Training in progress, step 320, checkpoint

.gitattributes

@@ -65,3 +65,4 @@ checkpoint-280/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-290/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-310/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-320/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-320/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen3-14B
+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 0.15.2

checkpoint-320/adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen3-14B",
+  "bias": "none",
+  "corda_config": null,
+  "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": [
+    20
+  ],
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 1,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": true
+}

checkpoint-320/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39de5db2ffd5204c7ea69448e0ff8a3449b3148edeb6fa586ddca627658a8d22
+size 90400

checkpoint-320/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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-320/chat_template.jinja

@@ -0,0 +1,98 @@
+{%- 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 forward_message in messages %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- set message = messages[index] %}
+    {%- set current_content = message.content if message.content is not none else '' %}
+    {%- set tool_start = '<tool_response>' %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = current_content[:tool_start_length] %}
+    {%- set tool_end = '</tool_response>' %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (current_content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = current_content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = (message.content.split('</think>')|last).lstrip('\n') %}
+                {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).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' }}
+        {{- message.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 %}

checkpoint-320/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9988c98d60dfe1c71bb17ddc2d97ca0fed0e7682b5bb90a8a9ac6d3170f33b1
+size 52133

checkpoint-320/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f90246cca0664f0a4cfe8c5c39faa439e3d16795cf43d63a33a62016030bea00
+size 14581

checkpoint-320/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a26f5c5b1c68d2810c13fa2f3255de9b191e480d8d48e98b35e99de9c7538a5
+size 1465

checkpoint-320/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": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-320/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-320/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 40960,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-320/trainer_state.json

@@ -0,0 +1,2530 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8533333333333334,
+  "eval_steps": 10,
+  "global_step": 320,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0026666666666666666,
+      "grad_norm": 1.7862446308135986,
+      "learning_rate": 0.0,
+      "loss": 2.9911,
+      "step": 1
+    },
+    {
+      "epoch": 0.005333333333333333,
+      "grad_norm": 1.6373525857925415,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.7849,
+      "step": 2
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 1.854131817817688,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 3.2249,
+      "step": 3
+    },
+    {
+      "epoch": 0.010666666666666666,
+      "grad_norm": 2.1694631576538086,
+      "learning_rate": 1.2e-05,
+      "loss": 3.0053,
+      "step": 4
+    },
+    {
+      "epoch": 0.013333333333333334,
+      "grad_norm": 1.9107239246368408,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 3.0852,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 2.75483775138855,
+      "learning_rate": 2e-05,
+      "loss": 3.403,
+      "step": 6
+    },
+    {
+      "epoch": 0.018666666666666668,
+      "grad_norm": 2.3957889080047607,
+      "learning_rate": 1.994594594594595e-05,
+      "loss": 3.0099,
+      "step": 7
+    },
+    {
+      "epoch": 0.021333333333333333,
+      "grad_norm": 2.6320505142211914,
+      "learning_rate": 1.9891891891891894e-05,
+      "loss": 2.8505,
+      "step": 8
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 3.0003180503845215,
+      "learning_rate": 1.983783783783784e-05,
+      "loss": 3.1323,
+      "step": 9
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 3.0332396030426025,
+      "learning_rate": 1.9783783783783786e-05,
+      "loss": 3.0652,
+      "step": 10
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "eval_loss": 4.045619010925293,
+      "eval_runtime": 2.7753,
+      "eval_samples_per_second": 36.032,
+      "eval_steps_per_second": 18.016,
+      "step": 10
+    },
+    {
+      "epoch": 0.029333333333333333,
+      "grad_norm": 3.702634334564209,
+      "learning_rate": 1.972972972972973e-05,
+      "loss": 3.0556,
+      "step": 11
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 3.6853737831115723,
+      "learning_rate": 1.967567567567568e-05,
+      "loss": 3.0048,
+      "step": 12
+    },
+    {
+      "epoch": 0.034666666666666665,
+      "grad_norm": 4.051983833312988,
+      "learning_rate": 1.9621621621621623e-05,
+      "loss": 3.1057,
+      "step": 13
+    },
+    {
+      "epoch": 0.037333333333333336,
+      "grad_norm": 4.531636714935303,
+      "learning_rate": 1.956756756756757e-05,
+      "loss": 3.0091,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.036567211151123,
+      "learning_rate": 1.9513513513513515e-05,
+      "loss": 3.0542,
+      "step": 15
+    },
+    {
+      "epoch": 0.042666666666666665,
+      "grad_norm": 5.271779537200928,
+      "learning_rate": 1.9459459459459463e-05,
+      "loss": 3.0283,
+      "step": 16
+    },
+    {
+      "epoch": 0.04533333333333334,
+      "grad_norm": 5.242419719696045,
+      "learning_rate": 1.9405405405405408e-05,
+      "loss": 3.009,
+      "step": 17
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 5.3435468673706055,
+      "learning_rate": 1.9351351351351352e-05,
+      "loss": 2.9077,
+      "step": 18
+    },
+    {
+      "epoch": 0.050666666666666665,
+      "grad_norm": 5.714112281799316,
+      "learning_rate": 1.92972972972973e-05,
+      "loss": 2.7583,
+      "step": 19
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 6.753252029418945,
+      "learning_rate": 1.9243243243243244e-05,
+      "loss": 3.1582,
+      "step": 20
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "eval_loss": 3.9551641941070557,
+      "eval_runtime": 4.4782,
+      "eval_samples_per_second": 22.331,
+      "eval_steps_per_second": 11.165,
+      "step": 20
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 7.844405174255371,
+      "learning_rate": 1.918918918918919e-05,
+      "loss": 3.031,
+      "step": 21
+    },
+    {
+      "epoch": 0.058666666666666666,
+      "grad_norm": 6.625480651855469,
+      "learning_rate": 1.9135135135135137e-05,
+      "loss": 2.8052,
+      "step": 22
+    },
+    {
+      "epoch": 0.06133333333333333,
+      "grad_norm": 8.216512680053711,
+      "learning_rate": 1.9081081081081084e-05,
+      "loss": 3.0834,
+      "step": 23
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 9.459237098693848,
+      "learning_rate": 1.902702702702703e-05,
+      "loss": 3.2171,
+      "step": 24
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 7.314394474029541,
+      "learning_rate": 1.8972972972972973e-05,
+      "loss": 2.7412,
+      "step": 25
+    },
+    {
+      "epoch": 0.06933333333333333,
+      "grad_norm": 9.203798294067383,
+      "learning_rate": 1.891891891891892e-05,
+      "loss": 2.9472,
+      "step": 26
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 8.216959953308105,
+      "learning_rate": 1.8864864864864866e-05,
+      "loss": 2.8623,
+      "step": 27
+    },
+    {
+      "epoch": 0.07466666666666667,
+      "grad_norm": 9.286321640014648,
+      "learning_rate": 1.8810810810810813e-05,
+      "loss": 2.9202,
+      "step": 28
+    },
+    {
+      "epoch": 0.07733333333333334,
+      "grad_norm": 10.061506271362305,
