Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-241/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,208 @@
+---
+base_model: unsloth/Llama-3.3-70B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Llama-3.3-70B-Instruct
+- lora
+- transformers
+- unsloth
+---
+
+# 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 0.18.1

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "LlamaForCausalLM",
+    "parent_library": "transformers.models.llama.modeling_llama",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Llama-3.3-70B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b4ed940017aa43d9cbfa0752eb1a280f73c5264996fefd6c0844d61cc89f7a
+size 3313653480

chat_template.jinja

@@ -0,0 +1,109 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- set date_string = "26 Jul 2024" %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message + builtin tools #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if builtin_tools is defined or tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{%- if builtin_tools is defined %}
+    {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- "<|python_tag|>" + tool_call.name + ".call(" }}
+            {%- for arg_name, arg_val in tool_call.arguments | items %}
+                {{- arg_name + '="' + arg_val + '"' }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- endif %}
+                {%- endfor %}
+            {{- ")" }}
+        {%- else  %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- '{"name": "' + tool_call.name + '", ' }}
+            {{- '"parameters": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- "}" }}
+        {%- endif %}
+        {%- if builtin_tools is defined %}
+            {#- This means we're in ipython mode #}
+            {{- "<|eom_id|>" }}
+        {%- else %}
+            {{- "<|eot_id|>" }}
+        {%- endif %}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

checkpoint-241/README.md

@@ -0,0 +1,208 @@
+---
+base_model: unsloth/Llama-3.3-70B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Llama-3.3-70B-Instruct
+- lora
+- transformers
+- unsloth
+---
+
+# 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 0.18.1

checkpoint-241/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "LlamaForCausalLM",
+    "parent_library": "transformers.models.llama.modeling_llama",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Llama-3.3-70B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-241/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b4ed940017aa43d9cbfa0752eb1a280f73c5264996fefd6c0844d61cc89f7a
+size 3313653480

checkpoint-241/chat_template.jinja

@@ -0,0 +1,109 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- set date_string = "26 Jul 2024" %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message + builtin tools #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if builtin_tools is defined or tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{%- if builtin_tools is defined %}
+    {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- "<|python_tag|>" + tool_call.name + ".call(" }}
+            {%- for arg_name, arg_val in tool_call.arguments | items %}
+                {{- arg_name + '="' + arg_val + '"' }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- endif %}
+                {%- endfor %}
+            {{- ")" }}
+        {%- else  %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- '{"name": "' + tool_call.name + '", ' }}
+            {{- '"parameters": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- "}" }}
+        {%- endif %}
+        {%- if builtin_tools is defined %}
+            {#- This means we're in ipython mode #}
+            {{- "<|eom_id|>" }}
+        {%- else %}
+            {{- "<|eot_id|>" }}
+        {%- endif %}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

checkpoint-241/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:695cd7a8f68ce2a582c208593bc32b75450fbcf0da8c649de7ff6627f4b93b30
+size 6627963827

checkpoint-241/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoint-241/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd216a79bf36a073b8de03df89b5078ad5217e1c0c2703644ab0fbbdc132b05
+size 1465

checkpoint-241/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2f90a0ee1b41702c7b233b02234294a53bc0684a08d3bcd8c8ff702e9a12f64
+size 17210019

checkpoint-241/tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "from_slow": true,
+  "is_local": false,
+  "legacy": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}

