Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-390/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-447/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+library_name: peft
+license: other
+# base_model: ../Qwen2.5-32B-Instruct
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: sft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# sft
+
+This model is a fine-tuned version of [../Qwen2.5-32B-Instruct](https://huggingface.co/../Qwen2.5-32B-Instruct) on the alpaca_zh_demo dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 3
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 48
+- total_eval_batch_size: 24
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.49.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "../Qwen2.5-32B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8667f7e7ce7214f83b74ffbc9b1d4bb69612d27d2f334e5b0698d5ee4222921
+size 134337704

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.994161801501251,
+    "total_flos": 1153541636358144.0,
+    "train_loss": 1.1157796034876932,
+    "train_runtime": 7535.4115,
+    "train_samples_per_second": 2.864,
+    "train_steps_per_second": 0.059
+}

checkpoint-390/README.md

@@ -0,0 +1,202 @@
+---
+base_model: ../Qwen2.5-32B-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-390/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "../Qwen2.5-32B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-390/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3d676de0d090fda02a7dcac1070140b52bfe0068df33e5fe4b2df7f5eb4ef1a
+size 134337704

checkpoint-390/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-390/global_step390/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:ef797846eac8fbdf57c39d2cbd497d986dba975fb844100c67f8f0d1be73b273
+size 268444400

checkpoint-390/global_step390/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7836d97d0922df82e1dc3112e027f5e8fe735b41fd1e27f746c84e2c7d42d224
+size 268444400

checkpoint-390/global_step390/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5670aee4bca54f9a9cdbac26d219be668c1576dcd18ca02fefb17e7660ca2b39
+size 268444400

checkpoint-390/global_step390/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4012b8880ed279ec4fc26169123efe665287e0a8f06c174106b520c095347cd
+size 886126

checkpoint-390/global_step390/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4121f3bdd5e044465b6c1ba0e1f7c36b7767d68f04d2708ef721895f0f415127
+size 886126

checkpoint-390/global_step390/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95a51081addd270517a8af1871aa19deb9c08e7443fce6046b6dbedc1286077
+size 886126

checkpoint-390/latest

@@ -0,0 +1 @@
+global_step390

checkpoint-390/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2bf9ae13691c39ee7fbd9eb497b0127d60b8594c24b2891098b3739c25d5b1
+size 14768

checkpoint-390/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835f7198d4d5539c74a0ce15e3fbba2ee359088c79e0b77984b34308b954bd63
+size 14768

checkpoint-390/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19325cacb8d362ac4f02fb14163603ec88cb2fa312cb10277c2cad28943bdef3
+size 14768

checkpoint-390/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f9a02858e8c184a62874cc7d31cc1ac104374208c1375a97b843d8462a63bde
+size 1064

checkpoint-390/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-390/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-390/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-390/trainer_state.json