+      "learning_rate": 1.8756756756756758e-05,
+      "loss": 2.8955,
+      "step": 29
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 9.677040100097656,
+      "learning_rate": 1.8702702702702706e-05,
+      "loss": 2.8536,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 3.787959098815918,
+      "eval_runtime": 2.1272,
+      "eval_samples_per_second": 47.01,
+      "eval_steps_per_second": 23.505,
+      "step": 30
+    },
+    {
+      "epoch": 0.08266666666666667,
+      "grad_norm": 9.306242942810059,
+      "learning_rate": 1.864864864864865e-05,
+      "loss": 2.8001,
+      "step": 31
+    },
+    {
+      "epoch": 0.08533333333333333,
+      "grad_norm": 10.727829933166504,
+      "learning_rate": 1.8594594594594598e-05,
+      "loss": 2.7965,
+      "step": 32
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 10.815815925598145,
+      "learning_rate": 1.8540540540540542e-05,
+      "loss": 2.6971,
+      "step": 33
+    },
+    {
+      "epoch": 0.09066666666666667,
+      "grad_norm": 11.350202560424805,
+      "learning_rate": 1.8486486486486487e-05,
+      "loss": 2.8795,
+      "step": 34
+    },
+    {
+      "epoch": 0.09333333333333334,
+      "grad_norm": 9.992085456848145,
+      "learning_rate": 1.8432432432432435e-05,
+      "loss": 2.6501,
+      "step": 35
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 10.549501419067383,
+      "learning_rate": 1.8378378378378383e-05,
+      "loss": 2.933,
+      "step": 36
+    },
+    {
+      "epoch": 0.09866666666666667,
+      "grad_norm": 10.73929500579834,
+      "learning_rate": 1.8324324324324324e-05,
+      "loss": 2.5864,
+      "step": 37
+    },
+    {
+      "epoch": 0.10133333333333333,
+      "grad_norm": 11.373261451721191,
+      "learning_rate": 1.827027027027027e-05,
+      "loss": 2.6524,
+      "step": 38
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 10.380573272705078,
+      "learning_rate": 1.821621621621622e-05,
+      "loss": 2.799,
+      "step": 39
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 9.713451385498047,
+      "learning_rate": 1.8162162162162164e-05,
+      "loss": 2.5519,
+      "step": 40
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "eval_loss": 3.571579694747925,
+      "eval_runtime": 1.4327,
+      "eval_samples_per_second": 69.797,
+      "eval_steps_per_second": 34.899,
+      "step": 40
+    },
+    {
+      "epoch": 0.10933333333333334,
+      "grad_norm": 9.979620933532715,
+      "learning_rate": 1.8108108108108108e-05,
+      "loss": 2.5755,
+      "step": 41
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 10.395061492919922,
+      "learning_rate": 1.8054054054054056e-05,
+      "loss": 2.5486,
+      "step": 42
+    },
+    {
+      "epoch": 0.11466666666666667,
+      "grad_norm": 11.004101753234863,
+      "learning_rate": 1.8e-05,
+      "loss": 2.5827,
+      "step": 43
+    },
+    {
+      "epoch": 0.11733333333333333,
+      "grad_norm": 9.684545516967773,
+      "learning_rate": 1.7945945945945948e-05,
+      "loss": 2.4805,
+      "step": 44
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 10.790546417236328,
+      "learning_rate": 1.7891891891891893e-05,
+      "loss": 2.6273,
+      "step": 45
+    },
+    {
+      "epoch": 0.12266666666666666,
+      "grad_norm": 10.468328475952148,
+      "learning_rate": 1.783783783783784e-05,
+      "loss": 2.5212,
+      "step": 46
+    },
+    {
+      "epoch": 0.12533333333333332,
+      "grad_norm": 9.95167350769043,
+      "learning_rate": 1.7783783783783785e-05,
+      "loss": 2.5629,
+      "step": 47
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 10.529458045959473,
+      "learning_rate": 1.7729729729729733e-05,
+      "loss": 2.5741,
+      "step": 48
+    },
+    {
+      "epoch": 0.13066666666666665,
+      "grad_norm": 11.170886039733887,
+      "learning_rate": 1.7675675675675677e-05,
+      "loss": 2.5686,
+      "step": 49
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 12.337284088134766,
+      "learning_rate": 1.7621621621621622e-05,
+      "loss": 2.5845,
+      "step": 50
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "eval_loss": 3.3753364086151123,
+      "eval_runtime": 2.2458,
+      "eval_samples_per_second": 44.528,
+      "eval_steps_per_second": 22.264,
+      "step": 50
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 10.488581657409668,
+      "learning_rate": 1.756756756756757e-05,
+      "loss": 2.4452,
+      "step": 51
+    },
+    {
+      "epoch": 0.13866666666666666,
+      "grad_norm": 12.605925559997559,
+      "learning_rate": 1.7513513513513517e-05,
+      "loss": 2.5195,
+      "step": 52
+    },
+    {
+      "epoch": 0.14133333333333334,
+      "grad_norm": 10.83185863494873,
+      "learning_rate": 1.745945945945946e-05,
+      "loss": 2.3735,
+      "step": 53
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 11.12485408782959,
+      "learning_rate": 1.7405405405405406e-05,
+      "loss": 2.3537,
+      "step": 54
+    },
+    {
+      "epoch": 0.14666666666666667,
+      "grad_norm": 9.973689079284668,
+      "learning_rate": 1.7351351351351354e-05,
+      "loss": 2.4126,
+      "step": 55
+    },
+    {
+      "epoch": 0.14933333333333335,
+      "grad_norm": 10.478340148925781,
+      "learning_rate": 1.72972972972973e-05,
+      "loss": 2.4187,
+      "step": 56
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 10.768567085266113,
+      "learning_rate": 1.7243243243243243e-05,
+      "loss": 2.4077,
+      "step": 57
+    },
+    {
+      "epoch": 0.15466666666666667,
+      "grad_norm": 11.85825252532959,
+      "learning_rate": 1.718918918918919e-05,
+      "loss": 2.3058,
+      "step": 58
+    },
+    {
+      "epoch": 0.15733333333333333,
+      "grad_norm": 11.187318801879883,
+      "learning_rate": 1.7135135135135135e-05,
+      "loss": 2.4174,
+      "step": 59
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 11.785945892333984,
+      "learning_rate": 1.7081081081081083e-05,
+      "loss": 2.4399,
+      "step": 60
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 3.1655495166778564,
+      "eval_runtime": 2.0697,
+      "eval_samples_per_second": 48.317,
+      "eval_steps_per_second": 24.159,
+      "step": 60
+    },
+    {
+      "epoch": 0.16266666666666665,
+      "grad_norm": 10.854010581970215,
+      "learning_rate": 1.7027027027027028e-05,
+      "loss": 2.2329,
+      "step": 61
+    },
+    {
+      "epoch": 0.16533333333333333,
+      "grad_norm": 10.203400611877441,
+      "learning_rate": 1.6972972972972975e-05,
+      "loss": 2.2838,
+      "step": 62
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 11.539600372314453,
+      "learning_rate": 1.691891891891892e-05,
+      "loss": 2.3924,
+      "step": 63
+    },
+    {
+      "epoch": 0.17066666666666666,
+      "grad_norm": 11.250338554382324,
+      "learning_rate": 1.6864864864864868e-05,
+      "loss": 2.3058,
+      "step": 64
+    },
+    {
+      "epoch": 0.17333333333333334,
+      "grad_norm": 11.850069999694824,
+      "learning_rate": 1.6810810810810812e-05,
+      "loss": 2.2964,
+      "step": 65
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 9.700445175170898,
+      "learning_rate": 1.6756756756756757e-05,
+      "loss": 2.2423,
+      "step": 66
+    },
+    {
+      "epoch": 0.17866666666666667,
+      "grad_norm": 10.151924133300781,
+      "learning_rate": 1.6702702702702704e-05,
+      "loss": 2.3055,
+      "step": 67
+    },
+    {
+      "epoch": 0.18133333333333335,
+      "grad_norm": 10.716888427734375,
+      "learning_rate": 1.6648648648648652e-05,
+      "loss": 2.3243,
+      "step": 68
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 10.560665130615234,
+      "learning_rate": 1.6594594594594597e-05,
+      "loss": 2.2929,
+      "step": 69
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 9.572568893432617,
+      "learning_rate": 1.654054054054054e-05,
+      "loss": 2.2851,
+      "step": 70
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "eval_loss": 2.961385488510132,
+      "eval_runtime": 2.2787,