checkpoint-241/trainer_state.json

@@ -0,0 +1,1721 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 241,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004149377593360996,
+      "grad_norm": 0.5114469528198242,
+      "learning_rate": 2e-05,
+      "loss": 0.7995174527168274,
+      "step": 1
+    },
+    {
+      "epoch": 0.008298755186721992,
+      "grad_norm": 0.5205491185188293,
+      "learning_rate": 2e-05,
+      "loss": 0.8812965750694275,
+      "step": 2
+    },
+    {
+      "epoch": 0.012448132780082987,
+      "grad_norm": 0.6057224273681641,
+      "learning_rate": 2e-05,
+      "loss": 0.8402022123336792,
+      "step": 3
+    },
+    {
+      "epoch": 0.016597510373443983,
+      "grad_norm": 0.5623906254768372,
+      "learning_rate": 2e-05,
+      "loss": 0.8188848495483398,
+      "step": 4
+    },
+    {
+      "epoch": 0.02074688796680498,
+      "grad_norm": 0.574876606464386,
+      "learning_rate": 2e-05,
+      "loss": 0.8380811214447021,
+      "step": 5
+    },
+    {
+      "epoch": 0.024896265560165973,
+      "grad_norm": 0.4625989496707916,
+      "learning_rate": 2e-05,
+      "loss": 0.7132218480110168,
+      "step": 6
+    },
+    {
+      "epoch": 0.029045643153526972,
+      "grad_norm": 0.5183306336402893,
+      "learning_rate": 2e-05,
+      "loss": 0.8268325328826904,
+      "step": 7
+    },
+    {
+      "epoch": 0.03319502074688797,
+      "grad_norm": 0.4928549826145172,
+      "learning_rate": 2e-05,
+      "loss": 0.7686080932617188,
+      "step": 8
+    },
+    {
+      "epoch": 0.03734439834024896,
+      "grad_norm": 0.4636511206626892,
+      "learning_rate": 2e-05,
+      "loss": 0.8444753289222717,
+      "step": 9
+    },
+    {
+      "epoch": 0.04149377593360996,
+      "grad_norm": 0.5008803606033325,
+      "learning_rate": 2e-05,
+      "loss": 0.6671140789985657,
+      "step": 10
+    },
+    {
+      "epoch": 0.04564315352697095,
+      "grad_norm": 0.49685290455818176,
+      "learning_rate": 2e-05,
+      "loss": 0.7625027894973755,
+      "step": 11
+    },
+    {
+      "epoch": 0.04979253112033195,
+      "grad_norm": 0.5161386728286743,
+      "learning_rate": 2e-05,
+      "loss": 0.5999635457992554,
+      "step": 12
+    },
+    {
+      "epoch": 0.05394190871369295,
+      "grad_norm": 0.46996110677719116,
+      "learning_rate": 2e-05,
+      "loss": 0.7389070987701416,
+      "step": 13
+    },
+    {
+      "epoch": 0.058091286307053944,
+      "grad_norm": 0.45131370425224304,
+      "learning_rate": 2e-05,
+      "loss": 0.6111957430839539,
+      "step": 14
+    },
+    {
+      "epoch": 0.06224066390041494,
+      "grad_norm": 0.4911205470561981,
+      "learning_rate": 2e-05,
+      "loss": 0.5750669240951538,
+      "step": 15
+    },
+    {
+      "epoch": 0.06639004149377593,
+      "grad_norm": 0.46468034386634827,
+      "learning_rate": 2e-05,
+      "loss": 0.6607809066772461,
+      "step": 16
+    },
+    {
+      "epoch": 0.07053941908713693,
+      "grad_norm": 0.5140272378921509,
+      "learning_rate": 2e-05,
+      "loss": 0.8089659214019775,
+      "step": 17
+    },
+    {
+      "epoch": 0.07468879668049792,
+      "grad_norm": 0.49761149287223816,
+      "learning_rate": 2e-05,
+      "loss": 0.8017055988311768,
+      "step": 18
+    },
+    {
+      "epoch": 0.07883817427385892,
+      "grad_norm": 0.45623964071273804,
+      "learning_rate": 2e-05,
+      "loss": 0.725612223148346,
+      "step": 19
+    },
+    {
+      "epoch": 0.08298755186721991,
+      "grad_norm": 0.4778558015823364,
+      "learning_rate": 2e-05,
+      "loss": 0.6465242505073547,
+      "step": 20
+    },
+    {
+      "epoch": 0.08713692946058091,
+      "grad_norm": 0.4813624620437622,
+      "learning_rate": 2e-05,
+      "loss": 0.6812542676925659,
+      "step": 21
+    },
+    {
+      "epoch": 0.0912863070539419,
+      "grad_norm": 0.45828455686569214,
+      "learning_rate": 2e-05,
+      "loss": 0.6355943083763123,
+      "step": 22
+    },
+    {
+      "epoch": 0.0954356846473029,
+      "grad_norm": 0.39770182967185974,
+      "learning_rate": 2e-05,
+      "loss": 0.734164297580719,
+      "step": 23
+    },
+    {
+      "epoch": 0.0995850622406639,
+      "grad_norm": 0.515662431716919,
+      "learning_rate": 2e-05,
+      "loss": 0.775545060634613,
+      "step": 24
+    },
+    {
+      "epoch": 0.1037344398340249,
+      "grad_norm": 0.4875846207141876,
+      "learning_rate": 2e-05,
+      "loss": 0.7608263492584229,
+      "step": 25
+    },
+    {
+      "epoch": 0.1078838174273859,
+      "grad_norm": 0.4272926449775696,
+      "learning_rate": 2e-05,
+      "loss": 0.655767560005188,
+      "step": 26
+    },
+    {
+      "epoch": 0.11203319502074689,
+      "grad_norm": 0.47189342975616455,
+      "learning_rate": 2e-05,
+      "loss": 0.6984891295433044,
+      "step": 27
+    },
+    {
+      "epoch": 0.11618257261410789,
+      "grad_norm": 0.49677926301956177,
+      "learning_rate": 2e-05,
+      "loss": 0.6952549815177917,
+      "step": 28
+    },
+    {
+      "epoch": 0.12033195020746888,
+      "grad_norm": 0.5341811776161194,
+      "learning_rate": 2e-05,
+      "loss": 0.6844781041145325,
+      "step": 29
+    },
+    {
+      "epoch": 0.12448132780082988,
+      "grad_norm": 0.49139678478240967,
+      "learning_rate": 2e-05,
+      "loss": 0.7043532729148865,
+      "step": 30
+    },
+    {
+      "epoch": 0.12863070539419086,
+      "grad_norm": 0.42113780975341797,
+      "learning_rate": 2e-05,
+      "loss": 0.6791371703147888,
+      "step": 31
+    },
+    {
+      "epoch": 0.13278008298755187,
+      "grad_norm": 0.490699827671051,
+      "learning_rate": 2e-05,
+      "loss": 0.66917484998703,
+      "step": 32
+    },
+    {
+      "epoch": 0.13692946058091288,
+      "grad_norm": 0.48269012570381165,
+      "learning_rate": 2e-05,
+      "loss": 0.6663049459457397,
+      "step": 33
+    },
+    {
+      "epoch": 0.14107883817427386,
+      "grad_norm": 0.4833972454071045,
+      "learning_rate": 2e-05,
+      "loss": 0.7479192018508911,
+      "step": 34
+    },
+    {
+      "epoch": 0.14522821576763487,
+      "grad_norm": 0.4521920382976532,
+      "learning_rate": 2e-05,