@@ -0,0 +1,2763 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.613844870725605,
+  "eval_steps": 500,
+  "global_step": 390,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006672226855713094,
+      "grad_norm": 0.3732840765814082,
+      "learning_rate": 2.2222222222222224e-07,
+      "loss": 1.6647,
+      "step": 1
+    },
+    {
+      "epoch": 0.013344453711426188,
+      "grad_norm": 0.383618969512302,
+      "learning_rate": 4.444444444444445e-07,
+      "loss": 1.7073,
+      "step": 2
+    },
+    {
+      "epoch": 0.020016680567139282,
+      "grad_norm": 0.40769314152645725,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 1.7505,
+      "step": 3
+    },
+    {
+      "epoch": 0.026688907422852376,
+      "grad_norm": 0.4016260533661679,
+      "learning_rate": 8.88888888888889e-07,
+      "loss": 1.6952,
+      "step": 4
+    },
+    {
+      "epoch": 0.03336113427856547,
+      "grad_norm": 0.40174340733938796,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 1.7844,
+      "step": 5
+    },
+    {
+      "epoch": 0.040033361134278564,
+      "grad_norm": 0.40847133525152324,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 1.7765,
+      "step": 6
+    },
+    {
+      "epoch": 0.04670558798999166,
+      "grad_norm": 0.40604889051688275,
+      "learning_rate": 1.5555555555555558e-06,
+      "loss": 1.6995,
+      "step": 7
+    },
+    {
+      "epoch": 0.05337781484570475,
+      "grad_norm": 0.3894313779958969,
+      "learning_rate": 1.777777777777778e-06,
+      "loss": 1.7128,
+      "step": 8
+    },
+    {
+      "epoch": 0.060050041701417846,
+      "grad_norm": 0.38627201738251066,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.7789,
+      "step": 9
+    },
+    {
+      "epoch": 0.06672226855713094,
+      "grad_norm": 0.379007955799278,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.6907,
+      "step": 10
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.40293473844915795,
+      "learning_rate": 2.4444444444444447e-06,
+      "loss": 1.712,
+      "step": 11
+    },
+    {
+      "epoch": 0.08006672226855713,
+      "grad_norm": 0.3796921388422985,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 1.717,
+      "step": 12
+    },
+    {
+      "epoch": 0.08673894912427023,
+      "grad_norm": 0.363416530641245,
+      "learning_rate": 2.888888888888889e-06,
+      "loss": 1.6075,
+      "step": 13
+    },
+    {
+      "epoch": 0.09341117597998332,
+      "grad_norm": 0.42180934217352195,
+      "learning_rate": 3.1111111111111116e-06,
+      "loss": 1.7974,
+      "step": 14
+    },
+    {
+      "epoch": 0.10008340283569642,
+      "grad_norm": 0.4120160113974808,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.7485,
+      "step": 15
+    },
+    {
+      "epoch": 0.1067556296914095,
+      "grad_norm": 0.39278536183126506,
+      "learning_rate": 3.555555555555556e-06,
+      "loss": 1.5707,
+      "step": 16
+    },
+    {
+      "epoch": 0.1134278565471226,
+      "grad_norm": 0.4167599840383631,
+      "learning_rate": 3.777777777777778e-06,
+      "loss": 1.613,
+      "step": 17
+    },
+    {
+      "epoch": 0.12010008340283569,
+      "grad_norm": 0.4238875949015934,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.6816,
+      "step": 18
+    },
+    {
+      "epoch": 0.1267723102585488,
+      "grad_norm": 0.4720616555526343,
+      "learning_rate": 4.222222222222223e-06,
+      "loss": 1.7593,
+      "step": 19
+    },
+    {
+      "epoch": 0.13344453711426188,
+      "grad_norm": 0.4525263926368364,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 1.775,
+      "step": 20
+    },
+    {
+      "epoch": 0.14011676396997497,
+      "grad_norm": 0.48266597054805727,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 1.791,
+      "step": 21
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.45939880890244206,
+      "learning_rate": 4.888888888888889e-06,
+      "loss": 1.7338,
+      "step": 22
+    },
+    {
+      "epoch": 0.15346121768140117,
+      "grad_norm": 0.47764567898261373,
+      "learning_rate": 5.1111111111111115e-06,
+      "loss": 1.7483,
+      "step": 23
+    },
+    {
+      "epoch": 0.16013344453711426,
+      "grad_norm": 0.5017631959610884,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 1.7481,
+      "step": 24
+    },
+    {
+      "epoch": 0.16680567139282734,
+      "grad_norm": 0.4893567689357815,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 1.7136,
+      "step": 25
+    },
+    {
+      "epoch": 0.17347789824854046,
+      "grad_norm": 0.5105291717073872,
+      "learning_rate": 5.777777777777778e-06,
+      "loss": 1.7602,
+      "step": 26
+    },
+    {
+      "epoch": 0.18015012510425354,
+      "grad_norm": 0.46974781533253324,
+      "learning_rate": 6e-06,
+      "loss": 1.6153,
+      "step": 27
+    },
+    {
+      "epoch": 0.18682235195996663,
+      "grad_norm": 0.5383405971129123,
+      "learning_rate": 6.222222222222223e-06,
+      "loss": 1.6602,
+      "step": 28
+    },
+    {
+      "epoch": 0.19349457881567975,
+      "grad_norm": 0.5952748064288939,
+      "learning_rate": 6.444444444444445e-06,
+      "loss": 1.7177,
+      "step": 29
+    },
+    {
+      "epoch": 0.20016680567139283,
+      "grad_norm": 0.5399245254089347,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.7092,
+      "step": 30
+    },
+    {
+      "epoch": 0.20683903252710592,
+      "grad_norm": 0.5598787056956456,
+      "learning_rate": 6.88888888888889e-06,
+      "loss": 1.67,
+      "step": 31
+    },
+    {
+      "epoch": 0.213511259382819,
+      "grad_norm": 0.5992687712634374,
+      "learning_rate": 7.111111111111112e-06,
+      "loss": 1.7355,
+      "step": 32
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 0.6046798477314653,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 1.7322,
+      "step": 33
+    },
+    {
+      "epoch": 0.2268557130942452,
+      "grad_norm": 0.6320084975028277,
+      "learning_rate": 7.555555555555556e-06,
+      "loss": 1.8031,
+      "step": 34
+    },
+    {
+      "epoch": 0.2335279399499583,
+      "grad_norm": 0.5904036648454649,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 1.6945,
+      "step": 35
+    },
+    {
+      "epoch": 0.24020016680567138,
+      "grad_norm": 0.6104299430520795,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.6777,
+      "step": 36
+    },
+    {
+      "epoch": 0.2468723936613845,
+      "grad_norm": 0.6047786223470227,
+      "learning_rate": 8.222222222222222e-06,
+      "loss": 1.6366,
+      "step": 37
+    },
+    {
+      "epoch": 0.2535446205170976,
+      "grad_norm": 0.6387094238927912,
+      "learning_rate": 8.444444444444446e-06,
+      "loss": 1.6636,
+      "step": 38
+    },
+    {
+      "epoch": 0.2602168473728107,
+      "grad_norm": 0.6120207071048721,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 1.6292,
+      "step": 39
+    },
+    {
+      "epoch": 0.26688907422852376,
+      "grad_norm": 0.6088068565354802,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 1.6047,
+      "step": 40
+    },
+    {
+      "epoch": 0.2735613010842369,
+      "grad_norm": 0.6091668716984593,
+      "learning_rate": 9.111111111111112e-06,
+      "loss": 1.6258,
+      "step": 41
+    },
+    {
+      "epoch": 0.28023352793994993,
+      "grad_norm": 0.5682506824419054,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 1.5699,
+      "step": 42
+    },
+    {
+      "epoch": 0.28690575479566305,
+      "grad_norm": 0.5635810130587849,
+      "learning_rate": 9.555555555555556e-06,
+      "loss": 1.6314,
+      "step": 43
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.5841358241959886,
+      "learning_rate": 9.777777777777779e-06,
+      "loss": 1.5456,
+      "step": 44
+    },
+    {
+      "epoch": 0.3002502085070892,
+      "grad_norm": 0.5617293142392159,
+      "learning_rate": 1e-05,
+      "loss": 1.5272,
+      "step": 45
+    },
+    {
+      "epoch": 0.30692243536280234,
+      "grad_norm": 0.47772319074173303,
+      "learning_rate": 9.999847318844664e-06,
+      "loss": 1.5373,
+      "step": 46
+    },
+    {
+      "epoch": 0.31359466221851545,
+      "grad_norm": 0.510823048338545,
+      "learning_rate": 9.999389284703265e-06,
+      "loss": 1.6097,
+      "step": 47
+    },
+    {
+      "epoch": 0.3202668890742285,
+      "grad_norm": 0.5010538752769951,
+      "learning_rate": 9.99862592554908e-06,
+      "loss": 1.5344,
+      "step": 48
+    },
+    {
+      "epoch": 0.3269391159299416,
+      "grad_norm": 0.47226467172138603,
+      "learning_rate": 9.99755728800233e-06,
+      "loss": 1.5023,
+      "step": 49
+    },
+    {
+      "epoch": 0.3336113427856547,
+      "grad_norm": 0.4849966025454849,
+      "learning_rate": 9.996183437327342e-06,
+      "loss": 1.4975,
+      "step": 50
+    },
+    {
+      "epoch": 0.3402835696413678,
+      "grad_norm": 0.47126668835079394,
+      "learning_rate": 9.994504457428557e-06,
+      "loss": 1.5127,
+      "step": 51
+    },
+    {
+      "epoch": 0.3469557964970809,
+      "grad_norm": 0.4301425546280333,
+      "learning_rate": 9.992520450845415e-06,
+      "loss": 1.4456,
+      "step": 52
+    },
+    {
+      "epoch": 0.353628023352794,
+      "grad_norm": 0.4378182305752446,
+      "learning_rate": 9.99023153874608e-06,
+      "loss": 1.4695,
+      "step": 53
+    },
+    {
+      "epoch": 0.3603002502085071,
+      "grad_norm": 0.4297960171566437,
+      "learning_rate": 9.987637860920053e-06,
+      "loss": 1.5113,
+      "step": 54
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.4154036526185639,
+      "learning_rate": 9.984739575769619e-06,
+      "loss": 1.3419,
+      "step": 55
+    },
+    {
+      "epoch": 0.37364470391993326,
+      "grad_norm": 0.42590048753833515,
+      "learning_rate": 9.981536860300191e-06,
+      "loss": 1.4191,
+      "step": 56
+    },
+    {
+      "epoch": 0.3803169307756464,
+      "grad_norm": 0.4067719643823426,
+      "learning_rate": 9.978029910109491e-06,
+      "loss": 1.3983,
+      "step": 57
+    },
+    {
+      "epoch": 0.3869891576313595,
+      "grad_norm": 0.3969278459704296,
+      "learning_rate": 9.9742189393756e-06,
+      "loss": 1.3794,
+      "step": 58
+    },
+    {
+      "epoch": 0.39366138448707255,
+      "grad_norm": 0.3854670128621615,
+      "learning_rate": 9.970104180843881e-06,
+      "loss": 1.4305,
+      "step": 59
+    },
+    {
+      "epoch": 0.40033361134278567,
+      "grad_norm": 0.37743755476343405,
+      "learning_rate": 9.965685885812773e-06,
+      "loss": 1.4283,
+      "step": 60
+    },
+    {
+      "epoch": 0.4070058381984987,
+      "grad_norm": 0.3610253450226918,
+      "learning_rate": 9.960964324118428e-06,
+      "loss": 1.4135,
+      "step": 61
+    },
+    {
+      "epoch": 0.41367806505421184,
+      "grad_norm": 0.38314151063998836,
+      "learning_rate": 9.955939784118246e-06,
+      "loss": 1.4194,
+      "step": 62
+    },
+    {
+      "epoch": 0.42035029190992496,
+      "grad_norm": 0.391502563403777,
+      "learning_rate": 9.950612572673255e-06,
+      "loss": 1.3669,
+      "step": 63
+    },
+    {
+      "epoch": 0.427022518765638,
+      "grad_norm": 0.3606335039104152,
+      "learning_rate": 9.944983015129376e-06,
+      "loss": 1.3249,
+      "step": 64
+    },
+    {
+      "epoch": 0.43369474562135113,
+      "grad_norm": 0.3836886872726812,
+      "learning_rate": 9.939051455297548e-06,
+      "loss": 1.3323,
+      "step": 65
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.39513066746369385,
+      "learning_rate": 9.932818255432733e-06,
+      "loss": 1.3228,
+      "step": 66
+    },
+    {
+      "epoch": 0.4470391993327773,
+      "grad_norm": 0.3776395809498074,
+      "learning_rate": 9.926283796211796e-06,
+      "loss": 1.4202,
+      "step": 67
+    },
+    {
+      "epoch": 0.4537114261884904,
+      "grad_norm": 0.3536441979654702,
+      "learning_rate": 9.919448476710248e-06,
+      "loss": 1.3169,
+      "step": 68
+    },
+    {
+      "epoch": 0.4603836530442035,
+      "grad_norm": 0.35401704664244255,
+      "learning_rate": 9.91231271437788e-06,
+      "loss": 1.2869,
+      "step": 69
+    },
+    {
+      "epoch": 0.4670558798999166,
+      "grad_norm": 0.364086698791685,
+      "learning_rate": 9.904876945013272e-06,
+      "loss": 1.3558,
+      "step": 70
+    },
+    {
+      "epoch": 0.4737281067556297,
+      "grad_norm": 0.36643453456415837,
+      "learning_rate": 9.89714162273716e-06,
+      "loss": 1.2972,
+      "step": 71
+    },
+    {
+      "epoch": 0.48040033361134277,
+      "grad_norm": 0.35341632594055883,
+      "learning_rate": 9.889107219964726e-06,
+      "loss": 1.288,
+      "step": 72
+    },
+    {
+      "epoch": 0.4870725604670559,
+      "grad_norm": 0.35727226233776593,
+      "learning_rate": 9.880774227376727e-06,
+      "loss": 1.2919,
+      "step": 73
+    },
+    {
+      "epoch": 0.493744787322769,
+      "grad_norm": 0.36655136111497844,
+      "learning_rate": 9.872143153889538e-06,
+      "loss": 1.2864,
+      "step": 74
+    },
+    {
+      "epoch": 0.5004170141784821,
+      "grad_norm": 0.3580519341051248,
+      "learning_rate": 9.863214526624065e-06,
+      "loss": 1.3545,
+      "step": 75
+    },
+    {
+      "epoch": 0.5070892410341952,
+      "grad_norm": 0.3251286992451364,
+      "learning_rate": 9.853988890873563e-06,
+      "loss": 1.2463,
+      "step": 76
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 0.35154208731758474,
+      "learning_rate": 9.844466810070319e-06,
+      "loss": 1.2842,
+      "step": 77
+    },
+    {
+      "epoch": 0.5204336947456214,
+      "grad_norm": 0.35360327701201805,
+      "learning_rate": 9.834648865751254e-06,
+      "loss": 1.2074,
+      "step": 78
+    },
+    {
+      "epoch": 0.5271059216013344,
+      "grad_norm": 0.33827984275163614,
+      "learning_rate": 9.8245356575224e-06,
+      "loss": 1.2719,
+      "step": 79
+    },
+    {
+      "epoch": 0.5337781484570475,
+      "grad_norm": 0.34688277661237193,
+      "learning_rate": 9.814127803022281e-06,
+      "loss": 1.2809,
+      "step": 80
+    },
+    {
+      "epoch": 0.5404503753127606,
+      "grad_norm": 0.30446458893187955,
+      "learning_rate": 9.803425937884202e-06,
+      "loss": 1.2302,
+      "step": 81
+    },
+    {
+      "epoch": 0.5471226021684737,
+      "grad_norm": 0.31831189291520345,
+      "learning_rate": 9.792430715697412e-06,
+      "loss": 1.2329,
+      "step": 82
+    },
+    {
+      "epoch": 0.5537948290241869,
+      "grad_norm": 0.29801313071352337,
+      "learning_rate": 9.781142807967205e-06,
+      "loss": 1.2464,
+      "step": 83
+    },
+    {
+      "epoch": 0.5604670558798999,
+      "grad_norm": 0.3118984625981495,
+      "learning_rate": 9.769562904073896e-06,
+      "loss": 1.2388,
+      "step": 84
+    },
+    {
+      "epoch": 0.567139282735613,
+      "grad_norm": 0.28346870486129144,
+      "learning_rate": 9.757691711230728e-06,
+      "loss": 1.222,
+      "step": 85
+    },
+    {
+      "epoch": 0.5738115095913261,
+      "grad_norm": 0.3235682827850219,
+      "learning_rate": 9.745529954440675e-06,
+      "loss": 1.2167,
+      "step": 86
+    },
+    {
+      "epoch": 0.5804837364470392,
+      "grad_norm": 0.3025602896103518,
+      "learning_rate": 9.733078376452172e-06,
+      "loss": 1.2439,
+      "step": 87
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.2943206117574144,
+      "learning_rate": 9.72033773771374e-06,
+      "loss": 1.1714,
+      "step": 88
+    },
+    {
+      "epoch": 0.5938281901584654,
+      "grad_norm": 0.3043570350280811,
+      "learning_rate": 9.707308816327557e-06,
+      "loss": 1.2466,
+      "step": 89
+    },
+    {
+      "epoch": 0.6005004170141784,
+      "grad_norm": 0.3034637832523981,
+      "learning_rate": 9.693992408001934e-06,
+      "loss": 1.1737,
+      "step": 90
+    },
+    {
+      "epoch": 0.6071726438698916,
+      "grad_norm": 0.29378370873758436,
+      "learning_rate": 9.680389326002708e-06,
+      "loss": 1.2823,
+      "step": 91
+    },
+    {
+      "epoch": 0.6138448707256047,
+      "grad_norm": 0.25233208089640863,
+      "learning_rate": 9.666500401103595e-06,
+      "loss": 1.191,
+      "step": 92
+    },
+    {
+      "epoch": 0.6205170975813178,
+      "grad_norm": 0.264841896316846,
+      "learning_rate": 9.652326481535434e-06,
+      "loss": 1.1842,
+      "step": 93
+    },
+    {
+      "epoch": 0.6271893244370309,
+      "grad_norm": 0.276234903477221,
+      "learning_rate": 9.63786843293439e-06,
+      "loss": 1.1062,
+      "step": 94
+    },
+    {
+      "epoch": 0.6338615512927439,
+      "grad_norm": 0.25250932151404143,
+      "learning_rate": 9.623127138289087e-06,
+      "loss": 1.1036,
+      "step": 95
+    },
+    {
+      "epoch": 0.640533778148457,
+      "grad_norm": 0.27277526043956535,
+      "learning_rate": 9.608103497886687e-06,
+      "loss": 1.1332,
+      "step": 96
+    },
+    {
+      "epoch": 0.6472060050041701,
+      "grad_norm": 0.27812831319172243,
+      "learning_rate": 9.592798429257899e-06,
+      "loss": 1.1704,
+      "step": 97
+    },
+    {
+      "epoch": 0.6538782318598833,
+      "grad_norm": 0.24189134780796812,
+      "learning_rate": 9.577212867120947e-06,
+      "loss": 1.1644,
+      "step": 98
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.25645020937055246,
+      "learning_rate": 9.561347763324484e-06,
+      "loss": 1.147,
+      "step": 99
+    },
+    {
+      "epoch": 0.6672226855713094,
+      "grad_norm": 0.2595686790235878,
+      "learning_rate": 9.545204086789461e-06,
+      "loss": 1.2334,
+      "step": 100
+    },
+    {
+      "epoch": 0.6738949124270225,
+      "grad_norm": 0.24949960135623445,
+      "learning_rate": 9.528782823449954e-06,
+      "loss": 1.0824,
+      "step": 101
+    },
+    {
+      "epoch": 0.6805671392827356,
+      "grad_norm": 0.2457329952973373,
+      "learning_rate": 9.512084976192944e-06,
+      "loss": 1.1335,
+      "step": 102
+    },
+    {
+      "epoch": 0.6872393661384487,
+      "grad_norm": 0.26799579166131554,
+      "learning_rate": 9.495111564797073e-06,
+      "loss": 1.1403,
+      "step": 103
+    },
+    {
+      "epoch": 0.6939115929941618,
+      "grad_norm": 0.24843110380217398,
+      "learning_rate": 9.477863625870371e-06,
+      "loss": 1.1659,
+      "step": 104
+    },
+    {
+      "epoch": 0.700583819849875,
+      "grad_norm": 0.26596297978049915,
+      "learning_rate": 9.460342212786933e-06,
+      "loss": 1.1191,
+      "step": 105
+    },
+    {
+      "epoch": 0.707256046705588,
+      "grad_norm": 0.24609569923205743,
+      "learning_rate": 9.442548395622596e-06,
+      "loss": 1.1388,
+      "step": 106
+    },
+    {
+      "epoch": 0.7139282735613011,
+      "grad_norm": 0.30159400597802477,
+      "learning_rate": 9.424483261089584e-06,
+      "loss": 1.2705,
+      "step": 107
+    },
+    {
+      "epoch": 0.7206005004170142,
+      "grad_norm": 0.24911328963823176,
+      "learning_rate": 9.406147912470142e-06,
+      "loss": 1.1393,
+      "step": 108
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.2461854661834755,
+      "learning_rate": 9.387543469549156e-06,
+      "loss": 1.0897,
+      "step": 109
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.24427724214296034,
+      "learning_rate": 9.368671068545761e-06,
+      "loss": 1.0527,
+      "step": 110
+    },
+    {
+      "epoch": 0.7406171809841534,
+      "grad_norm": 0.24775041629357836,
+      "learning_rate": 9.349531862043952e-06,
+      "loss": 1.0695,
+      "step": 111
+    },
+    {
+      "epoch": 0.7472894078398665,
+      "grad_norm": 0.24100289437186362,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 1.0972,
+      "step": 112
+    },
+    {
+      "epoch": 0.7539616346955796,
+      "grad_norm": 0.22817385479165772,
+      "learning_rate": 9.310457724282034e-06,
+      "loss": 1.1354,
+      "step": 113
+    },
+    {
+      "epoch": 0.7606338615512928,
+      "grad_norm": 0.24351101122361835,
+      "learning_rate": 9.290525179375722e-06,
+      "loss": 1.1867,
+      "step": 114
+    },
+    {
+      "epoch": 0.7673060884070059,
+      "grad_norm": 0.23252679169251178,
+      "learning_rate": 9.270330601532855e-06,
+      "loss": 0.9749,
+      "step": 115
+    },
+    {
+      "epoch": 0.773978315262719,
+      "grad_norm": 0.24891852642577655,
+      "learning_rate": 9.249875224086023e-06,
+      "loss": 1.0428,
+      "step": 116
+    },
+    {
+      "epoch": 0.780650542118432,
+      "grad_norm": 0.2519892667083049,
+      "learning_rate": 9.229160296295488e-06,
+      "loss": 1.1525,
+      "step": 117
+    },
+    {
+      "epoch": 0.7873227689741451,
+      "grad_norm": 0.22842656407732698,
+      "learning_rate": 9.208187083272895e-06,
+      "loss": 1.0893,
+      "step": 118
+    },
+    {
+      "epoch": 0.7939949958298582,
+      "grad_norm": 0.23530353826931574,
+      "learning_rate": 9.186956865904004e-06,
+      "loss": 1.1461,
+      "step": 119
+    },
+    {
+      "epoch": 0.8006672226855713,
+      "grad_norm": 0.25930781535544006,
+      "learning_rate": 9.165470940770458e-06,
+      "loss": 1.0863,
+      "step": 120
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 0.24794978516182076,
+      "learning_rate": 9.143730620070609e-06,
+      "loss": 1.1216,
+      "step": 121
+    },
+    {
+      "epoch": 0.8140116763969975,
+      "grad_norm": 0.23948920252711808,
+      "learning_rate": 9.121737231539369e-06,
+      "loss": 1.1121,
+      "step": 122
+    },
+    {
+      "epoch": 0.8206839032527106,
+      "grad_norm": 0.2271047573553413,
+      "learning_rate": 9.099492118367123e-06,
+      "loss": 1.1543,
+      "step": 123
+    },
+    {
+      "epoch": 0.8273561301084237,
+      "grad_norm": 0.25315676717796304,
+      "learning_rate": 9.076996639117708e-06,
+      "loss": 1.1309,
+      "step": 124
+    },
+    {
+      "epoch": 0.8340283569641368,
+      "grad_norm": 0.24992513383867146,
+      "learning_rate": 9.054252167645426e-06,
+      "loss": 1.064,
+      "step": 125
+    },
+    {
+      "epoch": 0.8407005838198499,
+      "grad_norm": 0.24372502494677808,
+      "learning_rate": 9.03126009301115e-06,
+      "loss": 1.1069,
+      "step": 126
+    },
+    {
+      "epoch": 0.8473728106755629,
+      "grad_norm": 0.23106765610762486,
+      "learning_rate": 9.008021819397488e-06,
+      "loss": 1.1344,
+      "step": 127
+    },
+    {
+      "epoch": 0.854045037531276,
+      "grad_norm": 0.2638490777582001,
+      "learning_rate": 8.984538766023024e-06,
+      "loss": 1.1099,
+      "step": 128
+    },
+    {
+      "epoch": 0.8607172643869891,
+      "grad_norm": 0.2436361177633829,
+      "learning_rate": 8.960812367055646e-06,
+      "loss": 1.0879,
+      "step": 129
+    },
+    {
+      "epoch": 0.8673894912427023,
+      "grad_norm": 0.2435286627690007,
+      "learning_rate": 8.93684407152496e-06,
+      "loss": 1.1281,
+      "step": 130
+    },
+    {
+      "epoch": 0.8740617180984154,
+      "grad_norm": 0.2292808626156267,
+      "learning_rate": 8.912635343233784e-06,
+      "loss": 1.0638,
+      "step": 131
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.22525031331854853,
+      "learning_rate": 8.888187660668762e-06,
+      "loss": 1.1003,
