.4402332361516035,
+      "grad_norm": 0.3779749391776368,
+      "learning_rate": 3.715613460000727e-05,
+      "loss": 1.0399,
+      "step": 151
+    },
+    {
+      "epoch": 0.44314868804664725,
+      "grad_norm": 0.3737638848515894,
+      "learning_rate": 3.7105941464026535e-05,
+      "loss": 0.9976,
+      "step": 152
+    },
+    {
+      "epoch": 0.446064139941691,
+      "grad_norm": 0.39445068206910416,
+      "learning_rate": 3.705534377000723e-05,
+      "loss": 1.0081,
+      "step": 153
+    },
+    {
+      "epoch": 0.4489795918367347,
+      "grad_norm": 0.3970018541475319,
+      "learning_rate": 3.700434271459229e-05,
+      "loss": 1.0622,
+      "step": 154
+    },
+    {
+      "epoch": 0.4518950437317784,
+      "grad_norm": 0.41614934053800634,
+      "learning_rate": 3.695293950396419e-05,
+      "loss": 1.0184,
+      "step": 155
+    },
+    {
+      "epoch": 0.45481049562682213,
+      "grad_norm": 0.42879970357635455,
+      "learning_rate": 3.6901135353816444e-05,
+      "loss": 1.0692,
+      "step": 156
+    },
+    {
+      "epoch": 0.4577259475218659,
+      "grad_norm": 0.3956188265745643,
+      "learning_rate": 3.684893148932484e-05,
+      "loss": 1.0436,
+      "step": 157
+    },
+    {
+      "epoch": 0.4606413994169096,
+      "grad_norm": 0.351056787493942,
+      "learning_rate": 3.679632914511849e-05,
+      "loss": 1.0084,
+      "step": 158
+    },
+    {
+      "epoch": 0.46355685131195334,
+      "grad_norm": 0.42154821635414025,
+      "learning_rate": 3.6743329565250575e-05,
+      "loss": 0.965,
+      "step": 159
+    },
+    {
+      "epoch": 0.46647230320699706,
+      "grad_norm": 0.425347734771129,
+      "learning_rate": 3.668993400316898e-05,
+      "loss": 1.0146,
+      "step": 160
+    },
+    {
+      "epoch": 0.46938775510204084,
+      "grad_norm": 0.3719982532012811,
+      "learning_rate": 3.663614372168663e-05,
+      "loss": 1.0177,
+      "step": 161
+    },
+    {
+      "epoch": 0.47230320699708456,
+      "grad_norm": 0.4400972270054467,
+      "learning_rate": 3.658195999295161e-05,
+      "loss": 1.0366,
+      "step": 162
+    },
+    {
+      "epoch": 0.4752186588921283,
+      "grad_norm": 0.3605242363140329,
+      "learning_rate": 3.65273840984171e-05,
+      "loss": 1.0381,
+      "step": 163
+    },
+    {
+      "epoch": 0.478134110787172,
+      "grad_norm": 0.4066779201514536,
+      "learning_rate": 3.647241732881104e-05,
+      "loss": 0.9926,
+      "step": 164
+    },
+    {
+      "epoch": 0.48104956268221577,
+      "grad_norm": 0.38383029098926946,
+      "learning_rate": 3.641706098410566e-05,
+      "loss": 1.0053,
+      "step": 165
+    },
+    {
+      "epoch": 0.4839650145772595,
+      "grad_norm": 0.4540301261066676,
+      "learning_rate": 3.6361316373486666e-05,
+      "loss": 1.0027,
+      "step": 166
+    },
+    {
+      "epoch": 0.4868804664723032,
+      "grad_norm": 0.4766965097228693,
+      "learning_rate": 3.630518481532232e-05,
+      "loss": 1.0226,
+      "step": 167
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 0.3664211009679597,
+      "learning_rate": 3.624866763713225e-05,
+      "loss": 1.0028,
+      "step": 168
+    },
+    {
+      "epoch": 0.49271137026239065,
+      "grad_norm": 0.4328310790493932,
+      "learning_rate": 3.619176617555606e-05,
+      "loss": 1.1124,
+      "step": 169
+    },
+    {
+      "epoch": 0.4956268221574344,
+      "grad_norm": 0.5130318141830079,
+      "learning_rate": 3.613448177632171e-05,
+      "loss": 1.0168,
+      "step": 170
+    },
+    {
+      "epoch": 0.49854227405247814,
+      "grad_norm": 0.431130968592827,
+      "learning_rate": 3.607681579421369e-05,
+      "loss": 1.0359,
+      "step": 171
+    },
+    {
+      "epoch": 0.5014577259475219,
+      "grad_norm": 0.38524112616777045,
+      "learning_rate": 3.6018769593040973e-05,
+      "loss": 1.0614,
+      "step": 172
+    },
+    {
+      "epoch": 0.5043731778425656,
+      "grad_norm": 0.35453421271369107,
+      "learning_rate": 3.5960344545604796e-05,
+      "loss": 1.0441,
+      "step": 173
+    },
+    {
+      "epoch": 0.5072886297376094,
+      "grad_norm": 0.41976737591927166,
+      "learning_rate": 3.590154203366613e-05,
+      "loss": 1.0446,
+      "step": 174
+    },
+    {
+      "epoch": 0.5102040816326531,
+      "grad_norm": 0.4259982924631218,
+      "learning_rate": 3.584236344791306e-05,
+      "loss": 1.0136,
+      "step": 175
+    },
+    {
+      "epoch": 0.5131195335276968,
+      "grad_norm": 0.4149244827409494,
+      "learning_rate": 3.578281018792788e-05,
+      "loss": 1.0287,
+      "step": 176
+    },
+    {
+      "epoch": 0.5160349854227405,
+      "grad_norm": 0.4611231037315541,
+      "learning_rate": 3.572288366215395e-05,
+      "loss": 1.0915,
+      "step": 177
+    },
+    {
+      "epoch": 0.5189504373177842,
+      "grad_norm": 0.41755776438019643,
+      "learning_rate": 3.566258528786246e-05,
+      "loss": 1.0648,
+      "step": 178
+    },
+    {
+      "epoch": 0.521865889212828,
+      "grad_norm": 0.3849110884427409,
+      "learning_rate": 3.560191649111885e-05,
+      "loss": 1.0319,
+      "step": 179
+    },
+    {
+      "epoch": 0.5247813411078717,
+      "grad_norm": 0.40902570967880714,
+      "learning_rate": 3.554087870674911e-05,
+      "loss": 1.0379,
+      "step": 180
+    },
+    {
+      "epoch": 0.5276967930029155,
+      "grad_norm": 0.3840959826247132,
+      "learning_rate": 3.547947337830584e-05,
+      "loss": 0.9727,
+      "step": 181
+    },
+    {
+      "epoch": 0.5306122448979592,
+      "grad_norm": 0.5183637429811634,
+      "learning_rate": 3.541770195803412e-05,
+      "loss": 1.0227,
+      "step": 182
+    },
+    {
+      "epoch": 0.5335276967930029,
+      "grad_norm": 0.4257410447947219,
+      "learning_rate": 3.5355565906837155e-05,
+      "loss": 0.9984,
+      "step": 183
+    },
+    {
+      "epoch": 0.5364431486880467,
+      "grad_norm": 0.4384769899775353,
+      "learning_rate": 3.5293066694241705e-05,
+      "loss": 1.0336,
+      "step": 184
+    },
+    {
+      "epoch": 0.5393586005830904,
+      "grad_norm": 0.3758195750644803,
+      "learning_rate": 3.523020579836338e-05,
+      "loss": 1.0325,
+      "step": 185
+    },
+    {
+      "epoch": 0.5422740524781341,
+      "grad_norm": 0.42491607255874136,
+      "learning_rate": 3.5166984705871634e-05,
+      "loss": 1.0012,
+      "step": 186
+    },
+    {
+      "epoch": 0.5451895043731778,
+      "grad_norm": 0.4013799418461195,
+      "learning_rate": 3.510340491195462e-05,
+      "loss": 1.0595,
+      "step": 187
+    },
+    {
+      "epoch": 0.5481049562682215,
+      "grad_norm": 0.38755015550966654,
+      "learning_rate": 3.5039467920283854e-05,
+      "loss": 1.0258,
+      "step": 188
+    },
+    {
+      "epoch": 0.5510204081632653,
+      "grad_norm": 0.419454333619642,
+      "learning_rate": 3.497517524297862e-05,
+      "loss": 0.997,
+      "step": 189
+    },
+    {
+      "epoch": 0.5539358600583091,
+      "grad_norm": 0.4030099888296478,
+      "learning_rate": 3.49105284005702e-05,
+      "loss": 1.0641,
+      "step": 190
+    },
+    {
+      "epoch": 0.5568513119533528,
+      "grad_norm": 0.4308216911553141,
+      "learning_rate": 3.4845528921965975e-05,
+      "loss": 1.0773,
+      "step": 191
+    },
+    {
+      "epoch": 0.5597667638483965,
+      "grad_norm": 0.4109261330841367,
+      "learning_rate": 3.478017834441319e-05,
+      "loss": 1.0348,
+      "step": 192
+    },
+    {
+      "epoch": 0.5626822157434402,
+      "grad_norm": 0.4391746023600184,
+      "learning_rate": 3.471447821346264e-05,
+      "loss": 1.0143,
+      "step": 193
+    },
+    {
+      "epoch": 0.565597667638484,
+      "grad_norm": 0.4231633568942445,
+      "learning_rate": 3.464843008293211e-05,
+      "loss": 1.0658,
+      "step": 194
+    },
+    {
+      "epoch": 0.5685131195335277,
+      "grad_norm": 0.4185436344137551,
+      "learning_rate": 3.458203551486964e-05,
+      "loss": 1.0132,
+      "step": 195
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.3689812388040208,
+      "learning_rate": 3.4515296079516547e-05,
+      "loss": 0.9811,
+      "step": 196
+    },
+    {
+      "epoch": 0.5743440233236151,
+      "grad_norm": 0.38614461808327916,
+      "learning_rate": 3.4448213355270327e-05,
+      "loss": 1.0357,
+      "step": 197
+    },
+    {
+      "epoch": 0.577259475218659,
+      "grad_norm": 0.46524563397545066,
