Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-32B
+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 0.15.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-32B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": [],
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b70daf71666bd835d97ced9e9104492fd821b19d632a73453b89d8b11e27a051
+size 2147605960

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,100 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 25600,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 64,
+  "model_type": "qwen3",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.10.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936,
+  "torch_dtype": "bfloat16"
+}

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": 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|>"
+  ],
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1176 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 162,
+  "global_step": 162,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012345679012345678,
+      "grad_norm": 0.3504016399383545,
+      "learning_rate": 1e-05,
+      "loss": 2.1533203125,
+      "step": 1
+    },
+    {
+      "epoch": 0.024691358024691357,
+      "grad_norm": 0.2849632203578949,
+      "learning_rate": 9.999059852242508e-06,
+      "loss": 1.943359375,
+      "step": 2
+    },
+    {
+      "epoch": 0.037037037037037035,
+      "grad_norm": 0.39613625407218933,
+      "learning_rate": 9.996239762521152e-06,
+      "loss": 2.1646728515625,
+      "step": 3
+    },
+    {
+      "epoch": 0.04938271604938271,
+      "grad_norm": 0.35534441471099854,
+      "learning_rate": 9.991540791356342e-06,
+      "loss": 2.091796875,
+      "step": 4
+    },
+    {
+      "epoch": 0.06172839506172839,
+      "grad_norm": 0.48331987857818604,
+      "learning_rate": 9.98496470583896e-06,
+      "loss": 2.210205078125,
+      "step": 5
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 0.4012807011604309,
+      "learning_rate": 9.976513978965829e-06,
+      "loss": 1.9215087890625,
+      "step": 6
+    },
+    {
+      "epoch": 0.08641975308641975,
+      "grad_norm": 0.44781288504600525,
+      "learning_rate": 9.966191788709716e-06,
+      "loss": 1.95263671875,
+      "step": 7
+    },
+    {
+      "epoch": 0.09876543209876543,
+      "grad_norm": 0.4039982259273529,
+      "learning_rate": 9.954002016824226e-06,
+      "loss": 1.783203125,
+      "step": 8
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.381326287984848,
+      "learning_rate": 9.939949247384046e-06,
+      "loss": 1.7802734375,
+      "step": 9
+    },
+    {
+      "epoch": 0.12345679012345678,
+      "grad_norm": 0.3175008296966553,
+      "learning_rate": 9.924038765061042e-06,
+      "loss": 1.7203369140625,
+      "step": 10
+    },
+    {
+      "epoch": 0.13580246913580246,
+      "grad_norm": 0.26221078634262085,
+      "learning_rate": 9.906276553136924e-06,
+      "loss": 1.67431640625,
+      "step": 11
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.26429814100265503,
+      "learning_rate": 9.886669291253178e-06,
+      "loss": 1.66455078125,
+      "step": 12
+    },
+    {
+      "epoch": 0.16049382716049382,
+      "grad_norm": 0.28965020179748535,
+      "learning_rate": 9.86522435289912e-06,
+      "loss": 1.6767578125,
+      "step": 13
+    },
+    {
+      "epoch": 0.1728395061728395,
+      "grad_norm": 0.25965702533721924,
+      "learning_rate": 9.841949802639031e-06,
+      "loss": 1.58154296875,
+      "step": 14
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 0.24088655412197113,
+      "learning_rate": 9.816854393079402e-06,
+      "loss": 1.58544921875,
+      "step": 15
+    },
+    {
+      "epoch": 0.19753086419753085,
+      "grad_norm": 0.2812812924385071,
+      "learning_rate": 9.789947561577445e-06,
+      "loss": 1.6029052734375,
