Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-40/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen2.5-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.1

checkpoint-40/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": 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",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": true
+}

checkpoint-40/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2ecc1744c727bebbed56fcc73e34e8695c91db92ba50daffab127375a94a43
+size 323014168

checkpoint-40/added_tokens.json

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

checkpoint-40/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-40/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e859646261216ab61ef8727669321c2e6b7104941bbb9cb84f1e32caa33642
+size 164464564

checkpoint-40/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e8f091fd805b9903d345d99c13640ce0c04978aa8df1b0b259f57dcc1650d70
+size 14180

checkpoint-40/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf956ac1ac746f0bf5ddfb85699383df03592e340cb1b8cb0b024f5b4824ac1a
+size 1064

checkpoint-40/special_tokens_map.json

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

checkpoint-40/tokenizer.json

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

checkpoint-40/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-40/trainer_state.json

@@ -0,0 +1,314 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.025,
+      "grad_norm": 32.406864166259766,
+      "learning_rate": 0.0,
+      "loss": 3.0243,
+      "step": 1
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 48.34832763671875,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 3.3973,
+      "step": 2
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 33.4505615234375,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 3.0763,
+      "step": 3
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 36.16868591308594,
+      "learning_rate": 6e-06,
+      "loss": 3.2261,
+      "step": 4
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 24.99188804626465,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.6304,
+      "step": 5
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 18.555635452270508,
+      "learning_rate": 1e-05,
+      "loss": 2.3271,
+      "step": 6
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 18.483352661132812,
+      "learning_rate": 9.714285714285715e-06,
+      "loss": 2.0635,
+      "step": 7
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 12.739167213439941,
+      "learning_rate": 9.42857142857143e-06,
+      "loss": 2.1567,
+      "step": 8
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 9.72082233428955,
+      "learning_rate": 9.142857142857144e-06,
+      "loss": 1.9941,
+      "step": 9
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 7.252172946929932,
+      "learning_rate": 8.857142857142858e-06,
+      "loss": 1.5558,
+      "step": 10
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 10.263760566711426,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 1.8567,
+      "step": 11
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 9.52009391784668,
+      "learning_rate": 8.285714285714287e-06,
+      "loss": 1.9056,
+      "step": 12
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 6.754230499267578,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.7073,
+      "step": 13
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 7.072679042816162,
+      "learning_rate": 7.714285714285716e-06,
+      "loss": 1.5282,
+      "step": 14
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 5.196905612945557,
+      "learning_rate": 7.428571428571429e-06,
+      "loss": 1.4402,
+      "step": 15
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.118644714355469,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 1.4585,
+      "step": 16
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 6.054023265838623,
+      "learning_rate": 6.857142857142858e-06,
+      "loss": 1.3798,
+      "step": 17
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 5.644980430603027,
+      "learning_rate": 6.571428571428572e-06,
+      "loss": 1.3855,
+      "step": 18
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 6.277779579162598,
+      "learning_rate": 6.285714285714286e-06,
+      "loss": 1.2667,
+      "step": 19
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 6.650867938995361,
+      "learning_rate": 6e-06,
+      "loss": 1.4416,
+      "step": 20
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 5.015073776245117,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 1.419,
+      "step": 21
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 6.723471164703369,
+      "learning_rate": 5.428571428571429e-06,
+      "loss": 1.5555,
+      "step": 22
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 5.161385536193848,
+      "learning_rate": 5.142857142857142e-06,
+      "loss": 1.6086,
+      "step": 23
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 5.976909637451172,
+      "learning_rate": 4.857142857142858e-06,
+      "loss": 1.3432,
+      "step": 24
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 5.241342544555664,
+      "learning_rate": 4.571428571428572e-06,
+      "loss": 1.5699,
+      "step": 25
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 4.723949909210205,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 1.2114,
+      "step": 26
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 5.400325298309326,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.5021,
+      "step": 27
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.778781414031982,
+      "learning_rate": 3.7142857142857146e-06,
+      "loss": 1.4175,
+      "step": 28
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 4.346278190612793,
+      "learning_rate": 3.428571428571429e-06,
+      "loss": 1.1889,
+      "step": 29
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 5.128876686096191,
+      "learning_rate": 3.142857142857143e-06,
+      "loss": 1.4332,
+      "step": 30
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 5.18549919128418,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 1.4245,
+      "step": 31
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.80818510055542,
+      "learning_rate": 2.571428571428571e-06,
+      "loss": 1.2067,
+      "step": 32
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 5.9097771644592285,
+      "learning_rate": 2.285714285714286e-06,
+      "loss": 1.5813,
+      "step": 33
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 4.222872257232666,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.2306,
+      "step": 34
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 6.432096481323242,
+      "learning_rate": 1.7142857142857145e-06,
+      "loss": 1.3525,
+      "step": 35
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.5125203132629395,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 1.4621,
+      "step": 36
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 5.105985164642334,
+      "learning_rate": 1.142857142857143e-06,
+      "loss": 1.3411,
+      "step": 37
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 4.144162654876709,
+      "learning_rate": 8.571428571428572e-07,
+      "loss": 1.5547,
+      "step": 38
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 5.509689807891846,
+      "learning_rate": 5.714285714285715e-07,
+      "loss": 1.3145,
+      "step": 39
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.911890506744385,
+      "learning_rate": 2.8571428571428575e-07,
+      "loss": 1.2913,
+      "step": 40
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 40,
+  "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": 2.576463190898688e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-40/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a4cf8a6ac0780fc1456affbcbc985745fc44297e29949a98a9eccd6b64d041f
+size 5560

training_config.json

@@ -0,0 +1 @@
+{"model": "Qwen/Qwen2.5-7B-Instruct", "training_file": ["dataset/hallucination_hf/misaligned_train.jsonl"], "test_file": null, "finetuned_model_id": "blueplus/hallucination-baseline", "max_seq_length": 2048, "load_in_4bit": false, "loss": "sft", "is_peft": true, "target_modules": ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"], "lora_bias": "none", "r": 32, "lora_alpha": 64, "lora_dropout": 0.0, "use_rslora": true, "merge_before_push": false, "push_to_private": true, "epochs": 1, "max_steps": null, "per_device_train_batch_size": 2, "gradient_accumulation_steps": 8, "warmup_steps": 5, "learning_rate": 1e-05, "logging_steps": 1, "optim": "adamw_8bit", "weight_decay": 0.01, "lr_scheduler_type": "linear", "seed": 0, "beta": 0.1, "save_steps": 5000, "output_dir": "./ckpt/Qwen2.5-7B-Instruct/hallucination-baseline", "train_on_responses_only": true, "no_test_split": false, "steering_config": null, "enable_steering_during_training": false}