+      "learning_rate": 3.43807889286473e-05,
+      "loss": 1.0115,
+      "step": 198
+    },
+    {
+      "epoch": 0.5801749271137027,
+      "grad_norm": 0.41968912546661996,
+      "learning_rate": 3.43130243942451e-05,
+      "loss": 1.0687,
+      "step": 199
+    },
+    {
+      "epoch": 0.5830903790087464,
+      "grad_norm": 0.4467937397647347,
+      "learning_rate": 3.424492135470496e-05,
+      "loss": 1.0688,
+      "step": 200
+    },
+    {
+      "epoch": 0.5860058309037901,
+      "grad_norm": 0.6603485797707492,
+      "learning_rate": 3.4176481420673806e-05,
+      "loss": 1.0105,
+      "step": 201
+    },
+    {
+      "epoch": 0.5889212827988338,
+      "grad_norm": 0.47934564972994936,
+      "learning_rate": 3.410770621076618e-05,
+      "loss": 1.0196,
+      "step": 202
+    },
+    {
+      "epoch": 0.5918367346938775,
+      "grad_norm": 0.42028075345133814,
+      "learning_rate": 3.403859735152593e-05,
+      "loss": 1.0335,
+      "step": 203
+    },
+    {
+      "epoch": 0.5947521865889213,
+      "grad_norm": 0.41920419384521423,
+      "learning_rate": 3.3969156477387775e-05,
+      "loss": 1.0102,
+      "step": 204
+    },
+    {
+      "epoch": 0.597667638483965,
+      "grad_norm": 0.4314609472381487,
+      "learning_rate": 3.389938523063864e-05,
+      "loss": 1.026,
+      "step": 205
+    },
+    {
+      "epoch": 0.6005830903790087,
+      "grad_norm": 0.400148137177815,
+      "learning_rate": 3.382928526137878e-05,
+      "loss": 1.0375,
+      "step": 206
+    },
+    {
+      "epoch": 0.6034985422740525,
+      "grad_norm": 0.4149559442787825,
+      "learning_rate": 3.375885822748282e-05,
+      "loss": 0.9966,
+      "step": 207
+    },
+    {
+      "epoch": 0.6064139941690962,
+      "grad_norm": 0.43073644415383394,
+      "learning_rate": 3.36881057945605e-05,
+      "loss": 1.0549,
+      "step": 208
+    },
+    {
+      "epoch": 0.60932944606414,
+      "grad_norm": 0.44927459389603297,
+      "learning_rate": 3.361702963591729e-05,
+      "loss": 1.0263,
+      "step": 209
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 0.3832872805795473,
+      "learning_rate": 3.354563143251483e-05,
+      "loss": 1.0359,
+      "step": 210
+    },
+    {
+      "epoch": 0.6151603498542274,
+      "grad_norm": 0.3750674262349031,
+      "learning_rate": 3.347391287293115e-05,
+      "loss": 1.0246,
+      "step": 211
+    },
+    {
+      "epoch": 0.6180758017492711,
+      "grad_norm": 0.4356003464009786,
+      "learning_rate": 3.340187565332077e-05,
+      "loss": 1.0415,
+      "step": 212
+    },
+    {
+      "epoch": 0.6209912536443148,
+      "grad_norm": 0.3832024635421635,
+      "learning_rate": 3.332952147737456e-05,
+      "loss": 0.9936,
+      "step": 213
+    },
+    {
+      "epoch": 0.6239067055393586,
+      "grad_norm": 0.39631432623065777,
+      "learning_rate": 3.325685205627944e-05,
+      "loss": 1.0409,
+      "step": 214
+    },
+    {
+      "epoch": 0.6268221574344023,
+      "grad_norm": 0.4960530056723912,
+      "learning_rate": 3.318386910867796e-05,
+      "loss": 0.9819,
+      "step": 215
+    },
+    {
+      "epoch": 0.6297376093294461,
+      "grad_norm": 0.48098440810607934,
+      "learning_rate": 3.3110574360627574e-05,
+      "loss": 1.0366,
+      "step": 216
+    },
+    {
+      "epoch": 0.6326530612244898,
+      "grad_norm": 0.40495158253103936,
+      "learning_rate": 3.30369695455599e-05,
+      "loss": 1.0169,
+      "step": 217
+    },
+    {
+      "epoch": 0.6355685131195336,
+      "grad_norm": 0.4136840317080595,
+      "learning_rate": 3.296305640423965e-05,
+      "loss": 1.0089,
+      "step": 218
+    },
+    {
+      "epoch": 0.6384839650145773,
+      "grad_norm": 0.41071579187843577,
+      "learning_rate": 3.288883668472353e-05,
+      "loss": 1.0245,
+      "step": 219
+    },
+    {
+      "epoch": 0.641399416909621,
+      "grad_norm": 0.44228843130743967,
+      "learning_rate": 3.2814312142318863e-05,
+      "loss": 1.0143,
+      "step": 220
+    },
+    {
+      "epoch": 0.6443148688046647,
+      "grad_norm": 0.5009960405186326,
+      "learning_rate": 3.273948453954205e-05,
+      "loss": 1.0122,
+      "step": 221
+    },
+    {
+      "epoch": 0.6472303206997084,
+      "grad_norm": 0.5126441090651163,
+      "learning_rate": 3.2664355646076944e-05,
+      "loss": 0.989,
+      "step": 222
+    },
+    {
+      "epoch": 0.6501457725947521,
+      "grad_norm": 0.4071977138096943,
+      "learning_rate": 3.2588927238732946e-05,
+      "loss": 1.0441,
+      "step": 223
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 0.38486281815191886,
+      "learning_rate": 3.2513201101403025e-05,
+      "loss": 1.0152,
+      "step": 224
+    },
+    {
+      "epoch": 0.6559766763848397,
+      "grad_norm": 0.38571804075512084,
+      "learning_rate": 3.24371790250215e-05,
+      "loss": 1.0474,
+      "step": 225
+    },
+    {
+      "epoch": 0.6588921282798834,
+      "grad_norm": 0.35752894010390635,
+      "learning_rate": 3.236086280752167e-05,
+      "loss": 0.9813,
+      "step": 226
+    },
+    {
+      "epoch": 0.6618075801749271,
+      "grad_norm": 0.5079505809169615,
+      "learning_rate": 3.2284254253793364e-05,
+      "loss": 1.0358,
+      "step": 227
+    },
+    {
+      "epoch": 0.6647230320699709,
+      "grad_norm": 0.41139665258470137,
+      "learning_rate": 3.220735517564015e-05,
+      "loss": 1.0367,
+      "step": 228
+    },
+    {
+      "epoch": 0.6676384839650146,
+      "grad_norm": 0.38126553570378735,
+      "learning_rate": 3.213016739173658e-05,
+      "loss": 0.9482,
+      "step": 229
+    },
+    {
+      "epoch": 0.6705539358600583,
+      "grad_norm": 0.4144347872593754,
+      "learning_rate": 3.205269272758513e-05,
+      "loss": 1.0193,
+      "step": 230
+    },
+    {
+      "epoch": 0.673469387755102,
+      "grad_norm": 0.5096571232126209,
+      "learning_rate": 3.197493301547302e-05,
+      "loss": 0.9819,
+      "step": 231
+    },
+    {
+      "epoch": 0.6763848396501457,
+      "grad_norm": 0.36383462161136243,
+      "learning_rate": 3.189689009442894e-05,
+      "loss": 0.9914,
+      "step": 232
+    },
+    {
+      "epoch": 0.6793002915451894,
+      "grad_norm": 0.46095765518459053,
+      "learning_rate": 3.181856581017946e-05,
+      "loss": 0.9897,
+      "step": 233
+    },
+    {
+      "epoch": 0.6822157434402333,
+      "grad_norm": 0.44886312747350354,
+      "learning_rate": 3.173996201510545e-05,
+      "loss": 1.0335,
+      "step": 234
+    },
+    {
+      "epoch": 0.685131195335277,
+      "grad_norm": 0.45631056555707983,
+      "learning_rate": 3.1661080568198266e-05,
+      "loss": 1.0346,
+      "step": 235
+    },
+    {
+      "epoch": 0.6880466472303207,
+      "grad_norm": 0.4136610032658645,
+      "learning_rate": 3.158192333501577e-05,
+      "loss": 1.0104,
+      "step": 236
+    },
+    {
+      "epoch": 0.6909620991253644,
+      "grad_norm": 0.4367296982258636,
+      "learning_rate": 3.150249218763818e-05,
+      "loss": 1.0428,
+      "step": 237
+    },
+    {
+      "epoch": 0.6938775510204082,
+      "grad_norm": 0.4306434247011164,
+      "learning_rate": 3.142278900462387e-05,
+      "loss": 1.0455,
+      "step": 238
+    },
+    {
+      "epoch": 0.6967930029154519,
+      "grad_norm": 0.4253113476475862,
+      "learning_rate": 3.134281567096485e-05,
+      "loss": 1.0496,
+      "step": 239
+    },
+    {
+      "epoch": 0.6997084548104956,
+      "grad_norm": 0.48183974058742907,
+      "learning_rate": 3.1262574078042285e-05,
+      "loss": 1.0465,
+      "step": 240
+    },
+    {
+      "epoch": 0.7026239067055393,
+      "grad_norm": 0.4119086984528717,
+      "learning_rate": 3.1182066123581654e-05,
+      "loss": 0.9854,
+      "step": 241
+    },
+    {
+      "epoch": 0.7055393586005831,
+      "grad_norm": 0.341284639409196,
+      "learning_rate": 3.110129371160797e-05,
+      "loss": 0.9783,
+      "step": 242
+    },
+    {
+      "epoch": 0.7084548104956269,
+      "grad_norm": 0.42056610876171097,
+      "learning_rate": 3.102025875240068e-05,
+      "loss": 1.0271,
+      "step": 243
+    },
+    {
+      "epoch": 0.7113702623906706,
+      "grad_norm": 0.4231983208975138,
+      "learning_rate": 3.093896316244855e-05,
+      "loss": 1.0432,
+      "step": 244
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.37689276896375645,
+      "learning_rate": 3.085740886440422e-05,