+      "step": 16
+    },
+    {
+      "epoch": 0.20987654320987653,
+      "grad_norm": 0.23914368450641632,
+      "learning_rate": 9.761239426692077e-06,
+      "loss": 1.52874755859375,
+      "step": 17
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.23985321819782257,
+      "learning_rate": 9.730740784378755e-06,
+      "loss": 1.5107421875,
+      "step": 18
+    },
+    {
+      "epoch": 0.2345679012345679,
+      "grad_norm": 0.23493242263793945,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 1.45654296875,
+      "step": 19
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 0.2240285575389862,
+      "learning_rate": 9.664418523660004e-06,
+      "loss": 1.44580078125,
+      "step": 20
+    },
+    {
+      "epoch": 0.25925925925925924,
+      "grad_norm": 0.21557030081748962,
+      "learning_rate": 9.628619846344453e-06,
+      "loss": 1.4422607421875,
+      "step": 21
+    },
+    {
+      "epoch": 0.2716049382716049,
+      "grad_norm": 0.2036324441432953,
+      "learning_rate": 9.591080534401371e-06,
+      "loss": 1.413330078125,
+      "step": 22
+    },
+    {
+      "epoch": 0.2839506172839506,
+      "grad_norm": 0.1956496238708496,
+      "learning_rate": 9.551814704830734e-06,
+      "loss": 1.37646484375,
+      "step": 23
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.20368410646915436,
+      "learning_rate": 9.51083712390519e-06,
+      "loss": 1.42236328125,
+      "step": 24
+    },
+    {
+      "epoch": 0.30864197530864196,
+      "grad_norm": 0.1811431646347046,
+      "learning_rate": 9.468163201617063e-06,
+      "loss": 1.3662109375,
+      "step": 25
+    },
+    {
+      "epoch": 0.32098765432098764,
+      "grad_norm": 0.25459423661231995,
+      "learning_rate": 9.423808985883289e-06,
+      "loss": 1.3360595703125,
+      "step": 26
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.1667819321155548,
+      "learning_rate": 9.377791156510456e-06,
+      "loss": 1.3681640625,
+      "step": 27
+    },
+    {
+      "epoch": 0.345679012345679,
+      "grad_norm": 0.1551096886396408,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 1.31402587890625,
+      "step": 28
+    },
+    {
+      "epoch": 0.35802469135802467,
+      "grad_norm": 0.14206942915916443,
+      "learning_rate": 9.280834497651334e-06,
+      "loss": 1.2802734375,
+      "step": 29
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.13667216897010803,
+      "learning_rate": 9.229932129599206e-06,
+      "loss": 1.2950439453125,
+      "step": 30
+    },
+    {
+      "epoch": 0.38271604938271603,
+      "grad_norm": 0.11959635466337204,
+      "learning_rate": 9.177439057064684e-06,
+      "loss": 1.31982421875,
+      "step": 31
+    },
+    {
+      "epoch": 0.3950617283950617,
+      "grad_norm": 0.1104661077260971,
+      "learning_rate": 9.123375020545534e-06,
+      "loss": 1.2674560546875,
+      "step": 32
+    },
+    {
+      "epoch": 0.4074074074074074,
+      "grad_norm": 0.10608602315187454,
+      "learning_rate": 9.067760351314838e-06,
+      "loss": 1.2978515625,
+      "step": 33
+    },
+    {
+      "epoch": 0.41975308641975306,
+      "grad_norm": 0.09825296700000763,
+      "learning_rate": 9.01061596377522e-06,
+      "loss": 1.25439453125,
+      "step": 34
+    },
+    {
+      "epoch": 0.43209876543209874,
+      "grad_norm": 0.09724781662225723,
+      "learning_rate": 8.951963347593797e-06,
+      "loss": 1.2310791015625,
+      "step": 35
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.0967152863740921,
+      "learning_rate": 8.891824559620801e-06,
+      "loss": 1.24981689453125,
+      "step": 36
+    },
+    {
+      "epoch": 0.4567901234567901,
+      "grad_norm": 0.10894442349672318,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 1.24609375,
+      "step": 37
+    },
+    {
+      "epoch": 0.4691358024691358,
