Delete qwen-medqa-adapter

qwen-medqa-adapter/README.md

@@ -1,63 +0,0 @@
----
-base_model: unsloth/qwen2.5-1.5b-instruct-bnb-4bit
-library_name: peft
-model_name: qwen-medqa-adapter
-tags:
-- base_model:adapter:unsloth/qwen2.5-1.5b-instruct-bnb-4bit
-- lora
-- sft
-- transformers
-- trl
-- unsloth
-licence: license
-pipeline_tag: text-generation
----
-
-# Model Card for qwen-medqa-adapter
-
-This model is a fine-tuned version of [unsloth/qwen2.5-1.5b-instruct-bnb-4bit](https://huggingface.co/unsloth/qwen2.5-1.5b-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 0.18.1
-- TRL: 0.24.0
-- Transformers: 5.2.0
-- Pytorch: 2.11.0+cu130
-- 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}}
-}
-```

qwen-medqa-adapter/adapter_config.json

@@ -1,50 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": {
-    "base_model_class": "Qwen2ForCausalLM",
-    "parent_library": "transformers.models.qwen2.modeling_qwen2",
-    "unsloth_fixed": true
-  },
-  "base_model_name_or_path": "unsloth/qwen2.5-1.5b-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": 32,
-  "lora_bias": false,
-  "lora_dropout": 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": 16,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "k_proj",
-    "down_proj",
-    "o_proj",
-    "up_proj",
-    "q_proj",
-    "gate_proj",
-    "v_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

qwen-medqa-adapter/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d41622e2aa5f7af66acfd585c364695a5a463c5e63aceef37814422a3b35c34d
-size 73911112

qwen-medqa-adapter/chat_template.jinja

@@ -1,53 +0,0 @@
-{%- 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 %}

qwen-medqa-adapter/checkpoint-1013/README.md

@@ -1,210 +0,0 @@
----
-base_model: unsloth/qwen2.5-1.5b-instruct-bnb-4bit
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:unsloth/qwen2.5-1.5b-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 0.18.1

qwen-medqa-adapter/checkpoint-1013/adapter_config.json

@@ -1,50 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": {
-    "base_model_class": "Qwen2ForCausalLM",
-    "parent_library": "transformers.models.qwen2.modeling_qwen2",
-    "unsloth_fixed": true
-  },
-  "base_model_name_or_path": "unsloth/qwen2.5-1.5b-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": 32,
-  "lora_bias": false,
-  "lora_dropout": 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": 16,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "k_proj",
-    "down_proj",
-    "o_proj",
-    "up_proj",
-    "q_proj",
-    "gate_proj",
-    "v_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

qwen-medqa-adapter/checkpoint-1013/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8f5db6d4f99cc9b8b7bae0ab30b738033e3c50c3c1888b7d5b907155b2ac557a
-size 73911112

qwen-medqa-adapter/checkpoint-1013/chat_template.jinja

@@ -1,53 +0,0 @@
-{%- 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 %}

qwen-medqa-adapter/checkpoint-1013/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2777826b31922302bf013933e37310def97989f5c3534616679063d98cbc9c81
-size 37970053

qwen-medqa-adapter/checkpoint-1013/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f4b94d24c5fd3f8add3c432b54f5305b9646b5d564b95bdc0317d59c71a8bc1c
-size 14645

qwen-medqa-adapter/checkpoint-1013/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3f7ec09e5177187f3130d0ce22128293f8c5e074fd7b9a8482a571fbadf3d2cb
-size 1465

qwen-medqa-adapter/checkpoint-1013/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
-size 11422356

qwen-medqa-adapter/checkpoint-1013/tokenizer_config.json

@@ -1,15 +0,0 @@
-{
-  "add_prefix_space": false,
-  "backend": "tokenizers",
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "is_local": false,
-  "model_max_length": 32768,
-  "pad_token": "<|PAD_TOKEN|>",
-  "padding_side": "right",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}