+      "loss": 0.9554,
+      "step": 245
+    },
+    {
+      "epoch": 0.717201166180758,
+      "grad_norm": 0.5479879616689535,
+      "learning_rate": 3.077559778703891e-05,
+      "loss": 0.9957,
+      "step": 246
+    },
+    {
+      "epoch": 0.7201166180758017,
+      "grad_norm": 0.36933525591223165,
+      "learning_rate": 3.069353186519665e-05,
+      "loss": 0.9806,
+      "step": 247
+    },
+    {
+      "epoch": 0.7230320699708455,
+      "grad_norm": 0.41541742087484357,
+      "learning_rate": 3.06112130397486e-05,
+      "loss": 1.0019,
+      "step": 248
+    },
+    {
+      "epoch": 0.7259475218658892,
+      "grad_norm": 0.4030147243701519,
+      "learning_rate": 3.052864325754712e-05,
+      "loss": 0.9609,
+      "step": 249
+    },
+    {
+      "epoch": 0.7288629737609329,
+      "grad_norm": 0.38097239049076487,
+      "learning_rate": 3.0445824471379735e-05,
+      "loss": 0.9906,
+      "step": 250
+    },
+    {
+      "epoch": 0.7317784256559767,
+      "grad_norm": 0.35094313646523306,
+      "learning_rate": 3.036275863992296e-05,
+      "loss": 1.0152,
+      "step": 251
+    },
+    {
+      "epoch": 0.7346938775510204,
+      "grad_norm": 0.39936296801568144,
+      "learning_rate": 3.0279447727695955e-05,
+      "loss": 1.0211,
+      "step": 252
+    },
+    {
+      "epoch": 0.7376093294460642,
+      "grad_norm": 0.3910974776654842,
+      "learning_rate": 3.0195893705014085e-05,
+      "loss": 1.0504,
+      "step": 253
+    },
+    {
+      "epoch": 0.7405247813411079,
+      "grad_norm": 0.43816416675730724,
+      "learning_rate": 3.01120985479423e-05,
+      "loss": 1.0076,
+      "step": 254
+    },
+    {
+      "epoch": 0.7434402332361516,
+      "grad_norm": 0.36698284475827536,
+      "learning_rate": 3.002806423824843e-05,
+      "loss": 0.9635,
+      "step": 255
+    },
+    {
+      "epoch": 0.7463556851311953,
+      "grad_norm": 0.39228423379591765,
+      "learning_rate": 2.9943792763356305e-05,
+      "loss": 0.9619,
+      "step": 256
+    },
+    {
+      "epoch": 0.749271137026239,
+      "grad_norm": 0.36070109767376196,
+      "learning_rate": 2.9859286116298714e-05,
+      "loss": 0.9851,
+      "step": 257
+    },
+    {
+      "epoch": 0.7521865889212828,
+      "grad_norm": 0.37912953951949635,
+      "learning_rate": 2.977454629567034e-05,
+      "loss": 0.9898,
+      "step": 258
+    },
+    {
+      "epoch": 0.7551020408163265,
+      "grad_norm": 0.37387389967325224,
+      "learning_rate": 2.968957530558043e-05,
+      "loss": 0.9977,
+      "step": 259
+    },
+    {
+      "epoch": 0.7580174927113703,
+      "grad_norm": 0.39972986361258667,
+      "learning_rate": 2.960437515560544e-05,
+      "loss": 0.9856,
+      "step": 260
+    },
+    {
+      "epoch": 0.760932944606414,
+      "grad_norm": 0.3826342975930071,
+      "learning_rate": 2.9518947860741476e-05,
+      "loss": 0.9588,
+      "step": 261
+    },
+    {
+      "epoch": 0.7638483965014577,
+      "grad_norm": 0.3576332727935384,
+      "learning_rate": 2.943329544135666e-05,
+      "loss": 0.9893,
+      "step": 262
+    },
+    {
+      "epoch": 0.7667638483965015,
+      "grad_norm": 0.464371743364152,
+      "learning_rate": 2.9347419923143355e-05,
+      "loss": 1.0135,
+      "step": 263
+    },
+    {
+      "epoch": 0.7696793002915452,
+      "grad_norm": 0.4133741281825162,
+      "learning_rate": 2.9261323337070212e-05,
+      "loss": 0.9489,
+      "step": 264
+    },
+    {
+      "epoch": 0.7725947521865889,
+      "grad_norm": 0.48836679547916445,
+      "learning_rate": 2.9175007719334213e-05,
+      "loss": 0.9644,
+      "step": 265
+    },
+    {
+      "epoch": 0.7755102040816326,
+      "grad_norm": 0.3887248594130963,
+      "learning_rate": 2.9088475111312434e-05,
+      "loss": 0.9809,
+      "step": 266
+    },
+    {
+      "epoch": 0.7784256559766763,
+      "grad_norm": 0.3918471548750329,
+      "learning_rate": 2.900172755951382e-05,
+      "loss": 0.9602,
+      "step": 267
+    },
+    {
+      "epoch": 0.7813411078717201,
+      "grad_norm": 0.4366666865657208,
+      "learning_rate": 2.891476711553077e-05,
+      "loss": 1.0474,
+      "step": 268
+    },
+    {
+      "epoch": 0.7842565597667639,
+      "grad_norm": 0.38108127915752593,
+      "learning_rate": 2.88275958359906e-05,
+      "loss": 0.9794,
+      "step": 269
+    },
+    {
+      "epoch": 0.7871720116618076,
+      "grad_norm": 0.3996038721397645,
+      "learning_rate": 2.8740215782506937e-05,
+      "loss": 1.0089,
+      "step": 270
+    },
+    {
+      "epoch": 0.7900874635568513,
+      "grad_norm": 0.4000788473276949,
+      "learning_rate": 2.8652629021630928e-05,
+      "loss": 0.9935,
+      "step": 271
+    },
+    {
+      "epoch": 0.793002915451895,
+      "grad_norm": 0.4311799335652256,
+      "learning_rate": 2.8564837624802394e-05,
+      "loss": 1.0085,
+      "step": 272
+    },
+    {
+      "epoch": 0.7959183673469388,
+      "grad_norm": 0.43802025453013554,
+      "learning_rate": 2.8476843668300805e-05,
+      "loss": 0.9818,
+      "step": 273
+    },
+    {
+      "epoch": 0.7988338192419825,
+      "grad_norm": 0.39878597038821745,
+      "learning_rate": 2.838864923319622e-05,
+      "loss": 1.031,
+      "step": 274
+    },
+    {
+      "epoch": 0.8017492711370262,
+      "grad_norm": 0.38849018574168676,
+      "learning_rate": 2.830025640530004e-05,
+      "loss": 0.9949,
+      "step": 275
+    },
+    {
+      "epoch": 0.8046647230320699,
+      "grad_norm": 0.3700883289439985,
+      "learning_rate": 2.821166727511567e-05,
+      "loss": 0.9896,
+      "step": 276
+    },
+    {
+      "epoch": 0.8075801749271136,
+      "grad_norm": 0.3722364712124695,
+      "learning_rate": 2.8122883937789117e-05,
+      "loss": 0.9941,
+      "step": 277
+    },
+    {
+      "epoch": 0.8104956268221575,
+      "grad_norm": 0.4096031852809965,
+      "learning_rate": 2.8033908493059394e-05,
+      "loss": 1.0378,
+      "step": 278
+    },
+    {
+      "epoch": 0.8134110787172012,
+      "grad_norm": 0.37372263404365025,
+      "learning_rate": 2.7944743045208897e-05,
+      "loss": 1.0253,
+      "step": 279
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.38881406149093034,
+      "learning_rate": 2.785538970301361e-05,
+      "loss": 0.9663,
+      "step": 280
+    },
+    {
+      "epoch": 0.8192419825072886,
+      "grad_norm": 0.42459440488854533,
+      "learning_rate": 2.7765850579693274e-05,
+      "loss": 1.0034,
+      "step": 281
+    },
+    {
+      "epoch": 0.8221574344023324,
+      "grad_norm": 0.4143201974978241,
+      "learning_rate": 2.767612779286134e-05,
+      "loss": 1.0368,
+      "step": 282
+    },
+    {
+      "epoch": 0.8250728862973761,
+      "grad_norm": 0.38362731189430754,
+      "learning_rate": 2.758622346447496e-05,
+      "loss": 1.0208,
+      "step": 283
+    },
+    {
+      "epoch": 0.8279883381924198,
+      "grad_norm": 0.41169832196779926,
+      "learning_rate": 2.7496139720784763e-05,
+      "loss": 1.0006,
+      "step": 284
+    },
+    {
+      "epoch": 0.8309037900874635,
+      "grad_norm": 0.34751593366178846,
+      "learning_rate": 2.7405878692284572e-05,
+      "loss": 1.0251,
+      "step": 285
+    },
+    {
+      "epoch": 0.8338192419825073,
+      "grad_norm": 0.4058210036935123,
+      "learning_rate": 2.7315442513661014e-05,
+      "loss": 1.0361,
+      "step": 286
+    },
+    {
+      "epoch": 0.8367346938775511,
+      "grad_norm": 0.4401679580816322,
+      "learning_rate": 2.7224833323743064e-05,
+      "loss": 1.0272,
+      "step": 287
+    },
+    {
+      "epoch": 0.8396501457725948,
+      "grad_norm": 0.4057761916028717,
+      "learning_rate": 2.713405326545142e-05,
+      "loss": 1.0383,
+      "step": 288
+    },
+    {
+      "epoch": 0.8425655976676385,
+      "grad_norm": 0.4245290759312782,
+      "learning_rate": 2.7043104485747852e-05,
+      "loss": 1.0464,
+      "step": 289
+    },
+    {
+      "epoch": 0.8454810495626822,
+      "grad_norm": 0.4038361202180251,
+      "learning_rate": 2.6951989135584417e-05,
+      "loss": 0.988,
+      "step": 290
+    },
+    {
+      "epoch": 0.8483965014577259,
+      "grad_norm": 0.36810376807434014,
+      "learning_rate": 2.686070936985258e-05,
+      "loss": 0.9561,
+      "step": 291
+    },
+    {
+      "epoch": 0.8513119533527697,
+      "grad_norm": 0.37195307131485894,
+      "learning_rate": 2.6769267347332265e-05,
+      "loss": 0.9575,