+      "grad_norm": 0.12250322848558426,
+      "learning_rate": 8.767179481638303e-06,
+      "loss": 1.21630859375,
+      "step": 38
+    },
+    {
+      "epoch": 0.48148148148148145,
+      "grad_norm": 0.12086455523967743,
+      "learning_rate": 8.702720065545024e-06,
+      "loss": 1.2171630859375,
+      "step": 39
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.13029126822948456,
+      "learning_rate": 8.636868207865244e-06,
+      "loss": 1.201171875,
+      "step": 40
+    },
+    {
+      "epoch": 0.5061728395061729,
+      "grad_norm": 0.1197105273604393,
+      "learning_rate": 8.569648672789496e-06,
+      "loss": 1.24029541015625,
+      "step": 41
+    },
+    {
+      "epoch": 0.5185185185185185,
+      "grad_norm": 0.10641508549451828,
+      "learning_rate": 8.501086738835843e-06,
+      "loss": 1.24267578125,
+      "step": 42
+    },
+    {
+      "epoch": 0.5308641975308642,
+      "grad_norm": 0.11860142648220062,
+      "learning_rate": 8.43120818934367e-06,
+      "loss": 1.1580810546875,
+      "step": 43
+    },
+    {
+      "epoch": 0.5432098765432098,
+      "grad_norm": 0.10126637667417526,
+      "learning_rate": 8.360039302777614e-06,
+      "loss": 1.19140625,
+      "step": 44
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.08920259028673172,
+      "learning_rate": 8.28760684284532e-06,
+      "loss": 1.25390625,
+      "step": 45
+    },
+    {
+      "epoch": 0.5679012345679012,
+      "grad_norm": 0.09504316747188568,
+      "learning_rate": 8.213938048432697e-06,
+      "loss": 1.1878662109375,
+      "step": 46
+    },
+    {
+      "epoch": 0.5802469135802469,
+      "grad_norm": 0.08583307266235352,
+      "learning_rate": 8.139060623360494e-06,
+      "loss": 1.16949462890625,
+      "step": 47
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.07538800686597824,
+      "learning_rate": 8.063002725966014e-06,
+      "loss": 1.166748046875,
+      "step": 48
+    },
+    {
+      "epoch": 0.6049382716049383,
+      "grad_norm": 0.0806780606508255,
+      "learning_rate": 7.985792958513932e-06,
+      "loss": 1.17333984375,
+      "step": 49
+    },
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 0.07670904695987701,
+      "learning_rate": 7.907460356440133e-06,
+      "loss": 1.22998046875,
+      "step": 50
+    },
+    {
+      "epoch": 0.6296296296296297,
+      "grad_norm": 0.06912268698215485,
+      "learning_rate": 7.828034377432694e-06,
+      "loss": 1.22021484375,
+      "step": 51
+    },
+    {
+      "epoch": 0.6419753086419753,
+      "grad_norm": 0.06748771667480469,
+      "learning_rate": 7.747544890354031e-06,
+      "loss": 1.181396484375,
+      "step": 52
+    },
+    {
+      "epoch": 0.654320987654321,
+      "grad_norm": 0.06408040970563889,
+      "learning_rate": 7.666022164008458e-06,
+      "loss": 1.1630859375,
+      "step": 53
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.07093410938978195,
+      "learning_rate": 7.5834968557593155e-06,
+      "loss": 1.16015625,
+      "step": 54
+    },
+    {
+      "epoch": 0.6790123456790124,
+      "grad_norm": 0.0701528862118721,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.1929931640625,
+      "step": 55
+    },
+    {
+      "epoch": 0.691358024691358,
+      "grad_norm": 0.06486670672893524,
+      "learning_rate": 7.415562996483193e-06,
+      "loss": 1.11865234375,
+      "step": 56
+    },
+    {
+      "epoch": 0.7037037037037037,
+      "grad_norm": 0.07944019138813019,
+      "learning_rate": 7.330217598512696e-06,
+      "loss": 1.146484375,
+      "step": 57
+    },
+    {
+      "epoch": 0.7160493827160493,
+      "grad_norm": 0.06304322928190231,
+      "learning_rate": 7.243995901002312e-06,
+      "loss": 1.1806640625,
+      "step": 58
+    },
+    {
+      "epoch": 0.7283950617283951,
+      "grad_norm": 0.06566708534955978,
+      "learning_rate": 7.156930328406268e-06,
