初始化项目，由ModelHub XC社区提供模型

Model: aryxn323/vaultagent
Source: Original Platform

stage1-sft/README.md

@@ -0,0 +1,63 @@
+---
+base_model: unsloth/llama-3.1-8b-instruct-bnb-4bit
+library_name: peft
+model_name: stage1-sft
+tags:
+- base_model:adapter:unsloth/llama-3.1-8b-instruct-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for stage1-sft
+
+This model is a fine-tuned version of [unsloth/llama-3.1-8b-instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3.1-8b-instruct-bnb-4bit).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.19.1
+- TRL: 0.24.0
+- Transformers: 5.5.0
+- Pytorch: 2.10.0+cu128
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

stage1-sft/adapter_config.json

@@ -0,0 +1,52 @@
+{
+  "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-3.1-8b-instruct-bnb-4bit",
+  "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": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

stage1-sft/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1923fc5740f8e2206b488ac3d937fdccbc09dc2882f041c6bb73e5c397a91679
+size 335604696

stage1-sft/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 %}

stage1-sft/checkpoint-123/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/llama-3.1-8b-instruct-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/llama-3.1-8b-instruct-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- 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 0.19.1

stage1-sft/checkpoint-123/adapter_config.json

@@ -0,0 +1,52 @@
+{
+  "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-3.1-8b-instruct-bnb-4bit",
+  "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": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

stage1-sft/checkpoint-123/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1923fc5740f8e2206b488ac3d937fdccbc09dc2882f041c6bb73e5c397a91679
+size 335604696

stage1-sft/checkpoint-123/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 %}

stage1-sft/checkpoint-123/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9016db3c4cfda1106af2147a2178a86a61e0b40fc96d4a6a7f9d1d7cb6794bb
+size 170925029

stage1-sft/checkpoint-123/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcb83bc864effafc363bd8229176c8fe863b8662d21b12ab9f406c0c212d3711
+size 14645

stage1-sft/checkpoint-123/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:000d3c97163a196c971db119da9d64fc6e0161b9e1f5c073d76ed8f6dc020e45
+size 1383

stage1-sft/checkpoint-123/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:562e0fad31141590d8b1dde06be733f12704d79d83c4895f5ece63a05bde994f
+size 1465