+      "eval_samples_per_second": 43.885,
+      "eval_steps_per_second": 21.942,
+      "step": 70
+    },
+    {
+      "epoch": 0.18933333333333333,
+      "grad_norm": 9.450087547302246,
+      "learning_rate": 1.648648648648649e-05,
+      "loss": 2.228,
+      "step": 71
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 8.937986373901367,
+      "learning_rate": 1.6432432432432434e-05,
+      "loss": 2.2546,
+      "step": 72
+    },
+    {
+      "epoch": 0.19466666666666665,
+      "grad_norm": 8.936970710754395,
+      "learning_rate": 1.6378378378378378e-05,
+      "loss": 2.1595,
+      "step": 73
+    },
+    {
+      "epoch": 0.19733333333333333,
+      "grad_norm": 10.161012649536133,
+      "learning_rate": 1.6324324324324326e-05,
+      "loss": 2.3542,
+      "step": 74
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 8.683395385742188,
+      "learning_rate": 1.6270270270270274e-05,
+      "loss": 2.2159,
+      "step": 75
+    },
+    {
+      "epoch": 0.20266666666666666,
+      "grad_norm": 9.587220191955566,
+      "learning_rate": 1.6216216216216218e-05,
+      "loss": 2.1507,
+      "step": 76
+    },
+    {
+      "epoch": 0.20533333333333334,
+      "grad_norm": 9.187430381774902,
+      "learning_rate": 1.6162162162162163e-05,
+      "loss": 2.1825,
+      "step": 77
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 9.975436210632324,
+      "learning_rate": 1.610810810810811e-05,
+      "loss": 2.1668,
+      "step": 78
+    },
+    {
+      "epoch": 0.21066666666666667,
+      "grad_norm": 8.30064868927002,
+      "learning_rate": 1.6054054054054055e-05,
+      "loss": 2.0934,
+      "step": 79
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 8.733392715454102,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.048,
+      "step": 80
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "eval_loss": 2.785585880279541,
+      "eval_runtime": 2.192,
+      "eval_samples_per_second": 45.621,
+      "eval_steps_per_second": 22.811,
+      "step": 80
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 9.764636993408203,
+      "learning_rate": 1.5945945945945947e-05,
+      "loss": 2.1008,
+      "step": 81
+    },
+    {
+      "epoch": 0.21866666666666668,
+      "grad_norm": 8.466041564941406,
+      "learning_rate": 1.589189189189189e-05,
+      "loss": 2.078,
+      "step": 82
+    },
+    {
+      "epoch": 0.22133333333333333,
+      "grad_norm": 8.215858459472656,
+      "learning_rate": 1.583783783783784e-05,
+      "loss": 2.0538,
+      "step": 83
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 8.34721851348877,
+      "learning_rate": 1.5783783783783787e-05,
+      "loss": 2.0686,
+      "step": 84
+    },
+    {
+      "epoch": 0.22666666666666666,
+      "grad_norm": 9.139016151428223,
+      "learning_rate": 1.572972972972973e-05,
+      "loss": 2.2258,
+      "step": 85
+    },
+    {
+      "epoch": 0.22933333333333333,
+      "grad_norm": 8.58658218383789,
+      "learning_rate": 1.5675675675675676e-05,
+      "loss": 2.1348,
+      "step": 86
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 8.499350547790527,
+      "learning_rate": 1.5621621621621624e-05,
+      "loss": 1.8911,
+      "step": 87
+    },
+    {
+      "epoch": 0.23466666666666666,
+      "grad_norm": 8.024872779846191,
+      "learning_rate": 1.556756756756757e-05,
+      "loss": 2.0628,
+      "step": 88
+    },
+    {
+      "epoch": 0.23733333333333334,
+      "grad_norm": 7.775054454803467,
+      "learning_rate": 1.5513513513513513e-05,
+      "loss": 2.0219,
+      "step": 89
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 7.737258434295654,
+      "learning_rate": 1.545945945945946e-05,
+      "loss": 1.9964,
+      "step": 90
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 2.653085708618164,
+      "eval_runtime": 2.2046,
+      "eval_samples_per_second": 45.36,
+      "eval_steps_per_second": 22.68,
+      "step": 90
+    },
+    {
+      "epoch": 0.24266666666666667,
+      "grad_norm": 6.859392166137695,
+      "learning_rate": 1.540540540540541e-05,
+      "loss": 1.9765,
+      "step": 91
+    },
+    {
+      "epoch": 0.24533333333333332,
+      "grad_norm": 7.554781913757324,
+      "learning_rate": 1.5351351351351353e-05,
+      "loss": 1.9451,
+      "step": 92
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 7.059022426605225,
+      "learning_rate": 1.5297297297297297e-05,
+      "loss": 1.9331,
+      "step": 93
+    },
+    {
+      "epoch": 0.25066666666666665,
+      "grad_norm": 8.107563018798828,
+      "learning_rate": 1.5243243243243244e-05,
+      "loss": 1.9622,
+      "step": 94
+    },
+    {
+      "epoch": 0.25333333333333335,
+      "grad_norm": 7.543460369110107,
+      "learning_rate": 1.5189189189189191e-05,
+      "loss": 1.9835,
+      "step": 95
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 6.616236686706543,
+      "learning_rate": 1.5135135135135138e-05,
+      "loss": 1.8276,
+      "step": 96
+    },
+    {
+      "epoch": 0.25866666666666666,
+      "grad_norm": 7.753726005554199,
+      "learning_rate": 1.5081081081081082e-05,
+      "loss": 1.8814,
+      "step": 97
+    },
+    {
+      "epoch": 0.2613333333333333,
+      "grad_norm": 7.098799705505371,
+      "learning_rate": 1.5027027027027028e-05,
+      "loss": 1.9011,
+      "step": 98
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 8.696466445922852,
+      "learning_rate": 1.4972972972972974e-05,
+      "loss": 1.9896,
+      "step": 99
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 7.085773468017578,
+      "learning_rate": 1.491891891891892e-05,
+      "loss": 1.9487,
+      "step": 100
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "eval_loss": 2.5445711612701416,
+      "eval_runtime": 2.2199,
+      "eval_samples_per_second": 45.048,
+      "eval_steps_per_second": 22.524,
+      "step": 100
+    },
+    {
+      "epoch": 0.2693333333333333,
+      "grad_norm": 7.898609161376953,
+      "learning_rate": 1.4864864864864865e-05,
+      "loss": 1.958,
+      "step": 101
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 8.978720664978027,
+      "learning_rate": 1.4810810810810811e-05,
+      "loss": 2.0213,
+      "step": 102
+    },
+    {
+      "epoch": 0.27466666666666667,
+      "grad_norm": 8.281126976013184,
+      "learning_rate": 1.4756756756756759e-05,
+      "loss": 1.982,
+      "step": 103
+    },
+    {
+      "epoch": 0.2773333333333333,
+      "grad_norm": 8.454890251159668,
+      "learning_rate": 1.4702702702702705e-05,
+      "loss": 2.0524,
+      "step": 104
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 7.288161277770996,
+      "learning_rate": 1.464864864864865e-05,
+      "loss": 1.8668,
+      "step": 105
+    },
+    {
+      "epoch": 0.2826666666666667,
+      "grad_norm": 8.173579216003418,
+      "learning_rate": 1.4594594594594596e-05,
+      "loss": 1.8674,
+      "step": 106
+    },
+    {
+      "epoch": 0.2853333333333333,
+      "grad_norm": 7.975004196166992,
+      "learning_rate": 1.4540540540540542e-05,
+      "loss": 1.8882,
+      "step": 107
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 9.3242769241333,
+      "learning_rate": 1.4486486486486488e-05,
+      "loss": 1.8648,
+      "step": 108
+    },
+    {
+      "epoch": 0.2906666666666667,
+      "grad_norm": 8.05557918548584,
+      "learning_rate": 1.4432432432432432e-05,
+      "loss": 1.8858,
+      "step": 109
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 8.509403228759766,
+      "learning_rate": 1.4378378378378378e-05,
+      "loss": 1.9615,
+      "step": 110
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "eval_loss": 2.4486212730407715,
+      "eval_runtime": 2.2817,
+      "eval_samples_per_second": 43.827,
+      "eval_steps_per_second": 21.913,
+      "step": 110
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 7.072972774505615,
+      "learning_rate": 1.4324324324324326e-05,
+      "loss": 1.8479,
+      "step": 111
+    },
+    {
+      "epoch": 0.2986666666666667,
+      "grad_norm": 7.796631813049316,