+      "step": 132
+    },
+    {
+      "epoch": 0.8874061718098415,
+      "grad_norm": 0.22555143759216476,
+      "learning_rate": 8.863502516910058e-06,
+      "loss": 0.9963,
+      "step": 133
+    },
+    {
+      "epoch": 0.8940783986655546,
+      "grad_norm": 0.23206135282498955,
+      "learning_rate": 8.838581419540183e-06,
+      "loss": 1.0354,
+      "step": 134
+    },
+    {
+      "epoch": 0.9007506255212677,
+      "grad_norm": 0.2332933329851816,
+      "learning_rate": 8.81342589055191e-06,
+      "loss": 1.0629,
+      "step": 135
+    },
+    {
+      "epoch": 0.9074228523769808,
+      "grad_norm": 0.21598906842259502,
+      "learning_rate": 8.788037466255334e-06,
+      "loss": 1.0368,
+      "step": 136
+    },
+    {
+      "epoch": 0.914095079232694,
+      "grad_norm": 0.2510622429683598,
+      "learning_rate": 8.762417697184034e-06,
+      "loss": 1.018,
+      "step": 137
+    },
+    {
+      "epoch": 0.920767306088407,
+      "grad_norm": 0.25761970215631363,
+      "learning_rate": 8.736568148000386e-06,
+      "loss": 1.0496,
+      "step": 138
+    },
+    {
+      "epoch": 0.9274395329441201,
+      "grad_norm": 0.267375239616011,
+      "learning_rate": 8.710490397400007e-06,
+      "loss": 1.1176,
+      "step": 139
+    },
+    {
+      "epoch": 0.9341117597998332,
+      "grad_norm": 0.23104284046945558,
+      "learning_rate": 8.684186038015327e-06,
+      "loss": 1.0221,
+      "step": 140
+    },
+    {
+      "epoch": 0.9407839866555463,
+      "grad_norm": 0.2560542899746131,
+      "learning_rate": 8.657656676318346e-06,
+      "loss": 1.0761,
+      "step": 141
+    },
+    {
+      "epoch": 0.9474562135112594,
+      "grad_norm": 0.25675258631662545,
+      "learning_rate": 8.630903932522496e-06,
+      "loss": 1.0371,
+      "step": 142
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 0.2609140179674428,
+      "learning_rate": 8.603929440483714e-06,
+      "loss": 1.0895,
+      "step": 143
+    },
+    {
+      "epoch": 0.9608006672226855,
+      "grad_norm": 0.23996253406165996,
+      "learning_rate": 8.576734847600639e-06,
+      "loss": 1.0905,
+      "step": 144
+    },
+    {
+      "epoch": 0.9674728940783986,
+      "grad_norm": 0.2545575065577051,
+      "learning_rate": 8.549321814714018e-06,
+      "loss": 1.1054,
+      "step": 145
+    },
+    {
+      "epoch": 0.9741451209341118,
+      "grad_norm": 0.2514055738350408,
+      "learning_rate": 8.521692016005262e-06,
+      "loss": 1.1183,
+      "step": 146
+    },
+    {
+      "epoch": 0.9808173477898249,
+      "grad_norm": 0.2792023557673277,
+      "learning_rate": 8.49384713889421e-06,
+      "loss": 1.106,
+      "step": 147
+    },
+    {
+      "epoch": 0.987489574645538,
+      "grad_norm": 0.22340105561162074,
+      "learning_rate": 8.46578888393606e-06,
+      "loss": 1.0232,
+      "step": 148
+    },
+    {
+      "epoch": 0.994161801501251,
+      "grad_norm": 0.25568989349658056,
+      "learning_rate": 8.43751896471753e-06,
+      "loss": 1.0899,
+      "step": 149
+    },
+    {
+      "epoch": 1.0066722268557131,
+      "grad_norm": 0.7802055347834813,
+      "learning_rate": 8.40903910775219e-06,
+      "loss": 1.9774,
+      "step": 150
+    },
+    {
+      "epoch": 1.0133444537114262,
+      "grad_norm": 0.2595541681581563,
+      "learning_rate": 8.380351052375023e-06,
+      "loss": 1.045,
+      "step": 151
+    },
+    {
+      "epoch": 1.0200166805671393,
+      "grad_norm": 0.25723642565217814,
+      "learning_rate": 8.35145655063621e-06,
+      "loss": 1.0245,
+      "step": 152
+    },
+    {
+      "epoch": 1.0266889074228525,
+      "grad_norm": 0.27362291141864464,
+      "learning_rate": 8.32235736719411e-06,
+      "loss": 1.0868,
+      "step": 153
+    },
+    {
+      "epoch": 1.0333611342785656,
+      "grad_norm": 0.2458791941756008,
+      "learning_rate": 8.293055279207503e-06,
+      "loss": 1.0889,
+      "step": 154
+    },
+    {
+      "epoch": 1.0400333611342785,
+      "grad_norm": 0.31147103624378575,
+      "learning_rate": 8.263552076227048e-06,
+      "loss": 0.9933,
+      "step": 155
+    },
+    {
+      "epoch": 1.0467055879899916,
+      "grad_norm": 0.2672690864798242,
+      "learning_rate": 8.233849560085994e-06,
+      "loss": 1.0815,
+      "step": 156
+    },
+    {
+      "epoch": 1.0533778148457047,
+      "grad_norm": 0.2422074236035313,
+      "learning_rate": 8.203949544790131e-06,
+      "loss": 1.1015,
+      "step": 157
+    },
+    {
+      "epoch": 1.0600500417014178,
+      "grad_norm": 0.27579765876295836,
+      "learning_rate": 8.173853856407011e-06,
+      "loss": 1.0386,
+      "step": 158
+    },
+    {
+      "epoch": 1.066722268557131,
+      "grad_norm": 0.25869695071730053,
+      "learning_rate": 8.143564332954426e-06,
+      "loss": 1.0408,
+      "step": 159
+    },
+    {
+      "epoch": 1.073394495412844,
+      "grad_norm": 0.2902505945569461,
+      "learning_rate": 8.113082824288145e-06,
+      "loss": 1.0253,
+      "step": 160
+    },
+    {
+      "epoch": 1.0800667222685572,
+      "grad_norm": 0.23657511088258748,
+      "learning_rate": 8.082411191988956e-06,
+      "loss": 1.0282,
+      "step": 161
+    },
+    {
+      "epoch": 1.0867389491242703,
+      "grad_norm": 0.2841268408399986,
+      "learning_rate": 8.051551309248961e-06,
+      "loss": 1.1055,
+      "step": 162
+    },
+    {
+      "epoch": 1.0934111759799834,
+      "grad_norm": 0.26372063674010376,
+      "learning_rate": 8.02050506075718e-06,
+      "loss": 1.0589,
+      "step": 163
+    },
+    {
+      "epoch": 1.1000834028356965,
+      "grad_norm": 0.27690358093295814,
+      "learning_rate": 7.989274342584446e-06,
+      "loss": 0.949,
+      "step": 164
+    },
+    {
+      "epoch": 1.1067556296914094,
+      "grad_norm": 0.2712773483518729,
+      "learning_rate": 7.957861062067614e-06,
+      "loss": 1.0729,
+      "step": 165
+    },
+    {
+      "epoch": 1.1134278565471225,
+      "grad_norm": 0.30516214609809805,
+      "learning_rate": 7.926267137693066e-06,
+      "loss": 1.037,
+      "step": 166
+    },
+    {
+      "epoch": 1.1201000834028356,
+      "grad_norm": 0.2576349226719825,
+      "learning_rate": 7.894494498979558e-06,
+      "loss": 1.0497,
+      "step": 167
+    },
+    {
+      "epoch": 1.1267723102585487,
+      "grad_norm": 0.24801992242605783,
+      "learning_rate": 7.86254508636036e-06,
+      "loss": 1.0313,
+      "step": 168
+    },
+    {
+      "epoch": 1.1334445371142619,
+      "grad_norm": 0.3166344694109662,
+      "learning_rate": 7.830420851064767e-06,
+      "loss": 1.0967,
+      "step": 169
+    },
+    {
+      "epoch": 1.140116763969975,
+      "grad_norm": 0.24751199793145093,
+      "learning_rate": 7.798123754998922e-06,
+      "loss": 1.0031,
+      "step": 170
+    },
+    {
+      "epoch": 1.146788990825688,
+      "grad_norm": 0.2586884189404244,
+      "learning_rate": 7.765655770625997e-06,
+      "loss": 1.0219,
+      "step": 171
+    },
+    {
+      "epoch": 1.1534612176814012,
+      "grad_norm": 0.235632902703973,
+      "learning_rate": 7.733018880845747e-06,
+      "loss": 1.0207,
+      "step": 172
+    },
+    {
+      "epoch": 1.1601334445371143,
+      "grad_norm": 0.25234095064849044,
+      "learning_rate": 7.70021507887338e-06,
+      "loss": 1.0061,
+      "step": 173
+    },
+    {
+      "epoch": 1.1668056713928274,
+      "grad_norm": 0.2326635498094972,
+      "learning_rate": 7.667246368117852e-06,
+      "loss": 1.0587,
+      "step": 174
+    },
+    {
+      "epoch": 1.1734778982485405,
+      "grad_norm": 0.2649027893834019,
+      "learning_rate": 7.634114762059504e-06,
+      "loss": 0.9703,
+      "step": 175
+    },
+    {
+      "epoch": 1.1801501251042534,
+      "grad_norm": 0.2728476550775381,
+      "learning_rate": 7.600822284127091e-06,
+      "loss": 1.0392,
+      "step": 176
+    },
+    {
+      "epoch": 1.1868223519599665,
+      "grad_norm": 0.24549914761915478,
+      "learning_rate": 7.56737096757421e-06,
+      "loss": 0.9954,
+      "step": 177
+    },
+    {
+      "epoch": 1.1934945788156797,
+      "grad_norm": 0.2815251829331306,
+      "learning_rate": 7.533762855355126e-06,
+      "loss": 1.0291,
+      "step": 178
+    },
+    {
+      "epoch": 1.2001668056713928,
+      "grad_norm": 0.26632117503517927,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.1419,
+      "step": 179
+    },
+    {
+      "epoch": 1.206839032527106,
+      "grad_norm": 0.2966134642339934,
+      "learning_rate": 7.466084463489537e-06,
+      "loss": 1.0036,
+      "step": 180
+    },
+    {
+      "epoch": 1.213511259382819,
+      "grad_norm": 0.26223635549866403,
+      "learning_rate": 7.432018317129056e-06,
+      "loss": 1.0285,
+      "step": 181
+    },
+    {
+      "epoch": 1.2201834862385321,
+      "grad_norm": 0.30911626688190436,
+      "learning_rate": 7.39780364142199e-06,
+      "loss": 1.0041,
+      "step": 182
+    },
+    {
+      "epoch": 1.2268557130942452,
+      "grad_norm": 0.283762152043488,
+      "learning_rate": 7.363442525942827e-06,
+      "loss": 1.0517,
+      "step": 183
+    },
+    {
+      "epoch": 1.2335279399499584,
+      "grad_norm": 0.3425818937559889,
+      "learning_rate": 7.32893706920949e-06,
+      "loss": 1.0177,
+      "step": 184
+    },
+    {
+      "epoch": 1.2402001668056715,
+      "grad_norm": 0.35518044492578266,
+      "learning_rate": 7.294289378555179e-06,
+      "loss": 1.039,
+      "step": 185
+    },
+    {
+      "epoch": 1.2468723936613846,
+      "grad_norm": 0.2953658322519591,
+      "learning_rate": 7.25950156999967e-06,
+      "loss": 1.0239,
+      "step": 186
+    },
+    {
+      "epoch": 1.2535446205170975,
+      "grad_norm": 0.30127312537141965,
+      "learning_rate": 7.2245757681200835e-06,
+      "loss": 0.9763,
+      "step": 187
+    },
+    {
+      "epoch": 1.2602168473728108,
+      "grad_norm": 0.282352211179054,
+      "learning_rate": 7.189514105921132e-06,
+      "loss": 0.991,
+      "step": 188
+    },
+    {
+      "epoch": 1.2668890742285237,
+      "grad_norm": 0.27942599700546883,
+      "learning_rate": 7.1543187247048525e-06,
+      "loss": 0.9997,
+      "step": 189
+    },
+    {
+      "epoch": 1.2735613010842368,
+      "grad_norm": 0.34032643799945067,
+      "learning_rate": 7.118991773939832e-06,
+      "loss": 1.0323,
+      "step": 190
+    },
+    {
+      "epoch": 1.28023352793995,
+      "grad_norm": 0.2833978681025291,
+      "learning_rate": 7.083535411129934e-06,
+      "loss": 0.965,
+      "step": 191
+    },
+    {
+      "epoch": 1.286905754795663,
+      "grad_norm": 0.28066028962170614,
+      "learning_rate": 7.047951801682533e-06,
+      "loss": 0.9827,
+      "step": 192
+    },
+    {
+      "epoch": 1.2935779816513762,
+      "grad_norm": 0.3451242223474228,
+      "learning_rate": 7.01224311877627e-06,
+      "loss": 1.013,
+      "step": 193
+    },
+    {
+      "epoch": 1.3002502085070893,
+      "grad_norm": 0.28576160899229214,
+      "learning_rate": 6.976411543228328e-06,
+      "loss": 1.0147,
+      "step": 194
+    },
+    {
+      "epoch": 1.3069224353628024,
+      "grad_norm": 0.26405586969472095,
+      "learning_rate": 6.9404592633612486e-06,
+      "loss": 1.0222,
+      "step": 195
+    },
+    {
+      "epoch": 1.3135946622185155,
+      "grad_norm": 0.23979743466387593,
+      "learning_rate": 6.904388474869284e-06,
+      "loss": 0.9763,
+      "step": 196
+    },
+    {
+      "epoch": 1.3202668890742286,
+      "grad_norm": 0.26278250196725494,
+      "learning_rate": 6.8682013806842985e-06,
+      "loss": 1.0177,
+      "step": 197
+    },
+    {
+      "epoch": 1.3269391159299415,
+      "grad_norm": 0.3616613201338565,
+      "learning_rate": 6.831900190841232e-06,
+      "loss": 1.0189,
+      "step": 198
+    },
+    {
+      "epoch": 1.3336113427856546,
+      "grad_norm": 0.317805954218629,
+      "learning_rate": 6.795487122343124e-06,
+      "loss": 1.0761,
+      "step": 199
+    },
+    {
+      "epoch": 1.3402835696413677,
+      "grad_norm": 0.3267310563691638,
+      "learning_rate": 6.758964399025721e-06,
+      "loss": 1.0103,
+      "step": 200
+    },
+    {
+      "epoch": 1.3469557964970809,
+      "grad_norm": 0.3367394677015302,
+      "learning_rate": 6.722334251421665e-06,
+      "loss": 0.9504,
+      "step": 201
+    },
+    {
+      "epoch": 1.353628023352794,
+      "grad_norm": 0.323985054612315,
+      "learning_rate": 6.685598916624254e-06,
+      "loss": 1.0425,
+      "step": 202
+    },
+    {
+      "epoch": 1.360300250208507,
+      "grad_norm": 0.31744623672148714,
+      "learning_rate": 6.648760638150833e-06,
+      "loss": 1.0284,
+      "step": 203
+    },
+    {
+      "epoch": 1.3669724770642202,
+      "grad_norm": 0.32506007928496355,
+      "learning_rate": 6.611821665805769e-06,
+      "loss": 1.0494,
+      "step": 204
+    },
+    {
+      "epoch": 1.3736447039199333,
+      "grad_norm": 0.31683692701232863,
+      "learning_rate": 6.574784255543052e-06,
+      "loss": 0.9341,
+      "step": 205
+    },
+    {
+      "epoch": 1.3803169307756464,
+      "grad_norm": 0.339014481901513,
+      "learning_rate": 6.537650669328518e-06,
+      "loss": 0.9351,
+      "step": 206
+    },
+    {
+      "epoch": 1.3869891576313595,
+      "grad_norm": 0.2908501088905977,
+      "learning_rate": 6.500423175001705e-06,
+      "loss": 0.9636,
+      "step": 207
+    },
+    {
+      "epoch": 1.3936613844870727,
+      "grad_norm": 0.29622441402682287,
+      "learning_rate": 6.4631040461373494e-06,
+      "loss": 0.991,
+      "step": 208
+    },
+    {
+      "epoch": 1.4003336113427856,
+      "grad_norm": 0.259706989545213,
+      "learning_rate": 6.4256955619065375e-06,
+      "loss": 1.0265,
+      "step": 209
+    },
+    {
+      "epoch": 1.4070058381984987,
+      "grad_norm": 0.27351346614577177,
+      "learning_rate": 6.388200006937503e-06,
+      "loss": 1.1127,
+      "step": 210
+    },
+    {
+      "epoch": 1.4136780650542118,
+      "grad_norm": 0.2569362561775431,
+      "learning_rate": 6.350619671176111e-06,
+      "loss": 0.9848,
+      "step": 211
+    },
+    {
+      "epoch": 1.420350291909925,
+      "grad_norm": 0.3031398363213745,
+      "learning_rate": 6.312956849745993e-06,
+      "loss": 1.0439,
+      "step": 212
+    },
+    {
+      "epoch": 1.427022518765638,
+      "grad_norm": 0.29741800552671255,
+      "learning_rate": 6.275213842808383e-06,
+      "loss": 1.0295,
+      "step": 213
+    },
+    {
+      "epoch": 1.4336947456213511,
+      "grad_norm": 0.2858593332853522,
+      "learning_rate": 6.237392955421644e-06,
+      "loss": 0.9632,
+      "step": 214
+    },
+    {
+      "epoch": 1.4403669724770642,
+      "grad_norm": 0.2717253920058818,
+      "learning_rate": 6.19949649740049e-06,
+      "loss": 0.9708,
+      "step": 215
+    },
+    {
+      "epoch": 1.4470391993327774,
+      "grad_norm": 0.2755282096882548,
+      "learning_rate": 6.161526783174917e-06,
+      "loss": 1.0894,
+      "step": 216
+    },
+    {
+      "epoch": 1.4537114261884905,
+      "grad_norm": 0.277037632676125,
+      "learning_rate": 6.123486131648859e-06,
+      "loss": 1.0682,
+      "step": 217
+    },
+    {
+      "epoch": 1.4603836530442034,
+      "grad_norm": 0.3020180443959382,
+      "learning_rate": 6.085376866058569e-06,
+      "loss": 1.0672,
+      "step": 218
+    },
+    {
+      "epoch": 1.4670558798999167,
+      "grad_norm": 0.2819163434265071,
+      "learning_rate": 6.047201313830724e-06,
+      "loss": 0.9994,
+      "step": 219
+    },
+    {
+      "epoch": 1.4737281067556296,
+      "grad_norm": 0.2800183935957482,
+      "learning_rate": 6.0089618064402896e-06,
+      "loss": 1.022,
+      "step": 220
+    },
+    {
+      "epoch": 1.4804003336113427,
+      "grad_norm": 0.2719182825453672,
+      "learning_rate": 5.970660679268139e-06,
+      "loss": 1.0183,
+      "step": 221
+    },
+    {
+      "epoch": 1.4870725604670558,
+      "grad_norm": 0.2922309116254843,
+      "learning_rate": 5.932300271458406e-06,
+      "loss": 0.9777,
+      "step": 222
+    },
+    {
+      "epoch": 1.493744787322769,
+      "grad_norm": 0.2744738064356238,
+      "learning_rate": 5.893882925775648e-06,
+      "loss": 0.9841,
+      "step": 223
+    },
+    {
+      "epoch": 1.500417014178482,
+      "grad_norm": 0.2618241413789887,
+      "learning_rate": 5.85541098846175e-06,
+      "loss": 0.9789,
+      "step": 224
+    },
+    {
+      "epoch": 1.5070892410341952,
+      "grad_norm": 0.29331697175604643,
+      "learning_rate": 5.816886809092651e-06,
+      "loss": 0.9889,
+      "step": 225
+    },
+    {
+      "epoch": 1.5137614678899083,
+      "grad_norm": 0.293938259486948,
+      "learning_rate": 5.778312740434835e-06,
+      "loss": 1.0398,
+      "step": 226
+    },
+    {
+      "epoch": 1.5204336947456214,
+      "grad_norm": 0.3149805373750932,
+      "learning_rate": 5.73969113830165e-06,
+      "loss": 1.0356,
+      "step": 227
+    },
+    {
+      "epoch": 1.5271059216013345,
+      "grad_norm": 0.2882296792753476,
+      "learning_rate": 5.701024361409431e-06,
+      "loss": 1.066,
+      "step": 228
+    },
+    {
+      "epoch": 1.5337781484570474,
+      "grad_norm": 0.3264587076590878,
+      "learning_rate": 5.66231477123344e-06,
+      "loss": 0.9717,
+      "step": 229
+    },
+    {
+      "epoch": 1.5404503753127607,
+      "grad_norm": 0.28816187489358347,
+      "learning_rate": 5.623564731863664e-06,
+      "loss": 1.0055,
+      "step": 230
+    },
+    {
+      "epoch": 1.5471226021684736,
+      "grad_norm": 0.26876813399349714,
+      "learning_rate": 5.584776609860414e-06,
+      "loss": 1.0118,
+      "step": 231
+    },
+    {
+      "epoch": 1.553794829024187,
+      "grad_norm": 0.25656136721296807,
+      "learning_rate": 5.545952774109798e-06,
+      "loss": 1.0441,
+      "step": 232
+    },
+    {
+      "epoch": 1.5604670558798999,
+      "grad_norm": 0.2927283912839115,
+      "learning_rate": 5.507095595679059e-06,
+      "loss": 0.9875,
+      "step": 233
+    },
+    {
+      "epoch": 1.567139282735613,
+      "grad_norm": 0.26847113941733736,
+      "learning_rate": 5.468207447671755e-06,
+      "loss": 0.942,
+      "step": 234
+    },
+    {
+      "epoch": 1.573811509591326,
+      "grad_norm": 0.35285592222755574,
+      "learning_rate": 5.42929070508283e-06,
+      "loss": 1.0382,
+      "step": 235
+    },
+    {
+      "epoch": 1.5804837364470392,
+      "grad_norm": 0.28225631872241425,
+      "learning_rate": 5.390347744653576e-06,
+      "loss": 1.0041,
+      "step": 236
+    },
+    {
+      "epoch": 1.5871559633027523,
+      "grad_norm": 0.2894670959272741,
+      "learning_rate": 5.351380944726465e-06,
+      "loss": 1.0017,
+      "step": 237
+    },
+    {
+      "epoch": 1.5938281901584654,
+      "grad_norm": 0.28265496307817667,
+      "learning_rate": 5.312392685099915e-06,
+      "loss": 1.0073,
+      "step": 238
+    },
+    {
+      "epoch": 1.6005004170141786,
+      "grad_norm": 0.3412461315872378,
+      "learning_rate": 5.2733853468829295e-06,
+      "loss": 0.9839,
+      "step": 239
+    },
+    {
+      "epoch": 1.6071726438698914,
+      "grad_norm": 0.2954038595818766,
+      "learning_rate": 5.234361312349701e-06,
+      "loss": 1.0132,
+      "step": 240
+    },
+    {
+      "epoch": 1.6138448707256048,
+      "grad_norm": 0.2840364660523181,
+      "learning_rate": 5.195322964794098e-06,
+      "loss": 0.9473,
+      "step": 241
+    },
+    {
+      "epoch": 1.6205170975813177,
+      "grad_norm": 0.2986907397693315,
+      "learning_rate": 5.156272688384123e-06,
+      "loss": 1.0077,
+      "step": 242
+    },
+    {
+      "epoch": 1.627189324437031,
+      "grad_norm": 0.292176824846797,
+      "learning_rate": 5.117212868016303e-06,
+      "loss": 0.9315,
+      "step": 243
+    },
+    {
+      "epoch": 1.633861551292744,
+      "grad_norm": 0.3135774476957044,
+      "learning_rate": 5.07814588917004e-06,
+      "loss": 1.0088,
+      "step": 244
+    },
+    {
+      "epoch": 1.640533778148457,
+      "grad_norm": 0.31002794668270833,
+      "learning_rate": 5.03907413776192e-06,
+      "loss": 1.007,
+      "step": 245
+    },
+    {
+      "epoch": 1.6472060050041701,
+      "grad_norm": 0.3045456413966571,
+      "learning_rate": 5e-06,
+      "loss": 0.9872,
+      "step": 246
+    },
+    {
+      "epoch": 1.6538782318598833,
+      "grad_norm": 0.344623415610902,
+      "learning_rate": 4.96092586223808e-06,
+      "loss": 0.9343,
+      "step": 247
+    },
+    {
+      "epoch": 1.6605504587155964,
+      "grad_norm": 0.2888473591105003,
+      "learning_rate": 4.921854110829962e-06,
+      "loss": 1.0071,
+      "step": 248
+    },
+    {
+      "epoch": 1.6672226855713093,
+      "grad_norm": 0.3424869438582918,
+      "learning_rate": 4.882787131983698e-06,
+      "loss": 1.0513,
+      "step": 249
+    },
+    {
+      "epoch": 1.6738949124270226,
+      "grad_norm": 0.3044802192543269,
+      "learning_rate": 4.84372731161588e-06,
+      "loss": 1.0034,
+      "step": 250
+    },
+    {
+      "epoch": 1.6805671392827355,
+      "grad_norm": 0.3676369886348423,
+      "learning_rate": 4.804677035205903e-06,
+      "loss": 1.0679,
+      "step": 251
+    },
+    {
+      "epoch": 1.6872393661384488,
+      "grad_norm": 0.2821236895464674,
+      "learning_rate": 4.765638687650299e-06,
+      "loss": 0.9711,
+      "step": 252
+    },
+    {
+      "epoch": 1.6939115929941617,
+      "grad_norm": 0.32097634201487724,
+      "learning_rate": 4.726614653117071e-06,
+      "loss": 1.0368,
+      "step": 253
+    },
+    {
+      "epoch": 1.700583819849875,
+      "grad_norm": 0.30833620328617434,
+      "learning_rate": 4.687607314900087e-06,
+      "loss": 0.9419,
+      "step": 254
+    },
+    {
+      "epoch": 1.707256046705588,
+      "grad_norm": 0.3161695903169762,
+      "learning_rate": 4.6486190552735375e-06,
+      "loss": 0.947,
+      "step": 255
+    },
+    {
+      "epoch": 1.713928273561301,
+      "grad_norm": 0.3222992290291398,
+      "learning_rate": 4.6096522553464265e-06,
+      "loss": 0.9391,
+      "step": 256
+    },
+    {
+      "epoch": 1.7206005004170142,
+      "grad_norm": 0.27889539086250337,
+      "learning_rate": 4.57070929491717e-06,
+      "loss": 1.0359,
+      "step": 257
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 0.2916579428323436,
+      "learning_rate": 4.531792552328247e-06,
+      "loss": 1.0094,
+      "step": 258
+    },
+    {
+      "epoch": 1.7339449541284404,
+      "grad_norm": 0.24997244028612386,
+      "learning_rate": 4.492904404320942e-06,
+      "loss": 0.7959,
+      "step": 259
+    },
+    {
+      "epoch": 1.7406171809841533,
+      "grad_norm": 0.29868404836632323,
+      "learning_rate": 4.454047225890204e-06,
+      "loss": 1.0109,
+      "step": 260
+    },
+    {
+      "epoch": 1.7472894078398666,
+      "grad_norm": 0.2969807612243251,
+      "learning_rate": 4.415223390139588e-06,
+      "loss": 0.9875,
+      "step": 261
+    },
+    {
+      "epoch": 1.7539616346955795,
+      "grad_norm": 0.3604232218198932,
+      "learning_rate": 4.3764352681363365e-06,
+      "loss": 0.989,
+      "step": 262
+    },
+    {
+      "epoch": 1.7606338615512929,