+      "step": 292
+    },
+    {
+      "epoch": 0.8542274052478134,
+      "grad_norm": 0.390443868115284,
+      "learning_rate": 2.6677665230640798e-05,
+      "loss": 0.9699,
+      "step": 293
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.4042815574880434,
+      "learning_rate": 2.6585905186181738e-05,
+      "loss": 1.042,
+      "step": 294
+    },
+    {
+      "epoch": 0.8600583090379009,
+      "grad_norm": 0.3959869863268726,
+      "learning_rate": 2.6493989384093674e-05,
+      "loss": 0.9752,
+      "step": 295
+    },
+    {
+      "epoch": 0.8629737609329446,
+      "grad_norm": 0.3618071430236251,
+      "learning_rate": 2.6401919998198883e-05,
+      "loss": 1.0231,
+      "step": 296
+    },
+    {
+      "epoch": 0.8658892128279884,
+      "grad_norm": 0.4176948830244882,
+      "learning_rate": 2.630969920595192e-05,
+      "loss": 0.9362,
+      "step": 297
+    },
+    {
+      "epoch": 0.8688046647230321,
+      "grad_norm": 0.3791793063855236,
+      "learning_rate": 2.6217329188388127e-05,
+      "loss": 0.999,
+      "step": 298
+    },
+    {
+      "epoch": 0.8717201166180758,
+      "grad_norm": 0.37050615706622725,
+      "learning_rate": 2.612481213007204e-05,
+      "loss": 0.9698,
+      "step": 299
+    },
+    {
+      "epoch": 0.8746355685131195,
+      "grad_norm": 0.4262982030520383,
+      "learning_rate": 2.603215021904573e-05,
+      "loss": 1.0253,
+      "step": 300
+    },
+    {
+      "epoch": 0.8775510204081632,
+      "grad_norm": 0.4100689842059256,
+      "learning_rate": 2.5939345646777066e-05,
+      "loss": 1.0282,
+      "step": 301
+    },
+    {
+      "epoch": 0.880466472303207,
+      "grad_norm": 0.42174481372887873,
+      "learning_rate": 2.5846400608107864e-05,
+      "loss": 0.9907,
+      "step": 302
+    },
+    {
+      "epoch": 0.8833819241982507,
+      "grad_norm": 0.4314163530656172,
+      "learning_rate": 2.5753317301201998e-05,
+      "loss": 1.0558,
+      "step": 303
+    },
+    {
+      "epoch": 0.8862973760932945,
+      "grad_norm": 0.4010560503450353,
+      "learning_rate": 2.5660097927493407e-05,
+      "loss": 0.9557,
+      "step": 304
+    },
+    {
+      "epoch": 0.8892128279883382,
+      "grad_norm": 0.4395765405207931,
+      "learning_rate": 2.5566744691634027e-05,
+      "loss": 1.0059,
+      "step": 305
+    },
+    {
+      "epoch": 0.892128279883382,
+      "grad_norm": 0.4082847256609399,
+      "learning_rate": 2.5473259801441663e-05,
+      "loss": 1.0103,
+      "step": 306
+    },
+    {
+      "epoch": 0.8950437317784257,
+      "grad_norm": 0.4083786483549625,
+      "learning_rate": 2.537964546784774e-05,
+      "loss": 0.986,
+      "step": 307
+    },
+    {
+      "epoch": 0.8979591836734694,
+      "grad_norm": 0.37572180654125914,
+      "learning_rate": 2.5285903904845066e-05,
+      "loss": 0.9896,
+      "step": 308
+    },
+    {
+      "epoch": 0.9008746355685131,
+      "grad_norm": 0.4027132060553977,
+      "learning_rate": 2.5192037329435426e-05,
+      "loss": 0.979,
+      "step": 309
+    },
+    {
+      "epoch": 0.9037900874635568,
+      "grad_norm": 0.36888494424117924,
+      "learning_rate": 2.5098047961577177e-05,
+      "loss": 0.9471,
+      "step": 310
+    },
+    {
+      "epoch": 0.9067055393586005,
+      "grad_norm": 0.3786111360905341,
+      "learning_rate": 2.500393802413273e-05,
+      "loss": 0.9892,
+      "step": 311
+    },
+    {
+      "epoch": 0.9096209912536443,
+      "grad_norm": 0.45712819166253305,
+      "learning_rate": 2.4909709742815986e-05,
+      "loss": 1.01,
+      "step": 312
+    },
+    {
+      "epoch": 0.9125364431486881,
+      "grad_norm": 0.3842470085901606,
+      "learning_rate": 2.4815365346139696e-05,
+      "loss": 0.9778,
+      "step": 313
+    },
+    {
+      "epoch": 0.9154518950437318,
+      "grad_norm": 0.433547968789441,
+      "learning_rate": 2.4720907065362752e-05,
+      "loss": 1.0222,
+      "step": 314
+    },
+    {
+      "epoch": 0.9183673469387755,
+      "grad_norm": 0.4391573887982836,
+      "learning_rate": 2.4626337134437437e-05,
+      "loss": 1.0405,
+      "step": 315
+    },
+    {
+      "epoch": 0.9212827988338192,
+      "grad_norm": 0.39208976407075724,
+      "learning_rate": 2.4531657789956547e-05,
+      "loss": 1.0437,
+      "step": 316
+    },
+    {
+      "epoch": 0.924198250728863,
+      "grad_norm": 0.3768972618887708,
+      "learning_rate": 2.4436871271100556e-05,
+      "loss": 1.0207,
+      "step": 317
+    },
+    {
+      "epoch": 0.9271137026239067,
+      "grad_norm": 0.43610556057213695,
+      "learning_rate": 2.4341979819584625e-05,
+      "loss": 0.9861,
+      "step": 318
+    },
+    {
+      "epoch": 0.9300291545189504,
+      "grad_norm": 0.363583976831923,
+      "learning_rate": 2.4246985679605554e-05,
+      "loss": 0.9383,
+      "step": 319
+    },
+    {
+      "epoch": 0.9329446064139941,
+      "grad_norm": 0.37854946885829915,
+      "learning_rate": 2.4151891097788775e-05,
+      "loss": 1.0158,
+      "step": 320
+    },
+    {
+      "epoch": 0.9358600583090378,
+      "grad_norm": 0.37464026411645185,
+      "learning_rate": 2.4056698323135176e-05,
+      "loss": 0.9712,
+      "step": 321
+    },
+    {
+      "epoch": 0.9387755102040817,
+      "grad_norm": 0.43100644059903814,
+      "learning_rate": 2.3961409606967925e-05,
+      "loss": 1.0003,
+      "step": 322
+    },
+    {
+      "epoch": 0.9416909620991254,
+      "grad_norm": 0.38980347880232474,
+      "learning_rate": 2.3866027202879192e-05,
+      "loss": 0.914,
+      "step": 323
+    },
+    {
+      "epoch": 0.9446064139941691,
+      "grad_norm": 0.48554638696145264,
+      "learning_rate": 2.377055336667692e-05,
+      "loss": 0.9585,
+      "step": 324
+    },
+    {
+      "epoch": 0.9475218658892128,
+      "grad_norm": 0.36898646954208214,
+      "learning_rate": 2.367499035633141e-05,
+      "loss": 0.9835,
+      "step": 325
+    },
+    {
+      "epoch": 0.9504373177842566,
+      "grad_norm": 0.4297200560129973,
+      "learning_rate": 2.357934043192195e-05,
+      "loss": 0.9952,
+      "step": 326
+    },
+    {
+      "epoch": 0.9533527696793003,
+      "grad_norm": 0.39165249508490607,
+      "learning_rate": 2.3483605855583362e-05,
+      "loss": 0.9882,
+      "step": 327
+    },
+    {
+      "epoch": 0.956268221574344,
+      "grad_norm": 0.41742394941388217,
+      "learning_rate": 2.338778889145249e-05,
+      "loss": 0.9717,
+      "step": 328
+    },
+    {
+      "epoch": 0.9591836734693877,
+      "grad_norm": 0.3886638817329252,
+      "learning_rate": 2.329189180561468e-05,
+      "loss": 0.9663,
+      "step": 329
+    },
+    {
+      "epoch": 0.9620991253644315,
+      "grad_norm": 0.4332990337620019,
+      "learning_rate": 2.3195916866050144e-05,
+      "loss": 0.9852,
+      "step": 330
+    },
+    {
+      "epoch": 0.9650145772594753,
+      "grad_norm": 0.3704146023415907,
+      "learning_rate": 2.3099866342580367e-05,
+      "loss": 0.9486,
+      "step": 331
+    },
+    {
+      "epoch": 0.967930029154519,
+      "grad_norm": 0.4371661371336054,
+      "learning_rate": 2.300374250681439e-05,
+      "loss": 0.9657,
+      "step": 332
+    },
+    {
+      "epoch": 0.9708454810495627,
+      "grad_norm": 0.4303408791719072,
+      "learning_rate": 2.2907547632095107e-05,
+      "loss": 1.0448,
+      "step": 333
+    },
+    {
+      "epoch": 0.9737609329446064,
+      "grad_norm": 0.3768181576852921,
+      "learning_rate": 2.2811283993445496e-05,
+      "loss": 0.9616,
+      "step": 334
+    },
+    {
+      "epoch": 0.9766763848396501,
+      "grad_norm": 0.3724772962800981,
+      "learning_rate": 2.2714953867514797e-05,
+      "loss": 1.0466,
+      "step": 335
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 0.363005384837364,
+      "learning_rate": 2.261855953252471e-05,
+      "loss": 0.9818,
+      "step": 336
+    },
+    {
+      "epoch": 0.9825072886297376,
+      "grad_norm": 0.41490379204887295,
+      "learning_rate": 2.252210326821547e-05,
+      "loss": 1.0075,
+      "step": 337
+    },
+    {
+      "epoch": 0.9854227405247813,
+      "grad_norm": 0.41297107841340125,
+      "learning_rate": 2.2425587355791953e-05,
+      "loss": 1.0264,
+      "step": 338
+    },
+    {
+      "epoch": 0.9883381924198251,
+      "grad_norm": 0.4120966355909792,
+      "learning_rate": 2.232901407786973e-05,
+      "loss": 1.0295,
+      "step": 339
+    },
+    {