+      "loss": 1.166015625,
+      "step": 59
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.06502839177846909,
+      "learning_rate": 7.069053622525697e-06,
+      "loss": 1.1337890625,
+      "step": 60
+    },
+    {
+      "epoch": 0.7530864197530864,
+      "grad_norm": 0.05706457421183586,
+      "learning_rate": 6.980398830195785e-06,
+      "loss": 1.16357421875,
+      "step": 61
+    },
+    {
+      "epoch": 0.7654320987654321,
+      "grad_norm": 0.059692319482564926,
+      "learning_rate": 6.890999290858213e-06,
+      "loss": 1.171875,
+      "step": 62
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.0484984889626503,
+      "learning_rate": 6.800888624023552e-06,
+      "loss": 1.2109375,
+      "step": 63
+    },
+    {
+      "epoch": 0.7901234567901234,
+      "grad_norm": 0.0469343475997448,
+      "learning_rate": 6.710100716628345e-06,
+      "loss": 1.15325927734375,
+      "step": 64
+    },
+    {
+      "epoch": 0.8024691358024691,
+      "grad_norm": 0.04828719422221184,
+      "learning_rate": 6.618669710291607e-06,
+      "loss": 1.1181640625,
+      "step": 65
+    },
+    {
+      "epoch": 0.8148148148148148,
+      "grad_norm": 0.05165661498904228,
+      "learning_rate": 6.526629988475567e-06,
+      "loss": 1.1224365234375,
+      "step": 66
+    },
+    {
+      "epoch": 0.8271604938271605,
+      "grad_norm": 0.04464888572692871,
+      "learning_rate": 6.434016163555452e-06,
+      "loss": 1.11822509765625,
+      "step": 67
+    },
+    {
+      "epoch": 0.8395061728395061,
+      "grad_norm": 0.04451960325241089,
+      "learning_rate": 6.340863063803187e-06,
+      "loss": 1.16094970703125,
+      "step": 68
+    },
+    {
+      "epoch": 0.8518518518518519,
+      "grad_norm": 0.043933067470788956,
+      "learning_rate": 6.247205720289907e-06,
+      "loss": 1.1513671875,
+      "step": 69
+    },
+    {
+      "epoch": 0.8641975308641975,
+      "grad_norm": 0.06273156404495239,
+      "learning_rate": 6.153079353712201e-06,
+      "loss": 1.1090087890625,
+      "step": 70
+    },
+    {
+      "epoch": 0.8765432098765432,
+      "grad_norm": 0.041264940053224564,
+      "learning_rate": 6.058519361147055e-06,
+      "loss": 1.099609375,
+      "step": 71
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.03963320702314377,
+      "learning_rate": 5.9635613027404495e-06,
+      "loss": 1.1201171875,
+      "step": 72
+    },
+    {
+      "epoch": 0.9012345679012346,
+      "grad_norm": 0.059883832931518555,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 1.12451171875,
+      "step": 73
+    },
+    {
+      "epoch": 0.9135802469135802,
+      "grad_norm": 0.04652964696288109,
+      "learning_rate": 5.772593964039203e-06,
+      "loss": 1.150146484375,
+      "step": 74
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 0.04225148260593414,
+      "learning_rate": 5.6766564987506564e-06,
+      "loss": 1.09912109375,
+      "step": 75
+    },
+    {
+      "epoch": 0.9382716049382716,
+      "grad_norm": 0.0415518693625927,
+      "learning_rate": 5.5804645706261515e-06,
+      "loss": 1.0869140625,
+      "step": 76
+    },
+    {
+      "epoch": 0.9506172839506173,
+      "grad_norm": 0.041372768580913544,
+      "learning_rate": 5.484054353515896e-06,
+      "loss": 1.20196533203125,
+      "step": 77
+    },
+    {
+      "epoch": 0.9629629629629629,
+      "grad_norm": 0.04058866947889328,
+      "learning_rate": 5.387462103359655e-06,
+      "loss": 1.08984375,
+      "step": 78
+    },
+    {
+      "epoch": 0.9753086419753086,
+      "grad_norm": 0.03967684879899025,
+      "learning_rate": 5.290724144552379e-06,
+      "loss": 1.12066650390625,
+      "step": 79
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.039729781448841095,
+      "learning_rate": 5.193876856284085e-06,
+      "loss": 1.123779296875,