+      "grad_norm": 0.36824762919465986,
+      "learning_rate": 4.337685228766561e-06,
+      "loss": 1.0049,
+      "step": 263
+    },
+    {
+      "epoch": 1.7673060884070058,
+      "grad_norm": 0.3500725820945927,
+      "learning_rate": 4.2989756385905715e-06,
+      "loss": 0.9718,
+      "step": 264
+    },
+    {
+      "epoch": 1.773978315262719,
+      "grad_norm": 0.2834505359886034,
+      "learning_rate": 4.260308861698351e-06,
+      "loss": 1.0465,
+      "step": 265
+    },
+    {
+      "epoch": 1.780650542118432,
+      "grad_norm": 0.3576818688058849,
+      "learning_rate": 4.221687259565166e-06,
+      "loss": 1.0372,
+      "step": 266
+    },
+    {
+      "epoch": 1.787322768974145,
+      "grad_norm": 0.31757170580776606,
+      "learning_rate": 4.183113190907349e-06,
+      "loss": 0.9565,
+      "step": 267
+    },
+    {
+      "epoch": 1.7939949958298582,
+      "grad_norm": 0.3231504978728471,
+      "learning_rate": 4.144589011538251e-06,
+      "loss": 0.9622,
+      "step": 268
+    },
+    {
+      "epoch": 1.8006672226855713,
+      "grad_norm": 0.30845575748951204,
+      "learning_rate": 4.106117074224354e-06,
+      "loss": 1.0258,
+      "step": 269
+    },
+    {
+      "epoch": 1.8073394495412844,
+      "grad_norm": 0.30421622601970244,
+      "learning_rate": 4.067699728541595e-06,
+      "loss": 1.0356,
+      "step": 270
+    },
+    {
+      "epoch": 1.8140116763969973,
+      "grad_norm": 0.2920513251222264,
+      "learning_rate": 4.029339320731862e-06,
+      "loss": 0.9939,
+      "step": 271
+    },
+    {
+      "epoch": 1.8206839032527107,
+      "grad_norm": 0.27807604400588937,
+      "learning_rate": 3.99103819355971e-06,
+      "loss": 0.9878,
+      "step": 272
+    },
+    {
+      "epoch": 1.8273561301084236,
+      "grad_norm": 0.3266996176440113,
+      "learning_rate": 3.952798686169279e-06,
+      "loss": 1.0041,
+      "step": 273
+    },
+    {
+      "epoch": 1.834028356964137,
+      "grad_norm": 0.3053490567275808,
+      "learning_rate": 3.914623133941432e-06,
+      "loss": 0.9872,
+      "step": 274
+    },
+    {
+      "epoch": 1.8407005838198498,
+      "grad_norm": 0.31477790189099164,
+      "learning_rate": 3.876513868351142e-06,
+      "loss": 0.9359,
+      "step": 275
+    },
+    {
+      "epoch": 1.847372810675563,
+      "grad_norm": 0.27149053344889523,
+      "learning_rate": 3.838473216825085e-06,
+      "loss": 1.0067,
+      "step": 276
+    },
+    {
+      "epoch": 1.854045037531276,
+      "grad_norm": 0.3204843702460214,
+      "learning_rate": 3.800503502599511e-06,
+      "loss": 0.9585,
+      "step": 277
+    },
+    {
+      "epoch": 1.8607172643869891,
+      "grad_norm": 0.3498778905670181,
+      "learning_rate": 3.762607044578357e-06,
+      "loss": 0.9697,
+      "step": 278
+    },
+    {
+      "epoch": 1.8673894912427023,
+      "grad_norm": 0.3180400555344581,
+      "learning_rate": 3.7247861571916183e-06,
+      "loss": 1.0226,
+      "step": 279
+    },
+    {
+      "epoch": 1.8740617180984154,
+      "grad_norm": 0.3480360514374549,
+      "learning_rate": 3.6870431502540096e-06,
+      "loss": 1.0358,
+      "step": 280
+    },
+    {
+      "epoch": 1.8807339449541285,
+      "grad_norm": 0.3187430568425493,
+      "learning_rate": 3.6493803288238894e-06,
+      "loss": 1.0073,
+      "step": 281
+    },
+    {
+      "epoch": 1.8874061718098414,
+      "grad_norm": 0.3464506380317717,
+      "learning_rate": 3.611799993062497e-06,
+      "loss": 0.943,
+      "step": 282
+    },
+    {
+      "epoch": 1.8940783986655547,
+      "grad_norm": 0.2880834965055193,
+      "learning_rate": 3.5743044380934655e-06,
+      "loss": 0.9721,
+      "step": 283
+    },
+    {
+      "epoch": 1.9007506255212676,
+      "grad_norm": 0.3210835495717625,
+      "learning_rate": 3.536895953862652e-06,
+      "loss": 1.0209,
+      "step": 284
+    },
+    {
+      "epoch": 1.907422852376981,
+      "grad_norm": 0.3047811453432249,
+      "learning_rate": 3.4995768249982975e-06,
+      "loss": 1.0284,
+      "step": 285
+    },
+    {
+      "epoch": 1.9140950792326938,
+      "grad_norm": 0.35570769296041677,
+      "learning_rate": 3.462349330671484e-06,
+      "loss": 0.9161,
+      "step": 286
+    },
+    {
+      "epoch": 1.920767306088407,
+      "grad_norm": 0.35749623557347504,
+      "learning_rate": 3.4252157444569478e-06,
+      "loss": 0.9152,
+      "step": 287
+    },
+    {
+      "epoch": 1.92743953294412,
+      "grad_norm": 0.3377788624601496,
+      "learning_rate": 3.388178334194232e-06,
+      "loss": 0.925,
+      "step": 288
+    },
+    {
+      "epoch": 1.9341117597998332,
+      "grad_norm": 0.3798661249068725,
+      "learning_rate": 3.351239361849168e-06,
+      "loss": 0.9846,
+      "step": 289
+    },
+    {
+      "epoch": 1.9407839866555463,
+      "grad_norm": 0.29999286355310334,
+      "learning_rate": 3.314401083375748e-06,
+      "loss": 0.9753,
+      "step": 290
+    },
+    {
+      "epoch": 1.9474562135112594,
+      "grad_norm": 0.35781167804812974,
+      "learning_rate": 3.2776657485783357e-06,
+      "loss": 0.9487,
+      "step": 291
+    },
+    {
+      "epoch": 1.9541284403669725,
+      "grad_norm": 0.3084397268778666,
+      "learning_rate": 3.2410356009742784e-06,
+      "loss": 1.0787,
+      "step": 292
+    },
+    {
+      "epoch": 1.9608006672226854,
+      "grad_norm": 0.317448351646333,
+      "learning_rate": 3.2045128776568783e-06,
+      "loss": 0.9257,
+      "step": 293
+    },
+    {
+      "epoch": 1.9674728940783988,
+      "grad_norm": 0.3686880962008835,
+      "learning_rate": 3.168099809158769e-06,
+      "loss": 0.9529,
+      "step": 294
+    },
+    {
+      "epoch": 1.9741451209341117,
+      "grad_norm": 0.30324127420271724,
+      "learning_rate": 3.1317986193157023e-06,
+      "loss": 0.9185,
+      "step": 295
+    },
+    {
+      "epoch": 1.980817347789825,
+      "grad_norm": 0.3439386421881959,
+      "learning_rate": 3.095611525130716e-06,
+      "loss": 1.1113,
+      "step": 296
+    },
+    {
+      "epoch": 1.9874895746455379,
+      "grad_norm": 0.31828525154875525,
+      "learning_rate": 3.059540736638751e-06,
+      "loss": 0.9624,
+      "step": 297
+    },
+    {
+      "epoch": 1.994161801501251,
+      "grad_norm": 0.3528601662749728,
+      "learning_rate": 3.023588456771674e-06,
+      "loss": 1.025,
+      "step": 298
+    },
+    {
+      "epoch": 2.006672226855713,
+      "grad_norm": 1.0381811083452561,
+      "learning_rate": 2.9877568812237325e-06,
+      "loss": 1.8823,
+      "step": 299
+    },
+    {
+      "epoch": 2.0133444537114262,
+      "grad_norm": 0.28745904791303756,
+      "learning_rate": 2.9520481983174675e-06,
+      "loss": 1.0051,
+      "step": 300
+    },
+    {
+      "epoch": 2.020016680567139,
+      "grad_norm": 0.3037470770313497,
+      "learning_rate": 2.916464588870067e-06,
+      "loss": 1.0253,
+      "step": 301
+    },
+    {
+      "epoch": 2.0266889074228525,
+      "grad_norm": 0.3264286058702715,
+      "learning_rate": 2.881008226060168e-06,
+      "loss": 0.9722,
+      "step": 302
+    },
+    {
+      "epoch": 2.0333611342785654,
+      "grad_norm": 0.3168792873407282,
+      "learning_rate": 2.8456812752951483e-06,
+      "loss": 0.9199,
+      "step": 303
+    },
+    {
+      "epoch": 2.0400333611342787,
+      "grad_norm": 0.3658230155927171,
+      "learning_rate": 2.8104858940788705e-06,
+      "loss": 0.9747,
+      "step": 304
+    },
+    {
+      "epoch": 2.0467055879899916,
+      "grad_norm": 0.3196066484806665,
+      "learning_rate": 2.7754242318799174e-06,
+      "loss": 0.9597,
+      "step": 305
+    },
+    {
+      "epoch": 2.053377814845705,
+      "grad_norm": 0.36214258330419746,
+      "learning_rate": 2.740498430000332e-06,
+      "loss": 0.9637,
+      "step": 306
+    },
+    {
+      "epoch": 2.060050041701418,
+      "grad_norm": 0.32144023431445257,
+      "learning_rate": 2.7057106214448216e-06,
+      "loss": 1.0071,
+      "step": 307
+    },
+    {
+      "epoch": 2.066722268557131,
+      "grad_norm": 0.31788167947698615,
+      "learning_rate": 2.671062930790511e-06,
+      "loss": 0.9324,
+      "step": 308
+    },
+    {
+      "epoch": 2.073394495412844,
+      "grad_norm": 0.32411973935094873,
+      "learning_rate": 2.636557474057173e-06,
+      "loss": 0.9213,
+      "step": 309
+    },
+    {
+      "epoch": 2.080066722268557,
+      "grad_norm": 0.3061895381140455,
+      "learning_rate": 2.6021963585780106e-06,
+      "loss": 0.9829,
+      "step": 310
+    },
+    {
+      "epoch": 2.0867389491242703,
+      "grad_norm": 0.2829970996541261,
+      "learning_rate": 2.567981682870946e-06,
+      "loss": 1.0112,
+      "step": 311
+    },
+    {
+      "epoch": 2.093411175979983,
+      "grad_norm": 0.3251773046313095,
+      "learning_rate": 2.533915536510464e-06,
+      "loss": 0.962,
+      "step": 312
+    },
+    {
+      "epoch": 2.1000834028356965,
+      "grad_norm": 0.3117638913905796,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 1.0286,
+      "step": 313
+    },
+    {
+      "epoch": 2.1067556296914094,
+      "grad_norm": 0.3055554951200164,
+      "learning_rate": 2.466237144644874e-06,
+      "loss": 0.9782,
+      "step": 314
+    },
+    {
+      "epoch": 2.1134278565471227,
+      "grad_norm": 0.3093110501459989,
+      "learning_rate": 2.4326290324257896e-06,
+      "loss": 1.0203,
+      "step": 315
+    },
+    {
+      "epoch": 2.1201000834028356,
+      "grad_norm": 0.348167844578145,
+      "learning_rate": 2.3991777158729102e-06,
+      "loss": 0.9729,
+      "step": 316
+    },
+    {
+      "epoch": 2.126772310258549,
+      "grad_norm": 0.35896036414914057,
+      "learning_rate": 2.3658852379404973e-06,
+      "loss": 0.9687,
+      "step": 317
+    },
+    {
+      "epoch": 2.133444537114262,
+      "grad_norm": 0.33836897224758,
+      "learning_rate": 2.3327536318821496e-06,
+      "loss": 0.979,
+      "step": 318
+    },
+    {
+      "epoch": 2.140116763969975,
+      "grad_norm": 0.37686877855977563,
+      "learning_rate": 2.299784921126622e-06,
+      "loss": 0.9513,
+      "step": 319
+    },
+    {
+      "epoch": 2.146788990825688,
+      "grad_norm": 0.355801020401147,
+      "learning_rate": 2.2669811191542547e-06,
+      "loss": 0.9859,
+      "step": 320
+    },
+    {
+      "epoch": 2.153461217681401,
+      "grad_norm": 0.3010215082303293,
+      "learning_rate": 2.234344229374003e-06,
+      "loss": 0.9951,
+      "step": 321
+    },
+    {
+      "epoch": 2.1601334445371143,
+      "grad_norm": 0.32911989661603686,
+      "learning_rate": 2.20187624500108e-06,
+      "loss": 0.9708,
+      "step": 322
+    },
+    {
+      "epoch": 2.166805671392827,
+      "grad_norm": 0.3623670709775593,
+      "learning_rate": 2.1695791489352346e-06,
+      "loss": 0.9734,
+      "step": 323
+    },
+    {
+      "epoch": 2.1734778982485405,
+      "grad_norm": 0.31909897986159624,
+      "learning_rate": 2.1374549136396417e-06,
+      "loss": 0.9517,
+      "step": 324
+    },
+    {
+      "epoch": 2.1801501251042534,
+      "grad_norm": 0.31749439512516914,
+      "learning_rate": 2.1055055010204427e-06,
+      "loss": 0.9848,
+      "step": 325
+    },
+    {
+      "epoch": 2.1868223519599668,
+      "grad_norm": 0.29264160902990144,
+      "learning_rate": 2.073732862306935e-06,
+      "loss": 1.0053,
+      "step": 326
+    },
+    {
+      "epoch": 2.1934945788156797,
+      "grad_norm": 0.3668210964835384,
+      "learning_rate": 2.042138937932388e-06,
+      "loss": 1.0157,
+      "step": 327
+    },
+    {
+      "epoch": 2.200166805671393,
+      "grad_norm": 0.3133785285507638,
+      "learning_rate": 2.0107256574155564e-06,
+      "loss": 0.9808,
+      "step": 328
+    },
+    {
+      "epoch": 2.206839032527106,
+      "grad_norm": 0.3124366924714227,
+      "learning_rate": 1.979494939242822e-06,
+      "loss": 0.979,
+      "step": 329
+    },
+    {
+      "epoch": 2.213511259382819,
+      "grad_norm": 0.29545310894796867,
+      "learning_rate": 1.9484486907510405e-06,
+      "loss": 0.997,
+      "step": 330
+    },
+    {
+      "epoch": 2.220183486238532,
+      "grad_norm": 0.32367677669293343,
+      "learning_rate": 1.917588808011045e-06,
+      "loss": 0.8975,
+      "step": 331
+    },
+    {
+      "epoch": 2.226855713094245,
+      "grad_norm": 0.3299013625375276,
+      "learning_rate": 1.8869171757118554e-06,
+      "loss": 1.0025,
+      "step": 332
+    },
+    {
+      "epoch": 2.2335279399499584,
+      "grad_norm": 0.395626306344832,
+      "learning_rate": 1.856435667045577e-06,
+      "loss": 1.0349,
+      "step": 333
+    },
+    {
+      "epoch": 2.2402001668056712,
+      "grad_norm": 0.3255623940901644,
+      "learning_rate": 1.8261461435929895e-06,
+      "loss": 0.9994,
+      "step": 334
+    },
+    {
+      "epoch": 2.2468723936613846,
+      "grad_norm": 0.28569255358940876,
+      "learning_rate": 1.796050455209869e-06,
+      "loss": 0.9491,
+      "step": 335
+    },
+    {
+      "epoch": 2.2535446205170975,
+      "grad_norm": 0.29893680579074805,
+      "learning_rate": 1.7661504399140066e-06,
+      "loss": 0.979,
+      "step": 336
+    },
+    {
+      "epoch": 2.260216847372811,
+      "grad_norm": 0.3459559430460262,
+      "learning_rate": 1.7364479237729526e-06,
+      "loss": 0.9042,
+      "step": 337
+    },
+    {
+      "epoch": 2.2668890742285237,
+      "grad_norm": 0.3113640341471141,
+      "learning_rate": 1.7069447207924994e-06,
+      "loss": 0.9476,
+      "step": 338
+    },
+    {
+      "epoch": 2.273561301084237,
+      "grad_norm": 0.29758501306847707,
+      "learning_rate": 1.677642632805892e-06,
+      "loss": 0.9388,
+      "step": 339
+    },
+    {
+      "epoch": 2.28023352793995,
+      "grad_norm": 0.31704153540027663,
+      "learning_rate": 1.6485434493637915e-06,
+      "loss": 0.9918,
+      "step": 340
+    },
+    {
+      "epoch": 2.2869057547956633,
+      "grad_norm": 0.3475571370836834,
+      "learning_rate": 1.6196489476249777e-06,
+      "loss": 1.0017,
+      "step": 341
+    },
+    {
+      "epoch": 2.293577981651376,
+      "grad_norm": 0.3114674457835494,
+      "learning_rate": 1.5909608922478108e-06,
+      "loss": 1.0053,
+      "step": 342
+    },
+    {
+      "epoch": 2.300250208507089,
+      "grad_norm": 0.30298813780086953,
+      "learning_rate": 1.5624810352824709e-06,
+      "loss": 0.9641,
+      "step": 343
+    },
+    {
+      "epoch": 2.3069224353628024,
+      "grad_norm": 0.35762529414587724,
+      "learning_rate": 1.5342111160639412e-06,
+      "loss": 0.9616,
+      "step": 344
+    },
+    {
+      "epoch": 2.3135946622185153,
+      "grad_norm": 0.37005906694872853,
+      "learning_rate": 1.5061528611057917e-06,
+      "loss": 1.0249,
+      "step": 345
+    },
+    {
+      "epoch": 2.3202668890742286,
+      "grad_norm": 0.30759447735274864,
+      "learning_rate": 1.4783079839947396e-06,
+      "loss": 0.9851,
+      "step": 346
+    },
+    {
+      "epoch": 2.3269391159299415,
+      "grad_norm": 0.3014932344261013,
+      "learning_rate": 1.4506781852859836e-06,
+      "loss": 1.0052,
+      "step": 347
+    },
+    {
+      "epoch": 2.333611342785655,
+      "grad_norm": 0.31167411900209185,
+      "learning_rate": 1.4232651523993635e-06,
+      "loss": 0.956,
+      "step": 348
+    },
+    {
+      "epoch": 2.3402835696413677,
+      "grad_norm": 0.32652379262644254,
+      "learning_rate": 1.3960705595162876e-06,
+      "loss": 0.9825,
+      "step": 349
+    },
+    {
+      "epoch": 2.346955796497081,
+      "grad_norm": 0.3209030562572718,
+      "learning_rate": 1.369096067477505e-06,
+      "loss": 1.0177,
+      "step": 350
+    },
+    {
+      "epoch": 2.353628023352794,
+      "grad_norm": 0.3562229549612574,
+      "learning_rate": 1.3423433236816563e-06,
+      "loss": 0.9955,
+      "step": 351
+    },
+    {
+      "epoch": 2.360300250208507,
+      "grad_norm": 0.31080353838712754,
+      "learning_rate": 1.3158139619846734e-06,
+      "loss": 0.993,
+      "step": 352
+    },
+    {
+      "epoch": 2.36697247706422,
+      "grad_norm": 0.32276338892191286,
+      "learning_rate": 1.289509602599996e-06,
+      "loss": 0.9847,
+      "step": 353
+    },
+    {
+      "epoch": 2.373644703919933,
+      "grad_norm": 0.3162201171120057,
+      "learning_rate": 1.2634318519996148e-06,
+      "loss": 0.9645,
+      "step": 354
+    },
+    {
+      "epoch": 2.3803169307756464,
+      "grad_norm": 0.31907787951020794,
+      "learning_rate": 1.2375823028159667e-06,
+      "loss": 0.9949,
+      "step": 355
+    },
+    {
+      "epoch": 2.3869891576313593,
+      "grad_norm": 0.330999449587722,
+      "learning_rate": 1.2119625337446673e-06,
+      "loss": 0.9617,
+      "step": 356
+    },
+    {
+      "epoch": 2.3936613844870727,
+      "grad_norm": 0.37560901242187644,
+      "learning_rate": 1.186574109448091e-06,
+      "loss": 0.965,
+      "step": 357
+    },
+    {
+      "epoch": 2.4003336113427856,
+      "grad_norm": 0.3032851792093919,
+      "learning_rate": 1.16141858045982e-06,
+      "loss": 0.969,
+      "step": 358
+    },
+    {
+      "epoch": 2.407005838198499,
+      "grad_norm": 0.3120802157192034,
+      "learning_rate": 1.1364974830899438e-06,
+      "loss": 0.9821,
+      "step": 359
+    },
+    {
+      "epoch": 2.413678065054212,
+      "grad_norm": 0.34540220887991835,
+      "learning_rate": 1.1118123393312397e-06,
+      "loss": 0.9535,
+      "step": 360
+    },
+    {
+      "epoch": 2.420350291909925,
+      "grad_norm": 0.29306217474195717,
+      "learning_rate": 1.0873646567662165e-06,
+      "loss": 0.9548,
+      "step": 361
+    },
+    {
+      "epoch": 2.427022518765638,
+      "grad_norm": 0.3275471084256797,
+      "learning_rate": 1.0631559284750398e-06,
+      "loss": 0.9208,
+      "step": 362
+    },
+    {
+      "epoch": 2.4336947456213514,
+      "grad_norm": 0.3237098002556768,
+      "learning_rate": 1.0391876329443534e-06,
+      "loss": 0.9896,
+      "step": 363
+    },
+    {
+      "epoch": 2.4403669724770642,
+      "grad_norm": 0.31683152915795526,
+      "learning_rate": 1.0154612339769777e-06,
+      "loss": 0.9515,
+      "step": 364
+    },
+    {
+      "epoch": 2.447039199332777,
+      "grad_norm": 0.31260220662008054,
+      "learning_rate": 9.919781806025136e-07,
+      "loss": 0.9284,
+      "step": 365
+    },
+    {
+      "epoch": 2.4537114261884905,
+      "grad_norm": 0.3196141247915384,
+      "learning_rate": 9.687399069888515e-07,
+      "loss": 1.0529,
+      "step": 366
+    },
+    {
+      "epoch": 2.4603836530442034,
+      "grad_norm": 0.3390686830414771,
+      "learning_rate": 9.457478323545749e-07,
+      "loss": 0.906,
+      "step": 367
+    },
+    {
+      "epoch": 2.4670558798999167,
+      "grad_norm": 0.2976435803727035,
+      "learning_rate": 9.23003360882293e-07,
+      "loss": 0.9914,
+      "step": 368
+    },
+    {
+      "epoch": 2.4737281067556296,
+      "grad_norm": 0.3256745610569351,
+      "learning_rate": 9.005078816328772e-07,
+      "loss": 0.9923,
+      "step": 369
+    },
+    {
+      "epoch": 2.480400333611343,
+      "grad_norm": 0.3105480823035307,
+      "learning_rate": 8.782627684606332e-07,
+      "loss": 0.9996,
+      "step": 370
+    },
+    {
+      "epoch": 2.487072560467056,
+      "grad_norm": 0.33299836342381517,
+      "learning_rate": 8.562693799293931e-07,
+      "loss": 0.96,
+      "step": 371
+    },
+    {
+      "epoch": 2.493744787322769,
+      "grad_norm": 0.3114815813330825,
+      "learning_rate": 8.345290592295429e-07,
+      "loss": 0.9143,
+      "step": 372
+    },
+    {
+      "epoch": 2.500417014178482,
+      "grad_norm": 0.28937151523319904,
+      "learning_rate": 8.130431340959982e-07,
+      "loss": 0.9746,
+      "step": 373
+    },
+    {
+      "epoch": 2.507089241034195,
+      "grad_norm": 0.32619060975827346,
+      "learning_rate": 7.918129167271055e-07,
+      "loss": 0.9561,
+      "step": 374
+    },
+    {
+      "epoch": 2.5137614678899083,
+      "grad_norm": 0.31360364241751837,
+      "learning_rate": 7.708397037045129e-07,
+      "loss": 0.8092,
+      "step": 375
+    },
+    {
+      "epoch": 2.5204336947456216,
+      "grad_norm": 0.30558210448525414,
+      "learning_rate": 7.50124775913979e-07,
+      "loss": 0.9529,
+      "step": 376
+    },
+    {
+      "epoch": 2.5271059216013345,
+      "grad_norm": 0.32199398622868297,
+      "learning_rate": 7.296693984671465e-07,
+      "loss": 0.9798,
+      "step": 377
+    },
+    {
+      "epoch": 2.5337781484570474,
+      "grad_norm": 0.32592296410779964,
+      "learning_rate": 7.094748206242797e-07,
+      "loss": 1.0314,
+      "step": 378
+    },
+    {
+      "epoch": 2.5404503753127607,
+      "grad_norm": 0.3464187438731346,
+      "learning_rate": 6.895422757179682e-07,
+      "loss": 0.9811,
+      "step": 379
+    },
+    {
+      "epoch": 2.5471226021684736,
+      "grad_norm": 0.36090219930856193,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 0.9489,
+      "step": 380
+    },
+    {
+      "epoch": 2.553794829024187,
+      "grad_norm": 0.31856176752128185,
+      "learning_rate": 6.50468137956049e-07,
+      "loss": 0.9542,
+      "step": 381
+    },
+    {
+      "epoch": 2.5604670558799,
+      "grad_norm": 0.31996625435359055,
+      "learning_rate": 6.313289314542392e-07,
+      "loss": 0.9717,
+      "step": 382
+    },
+    {
+      "epoch": 2.5671392827356128,
+      "grad_norm": 0.3486660778765644,
+      "learning_rate": 6.12456530450844e-07,
+      "loss": 1.047,
+      "step": 383
+    },
+    {
+      "epoch": 2.573811509591326,
+      "grad_norm": 0.40268147548442224,
+      "learning_rate": 5.938520875298587e-07,
+      "loss": 1.0224,
+      "step": 384
+    },
+    {
+      "epoch": 2.5804837364470394,
+      "grad_norm": 0.3676526483372923,
+      "learning_rate": 5.755167389104166e-07,
+      "loss": 0.9871,
+      "step": 385
+    },
+    {
+      "epoch": 2.5871559633027523,
+      "grad_norm": 0.29607309034948626,
+      "learning_rate": 5.574516043774059e-07,
+      "loss": 0.9608,
+      "step": 386
+    },
+    {
+      "epoch": 2.593828190158465,
+      "grad_norm": 0.3351255483218255,
+      "learning_rate": 5.396577872130676e-07,
+      "loss": 0.9818,
+      "step": 387
+    },
+    {
+      "epoch": 2.6005004170141786,
+      "grad_norm": 0.3153076169997922,
+      "learning_rate": 5.221363741296298e-07,
+      "loss": 0.9962,
+      "step": 388
+    },
+    {
+      "epoch": 2.6071726438698914,
+      "grad_norm": 0.3816251930803852,
+      "learning_rate": 5.048884352029271e-07,
+      "loss": 0.9757,
+      "step": 389
+    },
+    {
+      "epoch": 2.613844870725605,
+      "grad_norm": 0.31190657046064496,
+      "learning_rate": 4.879150238070585e-07,
+      "loss": 0.9948,
+      "step": 390
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 447,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 30,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1006502470221824.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-390/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13aa99fb97f6ca47f05e0576e78b2984b387280caa0db367bbae1e4bc36a8891
+size 7544