+      "loss": 0.5006750822067261,
+      "step": 35
+    },
+    {
+      "epoch": 0.14937759336099585,
+      "grad_norm": 0.4805753231048584,
+      "learning_rate": 2e-05,
+      "loss": 0.7437685132026672,
+      "step": 36
+    },
+    {
+      "epoch": 0.15352697095435686,
+      "grad_norm": 0.4702300429344177,
+      "learning_rate": 2e-05,
+      "loss": 0.7820006608963013,
+      "step": 37
+    },
+    {
+      "epoch": 0.15767634854771784,
+      "grad_norm": 0.4416898190975189,
+      "learning_rate": 2e-05,
+      "loss": 0.5911201238632202,
+      "step": 38
+    },
+    {
+      "epoch": 0.16182572614107885,
+      "grad_norm": 0.46818608045578003,
+      "learning_rate": 2e-05,
+      "loss": 0.6237752437591553,
+      "step": 39
+    },
+    {
+      "epoch": 0.16597510373443983,
+      "grad_norm": 0.38742795586586,
+      "learning_rate": 2e-05,
+      "loss": 0.6044095754623413,
+      "step": 40
+    },
+    {
+      "epoch": 0.17012448132780084,
+      "grad_norm": 0.4806065857410431,
+      "learning_rate": 2e-05,
+      "loss": 0.6341798901557922,
+      "step": 41
+    },
+    {
+      "epoch": 0.17427385892116182,
+      "grad_norm": 0.4329955279827118,
+      "learning_rate": 2e-05,
+      "loss": 0.621407687664032,
+      "step": 42
+    },
+    {
+      "epoch": 0.17842323651452283,
+      "grad_norm": 0.46890074014663696,
+      "learning_rate": 2e-05,
+      "loss": 0.7025566697120667,
+      "step": 43
+    },
+    {
+      "epoch": 0.1825726141078838,
+      "grad_norm": 0.4821957051753998,
+      "learning_rate": 2e-05,
+      "loss": 0.6547812819480896,
+      "step": 44
+    },
+    {
+      "epoch": 0.18672199170124482,
+      "grad_norm": 0.4716266691684723,
+      "learning_rate": 2e-05,
+      "loss": 0.6434807777404785,
+      "step": 45
+    },
+    {
+      "epoch": 0.1908713692946058,
+      "grad_norm": 0.5017584562301636,
+      "learning_rate": 2e-05,
+      "loss": 0.6461539268493652,
+      "step": 46
+    },
+    {
+      "epoch": 0.1950207468879668,
+      "grad_norm": 0.4837803244590759,
+      "learning_rate": 2e-05,
+      "loss": 0.6638780236244202,
+      "step": 47
+    },
+    {
+      "epoch": 0.1991701244813278,
+      "grad_norm": 0.4523409605026245,
+      "learning_rate": 2e-05,
+      "loss": 0.5731872916221619,
+      "step": 48
+    },
+    {
+      "epoch": 0.2033195020746888,
+      "grad_norm": 0.46308189630508423,
+      "learning_rate": 2e-05,
+      "loss": 0.6024616956710815,
+      "step": 49
+    },
+    {
+      "epoch": 0.2074688796680498,
+      "grad_norm": 0.4565693140029907,
+      "learning_rate": 2e-05,
+      "loss": 0.5795129537582397,
+      "step": 50
+    },
+    {
+      "epoch": 0.21161825726141079,
+      "grad_norm": 0.48081323504447937,
+      "learning_rate": 2e-05,
+      "loss": 0.6645175814628601,
+      "step": 51
+    },
+    {
+      "epoch": 0.2157676348547718,
+      "grad_norm": 0.4649989902973175,
+      "learning_rate": 2e-05,
+      "loss": 0.6339988112449646,
+      "step": 52
+    },
+    {
+      "epoch": 0.21991701244813278,
+      "grad_norm": 0.45999905467033386,
+      "learning_rate": 2e-05,
+      "loss": 0.6070005297660828,
+      "step": 53
+    },
+    {
+      "epoch": 0.22406639004149378,
+      "grad_norm": 0.43405112624168396,
+      "learning_rate": 2e-05,
+      "loss": 0.6078118085861206,
+      "step": 54
+    },
+    {
+      "epoch": 0.22821576763485477,
+      "grad_norm": 0.557212233543396,
+      "learning_rate": 2e-05,
+      "loss": 0.6502783894538879,
+      "step": 55
+    },
+    {
+      "epoch": 0.23236514522821577,
+      "grad_norm": 0.4206949472427368,
+      "learning_rate": 2e-05,
+      "loss": 0.5604119896888733,
+      "step": 56
+    },
+    {
+      "epoch": 0.23651452282157676,
+      "grad_norm": 0.4931945502758026,
+      "learning_rate": 2e-05,
+      "loss": 0.5463195443153381,
+      "step": 57
+    },
+    {
+      "epoch": 0.24066390041493776,
+      "grad_norm": 0.44888630509376526,
+      "learning_rate": 2e-05,
+      "loss": 0.49333369731903076,
+      "step": 58
+    },
+    {
+      "epoch": 0.24481327800829875,
+      "grad_norm": 0.4515199363231659,
+      "learning_rate": 2e-05,
+      "loss": 0.66854327917099,
+      "step": 59
+    },
+    {
+      "epoch": 0.24896265560165975,
+      "grad_norm": 0.46686026453971863,
+      "learning_rate": 2e-05,
+      "loss": 0.5279274582862854,
+      "step": 60
+    },
+    {
+      "epoch": 0.25311203319502074,
+      "grad_norm": 0.46663975715637207,
+      "learning_rate": 2e-05,
+      "loss": 0.6141489148139954,
+      "step": 61
+    },
+    {
+      "epoch": 0.2572614107883817,
+      "grad_norm": 0.45049089193344116,
+      "learning_rate": 2e-05,
+      "loss": 0.6643646955490112,
+      "step": 62
+    },
+    {
+      "epoch": 0.26141078838174275,
+      "grad_norm": 0.49262335896492004,
+      "learning_rate": 2e-05,
+      "loss": 0.6589719653129578,
+      "step": 63
+    },
+    {
+      "epoch": 0.26556016597510373,
+      "grad_norm": 0.5234288573265076,
+      "learning_rate": 2e-05,
+      "loss": 0.6250555515289307,
+      "step": 64
+    },
+    {
+      "epoch": 0.2697095435684647,
+      "grad_norm": 0.4657873809337616,
+      "learning_rate": 2e-05,
+      "loss": 0.5761417150497437,
+      "step": 65
+    },
+    {
+      "epoch": 0.27385892116182575,
+      "grad_norm": 2.8522613048553467,
+      "learning_rate": 2e-05,
+      "loss": 0.6810148358345032,
+      "step": 66
+    },
+    {
+      "epoch": 0.27800829875518673,
+      "grad_norm": 0.45667174458503723,
+      "learning_rate": 2e-05,
+      "loss": 0.5667203664779663,
+      "step": 67
+    },
+    {
+      "epoch": 0.2821576763485477,
+      "grad_norm": 0.48965880274772644,
+      "learning_rate": 2e-05,
+      "loss": 0.6057634949684143,
+      "step": 68
+    },
+    {
+      "epoch": 0.2863070539419087,
+      "grad_norm": 0.4700252115726471,
+      "learning_rate": 2e-05,
+      "loss": 0.5498369932174683,
+      "step": 69
+    },
+    {
+      "epoch": 0.29045643153526973,
+      "grad_norm": 0.4457707703113556,
+      "learning_rate": 2e-05,
+      "loss": 0.5500881671905518,
+      "step": 70
+    },
+    {
+      "epoch": 0.2946058091286307,