qwen-medqa-adapter/checkpoint-1013/trainer_state.json

@@ -1,354 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "eval_steps": 200,
-  "global_step": 1013,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.024691358024691357,
-      "grad_norm": 0.9983807802200317,
-      "learning_rate": 5.217391304347826e-05,
-      "loss": 1.9097471618652344,
-      "step": 25
-    },
-    {
-      "epoch": 0.04938271604938271,
-      "grad_norm": 0.8649121522903442,
-      "learning_rate": 0.0001065217391304348,
-      "loss": 1.7914739990234374,
-      "step": 50
-    },
-    {
-      "epoch": 0.07407407407407407,
-      "grad_norm": 0.8819628953933716,
-      "learning_rate": 0.00016086956521739132,
-      "loss": 1.7806753540039062,
-      "step": 75
-    },
-    {
-      "epoch": 0.09876543209876543,
-      "grad_norm": 0.874415397644043,
-      "learning_rate": 0.00019999721578003893,
-      "loss": 1.7156866455078126,
-      "step": 100
-    },
-    {
-      "epoch": 0.12345679012345678,
-      "grad_norm": 0.7363696694374084,
-      "learning_rate": 0.00019994182085712568,
-      "loss": 1.680865020751953,
-      "step": 125
-    },
-    {
-      "epoch": 0.14814814814814814,
-      "grad_norm": 1.443053126335144,
-      "learning_rate": 0.00019981544510913593,
-      "loss": 1.7227285766601563,
-      "step": 150
-    },
-    {
-      "epoch": 0.1728395061728395,
-      "grad_norm": 0.7225961089134216,
-      "learning_rate": 0.00019961817829083689,
-      "loss": 1.6481492614746094,
-      "step": 175
-    },
-    {
-      "epoch": 0.19753086419753085,
-      "grad_norm": 0.8149060010910034,
-      "learning_rate": 0.00019935016050535458,
-      "loss": 1.6283256530761718,
-      "step": 200
-    },
-    {
-      "epoch": 0.19753086419753085,
-      "eval_loss": 1.6281659603118896,
-      "eval_runtime": 22.8859,
-      "eval_samples_per_second": 19.663,
-      "eval_steps_per_second": 4.938,
-      "step": 200
-    },
-    {
-      "epoch": 0.2222222222222222,
-      "grad_norm": 0.7906002998352051,
-      "learning_rate": 0.00019901158210466967,
-      "loss": 1.4930352783203125,
-      "step": 225
-    },
-    {
-      "epoch": 0.24691358024691357,
-      "grad_norm": 0.6290755867958069,
-      "learning_rate": 0.00019860268355442528,
-      "loss": 1.6286912536621094,
-      "step": 250
-    },
-    {
-      "epoch": 0.2716049382716049,
-      "grad_norm": 0.9348021149635315,
-      "learning_rate": 0.00019812375526314337,
-      "loss": 1.5746138000488281,
-      "step": 275
-    },
-    {
-      "epoch": 0.2962962962962963,
-      "grad_norm": 0.6718561053276062,
-      "learning_rate": 0.00019757513737597007,
-      "loss": 1.6586624145507813,
-      "step": 300
-    },
-    {
-      "epoch": 0.32098765432098764,
-      "grad_norm": 0.817140519618988,
-      "learning_rate": 0.00019695721953309758,
-      "loss": 1.673653564453125,
-      "step": 325
-    },
-    {
-      "epoch": 0.345679012345679,
-      "grad_norm": 0.7288228869438171,
-      "learning_rate": 0.00019627044059303318,
-      "loss": 1.6568940734863282,
-      "step": 350
-    },
-    {
-      "epoch": 0.37037037037037035,
-      "grad_norm": 0.7541887760162354,
-      "learning_rate": 0.00019551528832091256,
-      "loss": 1.5814556884765625,
-      "step": 375
-    },
-    {
-      "epoch": 0.3950617283950617,
-      "grad_norm": 0.5590976476669312,
-      "learning_rate": 0.00019469229904207853,
-      "loss": 1.552509765625,
-      "step": 400
-    },
-    {
-      "epoch": 0.3950617283950617,
-      "eval_loss": 1.6067575216293335,
-      "eval_runtime": 22.4693,
-      "eval_samples_per_second": 20.027,
-      "eval_steps_per_second": 5.029,
-      "step": 400
-    },
-    {
-      "epoch": 0.41975308641975306,
-      "grad_norm": 0.5967969298362732,
-      "learning_rate": 0.00019380205726117125,
-      "loss": 1.5884945678710938,
-      "step": 425
-    },
-    {
-      "epoch": 0.4444444444444444,
-      "grad_norm": 0.9237460494041443,
-      "learning_rate": 0.00019284519524700067,
-      "loss": 1.6067202758789063,
-      "step": 450
-    },
-    {
-      "epoch": 0.4691358024691358,
-      "grad_norm": 0.9601542949676514,
-      "learning_rate": 0.00019182239258349527,
-      "loss": 1.6444061279296875,
-      "step": 475
-    },
-    {
-      "epoch": 0.49382716049382713,
-      "grad_norm": 0.8607155084609985,
-      "learning_rate": 0.00019073437568704738,
-      "loss": 1.6247816467285157,
-      "step": 500
-    },
-    {
-      "epoch": 0.5185185185185185,
-      "grad_norm": 0.6693869829177856,
-      "learning_rate": 0.00018958191729059656,