checkpoint-390/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)

checkpoint-420/README.md

@@ -0,0 +1,202 @@
+---
+base_model: ../Qwen2.5-32B-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-420/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "../Qwen2.5-32B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-420/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5be117c1716dbf19357c3ccc093d69b61e5f7906e0caea7cc4311e65d8c33a9c
+size 134337704

checkpoint-420/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-420/global_step420/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad4f7d09ce65f208fc215fb7e9cc68af97fe04954343d047911f701e2c3d063
+size 268444400

checkpoint-420/global_step420/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13af80f84b2610626bf19621f261fcc4778ee47df20a8c4578d3a66b50c46ab3
+size 268444400

checkpoint-420/global_step420/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32a56182f87035997adf5e5acd4ee925080873c26d4cd828c37907e9271a9c4b
+size 268444400

checkpoint-420/global_step420/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8596d771204226d3a66b45e304b3415a7b74d52f6b2baa46efab2615ae519da0
+size 886126

checkpoint-420/global_step420/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9393b6547729c9b18c7d389a3a699b1f5367f1b6d12dd7c2ecab286062bb16d1
+size 886126

checkpoint-420/global_step420/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8286262169047760e1f5bd23389a0fe1ea63e330639c2d1fa33d5dc7cc407cf1
+size 886126

checkpoint-420/latest

@@ -0,0 +1 @@
+global_step420

checkpoint-420/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2bf9ae13691c39ee7fbd9eb497b0127d60b8594c24b2891098b3739c25d5b1
+size 14768

checkpoint-420/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835f7198d4d5539c74a0ce15e3fbba2ee359088c79e0b77984b34308b954bd63
+size 14768

checkpoint-420/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19325cacb8d362ac4f02fb14163603ec88cb2fa312cb10277c2cad28943bdef3
+size 14768

checkpoint-420/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97884e25997a58d77204aa10e04610c51f5b473dc04a55a332343d9debbcdf6e
+size 1064

checkpoint-420/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-420/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-420/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-420/trainer_state.json