+      "epoch": 0.9912536443148688,
+      "grad_norm": 0.4061162831072794,
+      "learning_rate": 2.2232385718421053e-05,
+      "loss": 0.9504,
+      "step": 340
+    },
+    {
+      "epoch": 0.9941690962099126,
+      "grad_norm": 0.3885457702367736,
+      "learning_rate": 2.2135704562720887e-05,
+      "loss": 0.9139,
+      "step": 341
+    },
+    {
+      "epoch": 0.9970845481049563,
+      "grad_norm": 0.43463625174294523,
+      "learning_rate": 2.2038972897292813e-05,
+      "loss": 0.9913,
+      "step": 342
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.3538735883267368,
+      "learning_rate": 2.1942193009854997e-05,
+      "loss": 1.0211,
+      "step": 343
+    },
+    {
+      "epoch": 1.0029154518950438,
+      "grad_norm": 0.3388449241745017,
+      "learning_rate": 2.184536718926604e-05,
+      "loss": 0.9067,
+      "step": 344
+    },
+    {
+      "epoch": 1.0058309037900874,
+      "grad_norm": 0.3958357821808929,
+      "learning_rate": 2.174849772547089e-05,
+      "loss": 0.9061,
+      "step": 345
+    },
+    {
+      "epoch": 1.0087463556851313,
+      "grad_norm": 0.41616322205845646,
+      "learning_rate": 2.165158690944665e-05,
+      "loss": 0.9362,
+      "step": 346
+    },
+    {
+      "epoch": 1.0116618075801749,
+      "grad_norm": 0.35202048574980316,
+      "learning_rate": 2.155463703314841e-05,
+      "loss": 0.8766,
+      "step": 347
+    },
+    {
+      "epoch": 1.0145772594752187,
+      "grad_norm": 0.34310062245683337,
+      "learning_rate": 2.145765038945504e-05,
+      "loss": 0.8642,
+      "step": 348
+    },
+    {
+      "epoch": 1.0174927113702623,
+      "grad_norm": 0.3981059330195169,
+      "learning_rate": 2.136062927211497e-05,
+      "loss": 0.8645,
+      "step": 349
+    },
+    {
+      "epoch": 1.0204081632653061,
+      "grad_norm": 0.3672358171644383,
+      "learning_rate": 2.1263575975691942e-05,
+      "loss": 0.9306,
+      "step": 350
+    },
+    {
+      "epoch": 1.0233236151603498,
+      "grad_norm": 0.3973336252454919,
+      "learning_rate": 2.116649279551072e-05,
+      "loss": 0.929,
+      "step": 351
+    },
+    {
+      "epoch": 1.0262390670553936,
+      "grad_norm": 0.3369031433982456,
+      "learning_rate": 2.106938202760284e-05,
+      "loss": 0.8762,
+      "step": 352
+    },
+    {
+      "epoch": 1.0291545189504374,
+      "grad_norm": 0.4117171514208426,
+      "learning_rate": 2.097224596865229e-05,
+      "loss": 0.8893,
+      "step": 353
+    },
+    {
+      "epoch": 1.032069970845481,
+      "grad_norm": 0.35518871719324885,
+      "learning_rate": 2.0875086915941183e-05,
+      "loss": 0.8674,
+      "step": 354
+    },
+    {
+      "epoch": 1.0349854227405249,
+      "grad_norm": 0.3890457229678617,
+      "learning_rate": 2.077790716729545e-05,
+      "loss": 0.9484,
+      "step": 355
+    },
+    {
+      "epoch": 1.0379008746355685,
+      "grad_norm": 0.39711639935921345,
+      "learning_rate": 2.068070902103047e-05,
+      "loss": 0.9082,
+      "step": 356
+    },
+    {
+      "epoch": 1.0408163265306123,
+      "grad_norm": 0.371896748401522,
+      "learning_rate": 2.0583494775896753e-05,
+      "loss": 0.9356,
+      "step": 357
+    },
+    {
+      "epoch": 1.043731778425656,
+      "grad_norm": 0.3487320833120989,
+      "learning_rate": 2.048626673102552e-05,
+      "loss": 0.8607,
+      "step": 358
+    },
+    {
+      "epoch": 1.0466472303206997,
+      "grad_norm": 0.41218299978568584,
+      "learning_rate": 2.0389027185874392e-05,
+      "loss": 0.8836,
+      "step": 359
+    },
+    {
+      "epoch": 1.0495626822157433,
+      "grad_norm": 0.37291671079144145,
+      "learning_rate": 2.029177844017293e-05,
+      "loss": 0.8612,
+      "step": 360
+    },
+    {
+      "epoch": 1.0524781341107872,
+      "grad_norm": 0.4195454108396945,
+      "learning_rate": 2.0194522793868323e-05,
+      "loss": 0.9009,
+      "step": 361
+    },
+    {
+      "epoch": 1.055393586005831,
+      "grad_norm": 0.3896114588981958,
+      "learning_rate": 2.009726254707095e-05,
+      "loss": 0.919,
+      "step": 362
+    },
+    {
+      "epoch": 1.0583090379008746,
+      "grad_norm": 0.36497741633912156,
+      "learning_rate": 2e-05,
+      "loss": 0.9151,
+      "step": 363
+    },
+    {
+      "epoch": 1.0612244897959184,
+      "grad_norm": 0.35583146774397306,
+      "learning_rate": 1.9902737452929052e-05,
+      "loss": 0.8999,
+      "step": 364
+    },
+    {
+      "epoch": 1.064139941690962,
+      "grad_norm": 0.3456016725198812,
+      "learning_rate": 1.9805477206131677e-05,
+      "loss": 0.8859,
+      "step": 365
+    },
+    {
+      "epoch": 1.0670553935860059,
+      "grad_norm": 0.5966960662679052,
+      "learning_rate": 1.9708221559827073e-05,
+      "loss": 0.9015,
+      "step": 366
+    },
+    {
+      "epoch": 1.0699708454810495,
+      "grad_norm": 0.3671094566365045,
+      "learning_rate": 1.9610972814125618e-05,
+      "loss": 0.9176,
+      "step": 367
+    },
+    {
+      "epoch": 1.0728862973760933,
+      "grad_norm": 0.4390906706069723,
+      "learning_rate": 1.9513733268974485e-05,
+      "loss": 0.9444,
+      "step": 368
+    },
+    {
+      "epoch": 1.075801749271137,
+      "grad_norm": 0.34661948587313707,
+      "learning_rate": 1.941650522410325e-05,
+      "loss": 0.8723,
+      "step": 369
+    },
+    {
+      "epoch": 1.0787172011661808,
+      "grad_norm": 0.39816272068553876,
+      "learning_rate": 1.9319290978969532e-05,
+      "loss": 0.9432,
+      "step": 370
+    },
+    {
+      "epoch": 1.0816326530612246,
+      "grad_norm": 0.3484825048580216,
+      "learning_rate": 1.9222092832704556e-05,
+      "loss": 0.9161,
+      "step": 371
+    },
+    {
+      "epoch": 1.0845481049562682,
+      "grad_norm": 0.36769340343082263,
+      "learning_rate": 1.9124913084058817e-05,
+      "loss": 0.8537,
+      "step": 372
+    },
+    {
+      "epoch": 1.087463556851312,
+      "grad_norm": 0.647745516060205,
+      "learning_rate": 1.9027754031347715e-05,
+      "loss": 0.9043,
+      "step": 373
+    },
+    {
+      "epoch": 1.0903790087463556,
+      "grad_norm": 0.39468021998569647,
+      "learning_rate": 1.8930617972397162e-05,
+      "loss": 0.9155,
+      "step": 374
+    },
+    {
+      "epoch": 1.0932944606413995,
+      "grad_norm": 0.5047238810446275,
+      "learning_rate": 1.8833507204489286e-05,
+      "loss": 0.9116,
+      "step": 375
+    },
+    {
+      "epoch": 1.096209912536443,
+      "grad_norm": 0.38578546256744967,
+      "learning_rate": 1.873642402430806e-05,
+      "loss": 0.9446,
+      "step": 376
+    },
+    {
+      "epoch": 1.099125364431487,
+      "grad_norm": 0.37853911957080766,
+      "learning_rate": 1.8639370727885032e-05,
+      "loss": 0.9033,
+      "step": 377
+    },
+    {
+      "epoch": 1.1020408163265305,
+      "grad_norm": 0.39191145713635545,
+      "learning_rate": 1.8542349610544965e-05,
+      "loss": 0.8971,
+      "step": 378
+    },
+    {
+      "epoch": 1.1049562682215743,
+      "grad_norm": 0.42552186647920914,
+      "learning_rate": 1.8445362966851603e-05,
+      "loss": 0.9197,
+      "step": 379
+    },
+    {
+      "epoch": 1.1078717201166182,
+      "grad_norm": 0.39878496811419945,
+      "learning_rate": 1.8348413090553356e-05,
+      "loss": 0.8382,
+      "step": 380
+    },
+    {
+      "epoch": 1.1107871720116618,
+      "grad_norm": 0.3532504119440214,
+      "learning_rate": 1.8251502274529113e-05,
+      "loss": 0.8854,
+      "step": 381
+    },
+    {
+      "epoch": 1.1137026239067056,
+      "grad_norm": 0.3794396182708985,
+      "learning_rate": 1.815463281073396e-05,
+      "loss": 0.9256,
+      "step": 382
+    },
+    {
+      "epoch": 1.1166180758017492,
+      "grad_norm": 0.3690962462197968,
+      "learning_rate": 1.8057806990145006e-05,
+      "loss": 0.9126,
+      "step": 383
+    },
+    {
+      "epoch": 1.119533527696793,
+      "grad_norm": 0.33118238380078774,
+      "learning_rate": 1.796102710270719e-05,
+      "loss": 0.8978,
+      "step": 384
+    },
+    {
+      "epoch": 1.1224489795918366,
+      "grad_norm": 0.4017437985742156,
+      "learning_rate": 1.7864295437279123e-05,
+      "loss": 0.9122,
+      "step": 385
+    },
+    {
+      "epoch": 1.1253644314868805,
+      "grad_norm": 0.3374384561910696,
+      "learning_rate": 1.7767614281578957e-05,
+      "loss": 0.8897,
+      "step": 386
+    },
+    {
+      "epoch": 1.128279883381924,