+      "learning_rate": 1.4270270270270272e-05,
+      "loss": 1.7927,
+      "step": 112
+    },
+    {
+      "epoch": 0.30133333333333334,
+      "grad_norm": 8.747613906860352,
+      "learning_rate": 1.4216216216216217e-05,
+      "loss": 1.8459,
+      "step": 113
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 7.166773319244385,
+      "learning_rate": 1.4162162162162163e-05,
+      "loss": 1.868,
+      "step": 114
+    },
+    {
+      "epoch": 0.30666666666666664,
+      "grad_norm": 7.192455768585205,
+      "learning_rate": 1.410810810810811e-05,
+      "loss": 1.7453,
+      "step": 115
+    },
+    {
+      "epoch": 0.30933333333333335,
+      "grad_norm": 8.136066436767578,
+      "learning_rate": 1.4054054054054055e-05,
+      "loss": 1.761,
+      "step": 116
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 8.393095016479492,
+      "learning_rate": 1.4e-05,
+      "loss": 1.8745,
+      "step": 117
+    },
+    {
+      "epoch": 0.31466666666666665,
+      "grad_norm": 8.157516479492188,
+      "learning_rate": 1.3945945945945946e-05,
+      "loss": 1.8127,
+      "step": 118
+    },
+    {
+      "epoch": 0.31733333333333336,
+      "grad_norm": 6.625328063964844,
+      "learning_rate": 1.3891891891891894e-05,
+      "loss": 1.7663,
+      "step": 119
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 8.206719398498535,
+      "learning_rate": 1.383783783783784e-05,
+      "loss": 1.8932,
+      "step": 120
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 2.3762967586517334,
+      "eval_runtime": 2.1215,
+      "eval_samples_per_second": 47.137,
+      "eval_steps_per_second": 23.568,
+      "step": 120
+    },
+    {
+      "epoch": 0.32266666666666666,
+      "grad_norm": 9.288111686706543,
+      "learning_rate": 1.3783783783783784e-05,
+      "loss": 1.7553,
+      "step": 121
+    },
+    {
+      "epoch": 0.3253333333333333,
+      "grad_norm": 6.770742893218994,
+      "learning_rate": 1.372972972972973e-05,
+      "loss": 1.7087,
+      "step": 122
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 7.87407922744751,
+      "learning_rate": 1.3675675675675677e-05,
+      "loss": 1.7909,
+      "step": 123
+    },
+    {
+      "epoch": 0.33066666666666666,
+      "grad_norm": 7.107893466949463,
+      "learning_rate": 1.3621621621621623e-05,
+      "loss": 1.7214,
+      "step": 124
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 8.586562156677246,
+      "learning_rate": 1.3567567567567567e-05,
+      "loss": 1.7738,
+      "step": 125
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 7.8112897872924805,
+      "learning_rate": 1.3513513513513515e-05,
+      "loss": 1.7817,
+      "step": 126
+    },
+    {
+      "epoch": 0.33866666666666667,
+      "grad_norm": 8.122381210327148,
+      "learning_rate": 1.3459459459459461e-05,
+      "loss": 1.8576,
+      "step": 127
+    },
+    {
+      "epoch": 0.3413333333333333,
+      "grad_norm": 6.482271194458008,
+      "learning_rate": 1.3405405405405407e-05,
+      "loss": 1.7903,
+      "step": 128
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 7.601424694061279,
+      "learning_rate": 1.3351351351351352e-05,
+      "loss": 1.667,
+      "step": 129
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 7.602461814880371,
+      "learning_rate": 1.3297297297297298e-05,
+      "loss": 1.8164,
+      "step": 130
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "eval_loss": 2.311195135116577,
+      "eval_runtime": 2.0939,
+      "eval_samples_per_second": 47.757,
+      "eval_steps_per_second": 23.878,
+      "step": 130
+    },
+    {
+      "epoch": 0.34933333333333333,
+      "grad_norm": 9.976211547851562,
+      "learning_rate": 1.3243243243243244e-05,
+      "loss": 1.7161,
+      "step": 131
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 8.048646926879883,
+      "learning_rate": 1.318918918918919e-05,
+      "loss": 1.682,
+      "step": 132
+    },
+    {
+      "epoch": 0.3546666666666667,
+      "grad_norm": 7.021885395050049,
+      "learning_rate": 1.3135135135135135e-05,
+      "loss": 1.769,
+      "step": 133
+    },
+    {
+      "epoch": 0.35733333333333334,
+      "grad_norm": 8.244754791259766,
+      "learning_rate": 1.3081081081081083e-05,
+      "loss": 1.8327,
+      "step": 134
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 6.376795768737793,
+      "learning_rate": 1.3027027027027029e-05,
+      "loss": 1.7386,
+      "step": 135
+    },
+    {
+      "epoch": 0.3626666666666667,
+      "grad_norm": 7.7868547439575195,
+      "learning_rate": 1.2972972972972975e-05,
+      "loss": 1.7875,
+      "step": 136
+    },
+    {
+      "epoch": 0.36533333333333334,
+      "grad_norm": 6.6984968185424805,
+      "learning_rate": 1.291891891891892e-05,
+      "loss": 1.6501,
+      "step": 137
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 6.149721622467041,
+      "learning_rate": 1.2864864864864865e-05,
+      "loss": 1.7127,
+      "step": 138
+    },
+    {
+      "epoch": 0.37066666666666664,
+      "grad_norm": 6.397825241088867,
+      "learning_rate": 1.2810810810810812e-05,
+      "loss": 1.6919,
+      "step": 139
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 7.291930675506592,
+      "learning_rate": 1.2756756756756758e-05,
+      "loss": 1.7225,
+      "step": 140
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "eval_loss": 2.246192693710327,
+      "eval_runtime": 2.167,
+      "eval_samples_per_second": 46.147,
+      "eval_steps_per_second": 23.073,
+      "step": 140
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 5.63145112991333,
+      "learning_rate": 1.2702702702702702e-05,
+      "loss": 1.6553,
+      "step": 141
+    },
+    {
+      "epoch": 0.37866666666666665,
+      "grad_norm": 5.660354137420654,
+      "learning_rate": 1.264864864864865e-05,
+      "loss": 1.7509,
+      "step": 142
+    },
+    {
+      "epoch": 0.38133333333333336,
+      "grad_norm": 6.128180027008057,
+      "learning_rate": 1.2594594594594596e-05,
+      "loss": 1.6916,
+      "step": 143
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 6.451909065246582,
+      "learning_rate": 1.2540540540540542e-05,
+      "loss": 1.6152,
+      "step": 144
+    },
+    {
+      "epoch": 0.38666666666666666,
+      "grad_norm": 6.305749893188477,
+      "learning_rate": 1.2486486486486487e-05,
+      "loss": 1.6637,
+      "step": 145
+    },
+    {
+      "epoch": 0.3893333333333333,
+      "grad_norm": 5.5497612953186035,
+      "learning_rate": 1.2432432432432433e-05,
+      "loss": 1.6574,
+      "step": 146
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 6.6420159339904785,
+      "learning_rate": 1.2378378378378379e-05,
+      "loss": 1.6683,
+      "step": 147
+    },
+    {
+      "epoch": 0.39466666666666667,
+      "grad_norm": 5.216001033782959,
+      "learning_rate": 1.2324324324324327e-05,
+      "loss": 1.6459,
+      "step": 148
+    },
+    {
+      "epoch": 0.3973333333333333,
+      "grad_norm": 5.373282432556152,
+      "learning_rate": 1.227027027027027e-05,
+      "loss": 1.7477,
+      "step": 149
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 5.689486026763916,
+      "learning_rate": 1.2216216216216217e-05,
+      "loss": 1.6712,
+      "step": 150
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 2.207843065261841,
+      "eval_runtime": 1.6945,
+      "eval_samples_per_second": 59.015,
+      "eval_steps_per_second": 29.508,
+      "step": 150
+    },
+    {
+      "epoch": 0.4026666666666667,
+      "grad_norm": 5.946493625640869,
+      "learning_rate": 1.2162162162162164e-05,
+      "loss": 1.6919,
+      "step": 151
+    },
+    {
+      "epoch": 0.4053333333333333,
+      "grad_norm": 6.135462284088135,
+      "learning_rate": 1.210810810810811e-05,
+      "loss": 1.689,
+      "step": 152
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 4.7930684089660645,
+      "learning_rate": 1.2054054054054054e-05,
+      "loss": 1.6548,
+      "step": 153
+    },
+    {
+      "epoch": 0.4106666666666667,
+      "grad_norm": 5.390539169311523,