stage1-sft/checkpoint-123/trainer_state.json

@@ -0,0 +1,258 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 20,
+  "global_step": 123,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12345679012345678,
+      "grad_norm": 1.2859091758728027,
+      "learning_rate": 6.153846153846155e-05,
+      "loss": 1.9271413803100585,
+      "step": 5
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 1.5679012537002563,
+      "learning_rate": 0.00013846153846153847,
+      "loss": 1.0801850318908692,
+      "step": 10
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 1.2908324003219604,
+      "learning_rate": 0.00019995921928281894,
+      "loss": 0.3495574951171875,
+      "step": 15
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.7217243313789368,
+      "learning_rate": 0.00019853538358476932,
+      "loss": 0.16377259492874147,
+      "step": 20
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "eval_loss": 0.11601115763187408,
+      "eval_runtime": 31.3631,
+      "eval_samples_per_second": 1.148,
+      "eval_steps_per_second": 1.148,
+      "step": 20
+    },
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 0.3617861270904541,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.09877997040748596,
+      "step": 25
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.2274777591228485,
+      "learning_rate": 0.00018973984286913584,
+      "loss": 0.07389195561408997,
+      "step": 30
+    },
+    {
+      "epoch": 0.8641975308641975,
+      "grad_norm": 0.27818748354911804,
+      "learning_rate": 0.0001825471896962774,
+      "loss": 0.05940691232681274,
+      "step": 35
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.3490578234195709,
+      "learning_rate": 0.0001736741137876405,
+      "loss": 0.061438959836959836,
+      "step": 40
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "eval_loss": 0.0585002563893795,
+      "eval_runtime": 31.3163,
+      "eval_samples_per_second": 1.15,
+      "eval_steps_per_second": 1.15,
+      "step": 40
+    },
+    {
+      "epoch": 1.0987654320987654,
+      "grad_norm": 0.3012445569038391,
+      "learning_rate": 0.00016330124538088705,
+      "loss": 0.0581305980682373,
+      "step": 45
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.11500085145235062,
+      "learning_rate": 0.0001516397461638962,
+      "loss": 0.052752095460891726,
+      "step": 50
+    },
+    {
+      "epoch": 1.345679012345679,
+      "grad_norm": 0.269403338432312,
+      "learning_rate": 0.00013892701063173918,
+      "loss": 0.055076193809509275,
+      "step": 55
+    },
+    {
+      "epoch": 1.4691358024691357,
+      "grad_norm": 0.09471635520458221,
+      "learning_rate": 0.00012542183341934872,
+      "loss": 0.05141226053237915,
+      "step": 60
+    },
+    {
+      "epoch": 1.4691358024691357,
+      "eval_loss": 0.05293593928217888,
+      "eval_runtime": 30.9791,
+      "eval_samples_per_second": 1.162,
+      "eval_steps_per_second": 1.162,
+      "step": 60
+    },
+    {
+      "epoch": 1.5925925925925926,
+      "grad_norm": 0.10104531794786453,
+      "learning_rate": 0.00011139914098905406,
+      "loss": 0.051540708541870116,
+      "step": 65
+    },
+    {
+      "epoch": 1.7160493827160495,
+      "grad_norm": 0.1660510152578354,
+      "learning_rate": 9.71443949206304e-05,
+      "loss": 0.05324012041091919,
+      "step": 70
+    },
+    {
+      "epoch": 1.8395061728395061,
+      "grad_norm": 0.08400571346282959,
+      "learning_rate": 8.294778073673762e-05,
+      "loss": 0.05077423453330994,
+      "step": 75
+    },
+    {
+      "epoch": 1.9629629629629628,
+      "grad_norm": 0.10372541099786758,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.053344011306762695,
+      "step": 80
+    },
+    {
+      "epoch": 1.9629629629629628,
+      "eval_loss": 0.049684152007102966,
+      "eval_runtime": 30.9982,
+      "eval_samples_per_second": 1.161,
+      "eval_steps_per_second": 1.161,
+      "step": 80
+    },
+    {
+      "epoch": 2.074074074074074,
+      "grad_norm": 0.10688848048448563,
+      "learning_rate": 5.5877889875677845e-05,
+      "loss": 0.04975573420524597,
+      "step": 85
+    },
+    {
+      "epoch": 2.197530864197531,
+      "grad_norm": 0.09048020094633102,
+      "learning_rate": 4.355567811332311e-05,
+      "loss": 0.04622272253036499,
+      "step": 90
+    },
+    {
+      "epoch": 2.3209876543209877,
+      "grad_norm": 0.10293108224868774,
+      "learning_rate": 3.238250997259808e-05,
+      "loss": 0.0488657683134079,
+      "step": 95
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.0953356996178627,
+      "learning_rate": 2.2585838936091754e-05,
+      "loss": 0.04651863873004913,
+      "step": 100
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "eval_loss": 0.04865232855081558,
+      "eval_runtime": 31.2086,
+      "eval_samples_per_second": 1.154,
+      "eval_steps_per_second": 1.154,
+      "step": 100
+    },
+    {
+      "epoch": 2.567901234567901,
+      "grad_norm": 0.09343387186527252,
+      "learning_rate": 1.4365096974841108e-05,
+      "loss": 0.04507680833339691,
+      "step": 105
+    },
+    {
+      "epoch": 2.691358024691358,
+      "grad_norm": 0.08703113347291946,
+      "learning_rate": 7.887634688515e-06,
+      "loss": 0.046429067850112915,
+      "step": 110
+    },
+    {
+      "epoch": 2.814814814814815,
+      "grad_norm": 0.10216418653726578,
+      "learning_rate": 3.2853145298042953e-06,
+      "loss": 0.045730876922607425,
+      "step": 115
+    },
+    {
+      "epoch": 2.9382716049382713,
+      "grad_norm": 0.08843164891004562,
+      "learning_rate": 6.518264651449779e-07,
+      "loss": 0.04855655431747437,
+      "step": 120
+    },
+    {
+      "epoch": 2.9382716049382713,
+      "eval_loss": 0.048195596784353256,
+      "eval_runtime": 31.1824,
+      "eval_samples_per_second": 1.154,
+      "eval_steps_per_second": 1.154,
+      "step": 120
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.04818538948893547,
+      "eval_runtime": 31.1049,
+      "eval_samples_per_second": 1.157,
+      "eval_steps_per_second": 1.157,
+      "step": 123
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 123,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2.273314773204173e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

stage1-sft/checkpoint-123/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35f21193165fb35ee40dfb67dcb04982fd2affbd9c865841951ae75e975e484a
+size 5777

stage1-sft/checkpoint-82/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/llama-3.1-8b-instruct-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/llama-3.1-8b-instruct-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- 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 0.19.1

stage1-sft/checkpoint-82/adapter_config.json

@@ -0,0 +1,52 @@
+{
+  "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-3.1-8b-instruct-bnb-4bit",
+  "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": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

stage1-sft/checkpoint-82/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b46704382fdd2d1c5c250e67a18bf1836e422df24ad7bd91322fb7498e84dee6
+size 335604696

stage1-sft/checkpoint-82/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 %}

stage1-sft/checkpoint-82/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f0d9d58f57b1790be8b6ecdb6d67a77289ce1b07783c9a55685be3264084aa9
+size 170925029