+      "step": 80
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.042973633855581284,
+      "learning_rate": 5.096956658859122e-06,
+      "loss": 1.103759765625,
+      "step": 81
+    },
+    {
+      "epoch": 1.0123456790123457,
+      "grad_norm": 0.03994538635015488,
+      "learning_rate": 5e-06,
+      "loss": 1.12353515625,
+      "step": 82
+    },
+    {
+      "epoch": 1.0246913580246915,
+      "grad_norm": 0.04001010209321976,
+      "learning_rate": 4.903043341140879e-06,
+      "loss": 1.11376953125,
+      "step": 83
+    },
+    {
+      "epoch": 1.037037037037037,
+      "grad_norm": 0.03813829645514488,
+      "learning_rate": 4.806123143715916e-06,
+      "loss": 1.08966064453125,
+      "step": 84
+    },
+    {
+      "epoch": 1.0493827160493827,
+      "grad_norm": 0.04175872728228569,
+      "learning_rate": 4.7092758554476215e-06,
+      "loss": 1.1650390625,
+      "step": 85
+    },
+    {
+      "epoch": 1.0617283950617284,
+      "grad_norm": 0.054764218628406525,
+      "learning_rate": 4.6125378966403465e-06,
+      "loss": 1.1142578125,
+      "step": 86
+    },
+    {
+      "epoch": 1.074074074074074,
+      "grad_norm": 0.037059519439935684,
+      "learning_rate": 4.515945646484105e-06,
+      "loss": 1.084716796875,
+      "step": 87
+    },
+    {
+      "epoch": 1.0864197530864197,
+      "grad_norm": 0.03715408220887184,
+      "learning_rate": 4.4195354293738484e-06,
+      "loss": 1.121337890625,
+      "step": 88
+    },
+    {
+      "epoch": 1.0987654320987654,
+      "grad_norm": 0.03572078049182892,
+      "learning_rate": 4.323343501249346e-06,
+      "loss": 1.1025390625,
+      "step": 89
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.039801325649023056,
+      "learning_rate": 4.227406035960798e-06,
+      "loss": 1.1318359375,
+      "step": 90
+    },
+    {
+      "epoch": 1.123456790123457,
+      "grad_norm": 0.03618643805384636,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 1.1199951171875,
+      "step": 91
+    },
+    {
+      "epoch": 1.1358024691358024,
+      "grad_norm": 0.039840616285800934,
+      "learning_rate": 4.036438697259551e-06,
+      "loss": 1.12451171875,
+      "step": 92
+    },
+    {
+      "epoch": 1.1481481481481481,
+      "grad_norm": 0.035334352403879166,
+      "learning_rate": 3.941480638852948e-06,
+      "loss": 1.1181640625,
+      "step": 93
+    },
+    {
+      "epoch": 1.1604938271604939,
+      "grad_norm": 0.05649956315755844,
+      "learning_rate": 3.8469206462878e-06,
+      "loss": 1.09619140625,
+      "step": 94
+    },
+    {
+      "epoch": 1.1728395061728394,
+      "grad_norm": 0.03644261509180069,
+      "learning_rate": 3.752794279710094e-06,
+      "loss": 1.07666015625,
+      "step": 95
+    },
+    {
+      "epoch": 1.1851851851851851,
+      "grad_norm": 0.03816032409667969,
+      "learning_rate": 3.6591369361968127e-06,
+      "loss": 1.1474609375,
+      "step": 96
+    },
+    {
+      "epoch": 1.1975308641975309,
+      "grad_norm": 0.06648016721010208,
+      "learning_rate": 3.5659838364445505e-06,
+      "loss": 1.116455078125,
+      "step": 97
+    },
+    {
+      "epoch": 1.2098765432098766,
+      "grad_norm": 0.03444468230009079,
+      "learning_rate": 3.473370011524435e-06,
+      "loss": 1.11590576171875,
+      "step": 98
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.035777244716882706,
+      "learning_rate": 3.3813302897083955e-06,
+      "loss": 1.11669921875,
+      "step": 99
+    },
+    {
+      "epoch": 1.2345679012345678,
+      "grad_norm": 0.04556313157081604,
+      "learning_rate": 3.289899283371657e-06,
+      "loss": 1.0751953125,
+      "step": 100
+    },
+    {
+      "epoch": 1.2469135802469136,
+      "grad_norm": 0.03846881538629532,
+      "learning_rate": 3.1991113759764493e-06,
+      "loss": 1.1162109375,
+      "step": 101
+    },
+    {