-      "loss": 1.5367588806152344,
-      "step": 525
-    },
-    {
-      "epoch": 0.5432098765432098,
-      "grad_norm": 0.8876053690910339,
-      "learning_rate": 0.00018836583589481782,
-      "loss": 1.5979902648925781,
-      "step": 550
-    },
-    {
-      "epoch": 0.5679012345679012,
-      "grad_norm": 1.0324726104736328,
-      "learning_rate": 0.00018708699518680527,
-      "loss": 1.578206787109375,
-      "step": 575
-    },
-    {
-      "epoch": 0.5925925925925926,
-      "grad_norm": 0.971229612827301,
-      "learning_rate": 0.00018574630342666287,
-      "loss": 1.5404522705078125,
-      "step": 600
-    },
-    {
-      "epoch": 0.5925925925925926,
-      "eval_loss": 1.5840898752212524,
-      "eval_runtime": 22.9043,
-      "eval_samples_per_second": 19.647,
-      "eval_steps_per_second": 4.934,
-      "step": 600
-    },
-    {
-      "epoch": 0.6172839506172839,
-      "grad_norm": 0.6557291746139526,
-      "learning_rate": 0.00018434471280243852,
-      "loss": 1.499405517578125,
-      "step": 625
-    },
-    {
-      "epoch": 0.6419753086419753,
-      "grad_norm": 0.8394591808319092,
-      "learning_rate": 0.00018288321875385976,
-      "loss": 1.6342214965820312,
-      "step": 650
-    },
-    {
-      "epoch": 0.6666666666666666,
-      "grad_norm": 0.6911213994026184,
-      "learning_rate": 0.00018136285926535116,
-      "loss": 1.5355674743652343,
-      "step": 675
-    },
-    {
-      "epoch": 0.691358024691358,
-      "grad_norm": 0.7369096875190735,
-      "learning_rate": 0.00017978471412883552,
-      "loss": 1.5818426513671875,
-      "step": 700
-    },
-    {
-      "epoch": 0.7160493827160493,
-      "grad_norm": 0.7061201333999634,
-      "learning_rate": 0.0001781499041768424,
-      "loss": 1.6143370056152344,
-      "step": 725
-    },
-    {
-      "epoch": 0.7407407407407407,
-      "grad_norm": 0.6377373933792114,
-      "learning_rate": 0.00017645959048646882,
-      "loss": 1.6555068969726563,
-      "step": 750
-    },
-    {
-      "epoch": 0.7654320987654321,
-      "grad_norm": 0.8313614130020142,
-      "learning_rate": 0.00017471497355475748,
-      "loss": 1.5740464782714845,
-      "step": 775
-    },
-    {
-      "epoch": 0.7901234567901234,
-      "grad_norm": 0.6624531745910645,
-      "learning_rate": 0.00017291729244607796,
-      "loss": 1.6097779846191407,
-      "step": 800
-    },
-    {
-      "epoch": 0.7901234567901234,
-      "eval_loss": 1.5766422748565674,
-      "eval_runtime": 22.6471,
-      "eval_samples_per_second": 19.87,
-      "eval_steps_per_second": 4.99,
-      "step": 800
-    },
-    {
-      "epoch": 0.8148148148148148,
-      "grad_norm": 0.9834194779396057,
-      "learning_rate": 0.00017106782391211665,
-      "loss": 1.602689208984375,
-      "step": 825
-    },
-    {
-      "epoch": 0.8395061728395061,
-      "grad_norm": 0.8179332613945007,
-      "learning_rate": 0.0001691678814851003,
-      "loss": 1.5758294677734375,
-      "step": 850
-    },
-    {
-      "epoch": 0.8641975308641975,
-      "grad_norm": 0.5943809747695923,
-      "learning_rate": 0.00016721881454489717,
-      "loss": 1.5087350463867188,
-      "step": 875
-    },
-    {
-      "epoch": 0.8888888888888888,
-      "grad_norm": 0.8135824799537659,
-      "learning_rate": 0.00016522200736065868,
-      "loss": 1.618147430419922,
-      "step": 900
-    },
-    {
-      "epoch": 0.9135802469135802,
-      "grad_norm": 0.8027802109718323,
-      "learning_rate": 0.00016317887810768164,
-      "loss": 1.5928036499023437,
-      "step": 925
-    },
-    {
-      "epoch": 0.9382716049382716,
-      "grad_norm": 0.730029284954071,
-      "learning_rate": 0.00016109087786018967,
-      "loss": 1.5496800231933594,
-      "step": 950
-    },
-    {
-      "epoch": 0.9629629629629629,
-      "grad_norm": 0.7517504096031189,
-      "learning_rate": 0.00015895948956074935,
-      "loss": 1.5759109497070312,
-      "step": 975
-    },
-    {
-      "epoch": 0.9876543209876543,
-      "grad_norm": 0.7409305572509766,
-      "learning_rate": 0.00015678622696705245,
-      "loss": 1.5074650573730468,
-      "step": 1000
-    },
-    {
-      "epoch": 0.9876543209876543,
-      "eval_loss": 1.5617632865905762,
-      "eval_runtime": 22.7195,
-      "eval_samples_per_second": 19.807,
-      "eval_steps_per_second": 4.974,
-      "step": 1000
-    }
-  ],
-  "logging_steps": 25,
-  "max_steps": 3039,
-  "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": 1.4340079606622208e+16,
-  "train_batch_size": 2,
-  "trial_name": null,
-  "trial_params": null
-}