+      "grad_norm": 0.5242801904678345,
+      "learning_rate": 2e-05,
+      "loss": 0.6648991703987122,
+      "step": 71
+    },
+    {
+      "epoch": 0.2987551867219917,
+      "grad_norm": 0.4845593273639679,
+      "learning_rate": 2e-05,
+      "loss": 0.6495253443717957,
+      "step": 72
+    },
+    {
+      "epoch": 0.3029045643153527,
+      "grad_norm": 0.4535577595233917,
+      "learning_rate": 2e-05,
+      "loss": 0.6440762281417847,
+      "step": 73
+    },
+    {
+      "epoch": 0.3070539419087137,
+      "grad_norm": 0.4424896240234375,
+      "learning_rate": 2e-05,
+      "loss": 0.5427602529525757,
+      "step": 74
+    },
+    {
+      "epoch": 0.3112033195020747,
+      "grad_norm": 0.4791293144226074,
+      "learning_rate": 2e-05,
+      "loss": 0.6312339901924133,
+      "step": 75
+    },
+    {
+      "epoch": 0.3153526970954357,
+      "grad_norm": 0.49440717697143555,
+      "learning_rate": 2e-05,
+      "loss": 0.7304765582084656,
+      "step": 76
+    },
+    {
+      "epoch": 0.31950207468879666,
+      "grad_norm": 0.47376683354377747,
+      "learning_rate": 2e-05,
+      "loss": 0.5550855994224548,
+      "step": 77
+    },
+    {
+      "epoch": 0.3236514522821577,
+      "grad_norm": 0.5386195182800293,
+      "learning_rate": 2e-05,
+      "loss": 0.7627665996551514,
+      "step": 78
+    },
+    {
+      "epoch": 0.3278008298755187,
+      "grad_norm": 0.5139470100402832,
+      "learning_rate": 2e-05,
+      "loss": 0.7294001579284668,
+      "step": 79
+    },
+    {
+      "epoch": 0.33195020746887965,
+      "grad_norm": 0.5727441310882568,
+      "learning_rate": 2e-05,
+      "loss": 0.6094337105751038,
+      "step": 80
+    },
+    {
+      "epoch": 0.3360995850622407,
+      "grad_norm": 0.4475933313369751,
+      "learning_rate": 2e-05,
+      "loss": 0.6689184904098511,
+      "step": 81
+    },
+    {
+      "epoch": 0.34024896265560167,
+      "grad_norm": 0.48615196347236633,
+      "learning_rate": 2e-05,
+      "loss": 0.5170673727989197,
+      "step": 82
+    },
+    {
+      "epoch": 0.34439834024896265,
+      "grad_norm": 0.4444977939128876,
+      "learning_rate": 2e-05,
+      "loss": 0.5426638126373291,
+      "step": 83
+    },
+    {
+      "epoch": 0.34854771784232363,
+      "grad_norm": 0.4532429873943329,
+      "learning_rate": 2e-05,
+      "loss": 0.5246436595916748,
+      "step": 84
+    },
+    {
+      "epoch": 0.35269709543568467,
+      "grad_norm": 0.5425305962562561,
+      "learning_rate": 2e-05,
+      "loss": 0.7444034814834595,
+      "step": 85
+    },
+    {
+      "epoch": 0.35684647302904565,
+      "grad_norm": 0.4604993164539337,
+      "learning_rate": 2e-05,
+      "loss": 0.6390590071678162,
+      "step": 86
+    },
+    {
+      "epoch": 0.36099585062240663,
+      "grad_norm": 0.4503551423549652,
+      "learning_rate": 2e-05,
+      "loss": 0.7437008023262024,
+      "step": 87
+    },
+    {
+      "epoch": 0.3651452282157676,
+      "grad_norm": 0.473531037569046,
+      "learning_rate": 2e-05,
+      "loss": 0.5801289677619934,
+      "step": 88
+    },
+    {
+      "epoch": 0.36929460580912865,
+      "grad_norm": 0.43614616990089417,
+      "learning_rate": 2e-05,
+      "loss": 0.5945846438407898,
+      "step": 89
+    },
+    {
+      "epoch": 0.37344398340248963,
+      "grad_norm": 0.5157416462898254,
+      "learning_rate": 2e-05,
+      "loss": 0.5870503187179565,
+      "step": 90
+    },
+    {
+      "epoch": 0.3775933609958506,
+      "grad_norm": 0.4724714756011963,
+      "learning_rate": 2e-05,
+      "loss": 0.7136172652244568,
+      "step": 91
+    },
+    {
+      "epoch": 0.3817427385892116,
+      "grad_norm": 0.49608129262924194,
+      "learning_rate": 2e-05,
+      "loss": 0.5707521438598633,
+      "step": 92
+    },
+    {
+      "epoch": 0.38589211618257263,
+      "grad_norm": 0.4372619390487671,
+      "learning_rate": 2e-05,
+      "loss": 0.6751445531845093,
+      "step": 93
+    },
+    {
+      "epoch": 0.3900414937759336,
+      "grad_norm": 0.8502039909362793,
+      "learning_rate": 2e-05,
+      "loss": 0.7432682514190674,
+      "step": 94
+    },
+    {
+      "epoch": 0.3941908713692946,
+      "grad_norm": 0.43237465620040894,
+      "learning_rate": 2e-05,
+      "loss": 0.5463064908981323,
+      "step": 95
+    },
+    {
+      "epoch": 0.3983402489626556,
+      "grad_norm": 0.4683166444301605,
+      "learning_rate": 2e-05,
+      "loss": 0.5722454190254211,
+      "step": 96
+    },
+    {
+      "epoch": 0.4024896265560166,
+      "grad_norm": 0.49307140707969666,
+      "learning_rate": 2e-05,
+      "loss": 0.7676360011100769,
+      "step": 97
+    },
+    {
+      "epoch": 0.4066390041493776,
+      "grad_norm": 0.45873740315437317,
+      "learning_rate": 2e-05,
+      "loss": 0.7670221328735352,
+      "step": 98
+    },
+    {
+      "epoch": 0.4107883817427386,
+      "grad_norm": 0.522739589214325,
+      "learning_rate": 2e-05,
+      "loss": 0.6198732256889343,
+      "step": 99
+    },
+    {
+      "epoch": 0.4149377593360996,
+      "grad_norm": 0.513500988483429,
+      "learning_rate": 2e-05,
+      "loss": 0.6557285189628601,
+      "step": 100
+    },
+    {
+      "epoch": 0.4190871369294606,
+      "grad_norm": 0.5162559747695923,
+      "learning_rate": 2e-05,
+      "loss": 0.6777411699295044,
+      "step": 101
+    },
+    {
+      "epoch": 0.42323651452282157,
+      "grad_norm": 0.4742807447910309,
+      "learning_rate": 2e-05,
+      "loss": 0.5189216732978821,
+      "step": 102
+    },
+    {
+      "epoch": 0.42738589211618255,
+      "grad_norm": 0.3864991068840027,
+      "learning_rate": 2e-05,
+      "loss": 0.5397198796272278,
+      "step": 103
+    },
+    {
+      "epoch": 0.4315352697095436,
+      "grad_norm": 0.44808462262153625,
+      "learning_rate": 2e-05,
+      "loss": 0.5719993710517883,
+      "step": 104
+    },
+    {
+      "epoch": 0.43568464730290457,
+      "grad_norm": 0.5047919154167175,
+      "learning_rate": 2e-05,
+      "loss": 0.7246726751327515,
+      "step": 105
+    },
+    {
+      "epoch": 0.43983402489626555,
+      "grad_norm": 0.4501510262489319,
+      "learning_rate": 2e-05,
+      "loss": 0.5421350598335266,