+      "epoch": 1.2592592592592593,
+      "grad_norm": 0.047668684273958206,
+      "learning_rate": 3.1090007091417884e-06,
+      "loss": 1.1358642578125,
+      "step": 102
+    },
+    {
+      "epoch": 1.2716049382716048,
+      "grad_norm": 0.03538711741566658,
+      "learning_rate": 3.019601169804216e-06,
+      "loss": 1.1220703125,
+      "step": 103
+    },
+    {
+      "epoch": 1.2839506172839505,
+      "grad_norm": 0.035502634942531586,
+      "learning_rate": 2.9309463774743047e-06,
+      "loss": 1.101318359375,
+      "step": 104
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.03785805031657219,
+      "learning_rate": 2.843069671593734e-06,
+      "loss": 1.15576171875,
+      "step": 105
+    },
+    {
+      "epoch": 1.308641975308642,
+      "grad_norm": 0.04106925055384636,
+      "learning_rate": 2.7560040989976894e-06,
+      "loss": 1.10888671875,
+      "step": 106
+    },
+    {
+      "epoch": 1.3209876543209877,
+      "grad_norm": 0.1851484477519989,
+      "learning_rate": 2.6697824014873076e-06,
+      "loss": 1.0380859375,
+      "step": 107
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.0330730564892292,
+      "learning_rate": 2.5844370035168077e-06,
+      "loss": 1.14306640625,
+      "step": 108
+    },
+    {
+      "epoch": 1.345679012345679,
+      "grad_norm": 0.040814485400915146,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 1.10137939453125,
+      "step": 109
+    },
+    {
+      "epoch": 1.3580246913580247,
+      "grad_norm": 0.03741513565182686,
+      "learning_rate": 2.4165031442406857e-06,
+      "loss": 1.08203125,
+      "step": 110
+    },
+    {
+      "epoch": 1.3703703703703702,
+      "grad_norm": 0.04464615136384964,
+      "learning_rate": 2.333977835991545e-06,
+      "loss": 1.09710693359375,
+      "step": 111
+    },
+    {
+      "epoch": 1.382716049382716,
+      "grad_norm": 0.06438415497541428,
+      "learning_rate": 2.2524551096459703e-06,
+      "loss": 1.140625,
+      "step": 112
+    },
+    {
+      "epoch": 1.3950617283950617,
+      "grad_norm": 0.045622579753398895,
+      "learning_rate": 2.171965622567308e-06,
+      "loss": 1.10125732421875,
+      "step": 113
+    },
+    {
+      "epoch": 1.4074074074074074,
+      "grad_norm": 0.041726406663656235,
+      "learning_rate": 2.0925396435598665e-06,
+      "loss": 1.13916015625,
+      "step": 114
+    },
+    {
+      "epoch": 1.4197530864197532,
+      "grad_norm": 0.04645635187625885,
+      "learning_rate": 2.0142070414860704e-06,
+      "loss": 1.10205078125,
+      "step": 115
+    },
+    {
+      "epoch": 1.4320987654320987,
+      "grad_norm": 0.04142511263489723,
+      "learning_rate": 1.936997274033986e-06,
+      "loss": 1.080810546875,
+      "step": 116
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.04133642837405205,
+      "learning_rate": 1.8609393766395083e-06,
+      "loss": 1.11456298828125,
+      "step": 117
+    },
+    {
+      "epoch": 1.4567901234567902,
+      "grad_norm": 0.037442710250616074,
+      "learning_rate": 1.7860619515673034e-06,
+      "loss": 1.1109619140625,
+      "step": 118
+    },
+    {
+      "epoch": 1.4691358024691357,
+      "grad_norm": 0.038170378655195236,
+      "learning_rate": 1.7123931571546826e-06,
+      "loss": 1.092041015625,
+      "step": 119
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.03954925388097763,
+      "learning_rate": 1.639960697222388e-06,
+      "loss": 1.0933837890625,
+      "step": 120
+    },
+    {
+      "epoch": 1.4938271604938271,
+      "grad_norm": 0.04117150604724884,
+      "learning_rate": 1.5687918106563326e-06,
+      "loss": 1.0859375,
+      "step": 121
+    },
+    {
+      "epoch": 1.5061728395061729,
+      "grad_norm": 0.04665956273674965,
+      "learning_rate": 1.4989132611641576e-06,
+      "loss": 1.12890625,
+      "step": 122
+    },
+    {