@@ -0,0 +1,2973 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.8140116763969973,
+  "eval_steps": 500,
+  "global_step": 420,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006672226855713094,
+      "grad_norm": 0.3732840765814082,
+      "learning_rate": 2.2222222222222224e-07,
+      "loss": 1.6647,
+      "step": 1
+    },
+    {
+      "epoch": 0.013344453711426188,
+      "grad_norm": 0.383618969512302,
+      "learning_rate": 4.444444444444445e-07,
+      "loss": 1.7073,
+      "step": 2
+    },
+    {
+      "epoch": 0.020016680567139282,
+      "grad_norm": 0.40769314152645725,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 1.7505,
+      "step": 3
+    },
+    {
+      "epoch": 0.026688907422852376,
+      "grad_norm": 0.4016260533661679,
+      "learning_rate": 8.88888888888889e-07,
+      "loss": 1.6952,
+      "step": 4
+    },
+    {
+      "epoch": 0.03336113427856547,
+      "grad_norm": 0.40174340733938796,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 1.7844,
+      "step": 5
+    },
+    {
+      "epoch": 0.040033361134278564,
+      "grad_norm": 0.40847133525152324,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 1.7765,
+      "step": 6
+    },
+    {
+      "epoch": 0.04670558798999166,
+      "grad_norm": 0.40604889051688275,
+      "learning_rate": 1.5555555555555558e-06,
+      "loss": 1.6995,
+      "step": 7
+    },
+    {
+      "epoch": 0.05337781484570475,
+      "grad_norm": 0.3894313779958969,
+      "learning_rate": 1.777777777777778e-06,
+      "loss": 1.7128,
+      "step": 8
+    },
+    {
+      "epoch": 0.060050041701417846,
+      "grad_norm": 0.38627201738251066,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.7789,
+      "step": 9
+    },
+    {
+      "epoch": 0.06672226855713094,
+      "grad_norm": 0.379007955799278,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.6907,
+      "step": 10
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.40293473844915795,
+      "learning_rate": 2.4444444444444447e-06,
+      "loss": 1.712,
+      "step": 11
+    },
+    {
+      "epoch": 0.08006672226855713,
+      "grad_norm": 0.3796921388422985,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 1.717,
+      "step": 12
+    },
+    {
+      "epoch": 0.08673894912427023,
+      "grad_norm": 0.363416530641245,
+      "learning_rate": 2.888888888888889e-06,
+      "loss": 1.6075,
+      "step": 13
+    },
+    {
+      "epoch": 0.09341117597998332,
+      "grad_norm": 0.42180934217352195,
+      "learning_rate": 3.1111111111111116e-06,
+      "loss": 1.7974,
+      "step": 14
+    },
+    {
+      "epoch": 0.10008340283569642,
+      "grad_norm": 0.4120160113974808,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.7485,
+      "step": 15
+    },
+    {
+      "epoch": 0.1067556296914095,
+      "grad_norm": 0.39278536183126506,
+      "learning_rate": 3.555555555555556e-06,
+      "loss": 1.5707,
+      "step": 16
+    },
+    {
+      "epoch": 0.1134278565471226,
+      "grad_norm": 0.4167599840383631,
+      "learning_rate": 3.777777777777778e-06,
+      "loss": 1.613,
+      "step": 17
+    },
+    {
+      "epoch": 0.12010008340283569,
+      "grad_norm": 0.4238875949015934,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.6816,
+      "step": 18
+    },
+    {
+      "epoch": 0.1267723102585488,
+      "grad_norm": 0.4720616555526343,
+      "learning_rate": 4.222222222222223e-06,
+      "loss": 1.7593,
+      "step": 19
+    },
+    {
+      "epoch": 0.13344453711426188,
+      "grad_norm": 0.4525263926368364,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 1.775,
+      "step": 20
+    },
+    {
+      "epoch": 0.14011676396997497,
+      "grad_norm": 0.48266597054805727,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 1.791,
+      "step": 21
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.45939880890244206,
+      "learning_rate": 4.888888888888889e-06,
+      "loss": 1.7338,
+      "step": 22
+    },
+    {
+      "epoch": 0.15346121768140117,
+      "grad_norm": 0.47764567898261373,
+      "learning_rate": 5.1111111111111115e-06,
+      "loss": 1.7483,
+      "step": 23
+    },
+    {
+      "epoch": 0.16013344453711426,
+      "grad_norm": 0.5017631959610884,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 1.7481,
+      "step": 24
+    },
+    {
+      "epoch": 0.16680567139282734,
+      "grad_norm": 0.4893567689357815,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 1.7136,
+      "step": 25
+    },
+    {
+      "epoch": 0.17347789824854046,
+      "grad_norm": 0.5105291717073872,
+      "learning_rate": 5.777777777777778e-06,
+      "loss": 1.7602,
+      "step": 26
+    },
+    {
+      "epoch": 0.18015012510425354,
+      "grad_norm": 0.46974781533253324,
+      "learning_rate": 6e-06,
+      "loss": 1.6153,
+      "step": 27
+    },
+    {
+      "epoch": 0.18682235195996663,
+      "grad_norm": 0.5383405971129123,
+      "learning_rate": 6.222222222222223e-06,
+      "loss": 1.6602,
+      "step": 28
+    },
+    {
+      "epoch": 0.19349457881567975,
+      "grad_norm": 0.5952748064288939,
+      "learning_rate": 6.444444444444445e-06,
+      "loss": 1.7177,
+      "step": 29
+    },
+    {
+      "epoch": 0.20016680567139283,
+      "grad_norm": 0.5399245254089347,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.7092,
+      "step": 30
+    },
+    {
+      "epoch": 0.20683903252710592,
+      "grad_norm": 0.5598787056956456,
+      "learning_rate": 6.88888888888889e-06,
+      "loss": 1.67,
+      "step": 31
+    },
+    {
+      "epoch": 0.213511259382819,
+      "grad_norm": 0.5992687712634374,
+      "learning_rate": 7.111111111111112e-06,
+      "loss": 1.7355,
+      "step": 32
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 0.6046798477314653,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 1.7322,
+      "step": 33
+    },
+    {
+      "epoch": 0.2268557130942452,
+      "grad_norm": 0.6320084975028277,
+      "learning_rate": 7.555555555555556e-06,
+      "loss": 1.8031,
+      "step": 34
+    },
+    {
+      "epoch": 0.2335279399499583,
+      "grad_norm": 0.5904036648454649,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 1.6945,
+      "step": 35
+    },
+    {
+      "epoch": 0.24020016680567138,
+      "grad_norm": 0.6104299430520795,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.6777,
+      "step": 36
+    },
+    {
+      "epoch": 0.2468723936613845,
+      "grad_norm": 0.6047786223470227,
+      "learning_rate": 8.222222222222222e-06,
+      "loss": 1.6366,
+      "step": 37
+    },
+    {
+      "epoch": 0.2535446205170976,
+      "grad_norm": 0.6387094238927912,
+      "learning_rate": 8.444444444444446e-06,
+      "loss": 1.6636,
+      "step": 38
+    },
+    {
+      "epoch": 0.2602168473728107,
+      "grad_norm": 0.6120207071048721,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 1.6292,
+      "step": 39
+    },
+    {
+      "epoch": 0.26688907422852376,
+      "grad_norm": 0.6088068565354802,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 1.6047,
+      "step": 40
+    },
+    {
+      "epoch": 0.2735613010842369,
+      "grad_norm": 0.6091668716984593,
+      "learning_rate": 9.111111111111112e-06,
+      "loss": 1.6258,
+      "step": 41
+    },
+    {
+      "epoch": 0.28023352793994993,
+      "grad_norm": 0.5682506824419054,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 1.5699,
+      "step": 42
+    },
+    {
+      "epoch": 0.28690575479566305,
+      "grad_norm": 0.5635810130587849,
+      "learning_rate": 9.555555555555556e-06,
+      "loss": 1.6314,
+      "step": 43
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.5841358241959886,
+      "learning_rate": 9.777777777777779e-06,
+      "loss": 1.5456,
+      "step": 44
+    },
+    {
+      "epoch": 0.3002502085070892,
+      "grad_norm": 0.5617293142392159,
+      "learning_rate": 1e-05,
+      "loss": 1.5272,
+      "step": 45
+    },
+    {
+      "epoch": 0.30692243536280234,
+      "grad_norm": 0.47772319074173303,
+      "learning_rate": 9.999847318844664e-06,
+      "loss": 1.5373,
+      "step": 46
+    },
+    {
+      "epoch": 0.31359466221851545,
+      "grad_norm": 0.510823048338545,
+      "learning_rate": 9.999389284703265e-06,
+      "loss": 1.6097,
+      "step": 47
+    },
+    {
+      "epoch": 0.3202668890742285,
+      "grad_norm": 0.5010538752769951,
+      "learning_rate": 9.99862592554908e-06,
+      "loss": 1.5344,
+      "step": 48
+    },
+    {
+      "epoch": 0.3269391159299416,
+      "grad_norm": 0.47226467172138603,
+      "learning_rate": 9.99755728800233e-06,
+      "loss": 1.5023,
+      "step": 49
+    },
+    {
+      "epoch": 0.3336113427856547,
+      "grad_norm": 0.4849966025454849,
+      "learning_rate": 9.996183437327342e-06,
+      "loss": 1.4975,
+      "step": 50
+    },
+    {
+      "epoch": 0.3402835696413678,
+      "grad_norm": 0.47126668835079394,
+      "learning_rate": 9.994504457428557e-06,
+      "loss": 1.5127,
+      "step": 51
+    },
+    {
+      "epoch": 0.3469557964970809,
+      "grad_norm": 0.4301425546280333,
+      "learning_rate": 9.992520450845415e-06,
+      "loss": 1.4456,
+      "step": 52
+    },
+    {
+      "epoch": 0.353628023352794,
+      "grad_norm": 0.4378182305752446,
+      "learning_rate": 9.99023153874608e-06,
+      "loss": 1.4695,
+      "step": 53
+    },
+    {
+      "epoch": 0.3603002502085071,
+      "grad_norm": 0.4297960171566437,
+      "learning_rate": 9.987637860920053e-06,
+      "loss": 1.5113,
+      "step": 54
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.4154036526185639,
+      "learning_rate": 9.984739575769619e-06,
+      "loss": 1.3419,
+      "step": 55
+    },
+    {
+      "epoch": 0.37364470391993326,
+      "grad_norm": 0.42590048753833515,
+      "learning_rate": 9.981536860300191e-06,
+      "loss": 1.4191,
+      "step": 56
+    },
+    {
+      "epoch": 0.3803169307756464,
+      "grad_norm": 0.4067719643823426,
+      "learning_rate": 9.978029910109491e-06,
+      "loss": 1.3983,
+      "step": 57
+    },
+    {
+      "epoch": 0.3869891576313595,
+      "grad_norm": 0.3969278459704296,
+      "learning_rate": 9.9742189393756e-06,
+      "loss": 1.3794,
+      "step": 58
+    },
+    {
+      "epoch": 0.39366138448707255,
+      "grad_norm": 0.3854670128621615,
+      "learning_rate": 9.970104180843881e-06,
+      "loss": 1.4305,
+      "step": 59
+    },
+    {
+      "epoch": 0.40033361134278567,
+      "grad_norm": 0.37743755476343405,
+      "learning_rate": 9.965685885812773e-06,
+      "loss": 1.4283,
+      "step": 60
+    },
+    {
+      "epoch": 0.4070058381984987,
+      "grad_norm": 0.3610253450226918,
+      "learning_rate": 9.960964324118428e-06,
+      "loss": 1.4135,
+      "step": 61
+    },
+    {
+      "epoch": 0.41367806505421184,
+      "grad_norm": 0.38314151063998836,
+      "learning_rate": 9.955939784118246e-06,
+      "loss": 1.4194,
+      "step": 62
+    },
+    {
+      "epoch": 0.42035029190992496,
+      "grad_norm": 0.391502563403777,
+      "learning_rate": 9.950612572673255e-06,
+      "loss": 1.3669,
+      "step": 63
+    },
+    {
+      "epoch": 0.427022518765638,
+      "grad_norm": 0.3606335039104152,
+      "learning_rate": 9.944983015129376e-06,
+      "loss": 1.3249,
+      "step": 64
+    },
+    {
+      "epoch": 0.43369474562135113,
+      "grad_norm": 0.3836886872726812,
+      "learning_rate": 9.939051455297548e-06,
+      "loss": 1.3323,
+      "step": 65
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.39513066746369385,
+      "learning_rate": 9.932818255432733e-06,
+      "loss": 1.3228,
+      "step": 66
+    },
+    {
+      "epoch": 0.4470391993327773,
+      "grad_norm": 0.3776395809498074,
+      "learning_rate": 9.926283796211796e-06,
+      "loss": 1.4202,
+      "step": 67
+    },
+    {
+      "epoch": 0.4537114261884904,
+      "grad_norm": 0.3536441979654702,
+      "learning_rate": 9.919448476710248e-06,
+      "loss": 1.3169,
+      "step": 68
+    },
+    {
+      "epoch": 0.4603836530442035,
+      "grad_norm": 0.35401704664244255,
+      "learning_rate": 9.91231271437788e-06,
+      "loss": 1.2869,
+      "step": 69
+    },
+    {
+      "epoch": 0.4670558798999166,
+      "grad_norm": 0.364086698791685,
+      "learning_rate": 9.904876945013272e-06,
+      "loss": 1.3558,
+      "step": 70
+    },
+    {
+      "epoch": 0.4737281067556297,
+      "grad_norm": 0.36643453456415837,
+      "learning_rate": 9.89714162273716e-06,
+      "loss": 1.2972,
+      "step": 71
+    },
+    {
+      "epoch": 0.48040033361134277,
+      "grad_norm": 0.35341632594055883,
+      "learning_rate": 9.889107219964726e-06,
+      "loss": 1.288,
+      "step": 72
+    },
+    {
+      "epoch": 0.4870725604670559,
+      "grad_norm": 0.35727226233776593,
+      "learning_rate": 9.880774227376727e-06,
+      "loss": 1.2919,
+      "step": 73
+    },
+    {
+      "epoch": 0.493744787322769,
+      "grad_norm": 0.36655136111497844,
+      "learning_rate": 9.872143153889538e-06,
+      "loss": 1.2864,
+      "step": 74
+    },
+    {
+      "epoch": 0.5004170141784821,
+      "grad_norm": 0.3580519341051248,
+      "learning_rate": 9.863214526624065e-06,
+      "loss": 1.3545,
+      "step": 75
+    },
+    {
+      "epoch": 0.5070892410341952,
+      "grad_norm": 0.3251286992451364,
+      "learning_rate": 9.853988890873563e-06,
+      "loss": 1.2463,
+      "step": 76
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 0.35154208731758474,
+      "learning_rate": 9.844466810070319e-06,
+      "loss": 1.2842,
+      "step": 77
+    },
+    {
+      "epoch": 0.5204336947456214,
+      "grad_norm": 0.35360327701201805,
+      "learning_rate": 9.834648865751254e-06,
+      "loss": 1.2074,
+      "step": 78
+    },
+    {
+      "epoch": 0.5271059216013344,
+      "grad_norm": 0.33827984275163614,
+      "learning_rate": 9.8245356575224e-06,
+      "loss": 1.2719,
+      "step": 79
+    },
+    {
+      "epoch": 0.5337781484570475,
+      "grad_norm": 0.34688277661237193,
+      "learning_rate": 9.814127803022281e-06,
+      "loss": 1.2809,
+      "step": 80
+    },
+    {
+      "epoch": 0.5404503753127606,
+      "grad_norm": 0.30446458893187955,
+      "learning_rate": 9.803425937884202e-06,
+      "loss": 1.2302,
+      "step": 81
+    },
+    {
+      "epoch": 0.5471226021684737,
+      "grad_norm": 0.31831189291520345,
+      "learning_rate": 9.792430715697412e-06,
+      "loss": 1.2329,
+      "step": 82
+    },
+    {
+      "epoch": 0.5537948290241869,
+      "grad_norm": 0.29801313071352337,
+      "learning_rate": 9.781142807967205e-06,
+      "loss": 1.2464,
+      "step": 83
+    },
+    {
+      "epoch": 0.5604670558798999,
+      "grad_norm": 0.3118984625981495,
+      "learning_rate": 9.769562904073896e-06,
+      "loss": 1.2388,
+      "step": 84
+    },
+    {
+      "epoch": 0.567139282735613,
+      "grad_norm": 0.28346870486129144,
+      "learning_rate": 9.757691711230728e-06,
+      "loss": 1.222,
+      "step": 85
+    },
+    {
+      "epoch": 0.5738115095913261,
+      "grad_norm": 0.3235682827850219,
+      "learning_rate": 9.745529954440675e-06,
+      "loss": 1.2167,
+      "step": 86
+    },
+    {
+      "epoch": 0.5804837364470392,
+      "grad_norm": 0.3025602896103518,
+      "learning_rate": 9.733078376452172e-06,
+      "loss": 1.2439,
+      "step": 87
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.2943206117574144,
+      "learning_rate": 9.72033773771374e-06,
+      "loss": 1.1714,
+      "step": 88
+    },
+    {
+      "epoch": 0.5938281901584654,
+      "grad_norm": 0.3043570350280811,
+      "learning_rate": 9.707308816327557e-06,
+      "loss": 1.2466,
+      "step": 89
+    },
+    {
+      "epoch": 0.6005004170141784,
+      "grad_norm": 0.3034637832523981,
+      "learning_rate": 9.693992408001934e-06,
+      "loss": 1.1737,
+      "step": 90
+    },
+    {
+      "epoch": 0.6071726438698916,
+      "grad_norm": 0.29378370873758436,
+      "learning_rate": 9.680389326002708e-06,
+      "loss": 1.2823,
+      "step": 91
+    },
+    {
+      "epoch": 0.6138448707256047,
+      "grad_norm": 0.25233208089640863,
+      "learning_rate": 9.666500401103595e-06,
+      "loss": 1.191,
+      "step": 92
+    },
+    {
+      "epoch": 0.6205170975813178,
+      "grad_norm": 0.264841896316846,
+      "learning_rate": 9.652326481535434e-06,
+      "loss": 1.1842,
+      "step": 93
+    },
+    {
+      "epoch": 0.6271893244370309,
+      "grad_norm": 0.276234903477221,
+      "learning_rate": 9.63786843293439e-06,
+      "loss": 1.1062,
+      "step": 94
+    },
+    {
+      "epoch": 0.6338615512927439,
+      "grad_norm": 0.25250932151404143,
+      "learning_rate": 9.623127138289087e-06,
+      "loss": 1.1036,
+      "step": 95
+    },
+    {
+      "epoch": 0.640533778148457,
+      "grad_norm": 0.27277526043956535,
+      "learning_rate": 9.608103497886687e-06,
+      "loss": 1.1332,
+      "step": 96
+    },
+    {
+      "epoch": 0.6472060050041701,
+      "grad_norm": 0.27812831319172243,
+      "learning_rate": 9.592798429257899e-06,
+      "loss": 1.1704,
+      "step": 97
+    },
+    {
+      "epoch": 0.6538782318598833,
+      "grad_norm": 0.24189134780796812,
+      "learning_rate": 9.577212867120947e-06,
+      "loss": 1.1644,
+      "step": 98
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.25645020937055246,
+      "learning_rate": 9.561347763324484e-06,
+      "loss": 1.147,
+      "step": 99
+    },
+    {
+      "epoch": 0.6672226855713094,
+      "grad_norm": 0.2595686790235878,
+      "learning_rate": 9.545204086789461e-06,
+      "loss": 1.2334,
+      "step": 100
+    },
+    {
+      "epoch": 0.6738949124270225,
+      "grad_norm": 0.24949960135623445,
+      "learning_rate": 9.528782823449954e-06,
+      "loss": 1.0824,
+      "step": 101
+    },
+    {
+      "epoch": 0.6805671392827356,
+      "grad_norm": 0.2457329952973373,
+      "learning_rate": 9.512084976192944e-06,
+      "loss": 1.1335,
+      "step": 102
+    },
+    {
+      "epoch": 0.6872393661384487,
+      "grad_norm": 0.26799579166131554,
+      "learning_rate": 9.495111564797073e-06,
+      "loss": 1.1403,
+      "step": 103
+    },
+    {
+      "epoch": 0.6939115929941618,
+      "grad_norm": 0.24843110380217398,
+      "learning_rate": 9.477863625870371e-06,
+      "loss": 1.1659,
+      "step": 104
+    },
+    {
+      "epoch": 0.700583819849875,
+      "grad_norm": 0.26596297978049915,
+      "learning_rate": 9.460342212786933e-06,
+      "loss": 1.1191,
+      "step": 105
+    },
+    {
+      "epoch": 0.707256046705588,
+      "grad_norm": 0.24609569923205743,
+      "learning_rate": 9.442548395622596e-06,
+      "loss": 1.1388,
+      "step": 106
+    },
+    {
+      "epoch": 0.7139282735613011,
+      "grad_norm": 0.30159400597802477,
+      "learning_rate": 9.424483261089584e-06,
+      "loss": 1.2705,
+      "step": 107
+    },
+    {
+      "epoch": 0.7206005004170142,
+      "grad_norm": 0.24911328963823176,
+      "learning_rate": 9.406147912470142e-06,
+      "loss": 1.1393,
+      "step": 108
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.2461854661834755,
+      "learning_rate": 9.387543469549156e-06,
+      "loss": 1.0897,
+      "step": 109
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.24427724214296034,
+      "learning_rate": 9.368671068545761e-06,
+      "loss": 1.0527,
+      "step": 110
+    },
+    {
+      "epoch": 0.7406171809841534,
+      "grad_norm": 0.24775041629357836,
+      "learning_rate": 9.349531862043952e-06,
+      "loss": 1.0695,
+      "step": 111
+    },
+    {
+      "epoch": 0.7472894078398665,
+      "grad_norm": 0.24100289437186362,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 1.0972,
+      "step": 112
+    },
+    {
+      "epoch": 0.7539616346955796,
+      "grad_norm": 0.22817385479165772,
+      "learning_rate": 9.310457724282034e-06,
+      "loss": 1.1354,
+      "step": 113
+    },
+    {
+      "epoch": 0.7606338615512928,
+      "grad_norm": 0.24351101122361835,
+      "learning_rate": 9.290525179375722e-06,
+      "loss": 1.1867,
+      "step": 114
+    },
+    {
+      "epoch": 0.7673060884070059,
+      "grad_norm": 0.23252679169251178,
+      "learning_rate": 9.270330601532855e-06,
+      "loss": 0.9749,
+      "step": 115
+    },
+    {
+      "epoch": 0.773978315262719,
+      "grad_norm": 0.24891852642577655,
+      "learning_rate": 9.249875224086023e-06,
+      "loss": 1.0428,
+      "step": 116
+    },
+    {
+      "epoch": 0.780650542118432,
+      "grad_norm": 0.2519892667083049,
+      "learning_rate": 9.229160296295488e-06,
+      "loss": 1.1525,
+      "step": 117
+    },
+    {
+      "epoch": 0.7873227689741451,
+      "grad_norm": 0.22842656407732698,
+      "learning_rate": 9.208187083272895e-06,
+      "loss": 1.0893,
+      "step": 118
+    },
+    {
+      "epoch": 0.7939949958298582,
+      "grad_norm": 0.23530353826931574,
+      "learning_rate": 9.186956865904004e-06,
+      "loss": 1.1461,
+      "step": 119
+    },
+    {
+      "epoch": 0.8006672226855713,
+      "grad_norm": 0.25930781535544006,
+      "learning_rate": 9.165470940770458e-06,
+      "loss": 1.0863,
+      "step": 120
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 0.24794978516182076,
+      "learning_rate": 9.143730620070609e-06,
+      "loss": 1.1216,
+      "step": 121
+    },
+    {
+      "epoch": 0.8140116763969975,
+      "grad_norm": 0.23948920252711808,
+      "learning_rate": 9.121737231539369e-06,
+      "loss": 1.1121,
+      "step": 122
+    },
+    {
+      "epoch": 0.8206839032527106,
+      "grad_norm": 0.2271047573553413,
+      "learning_rate": 9.099492118367123e-06,
+      "loss": 1.1543,
+      "step": 123
+    },
+    {
+      "epoch": 0.8273561301084237,
+      "grad_norm": 0.25315676717796304,
+      "learning_rate": 9.076996639117708e-06,
+      "loss": 1.1309,
+      "step": 124
+    },
+    {
+      "epoch": 0.8340283569641368,
+      "grad_norm": 0.24992513383867146,
+      "learning_rate": 9.054252167645426e-06,
+      "loss": 1.064,
+      "step": 125
+    },
+    {
+      "epoch": 0.8407005838198499,
+      "grad_norm": 0.24372502494677808,
+      "learning_rate": 9.03126009301115e-06,
+      "loss": 1.1069,
+      "step": 126
+    },
+    {
+      "epoch": 0.8473728106755629,
+      "grad_norm": 0.23106765610762486,
+      "learning_rate": 9.008021819397488e-06,
+      "loss": 1.1344,
+      "step": 127
+    },
+    {
+      "epoch": 0.854045037531276,
+      "grad_norm": 0.2638490777582001,
+      "learning_rate": 8.984538766023024e-06,
+      "loss": 1.1099,
+      "step": 128
+    },
+    {
+      "epoch": 0.8607172643869891,
+      "grad_norm": 0.2436361177633829,
+      "learning_rate": 8.960812367055646e-06,
+      "loss": 1.0879,
+      "step": 129
+    },
+    {
+      "epoch": 0.8673894912427023,
+      "grad_norm": 0.2435286627690007,
+      "learning_rate": 8.93684407152496e-06,
+      "loss": 1.1281,
+      "step": 130
+    },
+    {
+      "epoch": 0.8740617180984154,
+      "grad_norm": 0.2292808626156267,
+      "learning_rate": 8.912635343233784e-06,
+      "loss": 1.0638,
+      "step": 131
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.22525031331854853,
+      "learning_rate": 8.888187660668762e-06,
+      "loss": 1.1003,
+      "step": 132
+    },
+    {
+      "epoch": 0.8874061718098415,
+      "grad_norm": 0.22555143759216476,
+      "learning_rate": 8.863502516910058e-06,
+      "loss": 0.9963,
+      "step": 133
+    },
+    {
+      "epoch": 0.8940783986655546,
+      "grad_norm": 0.23206135282498955,
+      "learning_rate": 8.838581419540183e-06,
+      "loss": 1.0354,
+      "step": 134
+    },
+    {
+      "epoch": 0.9007506255212677,
+      "grad_norm": 0.2332933329851816,
+      "learning_rate": 8.81342589055191e-06,
+      "loss": 1.0629,
+      "step": 135
+    },
+    {
+      "epoch": 0.9074228523769808,
+      "grad_norm": 0.21598906842259502,
+      "learning_rate": 8.788037466255334e-06,
+      "loss": 1.0368,
+      "step": 136
+    },
+    {
+      "epoch": 0.914095079232694,
+      "grad_norm": 0.2510622429683598,
+      "learning_rate": 8.762417697184034e-06,
+      "loss": 1.018,
+      "step": 137
+    },
+    {
+      "epoch": 0.920767306088407,
+      "grad_norm": 0.25761970215631363,
+      "learning_rate": 8.736568148000386e-06,
+      "loss": 1.0496,
+      "step": 138
+    },
+    {
+      "epoch": 0.9274395329441201,
+      "grad_norm": 0.267375239616011,
+      "learning_rate": 8.710490397400007e-06,
+      "loss": 1.1176,
+      "step": 139
+    },
+    {
+      "epoch": 0.9341117597998332,
+      "grad_norm": 0.23104284046945558,
+      "learning_rate": 8.684186038015327e-06,
+      "loss": 1.0221,
+      "step": 140
+    },
+    {
+      "epoch": 0.9407839866555463,
+      "grad_norm": 0.2560542899746131,
+      "learning_rate": 8.657656676318346e-06,
+      "loss": 1.0761,
+      "step": 141
+    },
+    {
+      "epoch": 0.9474562135112594,
+      "grad_norm": 0.25675258631662545,
+      "learning_rate": 8.630903932522496e-06,
+      "loss": 1.0371,