+      "grad_norm": 0.38242886488399963,
+      "learning_rate": 1.7670985922130278e-05,
+      "loss": 0.8855,
+      "step": 387
+    },
+    {
+      "epoch": 1.131195335276968,
+      "grad_norm": 0.3118608652607213,
+      "learning_rate": 1.757441264420805e-05,
+      "loss": 0.8872,
+      "step": 388
+    },
+    {
+      "epoch": 1.1341107871720117,
+      "grad_norm": 0.38385193075347296,
+      "learning_rate": 1.7477896731784533e-05,
+      "loss": 0.9566,
+      "step": 389
+    },
+    {
+      "epoch": 1.1370262390670554,
+      "grad_norm": 0.320934960093107,
+      "learning_rate": 1.738144046747529e-05,
+      "loss": 0.842,
+      "step": 390
+    },
+    {
+      "epoch": 1.1399416909620992,
+      "grad_norm": 0.39934131018687274,
+      "learning_rate": 1.7285046132485213e-05,
+      "loss": 0.8921,
+      "step": 391
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.501779773738352,
+      "learning_rate": 1.7188716006554514e-05,
+      "loss": 0.8642,
+      "step": 392
+    },
+    {
+      "epoch": 1.1457725947521866,
+      "grad_norm": 0.3830686077134007,
+      "learning_rate": 1.7092452367904903e-05,
+      "loss": 0.8758,
+      "step": 393
+    },
+    {
+      "epoch": 1.1486880466472302,
+      "grad_norm": 0.5008440591261429,
+      "learning_rate": 1.6996257493185612e-05,
+      "loss": 0.9021,
+      "step": 394
+    },
+    {
+      "epoch": 1.151603498542274,
+      "grad_norm": 0.4511494170269456,
+      "learning_rate": 1.6900133657419636e-05,
+      "loss": 0.8622,
+      "step": 395
+    },
+    {
+      "epoch": 1.1545189504373177,
+      "grad_norm": 0.2984119660617534,
+      "learning_rate": 1.680408313394986e-05,
+      "loss": 0.8524,
+      "step": 396
+    },
+    {
+      "epoch": 1.1574344023323615,
+      "grad_norm": 0.3812683259088031,
+      "learning_rate": 1.670810819438532e-05,
+      "loss": 0.9313,
+      "step": 397
+    },
+    {
+      "epoch": 1.1603498542274053,
+      "grad_norm": 0.37166040845388637,
+      "learning_rate": 1.6612211108547516e-05,
+      "loss": 0.8665,
+      "step": 398
+    },
+    {
+      "epoch": 1.163265306122449,
+      "grad_norm": 0.351603148836399,
+      "learning_rate": 1.6516394144416644e-05,
+      "loss": 0.8902,
+      "step": 399
+    },
+    {
+      "epoch": 1.1661807580174928,
+      "grad_norm": 0.610085385951358,
+      "learning_rate": 1.6420659568078057e-05,
+      "loss": 0.8881,
+      "step": 400
+    },
+    {
+      "epoch": 1.1690962099125364,
+      "grad_norm": 0.3874546159794478,
+      "learning_rate": 1.6325009643668592e-05,
+      "loss": 0.8647,
+      "step": 401
+    },
+    {
+      "epoch": 1.1720116618075802,
+      "grad_norm": 0.38491777769529806,
+      "learning_rate": 1.6229446633323082e-05,
+      "loss": 0.8673,
+      "step": 402
+    },
+    {
+      "epoch": 1.1749271137026238,
+      "grad_norm": 0.48051830259266204,
+      "learning_rate": 1.613397279712081e-05,
+      "loss": 0.9143,
+      "step": 403
+    },
+    {
+      "epoch": 1.1778425655976676,
+      "grad_norm": 0.7099012144404129,
+      "learning_rate": 1.603859039303209e-05,
+      "loss": 0.9074,
+      "step": 404
+    },
+    {
+      "epoch": 1.1807580174927113,
+      "grad_norm": 0.32314820225527935,
+      "learning_rate": 1.5943301676864827e-05,
+      "loss": 0.8979,
+      "step": 405
+    },
+    {
+      "epoch": 1.183673469387755,
+      "grad_norm": 0.5871998008882374,
+      "learning_rate": 1.5848108902211228e-05,
+      "loss": 0.8903,
+      "step": 406
+    },
+    {
+      "epoch": 1.186588921282799,
+      "grad_norm": 0.3369401972398898,
+      "learning_rate": 1.5753014320394452e-05,
+      "loss": 0.8972,
+      "step": 407
+    },
+    {
+      "epoch": 1.1895043731778425,
+      "grad_norm": 0.3531724159844245,
+      "learning_rate": 1.565802018041538e-05,
+      "loss": 0.8644,
+      "step": 408
+    },
+    {
+      "epoch": 1.1924198250728864,
+      "grad_norm": 0.9398965424727117,
+      "learning_rate": 1.556312872889944e-05,
+      "loss": 0.9311,
+      "step": 409
+    },
+    {
+      "epoch": 1.19533527696793,
+      "grad_norm": 0.3689024843304816,
+      "learning_rate": 1.546834221004346e-05,
+      "loss": 0.9241,
+      "step": 410
+    },
+    {
+      "epoch": 1.1982507288629738,
+      "grad_norm": 0.43093464215869326,
+      "learning_rate": 1.5373662865562577e-05,
+      "loss": 0.8911,
+      "step": 411
+    },
+    {
+      "epoch": 1.2011661807580174,
+      "grad_norm": 0.4465894257328085,
+      "learning_rate": 1.5279092934637258e-05,
+      "loss": 0.8496,
+      "step": 412
+    },
+    {
+      "epoch": 1.2040816326530612,
+      "grad_norm": 0.34210040207353676,
+      "learning_rate": 1.5184634653860309e-05,
+      "loss": 0.8606,
+      "step": 413
+    },
+    {
+      "epoch": 1.2069970845481048,
+      "grad_norm": 0.41093683620818694,
+      "learning_rate": 1.5090290257184019e-05,
+      "loss": 0.8848,
+      "step": 414
+    },
+    {
+      "epoch": 1.2099125364431487,
+      "grad_norm": 0.35185182480819926,
+      "learning_rate": 1.499606197586727e-05,
+      "loss": 0.9152,
+      "step": 415
+    },
+    {
+      "epoch": 1.2128279883381925,
+      "grad_norm": 0.38820257625897675,
+      "learning_rate": 1.4901952038422832e-05,
+      "loss": 0.8928,
+      "step": 416
+    },
+    {
+      "epoch": 1.215743440233236,
+      "grad_norm": 0.371973353051329,
+      "learning_rate": 1.480796267056458e-05,
+      "loss": 0.8885,
+      "step": 417
+    },
+    {
+      "epoch": 1.21865889212828,
+      "grad_norm": 0.4007535912082386,
+      "learning_rate": 1.4714096095154942e-05,
+      "loss": 0.867,
+      "step": 418
+    },
+    {
+      "epoch": 1.2215743440233235,
+      "grad_norm": 0.3690054663984619,
+      "learning_rate": 1.4620354532152268e-05,
+      "loss": 0.889,
+      "step": 419
+    },
+    {
+      "epoch": 1.2244897959183674,
+      "grad_norm": 0.37463553204342753,
+      "learning_rate": 1.4526740198558345e-05,
+      "loss": 0.8706,
+      "step": 420
+    },
+    {
+      "epoch": 1.227405247813411,
+      "grad_norm": 0.4952730464254449,
+      "learning_rate": 1.4433255308365973e-05,
+      "loss": 0.8401,
+      "step": 421
+    },
+    {
+      "epoch": 1.2303206997084548,
+      "grad_norm": 0.345766761417753,
+      "learning_rate": 1.4339902072506591e-05,
+      "loss": 0.8835,
+      "step": 422
+    },
+    {
+      "epoch": 1.2332361516034984,
+      "grad_norm": 1.463217273899525,
+      "learning_rate": 1.4246682698798012e-05,
+      "loss": 0.8907,
+      "step": 423
+    },
+    {
+      "epoch": 1.2361516034985423,
+      "grad_norm": 0.39821570357245056,
+      "learning_rate": 1.4153599391892143e-05,
+      "loss": 0.9214,
+      "step": 424
+    },
+    {
+      "epoch": 1.239067055393586,
+      "grad_norm": 0.3433998600071002,
+      "learning_rate": 1.4060654353222942e-05,
+      "loss": 0.8962,
+      "step": 425
+    },
+    {
+      "epoch": 1.2419825072886297,
+      "grad_norm": 0.4000515497205946,
+      "learning_rate": 1.3967849780954277e-05,
+      "loss": 0.9037,
+      "step": 426
+    },
+    {
+      "epoch": 1.2448979591836735,
+      "grad_norm": 0.9571521264143225,
+      "learning_rate": 1.3875187869927965e-05,
+      "loss": 0.91,
+      "step": 427
+    },
+    {
+      "epoch": 1.2478134110787171,
+      "grad_norm": 0.3733616626840636,
+      "learning_rate": 1.3782670811611875e-05,
+      "loss": 0.8817,
+      "step": 428
+    },
+    {
+      "epoch": 1.250728862973761,
+      "grad_norm": 0.3642809314159708,
+      "learning_rate": 1.3690300794048085e-05,
+      "loss": 0.8813,
+      "step": 429
+    },
+    {
+      "epoch": 1.2536443148688048,
+      "grad_norm": 0.3647741657803098,
+      "learning_rate": 1.3598080001801126e-05,
+      "loss": 0.9274,
+      "step": 430
+    },
+    {
+      "epoch": 1.2565597667638484,
+      "grad_norm": 0.3458677417744315,
+      "learning_rate": 1.3506010615906333e-05,
+      "loss": 0.9027,
+      "step": 431
+    },
+    {
+      "epoch": 1.259475218658892,
+      "grad_norm": 0.34251500677540714,
+      "learning_rate": 1.341409481381827e-05,
+      "loss": 0.8474,
+      "step": 432
+    },
+    {
+      "epoch": 1.2623906705539358,
+      "grad_norm": 0.3190350803534079,
+      "learning_rate": 1.332233476935921e-05,
+      "loss": 0.8459,
+      "step": 433
+    },
+    {
+      "epoch": 1.2653061224489797,
+      "grad_norm": 0.3265461354474515,