+      "epoch": 1.5185185185185186,
+      "grad_norm": 0.03867404907941818,
+      "learning_rate": 1.4303513272105057e-06,
+      "loss": 1.13916015625,
+      "step": 123
+    },
+    {
+      "epoch": 1.5308641975308643,
+      "grad_norm": 0.039081573486328125,
+      "learning_rate": 1.3631317921347564e-06,
+      "loss": 1.05682373046875,
+      "step": 124
+    },
+    {
+      "epoch": 1.5432098765432098,
+      "grad_norm": 0.040184635668992996,
+      "learning_rate": 1.297279934454978e-06,
+      "loss": 1.0966796875,
+      "step": 125
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.03619195148348808,
+      "learning_rate": 1.2328205183616964e-06,
+      "loss": 1.16943359375,
+      "step": 126
+    },
+    {
+      "epoch": 1.567901234567901,
+      "grad_norm": 0.049317002296447754,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 1.095703125,
+      "step": 127
+    },
+    {
+      "epoch": 1.5802469135802468,
+      "grad_norm": 0.035242196172475815,
+      "learning_rate": 1.1081754403792e-06,
+      "loss": 1.08819580078125,
+      "step": 128
+    },
+    {
+      "epoch": 1.5925925925925926,
+      "grad_norm": 0.038244109600782394,
+      "learning_rate": 1.0480366524062041e-06,
+      "loss": 1.0908203125,
+      "step": 129
+    },
+    {
+      "epoch": 1.6049382716049383,
+      "grad_norm": 0.03420025855302811,
+      "learning_rate": 9.893840362247809e-07,
+      "loss": 1.09808349609375,
+      "step": 130
+    },
+    {
+      "epoch": 1.617283950617284,
+      "grad_norm": 0.039074983447790146,
+      "learning_rate": 9.322396486851626e-07,
+      "loss": 1.1611328125,
+      "step": 131
+    },
+    {
+      "epoch": 1.6296296296296298,
+      "grad_norm": 0.04157653823494911,
+      "learning_rate": 8.766249794544662e-07,
+      "loss": 1.152099609375,
+      "step": 132
+    },
+    {
+      "epoch": 1.6419753086419753,
+      "grad_norm": 0.035004787147045135,
+      "learning_rate": 8.225609429353187e-07,
+      "loss": 1.1126708984375,
+      "step": 133
+    },
+    {
+      "epoch": 1.654320987654321,
+      "grad_norm": 0.034718792885541916,
+      "learning_rate": 7.700678704007947e-07,
+      "loss": 1.09814453125,
+      "step": 134
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.040958672761917114,
+      "learning_rate": 7.191655023486682e-07,
+      "loss": 1.0972900390625,
+      "step": 135
+    },
+    {
+      "epoch": 1.6790123456790123,
+      "grad_norm": 0.0355539470911026,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 1.1375732421875,
+      "step": 136
+    },
+    {
+      "epoch": 1.691358024691358,
+      "grad_norm": 0.033885106444358826,
+      "learning_rate": 6.222088434895462e-07,
+      "loss": 1.060791015625,
+      "step": 137
+    },
+    {
+      "epoch": 1.7037037037037037,
+      "grad_norm": 0.04775747284293175,
+      "learning_rate": 5.76191014116711e-07,
+      "loss": 1.0908203125,
+      "step": 138
+    },
+    {
+      "epoch": 1.7160493827160495,
+      "grad_norm": 0.039114437997341156,
+      "learning_rate": 5.318367983829393e-07,
+      "loss": 1.1270751953125,
+      "step": 139
+    },
+    {
+      "epoch": 1.7283950617283952,
+      "grad_norm": 0.03365745022892952,
+      "learning_rate": 4.891628760948114e-07,
+      "loss": 1.11376953125,
+      "step": 140
+    },
+    {
+      "epoch": 1.7407407407407407,
+      "grad_norm": 0.03737064078450203,
+      "learning_rate": 4.481852951692672e-07,
+      "loss": 1.08740234375,
+      "step": 141
+    },
+    {
+      "epoch": 1.7530864197530864,
+      "grad_norm": 0.035218264907598495,
+      "learning_rate": 4.089194655986306e-07,
+      "loss": 1.11376953125,
+      "step": 142
+    },
+    {
+      "epoch": 1.765432098765432,
+      "grad_norm": 0.038012027740478516,
+      "learning_rate": 3.7138015365554834e-07,
+      "loss": 1.12548828125,