+      "step": 142
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 0.2609140179674428,
+      "learning_rate": 8.603929440483714e-06,
+      "loss": 1.0895,
+      "step": 143
+    },
+    {
+      "epoch": 0.9608006672226855,
+      "grad_norm": 0.23996253406165996,
+      "learning_rate": 8.576734847600639e-06,
+      "loss": 1.0905,
+      "step": 144
+    },
+    {
+      "epoch": 0.9674728940783986,
+      "grad_norm": 0.2545575065577051,
+      "learning_rate": 8.549321814714018e-06,
+      "loss": 1.1054,
+      "step": 145
+    },
+    {
+      "epoch": 0.9741451209341118,
+      "grad_norm": 0.2514055738350408,
+      "learning_rate": 8.521692016005262e-06,
+      "loss": 1.1183,
+      "step": 146
+    },
+    {
+      "epoch": 0.9808173477898249,
+      "grad_norm": 0.2792023557673277,
+      "learning_rate": 8.49384713889421e-06,
+      "loss": 1.106,
+      "step": 147
+    },
+    {
+      "epoch": 0.987489574645538,
+      "grad_norm": 0.22340105561162074,
+      "learning_rate": 8.46578888393606e-06,
+      "loss": 1.0232,
+      "step": 148
+    },
+    {
+      "epoch": 0.994161801501251,
+      "grad_norm": 0.25568989349658056,
+      "learning_rate": 8.43751896471753e-06,
+      "loss": 1.0899,
+      "step": 149
+    },
+    {
+      "epoch": 1.0066722268557131,
+      "grad_norm": 0.7802055347834813,
+      "learning_rate": 8.40903910775219e-06,
+      "loss": 1.9774,
+      "step": 150
+    },
+    {
+      "epoch": 1.0133444537114262,
+      "grad_norm": 0.2595541681581563,
+      "learning_rate": 8.380351052375023e-06,
+      "loss": 1.045,
+      "step": 151
+    },
+    {
+      "epoch": 1.0200166805671393,
+      "grad_norm": 0.25723642565217814,
+      "learning_rate": 8.35145655063621e-06,
+      "loss": 1.0245,
+      "step": 152
+    },
+    {
+      "epoch": 1.0266889074228525,
+      "grad_norm": 0.27362291141864464,
+      "learning_rate": 8.32235736719411e-06,
+      "loss": 1.0868,
+      "step": 153
+    },
+    {
+      "epoch": 1.0333611342785656,
+      "grad_norm": 0.2458791941756008,
+      "learning_rate": 8.293055279207503e-06,
+      "loss": 1.0889,
+      "step": 154
+    },
+    {
+      "epoch": 1.0400333611342785,
+      "grad_norm": 0.31147103624378575,
+      "learning_rate": 8.263552076227048e-06,
+      "loss": 0.9933,
+      "step": 155
+    },
+    {
+      "epoch": 1.0467055879899916,
+      "grad_norm": 0.2672690864798242,
+      "learning_rate": 8.233849560085994e-06,
+      "loss": 1.0815,
+      "step": 156
+    },
+    {
+      "epoch": 1.0533778148457047,
+      "grad_norm": 0.2422074236035313,
+      "learning_rate": 8.203949544790131e-06,
+      "loss": 1.1015,
+      "step": 157
+    },
+    {
+      "epoch": 1.0600500417014178,
+      "grad_norm": 0.27579765876295836,
+      "learning_rate": 8.173853856407011e-06,
+      "loss": 1.0386,
+      "step": 158
+    },
+    {
+      "epoch": 1.066722268557131,
+      "grad_norm": 0.25869695071730053,
+      "learning_rate": 8.143564332954426e-06,
+      "loss": 1.0408,
+      "step": 159
+    },
+    {
+      "epoch": 1.073394495412844,
+      "grad_norm": 0.2902505945569461,
+      "learning_rate": 8.113082824288145e-06,
+      "loss": 1.0253,
+      "step": 160
+    },
+    {
+      "epoch": 1.0800667222685572,
+      "grad_norm": 0.23657511088258748,
+      "learning_rate": 8.082411191988956e-06,
+      "loss": 1.0282,
+      "step": 161
+    },
+    {
+      "epoch": 1.0867389491242703,
+      "grad_norm": 0.2841268408399986,
+      "learning_rate": 8.051551309248961e-06,
+      "loss": 1.1055,
+      "step": 162
+    },
+    {
+      "epoch": 1.0934111759799834,
+      "grad_norm": 0.26372063674010376,
+      "learning_rate": 8.02050506075718e-06,
+      "loss": 1.0589,
+      "step": 163
+    },
+    {
+      "epoch": 1.1000834028356965,
+      "grad_norm": 0.27690358093295814,
+      "learning_rate": 7.989274342584446e-06,
+      "loss": 0.949,
+      "step": 164
+    },
+    {
+      "epoch": 1.1067556296914094,
+      "grad_norm": 0.2712773483518729,
+      "learning_rate": 7.957861062067614e-06,
+      "loss": 1.0729,
+      "step": 165
+    },
+    {
+      "epoch": 1.1134278565471225,
+      "grad_norm": 0.30516214609809805,
+      "learning_rate": 7.926267137693066e-06,
+      "loss": 1.037,
+      "step": 166
+    },
+    {
+      "epoch": 1.1201000834028356,
+      "grad_norm": 0.2576349226719825,
+      "learning_rate": 7.894494498979558e-06,
+      "loss": 1.0497,
+      "step": 167
+    },
+    {
+      "epoch": 1.1267723102585487,
+      "grad_norm": 0.24801992242605783,
+      "learning_rate": 7.86254508636036e-06,
+      "loss": 1.0313,
+      "step": 168
+    },
+    {
+      "epoch": 1.1334445371142619,
+      "grad_norm": 0.3166344694109662,
+      "learning_rate": 7.830420851064767e-06,
+      "loss": 1.0967,
+      "step": 169
+    },
+    {
+      "epoch": 1.140116763969975,
+      "grad_norm": 0.24751199793145093,
+      "learning_rate": 7.798123754998922e-06,
+      "loss": 1.0031,
+      "step": 170
+    },
+    {
+      "epoch": 1.146788990825688,
+      "grad_norm": 0.2586884189404244,
+      "learning_rate": 7.765655770625997e-06,
+      "loss": 1.0219,
+      "step": 171
+    },
+    {
+      "epoch": 1.1534612176814012,
+      "grad_norm": 0.235632902703973,
+      "learning_rate": 7.733018880845747e-06,
+      "loss": 1.0207,
+      "step": 172
+    },
+    {
+      "epoch": 1.1601334445371143,
+      "grad_norm": 0.25234095064849044,
+      "learning_rate": 7.70021507887338e-06,
+      "loss": 1.0061,
+      "step": 173
+    },
+    {
+      "epoch": 1.1668056713928274,
+      "grad_norm": 0.2326635498094972,
+      "learning_rate": 7.667246368117852e-06,
+      "loss": 1.0587,
+      "step": 174
+    },
+    {
+      "epoch": 1.1734778982485405,
+      "grad_norm": 0.2649027893834019,
+      "learning_rate": 7.634114762059504e-06,
+      "loss": 0.9703,
+      "step": 175
+    },
+    {
+      "epoch": 1.1801501251042534,
+      "grad_norm": 0.2728476550775381,
+      "learning_rate": 7.600822284127091e-06,
+      "loss": 1.0392,
+      "step": 176
+    },
+    {
+      "epoch": 1.1868223519599665,
+      "grad_norm": 0.24549914761915478,
+      "learning_rate": 7.56737096757421e-06,
+      "loss": 0.9954,
+      "step": 177
+    },
+    {
+      "epoch": 1.1934945788156797,
+      "grad_norm": 0.2815251829331306,
+      "learning_rate": 7.533762855355126e-06,
+      "loss": 1.0291,
+      "step": 178
+    },
+    {
+      "epoch": 1.2001668056713928,
+      "grad_norm": 0.26632117503517927,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.1419,
+      "step": 179
+    },
+    {
+      "epoch": 1.206839032527106,
+      "grad_norm": 0.2966134642339934,
+      "learning_rate": 7.466084463489537e-06,
+      "loss": 1.0036,
+      "step": 180
+    },
+    {
+      "epoch": 1.213511259382819,
+      "grad_norm": 0.26223635549866403,
+      "learning_rate": 7.432018317129056e-06,
+      "loss": 1.0285,
+      "step": 181
+    },
+    {
+      "epoch": 1.2201834862385321,
+      "grad_norm": 0.30911626688190436,
+      "learning_rate": 7.39780364142199e-06,
+      "loss": 1.0041,
+      "step": 182
+    },
+    {
+      "epoch": 1.2268557130942452,
+      "grad_norm": 0.283762152043488,
+      "learning_rate": 7.363442525942827e-06,
+      "loss": 1.0517,
+      "step": 183
+    },
+    {
+      "epoch": 1.2335279399499584,
+      "grad_norm": 0.3425818937559889,
+      "learning_rate": 7.32893706920949e-06,
+      "loss": 1.0177,
+      "step": 184
+    },
+    {
+      "epoch": 1.2402001668056715,
+      "grad_norm": 0.35518044492578266,
+      "learning_rate": 7.294289378555179e-06,
+      "loss": 1.039,
+      "step": 185
+    },
+    {
+      "epoch": 1.2468723936613846,
+      "grad_norm": 0.2953658322519591,
+      "learning_rate": 7.25950156999967e-06,
+      "loss": 1.0239,
+      "step": 186
+    },
+    {
+      "epoch": 1.2535446205170975,
+      "grad_norm": 0.30127312537141965,
+      "learning_rate": 7.2245757681200835e-06,
+      "loss": 0.9763,
+      "step": 187
+    },
+    {
+      "epoch": 1.2602168473728108,
+      "grad_norm": 0.282352211179054,
+      "learning_rate": 7.189514105921132e-06,
+      "loss": 0.991,
+      "step": 188
+    },
+    {
+      "epoch": 1.2668890742285237,
+      "grad_norm": 0.27942599700546883,
+      "learning_rate": 7.1543187247048525e-06,
+      "loss": 0.9997,
+      "step": 189
+    },
+    {
+      "epoch": 1.2735613010842368,
+      "grad_norm": 0.34032643799945067,
+      "learning_rate": 7.118991773939832e-06,
+      "loss": 1.0323,
+      "step": 190
+    },
+    {
+      "epoch": 1.28023352793995,
+      "grad_norm": 0.2833978681025291,
+      "learning_rate": 7.083535411129934e-06,
+      "loss": 0.965,
+      "step": 191
+    },
+    {
+      "epoch": 1.286905754795663,
+      "grad_norm": 0.28066028962170614,
+      "learning_rate": 7.047951801682533e-06,
+      "loss": 0.9827,
+      "step": 192
+    },
+    {
+      "epoch": 1.2935779816513762,
+      "grad_norm": 0.3451242223474228,
+      "learning_rate": 7.01224311877627e-06,
+      "loss": 1.013,
+      "step": 193
+    },
+    {
+      "epoch": 1.3002502085070893,
+      "grad_norm": 0.28576160899229214,
+      "learning_rate": 6.976411543228328e-06,
+      "loss": 1.0147,
+      "step": 194
+    },
+    {
+      "epoch": 1.3069224353628024,
+      "grad_norm": 0.26405586969472095,
+      "learning_rate": 6.9404592633612486e-06,
+      "loss": 1.0222,
+      "step": 195
+    },
+    {
+      "epoch": 1.3135946622185155,
+      "grad_norm": 0.23979743466387593,
+      "learning_rate": 6.904388474869284e-06,
+      "loss": 0.9763,
+      "step": 196
+    },
+    {
+      "epoch": 1.3202668890742286,
+      "grad_norm": 0.26278250196725494,
+      "learning_rate": 6.8682013806842985e-06,
+      "loss": 1.0177,
+      "step": 197
+    },
+    {
+      "epoch": 1.3269391159299415,
+      "grad_norm": 0.3616613201338565,
+      "learning_rate": 6.831900190841232e-06,
+      "loss": 1.0189,
+      "step": 198
+    },
+    {
+      "epoch": 1.3336113427856546,
+      "grad_norm": 0.317805954218629,
+      "learning_rate": 6.795487122343124e-06,
+      "loss": 1.0761,
+      "step": 199
+    },
+    {
+      "epoch": 1.3402835696413677,
+      "grad_norm": 0.3267310563691638,
+      "learning_rate": 6.758964399025721e-06,
+      "loss": 1.0103,
+      "step": 200
+    },
+    {
+      "epoch": 1.3469557964970809,
+      "grad_norm": 0.3367394677015302,
+      "learning_rate": 6.722334251421665e-06,
+      "loss": 0.9504,
+      "step": 201
+    },
+    {
+      "epoch": 1.353628023352794,
+      "grad_norm": 0.323985054612315,
+      "learning_rate": 6.685598916624254e-06,
+      "loss": 1.0425,
+      "step": 202
+    },
+    {
+      "epoch": 1.360300250208507,
+      "grad_norm": 0.31744623672148714,
+      "learning_rate": 6.648760638150833e-06,
+      "loss": 1.0284,
+      "step": 203
+    },
+    {
+      "epoch": 1.3669724770642202,
+      "grad_norm": 0.32506007928496355,
+      "learning_rate": 6.611821665805769e-06,
+      "loss": 1.0494,
+      "step": 204
+    },
+    {
+      "epoch": 1.3736447039199333,
+      "grad_norm": 0.31683692701232863,
+      "learning_rate": 6.574784255543052e-06,
+      "loss": 0.9341,
+      "step": 205
+    },
+    {
+      "epoch": 1.3803169307756464,
+      "grad_norm": 0.339014481901513,
+      "learning_rate": 6.537650669328518e-06,
+      "loss": 0.9351,
+      "step": 206
+    },
+    {
+      "epoch": 1.3869891576313595,
+      "grad_norm": 0.2908501088905977,
+      "learning_rate": 6.500423175001705e-06,
+      "loss": 0.9636,
+      "step": 207
+    },
+    {
+      "epoch": 1.3936613844870727,
+      "grad_norm": 0.29622441402682287,
+      "learning_rate": 6.4631040461373494e-06,
+      "loss": 0.991,
+      "step": 208
+    },
+    {
+      "epoch": 1.4003336113427856,
+      "grad_norm": 0.259706989545213,
+      "learning_rate": 6.4256955619065375e-06,
+      "loss": 1.0265,
+      "step": 209
+    },
+    {
+      "epoch": 1.4070058381984987,
+      "grad_norm": 0.27351346614577177,
+      "learning_rate": 6.388200006937503e-06,
+      "loss": 1.1127,
+      "step": 210
+    },
+    {
+      "epoch": 1.4136780650542118,
+      "grad_norm": 0.2569362561775431,
+      "learning_rate": 6.350619671176111e-06,
+      "loss": 0.9848,
+      "step": 211
+    },
+    {
+      "epoch": 1.420350291909925,
+      "grad_norm": 0.3031398363213745,
+      "learning_rate": 6.312956849745993e-06,
+      "loss": 1.0439,
+      "step": 212
+    },
+    {
+      "epoch": 1.427022518765638,
+      "grad_norm": 0.29741800552671255,
+      "learning_rate": 6.275213842808383e-06,
+      "loss": 1.0295,
+      "step": 213
+    },
+    {
+      "epoch": 1.4336947456213511,
+      "grad_norm": 0.2858593332853522,
+      "learning_rate": 6.237392955421644e-06,
+      "loss": 0.9632,
+      "step": 214
+    },
+    {
+      "epoch": 1.4403669724770642,
+      "grad_norm": 0.2717253920058818,
+      "learning_rate": 6.19949649740049e-06,
+      "loss": 0.9708,
+      "step": 215
+    },
+    {
+      "epoch": 1.4470391993327774,
+      "grad_norm": 0.2755282096882548,
+      "learning_rate": 6.161526783174917e-06,
+      "loss": 1.0894,
+      "step": 216
+    },
+    {
+      "epoch": 1.4537114261884905,
+      "grad_norm": 0.277037632676125,
+      "learning_rate": 6.123486131648859e-06,
+      "loss": 1.0682,
+      "step": 217
+    },
+    {
+      "epoch": 1.4603836530442034,
+      "grad_norm": 0.3020180443959382,
+      "learning_rate": 6.085376866058569e-06,
+      "loss": 1.0672,
+      "step": 218
+    },
+    {
+      "epoch": 1.4670558798999167,
+      "grad_norm": 0.2819163434265071,
+      "learning_rate": 6.047201313830724e-06,
+      "loss": 0.9994,
+      "step": 219
+    },
+    {
+      "epoch": 1.4737281067556296,
+      "grad_norm": 0.2800183935957482,
+      "learning_rate": 6.0089618064402896e-06,
+      "loss": 1.022,
+      "step": 220
+    },
+    {
+      "epoch": 1.4804003336113427,
+      "grad_norm": 0.2719182825453672,
+      "learning_rate": 5.970660679268139e-06,
+      "loss": 1.0183,
+      "step": 221
+    },
+    {
+      "epoch": 1.4870725604670558,
+      "grad_norm": 0.2922309116254843,
+      "learning_rate": 5.932300271458406e-06,
+      "loss": 0.9777,
+      "step": 222
+    },
+    {
+      "epoch": 1.493744787322769,
+      "grad_norm": 0.2744738064356238,
+      "learning_rate": 5.893882925775648e-06,
+      "loss": 0.9841,
+      "step": 223
+    },
+    {
+      "epoch": 1.500417014178482,
+      "grad_norm": 0.2618241413789887,
+      "learning_rate": 5.85541098846175e-06,
+      "loss": 0.9789,
+      "step": 224
+    },
+    {
+      "epoch": 1.5070892410341952,
+      "grad_norm": 0.29331697175604643,
+      "learning_rate": 5.816886809092651e-06,
+      "loss": 0.9889,
+      "step": 225
+    },
+    {
+      "epoch": 1.5137614678899083,
+      "grad_norm": 0.293938259486948,
+      "learning_rate": 5.778312740434835e-06,
+      "loss": 1.0398,
+      "step": 226
+    },
+    {
+      "epoch": 1.5204336947456214,
+      "grad_norm": 0.3149805373750932,
+      "learning_rate": 5.73969113830165e-06,
+      "loss": 1.0356,
+      "step": 227
+    },
+    {
+      "epoch": 1.5271059216013345,
+      "grad_norm": 0.2882296792753476,
+      "learning_rate": 5.701024361409431e-06,
+      "loss": 1.066,
+      "step": 228
+    },
+    {
+      "epoch": 1.5337781484570474,
+      "grad_norm": 0.3264587076590878,
+      "learning_rate": 5.66231477123344e-06,
+      "loss": 0.9717,
+      "step": 229
+    },
+    {
+      "epoch": 1.5404503753127607,
+      "grad_norm": 0.28816187489358347,
+      "learning_rate": 5.623564731863664e-06,
+      "loss": 1.0055,
+      "step": 230
+    },
+    {
+      "epoch": 1.5471226021684736,
+      "grad_norm": 0.26876813399349714,
+      "learning_rate": 5.584776609860414e-06,
+      "loss": 1.0118,
+      "step": 231
+    },
+    {
+      "epoch": 1.553794829024187,
+      "grad_norm": 0.25656136721296807,
+      "learning_rate": 5.545952774109798e-06,
+      "loss": 1.0441,
+      "step": 232
+    },
+    {
+      "epoch": 1.5604670558798999,
+      "grad_norm": 0.2927283912839115,
+      "learning_rate": 5.507095595679059e-06,
+      "loss": 0.9875,
+      "step": 233
+    },
+    {
+      "epoch": 1.567139282735613,
+      "grad_norm": 0.26847113941733736,
+      "learning_rate": 5.468207447671755e-06,
+      "loss": 0.942,
+      "step": 234
+    },
+    {
+      "epoch": 1.573811509591326,
+      "grad_norm": 0.35285592222755574,
+      "learning_rate": 5.42929070508283e-06,
+      "loss": 1.0382,
+      "step": 235
+    },
+    {
+      "epoch": 1.5804837364470392,
+      "grad_norm": 0.28225631872241425,
+      "learning_rate": 5.390347744653576e-06,
+      "loss": 1.0041,
+      "step": 236
+    },
+    {
+      "epoch": 1.5871559633027523,
+      "grad_norm": 0.2894670959272741,
+      "learning_rate": 5.351380944726465e-06,
+      "loss": 1.0017,
+      "step": 237
+    },
+    {
+      "epoch": 1.5938281901584654,
+      "grad_norm": 0.28265496307817667,
+      "learning_rate": 5.312392685099915e-06,
+      "loss": 1.0073,
+      "step": 238
+    },
+    {
+      "epoch": 1.6005004170141786,
+      "grad_norm": 0.3412461315872378,
+      "learning_rate": 5.2733853468829295e-06,
+      "loss": 0.9839,
+      "step": 239
+    },
+    {
+      "epoch": 1.6071726438698914,
+      "grad_norm": 0.2954038595818766,
+      "learning_rate": 5.234361312349701e-06,
+      "loss": 1.0132,
+      "step": 240
+    },
+    {
+      "epoch": 1.6138448707256048,
+      "grad_norm": 0.2840364660523181,
+      "learning_rate": 5.195322964794098e-06,
+      "loss": 0.9473,
+      "step": 241
+    },
+    {
+      "epoch": 1.6205170975813177,
+      "grad_norm": 0.2986907397693315,
+      "learning_rate": 5.156272688384123e-06,
+      "loss": 1.0077,
+      "step": 242
+    },
+    {
+      "epoch": 1.627189324437031,
+      "grad_norm": 0.292176824846797,
+      "learning_rate": 5.117212868016303e-06,
+      "loss": 0.9315,
+      "step": 243
+    },
+    {
+      "epoch": 1.633861551292744,
+      "grad_norm": 0.3135774476957044,
+      "learning_rate": 5.07814588917004e-06,
+      "loss": 1.0088,
+      "step": 244
+    },
+    {
+      "epoch": 1.640533778148457,
+      "grad_norm": 0.31002794668270833,
+      "learning_rate": 5.03907413776192e-06,
+      "loss": 1.007,
+      "step": 245
+    },
+    {
+      "epoch": 1.6472060050041701,
+      "grad_norm": 0.3045456413966571,
+      "learning_rate": 5e-06,
+      "loss": 0.9872,
+      "step": 246
+    },
+    {
+      "epoch": 1.6538782318598833,
+      "grad_norm": 0.344623415610902,
+      "learning_rate": 4.96092586223808e-06,
+      "loss": 0.9343,
+      "step": 247
+    },
+    {
+      "epoch": 1.6605504587155964,
+      "grad_norm": 0.2888473591105003,
+      "learning_rate": 4.921854110829962e-06,
+      "loss": 1.0071,
+      "step": 248
+    },
+    {
+      "epoch": 1.6672226855713093,
+      "grad_norm": 0.3424869438582918,
+      "learning_rate": 4.882787131983698e-06,
+      "loss": 1.0513,
+      "step": 249
+    },
+    {
+      "epoch": 1.6738949124270226,
+      "grad_norm": 0.3044802192543269,
+      "learning_rate": 4.84372731161588e-06,
+      "loss": 1.0034,
+      "step": 250
+    },
+    {
+      "epoch": 1.6805671392827355,
+      "grad_norm": 0.3676369886348423,
+      "learning_rate": 4.804677035205903e-06,
+      "loss": 1.0679,
+      "step": 251
+    },
+    {
+      "epoch": 1.6872393661384488,
+      "grad_norm": 0.2821236895464674,
+      "learning_rate": 4.765638687650299e-06,
+      "loss": 0.9711,
+      "step": 252
+    },
+    {
+      "epoch": 1.6939115929941617,
+      "grad_norm": 0.32097634201487724,
+      "learning_rate": 4.726614653117071e-06,
+      "loss": 1.0368,
+      "step": 253
+    },
+    {
+      "epoch": 1.700583819849875,
+      "grad_norm": 0.30833620328617434,
+      "learning_rate": 4.687607314900087e-06,
+      "loss": 0.9419,
+      "step": 254
+    },
+    {
+      "epoch": 1.707256046705588,
+      "grad_norm": 0.3161695903169762,
+      "learning_rate": 4.6486190552735375e-06,
+      "loss": 0.947,
+      "step": 255
+    },
+    {
+      "epoch": 1.713928273561301,
+      "grad_norm": 0.3222992290291398,
+      "learning_rate": 4.6096522553464265e-06,
+      "loss": 0.9391,
+      "step": 256
+    },
+    {
+      "epoch": 1.7206005004170142,
+      "grad_norm": 0.27889539086250337,
+      "learning_rate": 4.57070929491717e-06,
+      "loss": 1.0359,
+      "step": 257
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 0.2916579428323436,
+      "learning_rate": 4.531792552328247e-06,
+      "loss": 1.0094,
+      "step": 258
+    },
+    {
+      "epoch": 1.7339449541284404,
+      "grad_norm": 0.24997244028612386,
+      "learning_rate": 4.492904404320942e-06,
+      "loss": 0.7959,
+      "step": 259
+    },
+    {
+      "epoch": 1.7406171809841533,
+      "grad_norm": 0.29868404836632323,
+      "learning_rate": 4.454047225890204e-06,
+      "loss": 1.0109,
+      "step": 260
+    },
+    {
+      "epoch": 1.7472894078398666,
+      "grad_norm": 0.2969807612243251,
+      "learning_rate": 4.415223390139588e-06,
+      "loss": 0.9875,
+      "step": 261
+    },
+    {
+      "epoch": 1.7539616346955795,
+      "grad_norm": 0.3604232218198932,
+      "learning_rate": 4.3764352681363365e-06,
+      "loss": 0.989,
+      "step": 262
+    },
+    {
+      "epoch": 1.7606338615512929,
+      "grad_norm": 0.36824762919465986,
+      "learning_rate": 4.337685228766561e-06,
+      "loss": 1.0049,
+      "step": 263
+    },
+    {
+      "epoch": 1.7673060884070058,
+      "grad_norm": 0.3500725820945927,
+      "learning_rate": 4.2989756385905715e-06,
+      "loss": 0.9718,
+      "step": 264
+    },
+    {
+      "epoch": 1.773978315262719,
+      "grad_norm": 0.2834505359886034,
+      "learning_rate": 4.260308861698351e-06,
+      "loss": 1.0465,
+      "step": 265
+    },
+    {
+      "epoch": 1.780650542118432,
+      "grad_norm": 0.3576818688058849,
+      "learning_rate": 4.221687259565166e-06,
+      "loss": 1.0372,
+      "step": 266
+    },
+    {
+      "epoch": 1.787322768974145,
+      "grad_norm": 0.31757170580776606,
+      "learning_rate": 4.183113190907349e-06,
+      "loss": 0.9565,
+      "step": 267
+    },
+    {
+      "epoch": 1.7939949958298582,
+      "grad_norm": 0.3231504978728471,
+      "learning_rate": 4.144589011538251e-06,
+      "loss": 0.9622,
+      "step": 268
+    },
+    {
+      "epoch": 1.8006672226855713,
+      "grad_norm": 0.30845575748951204,
+      "learning_rate": 4.106117074224354e-06,
+      "loss": 1.0258,
+      "step": 269
+    },
+    {
+      "epoch": 1.8073394495412844,
+      "grad_norm": 0.30421622601970244,
+      "learning_rate": 4.067699728541595e-06,
+      "loss": 1.0356,
+      "step": 270
+    },
+    {
+      "epoch": 1.8140116763969973,
+      "grad_norm": 0.2920513251222264,
+      "learning_rate": 4.029339320731862e-06,
+      "loss": 0.9939,
+      "step": 271
+    },
+    {
+      "epoch": 1.8206839032527107,
+      "grad_norm": 0.27807604400588937,
+      "learning_rate": 3.99103819355971e-06,
+      "loss": 0.9878,
+      "step": 272
+    },
+    {
+      "epoch": 1.8273561301084236,
+      "grad_norm": 0.3266996176440113,
+      "learning_rate": 3.952798686169279e-06,
+      "loss": 1.0041,
+      "step": 273
+    },
+    {
+      "epoch": 1.834028356964137,
+      "grad_norm": 0.3053490567275808,
+      "learning_rate": 3.914623133941432e-06,
+      "loss": 0.9872,
+      "step": 274
+    },
+    {
+      "epoch": 1.8407005838198498,
+      "grad_norm": 0.31477790189099164,
+      "learning_rate": 3.876513868351142e-06,
+      "loss": 0.9359,
+      "step": 275
+    },
+    {
+      "epoch": 1.847372810675563,
+      "grad_norm": 0.27149053344889523,
+      "learning_rate": 3.838473216825085e-06,
+      "loss": 1.0067,
+      "step": 276
+    },
+    {
+      "epoch": 1.854045037531276,
+      "grad_norm": 0.3204843702460214,
+      "learning_rate": 3.800503502599511e-06,
+      "loss": 0.9585,
+      "step": 277
+    },
+    {
+      "epoch": 1.8607172643869891,
+      "grad_norm": 0.3498778905670181,
+      "learning_rate": 3.762607044578357e-06,
+      "loss": 0.9697,
+      "step": 278
+    },
+    {
+      "epoch": 1.8673894912427023,
+      "grad_norm": 0.3180400555344581,
+      "learning_rate": 3.7247861571916183e-06,
+      "loss": 1.0226,
+      "step": 279
+    },
+    {
+      "epoch": 1.8740617180984154,
+      "grad_norm": 0.3480360514374549,
+      "learning_rate": 3.6870431502540096e-06,
+      "loss": 1.0358,
+      "step": 280
+    },
+    {
+      "epoch": 1.8807339449541285,
+      "grad_norm": 0.3187430568425493,
+      "learning_rate": 3.6493803288238894e-06,
+      "loss": 1.0073,
+      "step": 281
+    },
+    {
+      "epoch": 1.8874061718098414,
+      "grad_norm": 0.3464506380317717,
+      "learning_rate": 3.611799993062497e-06,
+      "loss": 0.943,
+      "step": 282
+    },
+    {