+      "step": 106
+    },
+    {
+      "epoch": 0.44398340248962653,
+      "grad_norm": 0.5187399983406067,
+      "learning_rate": 2e-05,
+      "loss": 0.6851190328598022,
+      "step": 107
+    },
+    {
+      "epoch": 0.44813278008298757,
+      "grad_norm": 0.4442541003227234,
+      "learning_rate": 2e-05,
+      "loss": 0.7323095798492432,
+      "step": 108
+    },
+    {
+      "epoch": 0.45228215767634855,
+      "grad_norm": 0.4546023905277252,
+      "learning_rate": 2e-05,
+      "loss": 0.5949406027793884,
+      "step": 109
+    },
+    {
+      "epoch": 0.45643153526970953,
+      "grad_norm": 0.43765076994895935,
+      "learning_rate": 2e-05,
+      "loss": 0.5195109248161316,
+      "step": 110
+    },
+    {
+      "epoch": 0.4605809128630705,
+      "grad_norm": 0.6012418866157532,
+      "learning_rate": 2e-05,
+      "loss": 0.5891928672790527,
+      "step": 111
+    },
+    {
+      "epoch": 0.46473029045643155,
+      "grad_norm": 0.5350989699363708,
+      "learning_rate": 2e-05,
+      "loss": 0.7073556184768677,
+      "step": 112
+    },
+    {
+      "epoch": 0.46887966804979253,
+      "grad_norm": 0.40423402190208435,
+      "learning_rate": 2e-05,
+      "loss": 0.6081284284591675,
+      "step": 113
+    },
+    {
+      "epoch": 0.4730290456431535,
+      "grad_norm": 0.48459556698799133,
+      "learning_rate": 2e-05,
+      "loss": 0.7626031637191772,
+      "step": 114
+    },
+    {
+      "epoch": 0.47717842323651455,
+      "grad_norm": 0.5132282972335815,
+      "learning_rate": 2e-05,
+      "loss": 0.7070454359054565,
+      "step": 115
+    },
+    {
+      "epoch": 0.48132780082987553,
+      "grad_norm": 0.40754643082618713,
+      "learning_rate": 2e-05,
+      "loss": 0.7881268858909607,
+      "step": 116
+    },
+    {
+      "epoch": 0.4854771784232365,
+      "grad_norm": 0.46227574348449707,
+      "learning_rate": 2e-05,
+      "loss": 0.5589393973350525,
+      "step": 117
+    },
+    {
+      "epoch": 0.4896265560165975,
+      "grad_norm": 0.458891898393631,
+      "learning_rate": 2e-05,
+      "loss": 0.6076244711875916,
+      "step": 118
+    },
+    {
+      "epoch": 0.49377593360995853,
+      "grad_norm": 0.4314862787723541,
+      "learning_rate": 2e-05,
+      "loss": 0.58890700340271,
+      "step": 119
+    },
+    {
+      "epoch": 0.4979253112033195,
+      "grad_norm": 0.4849430322647095,
+      "learning_rate": 2e-05,
+      "loss": 0.7297042012214661,
+      "step": 120
+    },
+    {
+      "epoch": 0.5020746887966805,
+      "grad_norm": 0.4734286963939667,
+      "learning_rate": 2e-05,
+      "loss": 0.7929898500442505,
+      "step": 121
+    },
+    {
+      "epoch": 0.5062240663900415,
+      "grad_norm": 0.4982983469963074,
+      "learning_rate": 2e-05,
+      "loss": 0.6973749399185181,
+      "step": 122
+    },
+    {
+      "epoch": 0.5103734439834025,
+      "grad_norm": 0.4555007517337799,
+      "learning_rate": 2e-05,
+      "loss": 0.6363988518714905,
+      "step": 123
+    },
+    {
+      "epoch": 0.5145228215767634,
+      "grad_norm": 0.469707190990448,
+      "learning_rate": 2e-05,
+      "loss": 0.6936283111572266,
+      "step": 124
+    },
+    {
+      "epoch": 0.5186721991701245,
+      "grad_norm": 0.45310160517692566,
+      "learning_rate": 2e-05,
+      "loss": 0.8045607209205627,
+      "step": 125
+    },
+    {
+      "epoch": 0.5228215767634855,
+      "grad_norm": 0.5117340087890625,
+      "learning_rate": 2e-05,
+      "loss": 0.5602521300315857,
+      "step": 126
+    },
+    {
+      "epoch": 0.5269709543568465,
+      "grad_norm": 0.4890298545360565,
+      "learning_rate": 2e-05,
+      "loss": 0.5749447345733643,
+      "step": 127
+    },
+    {
+      "epoch": 0.5311203319502075,
+      "grad_norm": 0.4680368900299072,
+      "learning_rate": 2e-05,
+      "loss": 0.6603504419326782,
+      "step": 128
+    },
+    {
+      "epoch": 0.5352697095435685,
+      "grad_norm": 0.4364625811576843,
+      "learning_rate": 2e-05,
+      "loss": 0.6615546941757202,
+      "step": 129
+    },
+    {
+      "epoch": 0.5394190871369294,
+      "grad_norm": 0.44393712282180786,
+      "learning_rate": 2e-05,
+      "loss": 0.7206588387489319,
+      "step": 130
+    },
+    {
+      "epoch": 0.5435684647302904,
+      "grad_norm": 0.4770648777484894,
+      "learning_rate": 2e-05,
+      "loss": 0.5122599005699158,
+      "step": 131
+    },
+    {
+      "epoch": 0.5477178423236515,
+      "grad_norm": 0.4254826307296753,
+      "learning_rate": 2e-05,
+      "loss": 0.5919891595840454,
+      "step": 132
+    },
+    {
+      "epoch": 0.5518672199170125,
+      "grad_norm": 0.49948850274086,
+      "learning_rate": 2e-05,
+      "loss": 0.7168218493461609,
+      "step": 133
+    },
+    {
+      "epoch": 0.5560165975103735,
+      "grad_norm": 0.46940577030181885,
+      "learning_rate": 2e-05,
+      "loss": 0.559630274772644,
+      "step": 134
+    },
+    {
+      "epoch": 0.5601659751037344,
+      "grad_norm": 0.38155895471572876,
+      "learning_rate": 2e-05,
+      "loss": 0.35719043016433716,
+      "step": 135
+    },
+    {
+      "epoch": 0.5643153526970954,
+      "grad_norm": 0.446111798286438,
+      "learning_rate": 2e-05,
+      "loss": 0.5944488644599915,
+      "step": 136
+    },
+    {
+      "epoch": 0.5684647302904564,
+      "grad_norm": 0.44898721575737,
+      "learning_rate": 2e-05,
+      "loss": 0.6778333187103271,
+      "step": 137
+    },
+    {
+      "epoch": 0.5726141078838174,
+      "grad_norm": 0.4727020263671875,
+      "learning_rate": 2e-05,
+      "loss": 0.6683153510093689,
+      "step": 138
+    },
+    {
+      "epoch": 0.5767634854771784,
+      "grad_norm": 0.4775353968143463,
+      "learning_rate": 2e-05,
+      "loss": 0.7357037663459778,
+      "step": 139
+    },
+    {
+      "epoch": 0.5809128630705395,
+      "grad_norm": 0.5201453566551208,
+      "learning_rate": 2e-05,
+      "loss": 0.5672426819801331,
+      "step": 140
+    },
+    {
+      "epoch": 0.5850622406639004,
+      "grad_norm": 0.4446447491645813,
+      "learning_rate": 2e-05,
+      "loss": 0.6665009260177612,
+      "step": 141
+    },
+    {
+      "epoch": 0.5892116182572614,