+      "learning_rate": 1.2e-05,
+      "loss": 1.691,
+      "step": 154
+    },
+    {
+      "epoch": 0.41333333333333333,
+      "grad_norm": 4.942782878875732,
+      "learning_rate": 1.1945945945945946e-05,
+      "loss": 1.6996,
+      "step": 155
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 5.763488292694092,
+      "learning_rate": 1.1891891891891894e-05,
+      "loss": 1.7407,
+      "step": 156
+    },
+    {
+      "epoch": 0.4186666666666667,
+      "grad_norm": 6.6217732429504395,
+      "learning_rate": 1.1837837837837837e-05,
+      "loss": 1.7021,
+      "step": 157
+    },
+    {
+      "epoch": 0.42133333333333334,
+      "grad_norm": 5.423023223876953,
+      "learning_rate": 1.1783783783783785e-05,
+      "loss": 1.7716,
+      "step": 158
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 4.658130645751953,
+      "learning_rate": 1.1729729729729731e-05,
+      "loss": 1.6941,
+      "step": 159
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 5.114764213562012,
+      "learning_rate": 1.1675675675675677e-05,
+      "loss": 1.6352,
+      "step": 160
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "eval_loss": 2.176851749420166,
+      "eval_runtime": 2.2418,
+      "eval_samples_per_second": 44.608,
+      "eval_steps_per_second": 22.304,
+      "step": 160
+    },
+    {
+      "epoch": 0.42933333333333334,
+      "grad_norm": 5.478493690490723,
+      "learning_rate": 1.1621621621621622e-05,
+      "loss": 1.6397,
+      "step": 161
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 4.976323127746582,
+      "learning_rate": 1.1567567567567568e-05,
+      "loss": 1.6296,
+      "step": 162
+    },
+    {
+      "epoch": 0.43466666666666665,
+      "grad_norm": 6.247684955596924,
+      "learning_rate": 1.1513513513513514e-05,
+      "loss": 1.6706,
+      "step": 163
+    },
+    {
+      "epoch": 0.43733333333333335,
+      "grad_norm": 6.404987812042236,
+      "learning_rate": 1.1459459459459462e-05,
+      "loss": 1.6445,
+      "step": 164
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 7.287195205688477,
+      "learning_rate": 1.1405405405405404e-05,
+      "loss": 1.6573,
+      "step": 165
+    },
+    {
+      "epoch": 0.44266666666666665,
+      "grad_norm": 5.842925071716309,
+      "learning_rate": 1.1351351351351352e-05,
+      "loss": 1.6668,
+      "step": 166
+    },
+    {
+      "epoch": 0.44533333333333336,
+      "grad_norm": 4.8162617683410645,
+      "learning_rate": 1.1297297297297298e-05,
+      "loss": 1.6053,
+      "step": 167
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 5.256189346313477,
+      "learning_rate": 1.1243243243243245e-05,
+      "loss": 1.484,
+      "step": 168
+    },
+    {
+      "epoch": 0.45066666666666666,
+      "grad_norm": 5.5633134841918945,
+      "learning_rate": 1.1189189189189189e-05,
+      "loss": 1.6692,
+      "step": 169
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 6.114223003387451,
+      "learning_rate": 1.1135135135135135e-05,
+      "loss": 1.6313,
+      "step": 170
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "eval_loss": 2.1688404083251953,
+      "eval_runtime": 2.2251,
+      "eval_samples_per_second": 44.942,
+      "eval_steps_per_second": 22.471,
+      "step": 170
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 5.219391822814941,
+      "learning_rate": 1.1081081081081081e-05,
+      "loss": 1.6865,
+      "step": 171
+    },
+    {
+      "epoch": 0.45866666666666667,
+      "grad_norm": 4.586527347564697,
+      "learning_rate": 1.102702702702703e-05,
+      "loss": 1.6521,
+      "step": 172
+    },
+    {
+      "epoch": 0.4613333333333333,
+      "grad_norm": 6.360827445983887,
+      "learning_rate": 1.0972972972972974e-05,
+      "loss": 1.6779,
+      "step": 173
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 6.018531322479248,
+      "learning_rate": 1.091891891891892e-05,
+      "loss": 1.6432,
+      "step": 174
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 7.3478546142578125,
+      "learning_rate": 1.0864864864864866e-05,
+      "loss": 1.6754,
+      "step": 175
+    },
+    {
+      "epoch": 0.4693333333333333,
+      "grad_norm": 5.432449817657471,
+      "learning_rate": 1.0810810810810812e-05,
+      "loss": 1.6318,
+      "step": 176
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 4.748453617095947,
+      "learning_rate": 1.0756756756756757e-05,
+      "loss": 1.5996,
+      "step": 177
+    },
+    {
+      "epoch": 0.4746666666666667,
+      "grad_norm": 5.688570022583008,
+      "learning_rate": 1.0702702702702703e-05,
+      "loss": 1.5913,
+      "step": 178
+    },
+    {
+      "epoch": 0.47733333333333333,
+      "grad_norm": 5.226125717163086,
+      "learning_rate": 1.0648648648648649e-05,
+      "loss": 1.5602,
+      "step": 179
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.345921993255615,
+      "learning_rate": 1.0594594594594597e-05,
+      "loss": 1.4931,
+      "step": 180
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 2.170788288116455,
+      "eval_runtime": 2.3318,
+      "eval_samples_per_second": 42.885,
+      "eval_steps_per_second": 21.443,
+      "step": 180
+    },
+    {
+      "epoch": 0.4826666666666667,
+      "grad_norm": 4.630764007568359,
+      "learning_rate": 1.0540540540540541e-05,
+      "loss": 1.5779,
+      "step": 181
+    },
+    {
+      "epoch": 0.48533333333333334,
+      "grad_norm": 5.0662617683410645,
+      "learning_rate": 1.0486486486486487e-05,
+      "loss": 1.6422,
+      "step": 182
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 6.455874919891357,
+      "learning_rate": 1.0432432432432433e-05,
+      "loss": 1.4907,
+      "step": 183
+    },
+    {
+      "epoch": 0.49066666666666664,
+      "grad_norm": 5.871761798858643,
+      "learning_rate": 1.037837837837838e-05,
+      "loss": 1.6837,
+      "step": 184
+    },
+    {
+      "epoch": 0.49333333333333335,
+      "grad_norm": 5.1716766357421875,
+      "learning_rate": 1.0324324324324324e-05,
+      "loss": 1.6644,
+      "step": 185
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 5.504106044769287,
+      "learning_rate": 1.027027027027027e-05,
+      "loss": 1.5835,
+      "step": 186
+    },
+    {
+      "epoch": 0.49866666666666665,
+      "grad_norm": 5.897885322570801,
+      "learning_rate": 1.0216216216216216e-05,
+      "loss": 1.7067,
+      "step": 187
+    },
+    {
+      "epoch": 0.5013333333333333,
+      "grad_norm": 5.156588554382324,
+      "learning_rate": 1.0162162162162164e-05,
+      "loss": 1.6403,
+      "step": 188
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 5.252018451690674,
+      "learning_rate": 1.0108108108108109e-05,
+      "loss": 1.6234,
+      "step": 189
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 5.000985145568848,
+      "learning_rate": 1.0054054054054055e-05,
+      "loss": 1.5512,
+      "step": 190
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "eval_loss": 2.184048891067505,
+      "eval_runtime": 2.1897,
+      "eval_samples_per_second": 45.668,
+      "eval_steps_per_second": 22.834,
+      "step": 190
+    },
+    {
+      "epoch": 0.5093333333333333,
+      "grad_norm": 5.184759140014648,
+      "learning_rate": 1e-05,
+      "loss": 1.6048,
+      "step": 191
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 5.091919898986816,
+      "learning_rate": 9.945945945945947e-06,
+      "loss": 1.6016,
+      "step": 192
+    },
+    {
+      "epoch": 0.5146666666666667,
+      "grad_norm": 5.661059379577637,
+      "learning_rate": 9.891891891891893e-06,
+      "loss": 1.6025,
+      "step": 193
+    },
+    {
+      "epoch": 0.5173333333333333,
+      "grad_norm": 5.571784496307373,
+      "learning_rate": 9.83783783783784e-06,
+      "loss": 1.511,
+      "step": 194
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 5.084967613220215,
+      "learning_rate": 9.783783783783785e-06,
+      "loss": 1.524,
+      "step": 195
+    },
+    {
+      "epoch": 0.5226666666666666,
+      "grad_norm": 5.123044490814209,
+      "learning_rate": 9.729729729729732e-06,