+      "epoch": 1.8940783986655547,
+      "grad_norm": 0.2880834965055193,
+      "learning_rate": 3.5743044380934655e-06,
+      "loss": 0.9721,
+      "step": 283
+    },
+    {
+      "epoch": 1.9007506255212676,
+      "grad_norm": 0.3210835495717625,
+      "learning_rate": 3.536895953862652e-06,
+      "loss": 1.0209,
+      "step": 284
+    },
+    {
+      "epoch": 1.907422852376981,
+      "grad_norm": 0.3047811453432249,
+      "learning_rate": 3.4995768249982975e-06,
+      "loss": 1.0284,
+      "step": 285
+    },
+    {
+      "epoch": 1.9140950792326938,
+      "grad_norm": 0.35570769296041677,
+      "learning_rate": 3.462349330671484e-06,
+      "loss": 0.9161,
+      "step": 286
+    },
+    {
+      "epoch": 1.920767306088407,
+      "grad_norm": 0.35749623557347504,
+      "learning_rate": 3.4252157444569478e-06,
+      "loss": 0.9152,
+      "step": 287
+    },
+    {
+      "epoch": 1.92743953294412,
+      "grad_norm": 0.3377788624601496,
+      "learning_rate": 3.388178334194232e-06,
+      "loss": 0.925,
+      "step": 288
+    },
+    {
+      "epoch": 1.9341117597998332,
+      "grad_norm": 0.3798661249068725,
+      "learning_rate": 3.351239361849168e-06,
+      "loss": 0.9846,
+      "step": 289
+    },
+    {
+      "epoch": 1.9407839866555463,
+      "grad_norm": 0.29999286355310334,
+      "learning_rate": 3.314401083375748e-06,
+      "loss": 0.9753,
+      "step": 290
+    },
+    {
+      "epoch": 1.9474562135112594,
+      "grad_norm": 0.35781167804812974,
+      "learning_rate": 3.2776657485783357e-06,
+      "loss": 0.9487,
+      "step": 291
+    },
+    {
+      "epoch": 1.9541284403669725,
+      "grad_norm": 0.3084397268778666,
+      "learning_rate": 3.2410356009742784e-06,
+      "loss": 1.0787,
+      "step": 292
+    },
+    {
+      "epoch": 1.9608006672226854,
+      "grad_norm": 0.317448351646333,
+      "learning_rate": 3.2045128776568783e-06,
+      "loss": 0.9257,
+      "step": 293
+    },
+    {
+      "epoch": 1.9674728940783988,
+      "grad_norm": 0.3686880962008835,
+      "learning_rate": 3.168099809158769e-06,
+      "loss": 0.9529,
+      "step": 294
+    },
+    {
+      "epoch": 1.9741451209341117,
+      "grad_norm": 0.30324127420271724,
+      "learning_rate": 3.1317986193157023e-06,
+      "loss": 0.9185,
+      "step": 295
+    },
+    {
+      "epoch": 1.980817347789825,
+      "grad_norm": 0.3439386421881959,
+      "learning_rate": 3.095611525130716e-06,
+      "loss": 1.1113,
+      "step": 296
+    },
+    {
+      "epoch": 1.9874895746455379,
+      "grad_norm": 0.31828525154875525,
+      "learning_rate": 3.059540736638751e-06,
+      "loss": 0.9624,
+      "step": 297
+    },
+    {
+      "epoch": 1.994161801501251,
+      "grad_norm": 0.3528601662749728,
+      "learning_rate": 3.023588456771674e-06,
+      "loss": 1.025,
+      "step": 298
+    },
+    {
+      "epoch": 2.006672226855713,
+      "grad_norm": 1.0381811083452561,
+      "learning_rate": 2.9877568812237325e-06,
+      "loss": 1.8823,
+      "step": 299
+    },
+    {
+      "epoch": 2.0133444537114262,
+      "grad_norm": 0.28745904791303756,
+      "learning_rate": 2.9520481983174675e-06,
+      "loss": 1.0051,
+      "step": 300
+    },
+    {
+      "epoch": 2.020016680567139,
+      "grad_norm": 0.3037470770313497,
+      "learning_rate": 2.916464588870067e-06,
+      "loss": 1.0253,
+      "step": 301
+    },
+    {
+      "epoch": 2.0266889074228525,
+      "grad_norm": 0.3264286058702715,
+      "learning_rate": 2.881008226060168e-06,
+      "loss": 0.9722,
+      "step": 302
+    },
+    {
+      "epoch": 2.0333611342785654,
+      "grad_norm": 0.3168792873407282,
+      "learning_rate": 2.8456812752951483e-06,
+      "loss": 0.9199,
+      "step": 303
+    },
+    {
+      "epoch": 2.0400333611342787,
+      "grad_norm": 0.3658230155927171,
+      "learning_rate": 2.8104858940788705e-06,
+      "loss": 0.9747,
+      "step": 304
+    },
+    {
+      "epoch": 2.0467055879899916,
+      "grad_norm": 0.3196066484806665,
+      "learning_rate": 2.7754242318799174e-06,
+      "loss": 0.9597,
+      "step": 305
+    },
+    {
+      "epoch": 2.053377814845705,
+      "grad_norm": 0.36214258330419746,
+      "learning_rate": 2.740498430000332e-06,
+      "loss": 0.9637,
+      "step": 306
+    },
+    {
+      "epoch": 2.060050041701418,
+      "grad_norm": 0.32144023431445257,
+      "learning_rate": 2.7057106214448216e-06,
+      "loss": 1.0071,
+      "step": 307
+    },
+    {
+      "epoch": 2.066722268557131,
+      "grad_norm": 0.31788167947698615,
+      "learning_rate": 2.671062930790511e-06,
+      "loss": 0.9324,
+      "step": 308
+    },
+    {
+      "epoch": 2.073394495412844,
+      "grad_norm": 0.32411973935094873,
+      "learning_rate": 2.636557474057173e-06,
+      "loss": 0.9213,
+      "step": 309
+    },
+    {
+      "epoch": 2.080066722268557,
+      "grad_norm": 0.3061895381140455,
+      "learning_rate": 2.6021963585780106e-06,
+      "loss": 0.9829,
+      "step": 310
+    },
+    {
+      "epoch": 2.0867389491242703,
+      "grad_norm": 0.2829970996541261,
+      "learning_rate": 2.567981682870946e-06,
+      "loss": 1.0112,
+      "step": 311
+    },
+    {
+      "epoch": 2.093411175979983,
+      "grad_norm": 0.3251773046313095,
+      "learning_rate": 2.533915536510464e-06,
+      "loss": 0.962,
+      "step": 312
+    },
+    {
+      "epoch": 2.1000834028356965,
+      "grad_norm": 0.3117638913905796,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 1.0286,
+      "step": 313
+    },
+    {
+      "epoch": 2.1067556296914094,
+      "grad_norm": 0.3055554951200164,
+      "learning_rate": 2.466237144644874e-06,
+      "loss": 0.9782,
+      "step": 314
+    },
+    {
+      "epoch": 2.1134278565471227,
+      "grad_norm": 0.3093110501459989,
+      "learning_rate": 2.4326290324257896e-06,
+      "loss": 1.0203,
+      "step": 315
+    },
+    {
+      "epoch": 2.1201000834028356,
+      "grad_norm": 0.348167844578145,
+      "learning_rate": 2.3991777158729102e-06,
+      "loss": 0.9729,
+      "step": 316
+    },
+    {
+      "epoch": 2.126772310258549,
+      "grad_norm": 0.35896036414914057,
+      "learning_rate": 2.3658852379404973e-06,
+      "loss": 0.9687,
+      "step": 317
+    },
+    {
+      "epoch": 2.133444537114262,
+      "grad_norm": 0.33836897224758,
+      "learning_rate": 2.3327536318821496e-06,
+      "loss": 0.979,
+      "step": 318
+    },
+    {
+      "epoch": 2.140116763969975,
+      "grad_norm": 0.37686877855977563,
+      "learning_rate": 2.299784921126622e-06,
+      "loss": 0.9513,
+      "step": 319
+    },
+    {
+      "epoch": 2.146788990825688,
+      "grad_norm": 0.355801020401147,
+      "learning_rate": 2.2669811191542547e-06,
+      "loss": 0.9859,
+      "step": 320
+    },
+    {
+      "epoch": 2.153461217681401,
+      "grad_norm": 0.3010215082303293,
+      "learning_rate": 2.234344229374003e-06,
+      "loss": 0.9951,
+      "step": 321
+    },
+    {
+      "epoch": 2.1601334445371143,
+      "grad_norm": 0.32911989661603686,
+      "learning_rate": 2.20187624500108e-06,
+      "loss": 0.9708,
+      "step": 322
+    },
+    {
+      "epoch": 2.166805671392827,
+      "grad_norm": 0.3623670709775593,
+      "learning_rate": 2.1695791489352346e-06,
+      "loss": 0.9734,
+      "step": 323
+    },
+    {
+      "epoch": 2.1734778982485405,
+      "grad_norm": 0.31909897986159624,
+      "learning_rate": 2.1374549136396417e-06,
+      "loss": 0.9517,
+      "step": 324
+    },
+    {
+      "epoch": 2.1801501251042534,
+      "grad_norm": 0.31749439512516914,
+      "learning_rate": 2.1055055010204427e-06,
+      "loss": 0.9848,
+      "step": 325
+    },
+    {
+      "epoch": 2.1868223519599668,
+      "grad_norm": 0.29264160902990144,
+      "learning_rate": 2.073732862306935e-06,
+      "loss": 1.0053,
+      "step": 326
+    },
+    {
+      "epoch": 2.1934945788156797,
+      "grad_norm": 0.3668210964835384,
+      "learning_rate": 2.042138937932388e-06,
+      "loss": 1.0157,
+      "step": 327
+    },
+    {
+      "epoch": 2.200166805671393,
+      "grad_norm": 0.3133785285507638,
+      "learning_rate": 2.0107256574155564e-06,
+      "loss": 0.9808,
+      "step": 328
+    },
+    {
+      "epoch": 2.206839032527106,
+      "grad_norm": 0.3124366924714227,
+      "learning_rate": 1.979494939242822e-06,
+      "loss": 0.979,
+      "step": 329
+    },
+    {
+      "epoch": 2.213511259382819,
+      "grad_norm": 0.29545310894796867,
+      "learning_rate": 1.9484486907510405e-06,
+      "loss": 0.997,
+      "step": 330
+    },
+    {
+      "epoch": 2.220183486238532,
+      "grad_norm": 0.32367677669293343,
+      "learning_rate": 1.917588808011045e-06,
+      "loss": 0.8975,
+      "step": 331
+    },
+    {
+      "epoch": 2.226855713094245,
+      "grad_norm": 0.3299013625375276,
+      "learning_rate": 1.8869171757118554e-06,
+      "loss": 1.0025,
+      "step": 332
+    },
+    {
+      "epoch": 2.2335279399499584,
+      "grad_norm": 0.395626306344832,
+      "learning_rate": 1.856435667045577e-06,
+      "loss": 1.0349,
+      "step": 333
+    },
+    {
+      "epoch": 2.2402001668056712,
+      "grad_norm": 0.3255623940901644,
+      "learning_rate": 1.8261461435929895e-06,
+      "loss": 0.9994,
+      "step": 334
+    },
+    {
+      "epoch": 2.2468723936613846,
+      "grad_norm": 0.28569255358940876,
+      "learning_rate": 1.796050455209869e-06,
+      "loss": 0.9491,
+      "step": 335
+    },
+    {
+      "epoch": 2.2535446205170975,
+      "grad_norm": 0.29893680579074805,
+      "learning_rate": 1.7661504399140066e-06,
+      "loss": 0.979,
+      "step": 336
+    },
+    {
+      "epoch": 2.260216847372811,
+      "grad_norm": 0.3459559430460262,
+      "learning_rate": 1.7364479237729526e-06,
+      "loss": 0.9042,
+      "step": 337
+    },
+    {
+      "epoch": 2.2668890742285237,
+      "grad_norm": 0.3113640341471141,
+      "learning_rate": 1.7069447207924994e-06,
+      "loss": 0.9476,
+      "step": 338
+    },
+    {
+      "epoch": 2.273561301084237,
+      "grad_norm": 0.29758501306847707,
+      "learning_rate": 1.677642632805892e-06,
+      "loss": 0.9388,
+      "step": 339
+    },
+    {
+      "epoch": 2.28023352793995,
+      "grad_norm": 0.31704153540027663,
+      "learning_rate": 1.6485434493637915e-06,
+      "loss": 0.9918,
+      "step": 340
+    },
+    {
+      "epoch": 2.2869057547956633,
+      "grad_norm": 0.3475571370836834,
+      "learning_rate": 1.6196489476249777e-06,
+      "loss": 1.0017,
+      "step": 341
+    },
+    {
+      "epoch": 2.293577981651376,
+      "grad_norm": 0.3114674457835494,
+      "learning_rate": 1.5909608922478108e-06,
+      "loss": 1.0053,
+      "step": 342
+    },
+    {
+      "epoch": 2.300250208507089,
+      "grad_norm": 0.30298813780086953,
+      "learning_rate": 1.5624810352824709e-06,
+      "loss": 0.9641,
+      "step": 343
+    },
+    {
+      "epoch": 2.3069224353628024,
+      "grad_norm": 0.35762529414587724,
+      "learning_rate": 1.5342111160639412e-06,
+      "loss": 0.9616,
+      "step": 344
+    },
+    {
+      "epoch": 2.3135946622185153,
+      "grad_norm": 0.37005906694872853,
+      "learning_rate": 1.5061528611057917e-06,
+      "loss": 1.0249,
+      "step": 345
+    },
+    {
+      "epoch": 2.3202668890742286,
+      "grad_norm": 0.30759447735274864,
+      "learning_rate": 1.4783079839947396e-06,
+      "loss": 0.9851,
+      "step": 346
+    },
+    {
+      "epoch": 2.3269391159299415,
+      "grad_norm": 0.3014932344261013,
+      "learning_rate": 1.4506781852859836e-06,
+      "loss": 1.0052,
+      "step": 347
+    },
+    {
+      "epoch": 2.333611342785655,
+      "grad_norm": 0.31167411900209185,
+      "learning_rate": 1.4232651523993635e-06,
+      "loss": 0.956,
+      "step": 348
+    },
+    {
+      "epoch": 2.3402835696413677,
+      "grad_norm": 0.32652379262644254,
+      "learning_rate": 1.3960705595162876e-06,
+      "loss": 0.9825,
+      "step": 349
+    },
+    {
+      "epoch": 2.346955796497081,
+      "grad_norm": 0.3209030562572718,
+      "learning_rate": 1.369096067477505e-06,
+      "loss": 1.0177,
+      "step": 350
+    },
+    {
+      "epoch": 2.353628023352794,
+      "grad_norm": 0.3562229549612574,
+      "learning_rate": 1.3423433236816563e-06,
+      "loss": 0.9955,
+      "step": 351
+    },
+    {
+      "epoch": 2.360300250208507,
+      "grad_norm": 0.31080353838712754,
+      "learning_rate": 1.3158139619846734e-06,
+      "loss": 0.993,
+      "step": 352
+    },
+    {
+      "epoch": 2.36697247706422,
+      "grad_norm": 0.32276338892191286,
+      "learning_rate": 1.289509602599996e-06,
+      "loss": 0.9847,
+      "step": 353
+    },
+    {
+      "epoch": 2.373644703919933,
+      "grad_norm": 0.3162201171120057,
+      "learning_rate": 1.2634318519996148e-06,
+      "loss": 0.9645,
+      "step": 354
+    },
+    {
+      "epoch": 2.3803169307756464,
+      "grad_norm": 0.31907787951020794,
+      "learning_rate": 1.2375823028159667e-06,
+      "loss": 0.9949,
+      "step": 355
+    },
+    {
+      "epoch": 2.3869891576313593,
+      "grad_norm": 0.330999449587722,
+      "learning_rate": 1.2119625337446673e-06,
+      "loss": 0.9617,
+      "step": 356
+    },
+    {
+      "epoch": 2.3936613844870727,
+      "grad_norm": 0.37560901242187644,
+      "learning_rate": 1.186574109448091e-06,
+      "loss": 0.965,
+      "step": 357
+    },
+    {
+      "epoch": 2.4003336113427856,
+      "grad_norm": 0.3032851792093919,
+      "learning_rate": 1.16141858045982e-06,
+      "loss": 0.969,
+      "step": 358
+    },
+    {
+      "epoch": 2.407005838198499,
+      "grad_norm": 0.3120802157192034,
+      "learning_rate": 1.1364974830899438e-06,
+      "loss": 0.9821,
+      "step": 359
+    },
+    {
+      "epoch": 2.413678065054212,
+      "grad_norm": 0.34540220887991835,
+      "learning_rate": 1.1118123393312397e-06,
+      "loss": 0.9535,
+      "step": 360
+    },
+    {
+      "epoch": 2.420350291909925,
+      "grad_norm": 0.29306217474195717,
+      "learning_rate": 1.0873646567662165e-06,
+      "loss": 0.9548,
+      "step": 361
+    },
+    {
+      "epoch": 2.427022518765638,
+      "grad_norm": 0.3275471084256797,
+      "learning_rate": 1.0631559284750398e-06,
+      "loss": 0.9208,
+      "step": 362
+    },
+    {
+      "epoch": 2.4336947456213514,
+      "grad_norm": 0.3237098002556768,
+      "learning_rate": 1.0391876329443534e-06,
+      "loss": 0.9896,
+      "step": 363
+    },
+    {
+      "epoch": 2.4403669724770642,
+      "grad_norm": 0.31683152915795526,
+      "learning_rate": 1.0154612339769777e-06,
+      "loss": 0.9515,
+      "step": 364
+    },
+    {
+      "epoch": 2.447039199332777,
+      "grad_norm": 0.31260220662008054,
+      "learning_rate": 9.919781806025136e-07,
+      "loss": 0.9284,
+      "step": 365
+    },
+    {
+      "epoch": 2.4537114261884905,
+      "grad_norm": 0.3196141247915384,
+      "learning_rate": 9.687399069888515e-07,
+      "loss": 1.0529,
+      "step": 366
+    },
+    {
+      "epoch": 2.4603836530442034,
+      "grad_norm": 0.3390686830414771,
+      "learning_rate": 9.457478323545749e-07,
+      "loss": 0.906,
+      "step": 367
+    },
+    {
+      "epoch": 2.4670558798999167,
+      "grad_norm": 0.2976435803727035,
+      "learning_rate": 9.23003360882293e-07,
+      "loss": 0.9914,
+      "step": 368
+    },
+    {
+      "epoch": 2.4737281067556296,
+      "grad_norm": 0.3256745610569351,
+      "learning_rate": 9.005078816328772e-07,
+      "loss": 0.9923,
+      "step": 369
+    },
+    {
+      "epoch": 2.480400333611343,
+      "grad_norm": 0.3105480823035307,
+      "learning_rate": 8.782627684606332e-07,
+      "loss": 0.9996,
+      "step": 370
+    },
+    {
+      "epoch": 2.487072560467056,
+      "grad_norm": 0.33299836342381517,
+      "learning_rate": 8.562693799293931e-07,
+      "loss": 0.96,
+      "step": 371
+    },
+    {
+      "epoch": 2.493744787322769,
+      "grad_norm": 0.3114815813330825,
+      "learning_rate": 8.345290592295429e-07,
+      "loss": 0.9143,
+      "step": 372
+    },
+    {
+      "epoch": 2.500417014178482,
+      "grad_norm": 0.28937151523319904,
+      "learning_rate": 8.130431340959982e-07,
+      "loss": 0.9746,
+      "step": 373
+    },
+    {
+      "epoch": 2.507089241034195,
+      "grad_norm": 0.32619060975827346,
+      "learning_rate": 7.918129167271055e-07,
+      "loss": 0.9561,
+      "step": 374
+    },
+    {
+      "epoch": 2.5137614678899083,
+      "grad_norm": 0.31360364241751837,
+      "learning_rate": 7.708397037045129e-07,
+      "loss": 0.8092,
+      "step": 375
+    },
+    {
+      "epoch": 2.5204336947456216,
+      "grad_norm": 0.30558210448525414,
+      "learning_rate": 7.50124775913979e-07,
+      "loss": 0.9529,
+      "step": 376
+    },
+    {
+      "epoch": 2.5271059216013345,
+      "grad_norm": 0.32199398622868297,
+      "learning_rate": 7.296693984671465e-07,
+      "loss": 0.9798,
+      "step": 377
+    },
+    {
+      "epoch": 2.5337781484570474,
+      "grad_norm": 0.32592296410779964,
+      "learning_rate": 7.094748206242797e-07,
+      "loss": 1.0314,
+      "step": 378
+    },
+    {
+      "epoch": 2.5404503753127607,
+      "grad_norm": 0.3464187438731346,
+      "learning_rate": 6.895422757179682e-07,
+      "loss": 0.9811,
+      "step": 379
+    },
+    {
+      "epoch": 2.5471226021684736,
+      "grad_norm": 0.36090219930856193,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 0.9489,
+      "step": 380
+    },
+    {
+      "epoch": 2.553794829024187,
+      "grad_norm": 0.31856176752128185,
+      "learning_rate": 6.50468137956049e-07,
+      "loss": 0.9542,
+      "step": 381
+    },
+    {
+      "epoch": 2.5604670558799,
+      "grad_norm": 0.31996625435359055,
+      "learning_rate": 6.313289314542392e-07,
+      "loss": 0.9717,
+      "step": 382
+    },
+    {
+      "epoch": 2.5671392827356128,
+      "grad_norm": 0.3486660778765644,
+      "learning_rate": 6.12456530450844e-07,
+      "loss": 1.047,
+      "step": 383
+    },
+    {
+      "epoch": 2.573811509591326,
+      "grad_norm": 0.40268147548442224,
+      "learning_rate": 5.938520875298587e-07,
+      "loss": 1.0224,
+      "step": 384
+    },
+    {
+      "epoch": 2.5804837364470394,
+      "grad_norm": 0.3676526483372923,
+      "learning_rate": 5.755167389104166e-07,
+      "loss": 0.9871,
+      "step": 385
+    },
+    {
+      "epoch": 2.5871559633027523,
+      "grad_norm": 0.29607309034948626,
+      "learning_rate": 5.574516043774059e-07,
+      "loss": 0.9608,
+      "step": 386
+    },
+    {
+      "epoch": 2.593828190158465,
+      "grad_norm": 0.3351255483218255,
+      "learning_rate": 5.396577872130676e-07,
+      "loss": 0.9818,
+      "step": 387
+    },
+    {
+      "epoch": 2.6005004170141786,
+      "grad_norm": 0.3153076169997922,
+      "learning_rate": 5.221363741296298e-07,
+      "loss": 0.9962,
+      "step": 388
+    },
+    {
+      "epoch": 2.6071726438698914,
+      "grad_norm": 0.3816251930803852,
+      "learning_rate": 5.048884352029271e-07,
+      "loss": 0.9757,
+      "step": 389
+    },
+    {
+      "epoch": 2.613844870725605,
+      "grad_norm": 0.31190657046064496,
+      "learning_rate": 4.879150238070585e-07,
+      "loss": 0.9948,
+      "step": 390
+    },
+    {
+      "epoch": 2.6205170975813177,
+      "grad_norm": 0.38637780955296236,
+      "learning_rate": 4.712171765500484e-07,
+      "loss": 0.9479,
+      "step": 391
+    },
+    {
+      "epoch": 2.627189324437031,
+      "grad_norm": 0.3428247774477413,
+      "learning_rate": 4.5479591321053895e-07,
+      "loss": 0.9882,
+      "step": 392
+    },
+    {
+      "epoch": 2.633861551292744,
+      "grad_norm": 0.3418954616257825,
+      "learning_rate": 4.386522366755169e-07,
+      "loss": 0.9817,
+      "step": 393
+    },
+    {
+      "epoch": 2.6405337781484572,
+      "grad_norm": 0.30360358878330007,
+      "learning_rate": 4.2278713287905335e-07,
+      "loss": 0.9702,
+      "step": 394
+    },
+    {
+      "epoch": 2.64720600500417,
+      "grad_norm": 0.3262516329197568,
+      "learning_rate": 4.072015707421006e-07,
+      "loss": 0.9566,
+      "step": 395
+    },
+    {
+      "epoch": 2.653878231859883,
+      "grad_norm": 0.29298754809339406,
+      "learning_rate": 3.918965021133131e-07,
+      "loss": 0.9991,
+      "step": 396
+    },
+    {
+      "epoch": 2.6605504587155964,
+      "grad_norm": 0.3523770371797201,
+      "learning_rate": 3.7687286171091355e-07,
+      "loss": 0.9052,
+      "step": 397
+    },
+    {
+      "epoch": 2.6672226855713093,
+      "grad_norm": 0.3286065151191008,
+      "learning_rate": 3.621315670656117e-07,
+      "loss": 1.0313,
+      "step": 398
+    },
+    {
+      "epoch": 2.6738949124270226,
+      "grad_norm": 0.3327745593564552,
+      "learning_rate": 3.4767351846456744e-07,
+      "loss": 0.9391,
+      "step": 399
+    },
+    {
+      "epoch": 2.6805671392827355,
+      "grad_norm": 0.33904862886378573,
+      "learning_rate": 3.3349959889640516e-07,
+      "loss": 0.9358,
+      "step": 400
+    },
+    {
+      "epoch": 2.687239366138449,
+      "grad_norm": 0.327976050954257,
+      "learning_rate": 3.196106739972926e-07,
+      "loss": 1.0326,
+      "step": 401
+    },
+    {
+      "epoch": 2.6939115929941617,
+      "grad_norm": 0.3193292187888942,
+      "learning_rate": 3.0600759199806815e-07,
+      "loss": 0.9541,
+      "step": 402
+    },
+    {
+      "epoch": 2.700583819849875,
+      "grad_norm": 0.3774921796009617,
+      "learning_rate": 2.9269118367244385e-07,
+      "loss": 0.9841,
+      "step": 403
+    },
+    {
+      "epoch": 2.707256046705588,
+      "grad_norm": 0.31482273028522967,
+      "learning_rate": 2.7966226228626156e-07,
+      "loss": 0.9702,
+      "step": 404
+    },
+    {
+      "epoch": 2.713928273561301,
+      "grad_norm": 0.2902681756785998,
+      "learning_rate": 2.669216235478295e-07,
+      "loss": 0.8949,
+      "step": 405
+    },
+    {
+      "epoch": 2.720600500417014,
+      "grad_norm": 0.3358268040426097,
+      "learning_rate": 2.544700455593252e-07,
+      "loss": 0.9286,
+      "step": 406
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.3223051627272287,
+      "learning_rate": 2.4230828876927293e-07,
+      "loss": 0.9739,
+      "step": 407
+    },
+    {
+      "epoch": 2.7339449541284404,
+      "grad_norm": 0.31524135263431996,
+      "learning_rate": 2.3043709592610486e-07,
+      "loss": 0.9046,
+      "step": 408
+    },
+    {
+      "epoch": 2.7406171809841533,
+      "grad_norm": 0.30097063718894235,
+      "learning_rate": 2.1885719203279587e-07,
+      "loss": 0.9438,
+      "step": 409
+    },
+    {
+      "epoch": 2.7472894078398666,
+      "grad_norm": 0.35005277308808397,
+      "learning_rate": 2.0756928430258838e-07,
+      "loss": 0.986,
+      "step": 410
+    },
+    {
+      "epoch": 2.7539616346955795,
+      "grad_norm": 0.28128342646548465,
+      "learning_rate": 1.9657406211579966e-07,
+      "loss": 0.9488,
+      "step": 411
+    },
+    {
+      "epoch": 2.760633861551293,
+      "grad_norm": 0.30197051093171356,
+      "learning_rate": 1.8587219697771942e-07,
+      "loss": 0.9738,
+      "step": 412
+    },
+    {
+      "epoch": 2.7673060884070058,
+      "grad_norm": 0.31320873231724333,
+      "learning_rate": 1.7546434247760147e-07,
+      "loss": 0.9077,
+      "step": 413
+    },
+    {
+      "epoch": 2.773978315262719,
+      "grad_norm": 0.3281071984763327,
+      "learning_rate": 1.6535113424874683e-07,
+      "loss": 0.9133,
+      "step": 414
+    },
+    {
+      "epoch": 2.780650542118432,
+      "grad_norm": 0.34179101949267504,
+      "learning_rate": 1.555331899296808e-07,
+      "loss": 1.0089,
+      "step": 415
+    },
+    {
+      "epoch": 2.7873227689741453,
+      "grad_norm": 0.31629478659692434,
+      "learning_rate": 1.460111091264377e-07,
+      "loss": 0.9674,
+      "step": 416
+    },
+    {
+      "epoch": 2.793994995829858,
+      "grad_norm": 0.3248237469597133,
+      "learning_rate": 1.3678547337593494e-07,
+      "loss": 1.0218,
+      "step": 417
+    },
+    {
+      "epoch": 2.800667222685571,
+      "grad_norm": 0.31720738943716026,
+      "learning_rate": 1.2785684611046345e-07,
+      "loss": 0.9407,
+      "step": 418
+    },
+    {
+      "epoch": 2.8073394495412844,
+      "grad_norm": 0.2767770769664715,
+      "learning_rate": 1.1922577262327374e-07,
+      "loss": 0.9387,
+      "step": 419
+    },
+    {
+      "epoch": 2.8140116763969973,
+      "grad_norm": 0.34714214699914475,
+      "learning_rate": 1.1089278003527438e-07,
+      "loss": 1.0192,
+      "step": 420
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 447,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 30,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1084175513812992.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-420/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13aa99fb97f6ca47f05e0576e78b2984b387280caa0db367bbae1e4bc36a8891
+size 7544