+      "grad_norm": 0.44674625992774963,
+      "learning_rate": 2e-05,
+      "loss": 0.6256436705589294,
+      "step": 142
+    },
+    {
+      "epoch": 0.5933609958506224,
+      "grad_norm": 0.48278629779815674,
+      "learning_rate": 2e-05,
+      "loss": 0.652278482913971,
+      "step": 143
+    },
+    {
+      "epoch": 0.5975103734439834,
+      "grad_norm": 0.4608626067638397,
+      "learning_rate": 2e-05,
+      "loss": 0.687121570110321,
+      "step": 144
+    },
+    {
+      "epoch": 0.6016597510373444,
+      "grad_norm": 0.5146644711494446,
+      "learning_rate": 2e-05,
+      "loss": 0.7759085297584534,
+      "step": 145
+    },
+    {
+      "epoch": 0.6058091286307054,
+      "grad_norm": 0.4703519344329834,
+      "learning_rate": 2e-05,
+      "loss": 0.6268375515937805,
+      "step": 146
+    },
+    {
+      "epoch": 0.6099585062240664,
+      "grad_norm": 0.4373490512371063,
+      "learning_rate": 2e-05,
+      "loss": 0.7350006699562073,
+      "step": 147
+    },
+    {
+      "epoch": 0.6141078838174274,
+      "grad_norm": 0.48525917530059814,
+      "learning_rate": 2e-05,
+      "loss": 0.6609182357788086,
+      "step": 148
+    },
+    {
+      "epoch": 0.6182572614107884,
+      "grad_norm": 0.509609043598175,
+      "learning_rate": 2e-05,
+      "loss": 0.7720542550086975,
+      "step": 149
+    },
+    {
+      "epoch": 0.6224066390041494,
+      "grad_norm": 0.46813687682151794,
+      "learning_rate": 2e-05,
+      "loss": 0.658400297164917,
+      "step": 150
+    },
+    {
+      "epoch": 0.6265560165975104,
+      "grad_norm": 0.48811477422714233,
+      "learning_rate": 2e-05,
+      "loss": 0.6340473890304565,
+      "step": 151
+    },
+    {
+      "epoch": 0.6307053941908713,
+      "grad_norm": 0.48529860377311707,
+      "learning_rate": 2e-05,
+      "loss": 0.7543718218803406,
+      "step": 152
+    },
+    {
+      "epoch": 0.6348547717842323,
+      "grad_norm": 0.4565221965312958,
+      "learning_rate": 2e-05,
+      "loss": 0.5810791254043579,
+      "step": 153
+    },
+    {
+      "epoch": 0.6390041493775933,
+      "grad_norm": 0.4667608141899109,
+      "learning_rate": 2e-05,
+      "loss": 0.5940293669700623,
+      "step": 154
+    },
+    {
+      "epoch": 0.6431535269709544,
+      "grad_norm": 0.476724773645401,
+      "learning_rate": 2e-05,
+      "loss": 0.5076797604560852,
+      "step": 155
+    },
+    {
+      "epoch": 0.6473029045643154,
+      "grad_norm": 0.48997762799263,
+      "learning_rate": 2e-05,
+      "loss": 0.5588229894638062,
+      "step": 156
+    },
+    {
+      "epoch": 0.6514522821576764,
+      "grad_norm": 0.4687066674232483,
+      "learning_rate": 2e-05,
+      "loss": 0.7414963245391846,
+      "step": 157
+    },
+    {
+      "epoch": 0.6556016597510373,
+      "grad_norm": 0.5096819400787354,
+      "learning_rate": 2e-05,
+      "loss": 0.6766090393066406,
+      "step": 158
+    },
+    {
+      "epoch": 0.6597510373443983,
+      "grad_norm": 0.40396353602409363,
+      "learning_rate": 2e-05,
+      "loss": 0.5890622735023499,
+      "step": 159
+    },
+    {
+      "epoch": 0.6639004149377593,
+      "grad_norm": 0.46985870599746704,
+      "learning_rate": 2e-05,
+      "loss": 0.5969380140304565,
+      "step": 160
+    },
+    {
+      "epoch": 0.6680497925311203,
+      "grad_norm": 0.49084073305130005,
+      "learning_rate": 2e-05,
+      "loss": 0.6371229887008667,
+      "step": 161
+    },
+    {
+      "epoch": 0.6721991701244814,
+      "grad_norm": 0.4466313123703003,
+      "learning_rate": 2e-05,
+      "loss": 0.6732550263404846,
+      "step": 162
+    },
+    {
+      "epoch": 0.6763485477178424,
+      "grad_norm": 0.4656016528606415,
+      "learning_rate": 2e-05,
+      "loss": 0.7082672119140625,
+      "step": 163
+    },
+    {
+      "epoch": 0.6804979253112033,
+      "grad_norm": 0.43604540824890137,
+      "learning_rate": 2e-05,
+      "loss": 0.5961745977401733,
+      "step": 164
+    },
+    {
+      "epoch": 0.6846473029045643,
+      "grad_norm": 0.45962008833885193,
+      "learning_rate": 2e-05,
+      "loss": 0.5974591374397278,
+      "step": 165
+    },
+    {
+      "epoch": 0.6887966804979253,
+      "grad_norm": 0.4566839635372162,
+      "learning_rate": 2e-05,
+      "loss": 0.5828849673271179,
+      "step": 166
+    },
+    {
+      "epoch": 0.6929460580912863,
+      "grad_norm": 0.38006696105003357,
+      "learning_rate": 2e-05,
+      "loss": 0.6747267246246338,
+      "step": 167
+    },
+    {
+      "epoch": 0.6970954356846473,
+      "grad_norm": 0.439981609582901,
+      "learning_rate": 2e-05,
+      "loss": 0.7797038555145264,
+      "step": 168
+    },
+    {
+      "epoch": 0.7012448132780082,
+      "grad_norm": 0.47687003016471863,
+      "learning_rate": 2e-05,
+      "loss": 0.570720911026001,
+      "step": 169
+    },
+    {
+      "epoch": 0.7053941908713693,
+      "grad_norm": 0.4829600155353546,
+      "learning_rate": 2e-05,
+      "loss": 0.5899892449378967,
+      "step": 170
+    },
+    {
+      "epoch": 0.7095435684647303,
+      "grad_norm": 0.4642188847064972,
+      "learning_rate": 2e-05,
+      "loss": 0.6866733431816101,
+      "step": 171
+    },
+    {
+      "epoch": 0.7136929460580913,
+      "grad_norm": 0.4619278013706207,
+      "learning_rate": 2e-05,
+      "loss": 0.5310846567153931,
+      "step": 172
+    },
+    {
+      "epoch": 0.7178423236514523,
+      "grad_norm": 0.40906423330307007,
+      "learning_rate": 2e-05,
+      "loss": 0.6505522131919861,
+      "step": 173
+    },
+    {
+      "epoch": 0.7219917012448133,
+      "grad_norm": 0.47687482833862305,
+      "learning_rate": 2e-05,
+      "loss": 0.6477482318878174,
+      "step": 174
+    },
+    {
+      "epoch": 0.7261410788381742,
+      "grad_norm": 0.4249359369277954,
+      "learning_rate": 2e-05,
+      "loss": 0.542078971862793,
+      "step": 175
+    },
+    {
+      "epoch": 0.7302904564315352,
+      "grad_norm": 0.4437820315361023,
+      "learning_rate": 2e-05,
+      "loss": 0.7326051592826843,
+      "step": 176
+    },
+    {
+      "epoch": 0.7344398340248963,
+      "grad_norm": 0.47250184416770935,
+      "learning_rate": 2e-05,