+      "loss": 1.5507,
+      "step": 196
+    },
+    {
+      "epoch": 0.5253333333333333,
+      "grad_norm": 5.78058385848999,
+      "learning_rate": 9.675675675675676e-06,
+      "loss": 1.5892,
+      "step": 197
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 5.2647600173950195,
+      "learning_rate": 9.621621621621622e-06,
+      "loss": 1.5908,
+      "step": 198
+    },
+    {
+      "epoch": 0.5306666666666666,
+      "grad_norm": 5.385093688964844,
+      "learning_rate": 9.567567567567568e-06,
+      "loss": 1.5364,
+      "step": 199
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 5.6748151779174805,
+      "learning_rate": 9.513513513513514e-06,
+      "loss": 1.5799,
+      "step": 200
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 2.2051568031311035,
+      "eval_runtime": 2.1041,
+      "eval_samples_per_second": 47.525,
+      "eval_steps_per_second": 23.763,
+      "step": 200
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 5.698492527008057,
+      "learning_rate": 9.45945945945946e-06,
+      "loss": 1.6259,
+      "step": 201
+    },
+    {
+      "epoch": 0.5386666666666666,
+      "grad_norm": 5.980306625366211,
+      "learning_rate": 9.405405405405407e-06,
+      "loss": 1.5621,
+      "step": 202
+    },
+    {
+      "epoch": 0.5413333333333333,
+      "grad_norm": 5.281281471252441,
+      "learning_rate": 9.351351351351353e-06,
+      "loss": 1.5728,
+      "step": 203
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 4.0611090660095215,
+      "learning_rate": 9.297297297297299e-06,
+      "loss": 1.5227,
+      "step": 204
+    },
+    {
+      "epoch": 0.5466666666666666,
+      "grad_norm": 5.911980152130127,
+      "learning_rate": 9.243243243243243e-06,
+      "loss": 1.5494,
+      "step": 205
+    },
+    {
+      "epoch": 0.5493333333333333,
+      "grad_norm": 5.366306781768799,
+      "learning_rate": 9.189189189189191e-06,
+      "loss": 1.548,
+      "step": 206
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 5.686289310455322,
+      "learning_rate": 9.135135135135136e-06,
+      "loss": 1.5688,
+      "step": 207
+    },
+    {
+      "epoch": 0.5546666666666666,
+      "grad_norm": 5.282558441162109,
+      "learning_rate": 9.081081081081082e-06,
+      "loss": 1.4869,
+      "step": 208
+    },
+    {
+      "epoch": 0.5573333333333333,
+      "grad_norm": 7.519771575927734,
+      "learning_rate": 9.027027027027028e-06,
+      "loss": 1.5314,
+      "step": 209
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.988372802734375,
+      "learning_rate": 8.972972972972974e-06,
+      "loss": 1.4888,
+      "step": 210
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 2.2130188941955566,
+      "eval_runtime": 2.1537,
+      "eval_samples_per_second": 46.431,
+      "eval_steps_per_second": 23.216,
+      "step": 210
+    },
+    {
+      "epoch": 0.5626666666666666,
+      "grad_norm": 6.266903877258301,
+      "learning_rate": 8.91891891891892e-06,
+      "loss": 1.5963,
+      "step": 211
+    },
+    {
+      "epoch": 0.5653333333333334,
+      "grad_norm": 5.738575458526611,
+      "learning_rate": 8.864864864864866e-06,
+      "loss": 1.5943,
+      "step": 212
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 5.485104084014893,
+      "learning_rate": 8.810810810810811e-06,
+      "loss": 1.5369,
+      "step": 213
+    },
+    {
+      "epoch": 0.5706666666666667,
+      "grad_norm": 5.047416687011719,
+      "learning_rate": 8.756756756756759e-06,
+      "loss": 1.5862,
+      "step": 214
+    },
+    {
+      "epoch": 0.5733333333333334,
+      "grad_norm": 6.820781707763672,
+      "learning_rate": 8.702702702702703e-06,
+      "loss": 1.5022,
+      "step": 215
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 5.572027683258057,
+      "learning_rate": 8.64864864864865e-06,
+      "loss": 1.5256,
+      "step": 216
+    },
+    {
+      "epoch": 0.5786666666666667,
+      "grad_norm": 5.084157943725586,
+      "learning_rate": 8.594594594594595e-06,
+      "loss": 1.6196,
+      "step": 217
+    },
+    {
+      "epoch": 0.5813333333333334,
+      "grad_norm": 5.583468914031982,
+      "learning_rate": 8.540540540540542e-06,
+      "loss": 1.5351,
+      "step": 218
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 5.5146589279174805,
+      "learning_rate": 8.486486486486488e-06,
+      "loss": 1.5531,
+      "step": 219
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 5.2444047927856445,
+      "learning_rate": 8.432432432432434e-06,
+      "loss": 1.5122,
+      "step": 220
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "eval_loss": 2.2200913429260254,
+      "eval_runtime": 2.2659,
+      "eval_samples_per_second": 44.132,
+      "eval_steps_per_second": 22.066,
+      "step": 220
+    },
+    {
+      "epoch": 0.5893333333333334,
+      "grad_norm": 5.152411460876465,
+      "learning_rate": 8.378378378378378e-06,
+      "loss": 1.5952,
+      "step": 221
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 6.373597145080566,
+      "learning_rate": 8.324324324324326e-06,
+      "loss": 1.5996,
+      "step": 222
+    },
+    {
+      "epoch": 0.5946666666666667,
+      "grad_norm": 8.443867683410645,
+      "learning_rate": 8.27027027027027e-06,
+      "loss": 1.7069,
+      "step": 223
+    },
+    {
+      "epoch": 0.5973333333333334,
+      "grad_norm": 4.948009967803955,
+      "learning_rate": 8.216216216216217e-06,
+      "loss": 1.5674,
+      "step": 224
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 6.319730758666992,
+      "learning_rate": 8.162162162162163e-06,
+      "loss": 1.5318,
+      "step": 225
+    },
+    {
+      "epoch": 0.6026666666666667,
+      "grad_norm": 6.246556282043457,
+      "learning_rate": 8.108108108108109e-06,
+      "loss": 1.5119,
+      "step": 226
+    },
+    {
+      "epoch": 0.6053333333333333,
+      "grad_norm": 4.4453654289245605,
+      "learning_rate": 8.054054054054055e-06,
+      "loss": 1.5897,
+      "step": 227
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 5.012955665588379,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.5191,
+      "step": 228
+    },
+    {
+      "epoch": 0.6106666666666667,
+      "grad_norm": 5.844364643096924,
+      "learning_rate": 7.945945945945946e-06,
+      "loss": 1.545,
+      "step": 229
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 5.528176307678223,
+      "learning_rate": 7.891891891891894e-06,
+      "loss": 1.603,
+      "step": 230
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "eval_loss": 2.226846694946289,
+      "eval_runtime": 2.1778,
+      "eval_samples_per_second": 45.917,
+      "eval_steps_per_second": 22.959,
+      "step": 230
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 4.689690113067627,
+      "learning_rate": 7.837837837837838e-06,
+      "loss": 1.5484,
+      "step": 231
+    },
+    {
+      "epoch": 0.6186666666666667,
+      "grad_norm": 4.9281768798828125,
+      "learning_rate": 7.783783783783784e-06,
+      "loss": 1.4704,
+      "step": 232
+    },
+    {
+      "epoch": 0.6213333333333333,
+      "grad_norm": 5.297734260559082,
+      "learning_rate": 7.72972972972973e-06,
+      "loss": 1.5611,
+      "step": 233
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 7.491199493408203,
+      "learning_rate": 7.675675675675676e-06,
+      "loss": 1.4792,
+      "step": 234
+    },
+    {
+      "epoch": 0.6266666666666667,
+      "grad_norm": 7.286966323852539,
+      "learning_rate": 7.621621621621622e-06,
+      "loss": 1.4964,
+      "step": 235
+    },
+    {
+      "epoch": 0.6293333333333333,
+      "grad_norm": 5.235691070556641,
+      "learning_rate": 7.567567567567569e-06,
+      "loss": 1.6556,
+      "step": 236
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 5.370845317840576,
+      "learning_rate": 7.513513513513514e-06,
+      "loss": 1.5646,
+      "step": 237
+    },
+    {
+      "epoch": 0.6346666666666667,
+      "grad_norm": 5.199801921844482,
+      "learning_rate": 7.45945945945946e-06,
+      "loss": 1.5364,
+      "step": 238