+      "learning_rate": 1.3230732652667735e-05,
+      "loss": 0.8689,
+      "step": 434
+    },
+    {
+      "epoch": 1.2682215743440233,
+      "grad_norm": 0.3267958005137338,
+      "learning_rate": 1.3139290630147426e-05,
+      "loss": 0.8875,
+      "step": 435
+    },
+    {
+      "epoch": 1.271137026239067,
+      "grad_norm": 0.38778316009874764,
+      "learning_rate": 1.304801086441559e-05,
+      "loss": 0.8932,
+      "step": 436
+    },
+    {
+      "epoch": 1.2740524781341107,
+      "grad_norm": 0.3410085655324801,
+      "learning_rate": 1.2956895514252155e-05,
+      "loss": 0.9059,
+      "step": 437
+    },
+    {
+      "epoch": 1.2769679300291545,
+      "grad_norm": 0.41937944828658263,
+      "learning_rate": 1.2865946734548584e-05,
+      "loss": 0.9002,
+      "step": 438
+    },
+    {
+      "epoch": 1.2798833819241984,
+      "grad_norm": 0.38182491793130874,
+      "learning_rate": 1.2775166676256942e-05,
+      "loss": 0.9464,
+      "step": 439
+    },
+    {
+      "epoch": 1.282798833819242,
+      "grad_norm": 0.36240327212282164,
+      "learning_rate": 1.2684557486338991e-05,
+      "loss": 0.9037,
+      "step": 440
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.38163895310199947,
+      "learning_rate": 1.2594121307715441e-05,
+      "loss": 0.8961,
+      "step": 441
+    },
+    {
+      "epoch": 1.2886297376093294,
+      "grad_norm": 0.4177515236060373,
+      "learning_rate": 1.2503860279215242e-05,
+      "loss": 0.8718,
+      "step": 442
+    },
+    {
+      "epoch": 1.2915451895043732,
+      "grad_norm": 0.3414559830348138,
+      "learning_rate": 1.2413776535525043e-05,
+      "loss": 0.8944,
+      "step": 443
+    },
+    {
+      "epoch": 1.2944606413994169,
+      "grad_norm": 0.3444285556032968,
+      "learning_rate": 1.2323872207138666e-05,
+      "loss": 0.8882,
+      "step": 444
+    },
+    {
+      "epoch": 1.2973760932944607,
+      "grad_norm": 0.3481275643120278,
+      "learning_rate": 1.2234149420306731e-05,
+      "loss": 0.8574,
+      "step": 445
+    },
+    {
+      "epoch": 1.3002915451895043,
+      "grad_norm": 0.39334877331174234,
+      "learning_rate": 1.214461029698639e-05,
+      "loss": 0.9041,
+      "step": 446
+    },
+    {
+      "epoch": 1.3032069970845481,
+      "grad_norm": 0.45396505769468926,
+      "learning_rate": 1.2055256954791114e-05,
+      "loss": 0.8161,
+      "step": 447
+    },
+    {
+      "epoch": 1.306122448979592,
+      "grad_norm": 0.33669105009228384,
+      "learning_rate": 1.1966091506940616e-05,
+      "loss": 0.8329,
+      "step": 448
+    },
+    {
+      "epoch": 1.3090379008746356,
+      "grad_norm": 0.404159242739437,
+      "learning_rate": 1.1877116062210891e-05,
+      "loss": 0.8878,
+      "step": 449
+    },
+    {
+      "epoch": 1.3119533527696792,
+      "grad_norm": 0.36088083861016024,
+      "learning_rate": 1.1788332724884335e-05,
+      "loss": 0.8706,
+      "step": 450
+    },
+    {
+      "epoch": 1.314868804664723,
+      "grad_norm": 0.36792996117202054,
+      "learning_rate": 1.1699743594699969e-05,
+      "loss": 0.8936,
+      "step": 451
+    },
+    {
+      "epoch": 1.3177842565597668,
+      "grad_norm": 0.349538085141998,
+      "learning_rate": 1.1611350766803779e-05,
+      "loss": 0.9015,
+      "step": 452
+    },
+    {
+      "epoch": 1.3206997084548104,
+      "grad_norm": 0.334875040431663,
+      "learning_rate": 1.1523156331699193e-05,
+      "loss": 0.8756,
+      "step": 453
+    },
+    {
+      "epoch": 1.3236151603498543,
+      "grad_norm": 0.3531907780008996,
+      "learning_rate": 1.143516237519762e-05,
+      "loss": 0.8658,
+      "step": 454
+    },
+    {
+      "epoch": 1.3265306122448979,
+      "grad_norm": 0.362184223903246,
+      "learning_rate": 1.1347370978369079e-05,
+      "loss": 0.9037,
+      "step": 455
+    },
+    {
+      "epoch": 1.3294460641399417,
+      "grad_norm": 0.3587468921176296,
+      "learning_rate": 1.1259784217493066e-05,
+      "loss": 0.8701,
+      "step": 456
+    },
+    {
+      "epoch": 1.3323615160349855,
+      "grad_norm": 0.3298772264662029,
+      "learning_rate": 1.1172404164009407e-05,
+      "loss": 0.8736,
+      "step": 457
+    },
+    {
+      "epoch": 1.3352769679300291,
+      "grad_norm": 0.3815272524154801,
+      "learning_rate": 1.1085232884469236e-05,
+      "loss": 0.879,
+      "step": 458
+    },
+    {
+      "epoch": 1.3381924198250728,
+      "grad_norm": 0.36822484912081677,
+      "learning_rate": 1.099827244048618e-05,
+      "loss": 0.9244,
+      "step": 459
+    },
+    {
+      "epoch": 1.3411078717201166,
+      "grad_norm": 0.36072841946566814,
+      "learning_rate": 1.091152488868757e-05,
+      "loss": 0.8999,
+      "step": 460
+    },
+    {
+      "epoch": 1.3440233236151604,
+      "grad_norm": 0.33888396618261474,
+      "learning_rate": 1.0824992280665795e-05,
+      "loss": 0.8572,
+      "step": 461
+    },
+    {
+      "epoch": 1.346938775510204,
+      "grad_norm": 0.3901819048276413,
+      "learning_rate": 1.073867666292979e-05,
+      "loss": 0.9347,
+      "step": 462
+    },
+    {
+      "epoch": 1.3498542274052479,
+      "grad_norm": 0.40223314649198144,
+      "learning_rate": 1.0652580076856651e-05,
+      "loss": 0.9083,
+      "step": 463
+    },
+    {
+      "epoch": 1.3527696793002915,
+      "grad_norm": 0.3491884382940672,
+      "learning_rate": 1.0566704558643346e-05,
+      "loss": 0.8786,
+      "step": 464
+    },
+    {
+      "epoch": 1.3556851311953353,
+      "grad_norm": 0.4415544695353861,
+      "learning_rate": 1.048105213925853e-05,
+      "loss": 0.8776,
+      "step": 465
+    },
+    {
+      "epoch": 1.3586005830903791,
+      "grad_norm": 0.3453075343303145,
+      "learning_rate": 1.0395624844394572e-05,
+      "loss": 0.9093,
+      "step": 466
+    },
+    {
+      "epoch": 1.3615160349854227,
+      "grad_norm": 0.340399019623445,
+      "learning_rate": 1.0310424694419577e-05,
+      "loss": 0.8847,
+      "step": 467
+    },
+    {
+      "epoch": 1.3644314868804663,
+      "grad_norm": 0.35072478611605545,
+      "learning_rate": 1.0225453704329672e-05,
+      "loss": 0.8676,
+      "step": 468
+    },
+    {
+      "epoch": 1.3673469387755102,
+      "grad_norm": 0.366685868167488,
+      "learning_rate": 1.0140713883701291e-05,
+      "loss": 0.9,
+      "step": 469
+    },
+    {
+      "epoch": 1.370262390670554,
+      "grad_norm": 0.3970701863890074,
+      "learning_rate": 1.0056207236643702e-05,
+      "loss": 0.9122,
+      "step": 470
+    },
+    {
+      "epoch": 1.3731778425655976,
+      "grad_norm": 0.37213823009472397,
+      "learning_rate": 9.971935761751574e-06,
+      "loss": 0.8945,
+      "step": 471
+    },
+    {
+      "epoch": 1.3760932944606414,
+      "grad_norm": 0.3454352920544214,
+      "learning_rate": 9.887901452057713e-06,
+      "loss": 0.8981,
+      "step": 472
+    },
+    {
+      "epoch": 1.379008746355685,
+      "grad_norm": 0.360228295000985,
+      "learning_rate": 9.804106294985929e-06,
+      "loss": 0.8879,
+      "step": 473
+    },
+    {
+      "epoch": 1.3819241982507289,
+      "grad_norm": 0.42020731308194914,
+      "learning_rate": 9.720552272304052e-06,
+      "loss": 0.9226,
+      "step": 474
+    },
+    {
+      "epoch": 1.3848396501457727,
+      "grad_norm": 0.3412811092807568,
+      "learning_rate": 9.63724136007705e-06,
+      "loss": 0.8304,
+      "step": 475
+    },
+    {
+      "epoch": 1.3877551020408163,
+      "grad_norm": 0.3872889292215835,
+      "learning_rate": 9.554175528620268e-06,
+      "loss": 0.9462,
+      "step": 476
+    },
+    {
+      "epoch": 1.39067055393586,
+      "grad_norm": 0.34781062699895504,
+      "learning_rate": 9.471356742452881e-06,
+      "loss": 0.8765,
+      "step": 477
+    },
+    {
+      "epoch": 1.3935860058309038,
+      "grad_norm": 0.3483345892307839,
+      "learning_rate": 9.388786960251405e-06,
+      "loss": 0.8475,
+      "step": 478
+    },
+    {
+      "epoch": 1.3965014577259476,
+      "grad_norm": 0.3790773367687499,
+      "learning_rate": 9.30646813480336e-06,
+      "loss": 0.9009,
+      "step": 479
+    },
+    {
+      "epoch": 1.3994169096209912,
+      "grad_norm": 0.4205998029964938,
+      "learning_rate": 9.224402212961096e-06,
+      "loss": 0.8873,
+      "step": 480
+    },
+    {
+      "epoch": 1.402332361516035,
+      "grad_norm": 0.36628713096418625,