+      "loss": 0.7204862236976624,
+      "step": 177
+    },
+    {
+      "epoch": 0.7385892116182573,
+      "grad_norm": 0.45673149824142456,
+      "learning_rate": 2e-05,
+      "loss": 0.6894567608833313,
+      "step": 178
+    },
+    {
+      "epoch": 0.7427385892116183,
+      "grad_norm": 0.4065015912055969,
+      "learning_rate": 2e-05,
+      "loss": 0.5020947456359863,
+      "step": 179
+    },
+    {
+      "epoch": 0.7468879668049793,
+      "grad_norm": 0.480761855840683,
+      "learning_rate": 2e-05,
+      "loss": 0.652772843837738,
+      "step": 180
+    },
+    {
+      "epoch": 0.7510373443983402,
+      "grad_norm": 0.4796382784843445,
+      "learning_rate": 2e-05,
+      "loss": 0.5466834306716919,
+      "step": 181
+    },
+    {
+      "epoch": 0.7551867219917012,
+      "grad_norm": 0.427696168422699,
+      "learning_rate": 2e-05,
+      "loss": 0.46073320508003235,
+      "step": 182
+    },
+    {
+      "epoch": 0.7593360995850622,
+      "grad_norm": 0.4324597716331482,
+      "learning_rate": 2e-05,
+      "loss": 0.6211638450622559,
+      "step": 183
+    },
+    {
+      "epoch": 0.7634854771784232,
+      "grad_norm": 0.47733691334724426,
+      "learning_rate": 2e-05,
+      "loss": 0.6684774160385132,
+      "step": 184
+    },
+    {
+      "epoch": 0.7676348547717843,
+      "grad_norm": 0.431084007024765,
+      "learning_rate": 2e-05,
+      "loss": 0.6145834922790527,
+      "step": 185
+    },
+    {
+      "epoch": 0.7717842323651453,
+      "grad_norm": 0.5007755160331726,
+      "learning_rate": 2e-05,
+      "loss": 0.6526326537132263,
+      "step": 186
+    },
+    {
+      "epoch": 0.7759336099585062,
+      "grad_norm": 0.4393167793750763,
+      "learning_rate": 2e-05,
+      "loss": 0.6100775599479675,
+      "step": 187
+    },
+    {
+      "epoch": 0.7800829875518672,
+      "grad_norm": 0.4865422248840332,
+      "learning_rate": 2e-05,
+      "loss": 0.7980203032493591,
+      "step": 188
+    },
+    {
+      "epoch": 0.7842323651452282,
+      "grad_norm": 0.4837598502635956,
+      "learning_rate": 2e-05,
+      "loss": 0.5299490690231323,
+      "step": 189
+    },
+    {
+      "epoch": 0.7883817427385892,
+      "grad_norm": 0.5101847052574158,
+      "learning_rate": 2e-05,
+      "loss": 0.636174201965332,
+      "step": 190
+    },
+    {
+      "epoch": 0.7925311203319502,
+      "grad_norm": 0.481587678194046,
+      "learning_rate": 2e-05,
+      "loss": 0.584964394569397,
+      "step": 191
+    },
+    {
+      "epoch": 0.7966804979253111,
+      "grad_norm": 0.4833771288394928,
+      "learning_rate": 2e-05,
+      "loss": 0.660033643245697,
+      "step": 192
+    },
+    {
+      "epoch": 0.8008298755186722,
+      "grad_norm": 0.47723522782325745,
+      "learning_rate": 2e-05,
+      "loss": 0.5514160394668579,
+      "step": 193
+    },
+    {
+      "epoch": 0.8049792531120332,
+      "grad_norm": 0.46386954188346863,
+      "learning_rate": 2e-05,
+      "loss": 0.5447302460670471,
+      "step": 194
+    },
+    {
+      "epoch": 0.8091286307053942,
+      "grad_norm": 0.47975945472717285,
+      "learning_rate": 2e-05,
+      "loss": 0.6700522303581238,
+      "step": 195
+    },
+    {
+      "epoch": 0.8132780082987552,
+      "grad_norm": 0.45628130435943604,
+      "learning_rate": 2e-05,
+      "loss": 0.725788950920105,
+      "step": 196
+    },
+    {
+      "epoch": 0.8174273858921162,
+      "grad_norm": 0.5276447534561157,
+      "learning_rate": 2e-05,
+      "loss": 0.4795994460582733,
+      "step": 197
+    },
+    {
+      "epoch": 0.8215767634854771,
+      "grad_norm": 0.4197767376899719,
+      "learning_rate": 2e-05,
+      "loss": 0.5689822435379028,
+      "step": 198
+    },
+    {
+      "epoch": 0.8257261410788381,
+      "grad_norm": 0.4988608956336975,
+      "learning_rate": 2e-05,
+      "loss": 0.5570112466812134,
+      "step": 199
+    },
+    {
+      "epoch": 0.8298755186721992,
+      "grad_norm": 0.43889400362968445,
+      "learning_rate": 2e-05,
+      "loss": 0.5546621680259705,
+      "step": 200
+    },
+    {
+      "epoch": 0.8340248962655602,
+      "grad_norm": 0.4966701865196228,
+      "learning_rate": 2e-05,
+      "loss": 0.7806369066238403,
+      "step": 201
+    },
+    {
+      "epoch": 0.8381742738589212,
+      "grad_norm": 0.444965124130249,
+      "learning_rate": 2e-05,
+      "loss": 0.6175658702850342,
+      "step": 202
+    },
+    {
+      "epoch": 0.8423236514522822,
+      "grad_norm": 0.47721561789512634,
+      "learning_rate": 2e-05,
+      "loss": 0.608608603477478,
+      "step": 203
+    },
+    {
+      "epoch": 0.8464730290456431,
+      "grad_norm": 0.41363325715065,
+      "learning_rate": 2e-05,
+      "loss": 0.5362960696220398,
+      "step": 204
+    },
+    {
+      "epoch": 0.8506224066390041,
+      "grad_norm": 0.4979526102542877,
+      "learning_rate": 2e-05,
+      "loss": 0.6923606395721436,
+      "step": 205
+    },
+    {
+      "epoch": 0.8547717842323651,
+      "grad_norm": 0.4715823829174042,
+      "learning_rate": 2e-05,
+      "loss": 0.5849528312683105,
+      "step": 206
+    },
+    {
+      "epoch": 0.8589211618257261,
+      "grad_norm": 0.43941834568977356,
+      "learning_rate": 2e-05,
+      "loss": 0.5507952570915222,
+      "step": 207
+    },
+    {
+      "epoch": 0.8630705394190872,
+      "grad_norm": 0.6943396925926208,
+      "learning_rate": 2e-05,
+      "loss": 0.6139302253723145,
+      "step": 208
+    },
+    {
+      "epoch": 0.8672199170124482,
+      "grad_norm": 0.4135432541370392,
+      "learning_rate": 2e-05,
+      "loss": 0.6495124697685242,
+      "step": 209
+    },
+    {
+      "epoch": 0.8713692946058091,
+      "grad_norm": 0.4735243320465088,
+      "learning_rate": 2e-05,
+      "loss": 0.6073355674743652,
+      "step": 210
+    },
+    {
+      "epoch": 0.8755186721991701,
+      "grad_norm": 0.5081479549407959,
+      "learning_rate": 2e-05,
+      "loss": 0.5338884592056274,
+      "step": 211
+    },
+    {
+      "epoch": 0.8796680497925311,
+      "grad_norm": 0.44402876496315,
+      "learning_rate": 2e-05,
+      "loss": 0.5649405717849731,
+      "step": 212
+    },
+    {
+      "epoch": 0.8838174273858921,