+    },
+    {
+      "epoch": 0.6373333333333333,
+      "grad_norm": 6.853825569152832,
+      "learning_rate": 7.4054054054054055e-06,
+      "loss": 1.5362,
+      "step": 239
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 5.525668621063232,
+      "learning_rate": 7.3513513513513525e-06,
+      "loss": 1.5506,
+      "step": 240
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 2.232562303543091,
+      "eval_runtime": 2.2716,
+      "eval_samples_per_second": 44.021,
+      "eval_steps_per_second": 22.011,
+      "step": 240
+    },
+    {
+      "epoch": 0.6426666666666667,
+      "grad_norm": 6.260832786560059,
+      "learning_rate": 7.297297297297298e-06,
+      "loss": 1.6297,
+      "step": 241
+    },
+    {
+      "epoch": 0.6453333333333333,
+      "grad_norm": 5.482983589172363,
+      "learning_rate": 7.243243243243244e-06,
+      "loss": 1.5425,
+      "step": 242
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 5.244226455688477,
+      "learning_rate": 7.189189189189189e-06,
+      "loss": 1.4408,
+      "step": 243
+    },
+    {
+      "epoch": 0.6506666666666666,
+      "grad_norm": 5.57607364654541,
+      "learning_rate": 7.135135135135136e-06,
+      "loss": 1.5381,
+      "step": 244
+    },
+    {
+      "epoch": 0.6533333333333333,
+      "grad_norm": 5.063821315765381,
+      "learning_rate": 7.0810810810810815e-06,
+      "loss": 1.4967,
+      "step": 245
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 6.65706729888916,
+      "learning_rate": 7.027027027027028e-06,
+      "loss": 1.5474,
+      "step": 246
+    },
+    {
+      "epoch": 0.6586666666666666,
+      "grad_norm": 7.127385139465332,
+      "learning_rate": 6.972972972972973e-06,
+      "loss": 1.623,
+      "step": 247
+    },
+    {
+      "epoch": 0.6613333333333333,
+      "grad_norm": 5.080024242401123,
+      "learning_rate": 6.91891891891892e-06,
+      "loss": 1.5794,
+      "step": 248
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 6.4152021408081055,
+      "learning_rate": 6.864864864864865e-06,
+      "loss": 1.5768,
+      "step": 249
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 5.5897722244262695,
+      "learning_rate": 6.810810810810811e-06,
+      "loss": 1.4821,
+      "step": 250
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 2.2401955127716064,
+      "eval_runtime": 2.2869,
+      "eval_samples_per_second": 43.728,
+      "eval_steps_per_second": 21.864,
+      "step": 250
+    },
+    {
+      "epoch": 0.6693333333333333,
+      "grad_norm": 5.16597318649292,
+      "learning_rate": 6.7567567567567575e-06,
+      "loss": 1.4258,
+      "step": 251
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 4.679577350616455,
+      "learning_rate": 6.702702702702704e-06,
+      "loss": 1.5525,
+      "step": 252
+    },
+    {
+      "epoch": 0.6746666666666666,
+      "grad_norm": 6.435404300689697,
+      "learning_rate": 6.648648648648649e-06,
+      "loss": 1.6005,
+      "step": 253
+    },
+    {
+      "epoch": 0.6773333333333333,
+      "grad_norm": 8.688821792602539,
+      "learning_rate": 6.594594594594595e-06,
+      "loss": 1.5512,
+      "step": 254
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 6.536645889282227,
+      "learning_rate": 6.540540540540541e-06,
+      "loss": 1.607,
+      "step": 255
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 5.998849391937256,
+      "learning_rate": 6.486486486486487e-06,
+      "loss": 1.5952,
+      "step": 256
+    },
+    {
+      "epoch": 0.6853333333333333,
+      "grad_norm": 4.850104808807373,
+      "learning_rate": 6.432432432432433e-06,
+      "loss": 1.6334,
+      "step": 257
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 6.226448059082031,
+      "learning_rate": 6.378378378378379e-06,
+      "loss": 1.5808,
+      "step": 258
+    },
+    {
+      "epoch": 0.6906666666666667,
+      "grad_norm": 6.5038580894470215,
+      "learning_rate": 6.324324324324325e-06,
+      "loss": 1.5746,
+      "step": 259
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 7.246823787689209,
+      "learning_rate": 6.270270270270271e-06,
+      "loss": 1.5991,
+      "step": 260
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "eval_loss": 2.240321159362793,
+      "eval_runtime": 1.7225,
+      "eval_samples_per_second": 58.056,
+      "eval_steps_per_second": 29.028,
+      "step": 260
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 5.7667012214660645,
+      "learning_rate": 6.2162162162162164e-06,
+      "loss": 1.507,
+      "step": 261
+    },
+    {
+      "epoch": 0.6986666666666667,
+      "grad_norm": 5.739652156829834,
+      "learning_rate": 6.162162162162163e-06,
+      "loss": 1.6025,
+      "step": 262
+    },
+    {
+      "epoch": 0.7013333333333334,
+      "grad_norm": 7.7056708335876465,
+      "learning_rate": 6.108108108108109e-06,
+      "loss": 1.6331,
+      "step": 263
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 5.605151176452637,
+      "learning_rate": 6.054054054054055e-06,
+      "loss": 1.5661,
+      "step": 264
+    },
+    {
+      "epoch": 0.7066666666666667,
+      "grad_norm": 5.5743408203125,
+      "learning_rate": 6e-06,
+      "loss": 1.4722,
+      "step": 265
+    },
+    {
+      "epoch": 0.7093333333333334,
+      "grad_norm": 6.0111083984375,
+      "learning_rate": 5.945945945945947e-06,
+      "loss": 1.5211,
+      "step": 266
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 5.705929756164551,
+      "learning_rate": 5.8918918918918924e-06,
+      "loss": 1.5456,
+      "step": 267
+    },
+    {
+      "epoch": 0.7146666666666667,
+      "grad_norm": 5.9516496658325195,
+      "learning_rate": 5.837837837837839e-06,
+      "loss": 1.6294,
+      "step": 268
+    },
+    {
+      "epoch": 0.7173333333333334,
+      "grad_norm": 6.503254413604736,
+      "learning_rate": 5.783783783783784e-06,
+      "loss": 1.5536,
+      "step": 269
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 6.094985485076904,
+      "learning_rate": 5.729729729729731e-06,
+      "loss": 1.5569,
+      "step": 270
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 2.2432613372802734,
+      "eval_runtime": 2.1693,
+      "eval_samples_per_second": 46.097,
+      "eval_steps_per_second": 23.049,
+      "step": 270
+    },
+    {
+      "epoch": 0.7226666666666667,
+      "grad_norm": 6.073522090911865,
+      "learning_rate": 5.675675675675676e-06,
+      "loss": 1.582,
+      "step": 271
+    },
+    {
+      "epoch": 0.7253333333333334,
+      "grad_norm": 4.969118118286133,
+      "learning_rate": 5.621621621621622e-06,
+      "loss": 1.5085,
+      "step": 272
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 7.984470367431641,
+      "learning_rate": 5.567567567567568e-06,
+      "loss": 1.4996,
+      "step": 273
+    },
+    {
+      "epoch": 0.7306666666666667,
+      "grad_norm": 5.434286117553711,
+      "learning_rate": 5.513513513513515e-06,
+      "loss": 1.5012,
+      "step": 274
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 5.789276599884033,
+      "learning_rate": 5.45945945945946e-06,
+      "loss": 1.5482,
+      "step": 275
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 5.576483249664307,
+      "learning_rate": 5.405405405405406e-06,
+      "loss": 1.638,
+      "step": 276
+    },
+    {
+      "epoch": 0.7386666666666667,
+      "grad_norm": 6.0389533042907715,
+      "learning_rate": 5.351351351351351e-06,
+      "loss": 1.5486,
+      "step": 277
+    },
+    {
+      "epoch": 0.7413333333333333,
+      "grad_norm": 5.610621452331543,
+      "learning_rate": 5.297297297297298e-06,
+      "loss": 1.5533,
+      "step": 278
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 4.995850563049316,
+      "learning_rate": 5.243243243243244e-06,
+      "loss": 1.5462,
+      "step": 279
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 6.7199225425720215,
+      "learning_rate": 5.18918918918919e-06,
+      "loss": 1.44,
+      "step": 280
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "eval_loss": 2.2508785724639893,