+      "learning_rate": 9.142591135595782e-06,
+      "loss": 0.9311,
+      "step": 481
+    },
+    {
+      "epoch": 1.4052478134110786,
+      "grad_norm": 0.3435864317922267,
+      "learning_rate": 9.061036837551467e-06,
+      "loss": 0.8952,
+      "step": 482
+    },
+    {
+      "epoch": 1.4081632653061225,
+      "grad_norm": 0.377356721465227,
+      "learning_rate": 8.979741247599316e-06,
+      "loss": 0.9334,
+      "step": 483
+    },
+    {
+      "epoch": 1.4110787172011663,
+      "grad_norm": 0.36256826670709436,
+      "learning_rate": 8.89870628839203e-06,
+      "loss": 0.9042,
+      "step": 484
+    },
+    {
+      "epoch": 1.41399416909621,
+      "grad_norm": 0.3531404440716723,
+      "learning_rate": 8.817933876418349e-06,
+      "loss": 0.8659,
+      "step": 485
+    },
+    {
+      "epoch": 1.4169096209912537,
+      "grad_norm": 0.4187534028031517,
+      "learning_rate": 8.737425921957726e-06,
+      "loss": 0.8303,
+      "step": 486
+    },
+    {
+      "epoch": 1.4198250728862973,
+      "grad_norm": 0.3691883637551743,
+      "learning_rate": 8.657184329035151e-06,
+      "loss": 0.9052,
+      "step": 487
+    },
+    {
+      "epoch": 1.4227405247813412,
+      "grad_norm": 0.38858873680533296,
+      "learning_rate": 8.577210995376135e-06,
+      "loss": 0.8786,
+      "step": 488
+    },
+    {
+      "epoch": 1.4256559766763848,
+      "grad_norm": 0.36643937908368496,
+      "learning_rate": 8.497507812361826e-06,
+      "loss": 0.9161,
+      "step": 489
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.3823114752504239,
+      "learning_rate": 8.418076664984236e-06,
+      "loss": 0.8946,
+      "step": 490
+    },
+    {
+      "epoch": 1.4314868804664722,
+      "grad_norm": 0.35170467761018115,
+      "learning_rate": 8.338919431801738e-06,
+      "loss": 0.8571,
+      "step": 491
+    },
+    {
+      "epoch": 1.434402332361516,
+      "grad_norm": 0.3701359423395854,
+      "learning_rate": 8.260037984894553e-06,
+      "loss": 0.8641,
+      "step": 492
+    },
+    {
+      "epoch": 1.4373177842565599,
+      "grad_norm": 0.3665017275322417,
+      "learning_rate": 8.181434189820552e-06,
+      "loss": 0.8873,
+      "step": 493
+    },
+    {
+      "epoch": 1.4402332361516035,
+      "grad_norm": 0.3582809415312125,
+      "learning_rate": 8.103109905571062e-06,
+      "loss": 0.9288,
+      "step": 494
+    },
+    {
+      "epoch": 1.4431486880466473,
+      "grad_norm": 0.31631298202014885,
+      "learning_rate": 8.02506698452697e-06,
+      "loss": 0.825,
+      "step": 495
+    },
+    {
+      "epoch": 1.446064139941691,
+      "grad_norm": 0.3534409758588844,
+      "learning_rate": 7.947307272414874e-06,
+      "loss": 0.9054,
+      "step": 496
+    },
+    {
+      "epoch": 1.4489795918367347,
+      "grad_norm": 0.3598528867752392,
+      "learning_rate": 7.869832608263427e-06,
+      "loss": 0.8922,
+      "step": 497
+    },
+    {
+      "epoch": 1.4518950437317784,
+      "grad_norm": 0.3684455264389801,
+      "learning_rate": 7.792644824359858e-06,
+      "loss": 0.8585,
+      "step": 498
+    },
+    {
+      "epoch": 1.4548104956268222,
+      "grad_norm": 0.38121906726183624,
+      "learning_rate": 7.715745746206644e-06,
+      "loss": 0.8459,
+      "step": 499
+    },
+    {
+      "epoch": 1.4577259475218658,
+      "grad_norm": 0.3638442962640907,
+      "learning_rate": 7.639137192478334e-06,
+      "loss": 0.8539,
+      "step": 500
+    },
+    {
+      "epoch": 1.4606413994169096,
+      "grad_norm": 0.40163215440287875,
+      "learning_rate": 7.5628209749785084e-06,
+      "loss": 0.8732,
+      "step": 501
+    },
+    {
+      "epoch": 1.4635568513119535,
+      "grad_norm": 0.34533156621538597,
+      "learning_rate": 7.486798898596976e-06,
+      "loss": 0.8811,
+      "step": 502
+    },
+    {
+      "epoch": 1.466472303206997,
+      "grad_norm": 0.43990397905816536,
+      "learning_rate": 7.4110727612670575e-06,
+      "loss": 0.8852,
+      "step": 503
+    },
+    {
+      "epoch": 1.469387755102041,
+      "grad_norm": 0.5289781287921499,
+      "learning_rate": 7.3356443539230685e-06,
+      "loss": 0.8236,
+      "step": 504
+    },
+    {
+      "epoch": 1.4723032069970845,
+      "grad_norm": 0.3328540341889078,
+      "learning_rate": 7.260515460457958e-06,
+      "loss": 0.8851,
+      "step": 505
+    },
+    {
+      "epoch": 1.4752186588921283,
+      "grad_norm": 0.4870383351032914,
+      "learning_rate": 7.185687857681141e-06,
+      "loss": 0.9001,
+      "step": 506
+    },
+    {
+      "epoch": 1.478134110787172,
+      "grad_norm": 0.37408255528035744,
+      "learning_rate": 7.1111633152764705e-06,
+      "loss": 0.918,
+      "step": 507
+    },
+    {
+      "epoch": 1.4810495626822158,
+      "grad_norm": 0.3833103179567533,
+      "learning_rate": 7.036943595760353e-06,
+      "loss": 0.8998,
+      "step": 508
+    },
+    {
+      "epoch": 1.4839650145772594,
+      "grad_norm": 0.4014548252016667,
+      "learning_rate": 6.963030454440111e-06,
+      "loss": 0.8555,
+      "step": 509
+    },
+    {
+      "epoch": 1.4868804664723032,
+      "grad_norm": 0.390416467602609,
+      "learning_rate": 6.889425639372427e-06,
+      "loss": 0.915,
+      "step": 510
+    },
+    {
+      "epoch": 1.489795918367347,
+      "grad_norm": 0.36354946444392827,
+      "learning_rate": 6.816130891322048e-06,
+      "loss": 0.8467,
+      "step": 511
+    },
+    {
+      "epoch": 1.4927113702623906,
+      "grad_norm": 0.34245284338451154,
+      "learning_rate": 6.743147943720561e-06,
+      "loss": 0.8704,
+      "step": 512
+    },
+    {
+      "epoch": 1.4956268221574345,
+      "grad_norm": 0.3577510719440281,
+      "learning_rate": 6.6704785226254455e-06,
+      "loss": 0.8741,
+      "step": 513
+    },
+    {
+      "epoch": 1.498542274052478,
+      "grad_norm": 0.4257938974909593,
+      "learning_rate": 6.598124346679238e-06,
+      "loss": 0.9088,
+      "step": 514
+    },
+    {
+      "epoch": 1.501457725947522,
+      "grad_norm": 0.40239598681570304,
+      "learning_rate": 6.526087127068857e-06,
+      "loss": 0.8626,
+      "step": 515
+    },
+    {
+      "epoch": 1.5043731778425657,
+      "grad_norm": 0.33201278139400314,
+      "learning_rate": 6.4543685674851834e-06,
+      "loss": 0.8985,
+      "step": 516
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 686,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 172,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2140852218494976.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-516/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e4c923c8239e75e3b9f846483cac70cb0167e52a9c864115f5cae916c9a4021
+size 8376

checkpoint-516/zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/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 gc
+import json
+import numpy as np
+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, weights_only=False)
+
+        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 tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # 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}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] 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")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+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 = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * 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
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[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}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        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 to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=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
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    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.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    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")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+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,
+                                                          lazy_mode=True)
+
+    # 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")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_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 by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # 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)