+      "step": 143
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.039106547832489014,
+      "learning_rate": 3.355814763399973e-07,
+      "loss": 1.167724609375,
+      "step": 144
+    },
+    {
+      "epoch": 1.7901234567901234,
+      "grad_norm": 0.0369529202580452,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 1.11187744140625,
+      "step": 145
+    },
+    {
+      "epoch": 1.8024691358024691,
+      "grad_norm": 0.033403217792510986,
+      "learning_rate": 2.6925921562124867e-07,
+      "loss": 1.0771484375,
+      "step": 146
+    },
+    {
+      "epoch": 1.8148148148148149,
+      "grad_norm": 0.036414727568626404,
+      "learning_rate": 2.3876057330792344e-07,
+      "loss": 1.0810546875,
+      "step": 147
+    },
+    {
+      "epoch": 1.8271604938271606,
+      "grad_norm": 0.034531738609075546,
+      "learning_rate": 2.1005243842255552e-07,
+      "loss": 1.08123779296875,
+      "step": 148
+    },
+    {
+      "epoch": 1.8395061728395061,
+      "grad_norm": 0.03815017640590668,
+      "learning_rate": 1.8314560692059836e-07,
+      "loss": 1.12554931640625,
+      "step": 149
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 0.03700941801071167,
+      "learning_rate": 1.5805019736097105e-07,
+      "loss": 1.11328125,
+      "step": 150
+    },
+    {
+      "epoch": 1.8641975308641974,
+      "grad_norm": 0.05484495311975479,
+      "learning_rate": 1.3477564710088097e-07,
+      "loss": 1.0731201171875,
+      "step": 151
+    },
+    {
+      "epoch": 1.876543209876543,
+      "grad_norm": 0.035358965396881104,
+      "learning_rate": 1.1333070874682217e-07,
+      "loss": 1.06396484375,
+      "step": 152
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.032334230840206146,
+      "learning_rate": 9.372344686307655e-08,
+      "loss": 1.0888671875,
+      "step": 153
+    },
+    {
+      "epoch": 1.9012345679012346,
+      "grad_norm": 0.0475231297314167,
+      "learning_rate": 7.59612349389599e-08,
+      "loss": 1.09375,
+      "step": 154
+    },
+    {
+      "epoch": 1.9135802469135803,
+      "grad_norm": 0.03583948686718941,
+      "learning_rate": 6.005075261595495e-08,
+      "loss": 1.11962890625,
+      "step": 155
+    },
+    {
+      "epoch": 1.925925925925926,
+      "grad_norm": 0.03208550065755844,
+      "learning_rate": 4.599798317577342e-08,
+      "loss": 1.06982421875,
+      "step": 156
+    },
+    {
+      "epoch": 1.9382716049382716,
+      "grad_norm": 0.03310169279575348,
+      "learning_rate": 3.3808211290284886e-08,
+      "loss": 1.0625,
+      "step": 157
+    },
+    {
+      "epoch": 1.9506172839506173,
+      "grad_norm": 0.03629239648580551,
+      "learning_rate": 2.3486021034170857e-08,
+      "loss": 1.17596435546875,
+      "step": 158
+    },
+    {
+      "epoch": 1.9629629629629628,
+      "grad_norm": 0.0365874320268631,
+      "learning_rate": 1.5035294161039882e-08,
+      "loss": 1.0638427734375,
+      "step": 159
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.03390483185648918,
+      "learning_rate": 8.459208643659122e-09,
+      "loss": 1.09637451171875,
+      "step": 160
+    },
+    {
+      "epoch": 1.9876543209876543,
+      "grad_norm": 0.038602519780397415,
+      "learning_rate": 3.760237478849793e-09,
+      "loss": 1.1002197265625,
+      "step": 161
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.03919296711683273,
+      "learning_rate": 9.401477574932927e-10,
+      "loss": 1.082275390625,
+      "step": 162
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.14111328125,
+      "eval_runtime": 5.2059,
+      "eval_samples_per_second": 1.345,
+      "eval_steps_per_second": 0.192,
+      "step": 162
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 162,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0344488982217228e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}