+      "eval_runtime": 2.2821,
+      "eval_samples_per_second": 43.82,
+      "eval_steps_per_second": 21.91,
+      "step": 280
+    },
+    {
+      "epoch": 0.7493333333333333,
+      "grad_norm": 5.693479537963867,
+      "learning_rate": 5.135135135135135e-06,
+      "loss": 1.445,
+      "step": 281
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 5.529321193695068,
+      "learning_rate": 5.081081081081082e-06,
+      "loss": 1.5007,
+      "step": 282
+    },
+    {
+      "epoch": 0.7546666666666667,
+      "grad_norm": 5.192197799682617,
+      "learning_rate": 5.027027027027027e-06,
+      "loss": 1.5689,
+      "step": 283
+    },
+    {
+      "epoch": 0.7573333333333333,
+      "grad_norm": 6.242859363555908,
+      "learning_rate": 4.9729729729729735e-06,
+      "loss": 1.5279,
+      "step": 284
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.91813850402832,
+      "learning_rate": 4.91891891891892e-06,
+      "loss": 1.5494,
+      "step": 285
+    },
+    {
+      "epoch": 0.7626666666666667,
+      "grad_norm": 5.46779727935791,
+      "learning_rate": 4.864864864864866e-06,
+      "loss": 1.5293,
+      "step": 286
+    },
+    {
+      "epoch": 0.7653333333333333,
+      "grad_norm": 6.261353015899658,
+      "learning_rate": 4.810810810810811e-06,
+      "loss": 1.5371,
+      "step": 287
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 6.214474678039551,
+      "learning_rate": 4.756756756756757e-06,
+      "loss": 1.436,
+      "step": 288
+    },
+    {
+      "epoch": 0.7706666666666667,
+      "grad_norm": 4.978456974029541,
+      "learning_rate": 4.702702702702703e-06,
+      "loss": 1.5033,
+      "step": 289
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 5.478001117706299,
+      "learning_rate": 4.6486486486486495e-06,
+      "loss": 1.5482,
+      "step": 290
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "eval_loss": 2.2608802318573,
+      "eval_runtime": 2.4723,
+      "eval_samples_per_second": 40.448,
+      "eval_steps_per_second": 20.224,
+      "step": 290
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 6.418459415435791,
+      "learning_rate": 4.594594594594596e-06,
+      "loss": 1.552,
+      "step": 291
+    },
+    {
+      "epoch": 0.7786666666666666,
+      "grad_norm": 5.811317443847656,
+      "learning_rate": 4.540540540540541e-06,
+      "loss": 1.5471,
+      "step": 292
+    },
+    {
+      "epoch": 0.7813333333333333,
+      "grad_norm": 6.9032206535339355,
+      "learning_rate": 4.486486486486487e-06,
+      "loss": 1.5449,
+      "step": 293
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 6.512218952178955,
+      "learning_rate": 4.432432432432433e-06,
+      "loss": 1.5782,
+      "step": 294
+    },
+    {
+      "epoch": 0.7866666666666666,
+      "grad_norm": 6.343830108642578,
+      "learning_rate": 4.378378378378379e-06,
+      "loss": 1.6194,
+      "step": 295
+    },
+    {
+      "epoch": 0.7893333333333333,
+      "grad_norm": 5.638239860534668,
+      "learning_rate": 4.324324324324325e-06,
+      "loss": 1.5705,
+      "step": 296
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 5.549553394317627,
+      "learning_rate": 4.270270270270271e-06,
+      "loss": 1.5552,
+      "step": 297
+    },
+    {
+      "epoch": 0.7946666666666666,
+      "grad_norm": 5.946320533752441,
+      "learning_rate": 4.216216216216217e-06,
+      "loss": 1.4716,
+      "step": 298
+    },
+    {
+      "epoch": 0.7973333333333333,
+      "grad_norm": 4.266452312469482,
+      "learning_rate": 4.162162162162163e-06,
+      "loss": 1.6002,
+      "step": 299
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.8811750411987305,
+      "learning_rate": 4.108108108108108e-06,
+      "loss": 1.5286,
+      "step": 300
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 2.253636121749878,
+      "eval_runtime": 2.2603,
+      "eval_samples_per_second": 44.242,
+      "eval_steps_per_second": 22.121,
+      "step": 300
+    },
+    {
+      "epoch": 0.8026666666666666,
+      "grad_norm": 5.205958366394043,
+      "learning_rate": 4.0540540540540545e-06,
+      "loss": 1.5141,
+      "step": 301
+    },
+    {
+      "epoch": 0.8053333333333333,
+      "grad_norm": 6.4445929527282715,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.5721,
+      "step": 302
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 5.599625587463379,
+      "learning_rate": 3.945945945945947e-06,
+      "loss": 1.5702,
+      "step": 303
+    },
+    {
+      "epoch": 0.8106666666666666,
+      "grad_norm": 6.209537982940674,
+      "learning_rate": 3.891891891891892e-06,
+      "loss": 1.553,
+      "step": 304
+    },
+    {
+      "epoch": 0.8133333333333334,
+      "grad_norm": 5.1455979347229,
+      "learning_rate": 3.837837837837838e-06,
+      "loss": 1.5177,
+      "step": 305
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 6.070219993591309,
+      "learning_rate": 3.7837837837837844e-06,
+      "loss": 1.5271,
+      "step": 306
+    },
+    {
+      "epoch": 0.8186666666666667,
+      "grad_norm": 5.2099504470825195,
+      "learning_rate": 3.72972972972973e-06,
+      "loss": 1.5627,
+      "step": 307
+    },
+    {
+      "epoch": 0.8213333333333334,
+      "grad_norm": 5.216839790344238,
+      "learning_rate": 3.6756756756756763e-06,
+      "loss": 1.544,
+      "step": 308
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 6.461705684661865,
+      "learning_rate": 3.621621621621622e-06,
+      "loss": 1.5797,
+      "step": 309
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 6.210687637329102,
+      "learning_rate": 3.567567567567568e-06,
+      "loss": 1.598,
+      "step": 310
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "eval_loss": 2.2522964477539062,
+      "eval_runtime": 2.1897,
+      "eval_samples_per_second": 45.667,
+      "eval_steps_per_second": 22.834,
+      "step": 310
+    },
+    {
+      "epoch": 0.8293333333333334,
+      "grad_norm": 5.91581916809082,
+      "learning_rate": 3.513513513513514e-06,
+      "loss": 1.6017,
+      "step": 311
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 5.582605361938477,
+      "learning_rate": 3.45945945945946e-06,
+      "loss": 1.4786,
+      "step": 312
+    },
+    {
+      "epoch": 0.8346666666666667,
+      "grad_norm": 4.586456298828125,
+      "learning_rate": 3.4054054054054057e-06,
+      "loss": 1.5288,
+      "step": 313
+    },
+    {
+      "epoch": 0.8373333333333334,
+      "grad_norm": 5.894623279571533,
+      "learning_rate": 3.351351351351352e-06,
+      "loss": 1.5197,
+      "step": 314
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 5.776389122009277,
+      "learning_rate": 3.2972972972972976e-06,
+      "loss": 1.5655,
+      "step": 315
+    },
+    {
+      "epoch": 0.8426666666666667,
+      "grad_norm": 5.668336868286133,
+      "learning_rate": 3.2432432432432437e-06,
+      "loss": 1.5255,
+      "step": 316
+    },
+    {
+      "epoch": 0.8453333333333334,
+      "grad_norm": 6.561155319213867,
+      "learning_rate": 3.1891891891891894e-06,
+      "loss": 1.4802,
+      "step": 317
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 5.078688621520996,
+      "learning_rate": 3.1351351351351356e-06,
+      "loss": 1.5754,
+      "step": 318
+    },
+    {
+      "epoch": 0.8506666666666667,
+      "grad_norm": 5.22740364074707,
+      "learning_rate": 3.0810810810810817e-06,
+      "loss": 1.6293,
+      "step": 319
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 5.6544270515441895,
+      "learning_rate": 3.0270270270270274e-06,
+      "loss": 1.5225,
+      "step": 320
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "eval_loss": 2.2560644149780273,
+      "eval_runtime": 2.1308,
+      "eval_samples_per_second": 46.932,
+      "eval_steps_per_second": 23.466,
+      "step": 320
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.728905366044262e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-320/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed4071e241f6826eb1ee301ccead87bf9df9ca8e581b6c25eca5e624e73f217d
+size 6033