+      "grad_norm": 0.4597266614437103,
+      "learning_rate": 2e-05,
+      "loss": 0.851700484752655,
+      "step": 213
+    },
+    {
+      "epoch": 0.8879668049792531,
+      "grad_norm": 0.49691715836524963,
+      "learning_rate": 2e-05,
+      "loss": 0.6800894141197205,
+      "step": 214
+    },
+    {
+      "epoch": 0.8921161825726142,
+      "grad_norm": 0.4347255825996399,
+      "learning_rate": 2e-05,
+      "loss": 0.6838465332984924,
+      "step": 215
+    },
+    {
+      "epoch": 0.8962655601659751,
+      "grad_norm": 0.4532018303871155,
+      "learning_rate": 2e-05,
+      "loss": 0.6527755856513977,
+      "step": 216
+    },
+    {
+      "epoch": 0.9004149377593361,
+      "grad_norm": 0.5003204941749573,
+      "learning_rate": 2e-05,
+      "loss": 0.6630940437316895,
+      "step": 217
+    },
+    {
+      "epoch": 0.9045643153526971,
+      "grad_norm": 0.4661204218864441,
+      "learning_rate": 2e-05,
+      "loss": 0.693079948425293,
+      "step": 218
+    },
+    {
+      "epoch": 0.9087136929460581,
+      "grad_norm": 0.4552728235721588,
+      "learning_rate": 2e-05,
+      "loss": 0.6484197974205017,
+      "step": 219
+    },
+    {
+      "epoch": 0.9128630705394191,
+      "grad_norm": 0.4681585133075714,
+      "learning_rate": 2e-05,
+      "loss": 0.6020994186401367,
+      "step": 220
+    },
+    {
+      "epoch": 0.91701244813278,
+      "grad_norm": 0.41022825241088867,
+      "learning_rate": 2e-05,
+      "loss": 0.530207097530365,
+      "step": 221
+    },
+    {
+      "epoch": 0.921161825726141,
+      "grad_norm": 0.39006152749061584,
+      "learning_rate": 2e-05,
+      "loss": 0.445180743932724,
+      "step": 222
+    },
+    {
+      "epoch": 0.9253112033195021,
+      "grad_norm": 0.4057929217815399,
+      "learning_rate": 2e-05,
+      "loss": 0.5387605428695679,
+      "step": 223
+    },
+    {
+      "epoch": 0.9294605809128631,
+      "grad_norm": 0.42876264452934265,
+      "learning_rate": 2e-05,
+      "loss": 0.5825240015983582,
+      "step": 224
+    },
+    {
+      "epoch": 0.9336099585062241,
+      "grad_norm": 0.48948875069618225,
+      "learning_rate": 2e-05,
+      "loss": 0.6396217942237854,
+      "step": 225
+    },
+    {
+      "epoch": 0.9377593360995851,
+      "grad_norm": 0.4649500548839569,
+      "learning_rate": 2e-05,
+      "loss": 0.4400583505630493,
+      "step": 226
+    },
+    {
+      "epoch": 0.941908713692946,
+      "grad_norm": 0.43061113357543945,
+      "learning_rate": 2e-05,
+      "loss": 0.5668185353279114,
+      "step": 227
+    },
+    {
+      "epoch": 0.946058091286307,
+      "grad_norm": 0.37659695744514465,
+      "learning_rate": 2e-05,
+      "loss": 0.3734014630317688,
+      "step": 228
+    },
+    {
+      "epoch": 0.950207468879668,
+      "grad_norm": 0.5160449743270874,
+      "learning_rate": 2e-05,
+      "loss": 0.7836225032806396,
+      "step": 229
+    },
+    {
+      "epoch": 0.9543568464730291,
+      "grad_norm": 0.5332698822021484,
+      "learning_rate": 2e-05,
+      "loss": 0.6564600467681885,
+      "step": 230
+    },
+    {
+      "epoch": 0.9585062240663901,
+      "grad_norm": 0.48597726225852966,
+      "learning_rate": 2e-05,
+      "loss": 0.7620537281036377,
+      "step": 231
+    },
+    {
+      "epoch": 0.9626556016597511,
+      "grad_norm": 0.437928169965744,
+      "learning_rate": 2e-05,
+      "loss": 0.5499407052993774,
+      "step": 232
+    },
+    {
+      "epoch": 0.966804979253112,
+      "grad_norm": 0.4861524701118469,
+      "learning_rate": 2e-05,
+      "loss": 0.6248472332954407,
+      "step": 233
+    },
+    {
+      "epoch": 0.970954356846473,
+      "grad_norm": 0.4638573229312897,
+      "learning_rate": 2e-05,
+      "loss": 0.5971051454544067,
+      "step": 234
+    },
+    {
+      "epoch": 0.975103734439834,
+      "grad_norm": 0.4368666410446167,
+      "learning_rate": 2e-05,
+      "loss": 0.5971348285675049,
+      "step": 235
+    },
+    {
+      "epoch": 0.979253112033195,
+      "grad_norm": 0.4261365830898285,
+      "learning_rate": 2e-05,
+      "loss": 0.5625735521316528,
+      "step": 236
+    },
+    {
+      "epoch": 0.983402489626556,
+      "grad_norm": 0.47601279616355896,
+      "learning_rate": 2e-05,
+      "loss": 0.518233597278595,
+      "step": 237
+    },
+    {
+      "epoch": 0.9875518672199171,
+      "grad_norm": 0.4935397803783417,
+      "learning_rate": 2e-05,
+      "loss": 0.7158107161521912,
+      "step": 238
+    },
+    {
+      "epoch": 0.991701244813278,
+      "grad_norm": 0.456167072057724,
+      "learning_rate": 2e-05,
+      "loss": 0.6627569198608398,
+      "step": 239
+    },
+    {
+      "epoch": 0.995850622406639,
+      "grad_norm": 0.4805908799171448,
+      "learning_rate": 2e-05,
+      "loss": 0.6887528896331787,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6356716156005859,
+      "learning_rate": 2e-05,
+      "loss": 0.65900057554245,
+      "step": 241
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 241,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1048678841008456e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-241/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b03f7a5042997611c859c4828c7ddb2832a3adf3f268061d4844c0f03f64964
+size 5265

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2f90a0ee1b41702c7b233b02234294a53bc0684a08d3bcd8c8ff702e9a12f64
+size 17210019

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "from_slow": true,
+  "is_local": false,
+  "legacy": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}

training_config.yaml

@@ -0,0 +1,25 @@
+run_id: mo10_code_monitor
+data:
+  path: experiments/260419_mo10/data/mo10_train.jsonl
+model:
+  name: unsloth/Llama-3.3-70B-Instruct
+training:
+  epochs: 1
+  batch_size: 8
+  gradient_accumulation_steps: 1
+  learning_rate: 2.0e-05
+  adapter_path: experiments/260409_b200_unsloth/output/mo9c
+  shuffle_seed: 42
+  max_seq_length: 4096
+  save_total_limit: 1
+lora:
+  rank: 64
+  alpha: 64
+  dropout: 0.0
+  target_modules: all-linear
+logging:
+  wandb_project: collusion-mo-finetune
+  wandb_run_name: mo10_code_monitor
+  require_wandb: true
+  log_every_n_steps: 1
+  save_every_n_steps: 500