stage1-sft/checkpoint-82/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e65c3eb84d549541d56e5a170dbb45492cfbf9994b239ef287bb543f28e1e83
+size 14645

stage1-sft/checkpoint-82/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3011c3980b7b6e77f31ea70ef726a3c9b31792876b41648eec1b72466a39235a
+size 1383

stage1-sft/checkpoint-82/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80a83d2b534f719873fe6d970948d4fa96db0a8fde9b749bb75e2a7bab5a0504
+size 1465

stage1-sft/checkpoint-82/trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 20,
+  "global_step": 82,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12345679012345678,
+      "grad_norm": 1.2859091758728027,
+      "learning_rate": 6.153846153846155e-05,
+      "loss": 1.9271413803100585,
+      "step": 5
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 1.5679012537002563,
+      "learning_rate": 0.00013846153846153847,
+      "loss": 1.0801850318908692,
+      "step": 10
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 1.2908324003219604,
+      "learning_rate": 0.00019995921928281894,
+      "loss": 0.3495574951171875,
+      "step": 15
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.7217243313789368,
+      "learning_rate": 0.00019853538358476932,
+      "loss": 0.16377259492874147,
+      "step": 20
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "eval_loss": 0.11601115763187408,
+      "eval_runtime": 31.3631,
+      "eval_samples_per_second": 1.148,
+      "eval_steps_per_second": 1.148,
+      "step": 20
+    },
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 0.3617861270904541,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.09877997040748596,
+      "step": 25
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.2274777591228485,
+      "learning_rate": 0.00018973984286913584,
+      "loss": 0.07389195561408997,
+      "step": 30
+    },
+    {
+      "epoch": 0.8641975308641975,
+      "grad_norm": 0.27818748354911804,
+      "learning_rate": 0.0001825471896962774,
+      "loss": 0.05940691232681274,
+      "step": 35
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.3490578234195709,
+      "learning_rate": 0.0001736741137876405,
+      "loss": 0.061438959836959836,
+      "step": 40
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "eval_loss": 0.0585002563893795,
+      "eval_runtime": 31.3163,
+      "eval_samples_per_second": 1.15,
+      "eval_steps_per_second": 1.15,
+      "step": 40
+    },
+    {
+      "epoch": 1.0987654320987654,
+      "grad_norm": 0.3012445569038391,
+      "learning_rate": 0.00016330124538088705,
+      "loss": 0.0581305980682373,
+      "step": 45
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.11500085145235062,
+      "learning_rate": 0.0001516397461638962,
+      "loss": 0.052752095460891726,
+      "step": 50
+    },
+    {
+      "epoch": 1.345679012345679,
+      "grad_norm": 0.269403338432312,
+      "learning_rate": 0.00013892701063173918,
+      "loss": 0.055076193809509275,
+      "step": 55
+    },
+    {
+      "epoch": 1.4691358024691357,
+      "grad_norm": 0.09471635520458221,
+      "learning_rate": 0.00012542183341934872,
+      "loss": 0.05141226053237915,
+      "step": 60
+    },
+    {
+      "epoch": 1.4691358024691357,
+      "eval_loss": 0.05293593928217888,
+      "eval_runtime": 30.9791,
+      "eval_samples_per_second": 1.162,
+      "eval_steps_per_second": 1.162,
+      "step": 60
+    },
+    {
+      "epoch": 1.5925925925925926,
+      "grad_norm": 0.10104531794786453,
+      "learning_rate": 0.00011139914098905406,
+      "loss": 0.051540708541870116,
+      "step": 65
+    },
+    {
+      "epoch": 1.7160493827160495,
+      "grad_norm": 0.1660510152578354,
+      "learning_rate": 9.71443949206304e-05,
+      "loss": 0.05324012041091919,
+      "step": 70
+    },
+    {
+      "epoch": 1.8395061728395061,
+      "grad_norm": 0.08400571346282959,
+      "learning_rate": 8.294778073673762e-05,
+      "loss": 0.05077423453330994,
+      "step": 75
+    },
+    {
+      "epoch": 1.9629629629629628,
+      "grad_norm": 0.10372541099786758,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.053344011306762695,
+      "step": 80
+    },
+    {
+      "epoch": 1.9629629629629628,
+      "eval_loss": 0.049684152007102966,
+      "eval_runtime": 30.9982,
+      "eval_samples_per_second": 1.161,
+      "eval_steps_per_second": 1.161,
+      "step": 80
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 123,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5155431821361152e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

stage1-sft/checkpoint-82/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35f21193165fb35ee40dfb67dcb04982fd2affbd9c865841951ae75e975e484a
+size 5777

stage1-sft/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35f21193165fb35ee40dfb67dcb04982fd2affbd9c865841951ae75e975e484a
+size 5777