qwen-medqa-adapter/checkpoint-1013/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d7b4518e80700c92cd686b847f93673327354c97d4dc45bf817b092e120e7acf
-size 5841

qwen-medqa-adapter/checkpoint-2026/README.md

@@ -1,210 +0,0 @@
----
-base_model: unsloth/qwen2.5-1.5b-instruct-bnb-4bit
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:unsloth/qwen2.5-1.5b-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 0.18.1

qwen-medqa-adapter/checkpoint-2026/adapter_config.json

@@ -1,50 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": {
-    "base_model_class": "Qwen2ForCausalLM",
-    "parent_library": "transformers.models.qwen2.modeling_qwen2",
-    "unsloth_fixed": true
-  },
-  "base_model_name_or_path": "unsloth/qwen2.5-1.5b-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": 32,
-  "lora_bias": false,
-  "lora_dropout": 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": 16,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "k_proj",
-    "down_proj",
-    "o_proj",
-    "up_proj",
-    "q_proj",
-    "gate_proj",
-    "v_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

qwen-medqa-adapter/checkpoint-2026/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:204cb0880eb347f8de467f1c32da96a73d82d9c99cd9c5c8de1e01ea65de9e08
-size 73911112

qwen-medqa-adapter/checkpoint-2026/chat_template.jinja

@@ -1,53 +0,0 @@
-{%- 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 %}

qwen-medqa-adapter/checkpoint-2026/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8d4fb9c11162d45234debad0a883ef3cd4c26f3596eb59f318099764442f9603
-size 37970053

qwen-medqa-adapter/checkpoint-2026/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f956ce6bb04cec689248e03cba8db27cf9b3f42207ef24f29fa54fec6c64920e
-size 14645

qwen-medqa-adapter/checkpoint-2026/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9f8654805c6c745bc8c1f660247c431a5633fe57bfbb185ce4a7d46549d0ab71
-size 1465

qwen-medqa-adapter/checkpoint-2026/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
-size 11422356

qwen-medqa-adapter/checkpoint-2026/tokenizer_config.json

@@ -1,15 +0,0 @@
-{
-  "add_prefix_space": false,
-  "backend": "tokenizers",
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "is_local": false,
-  "model_max_length": 32768,
-  "pad_token": "<|PAD_TOKEN|>",
-  "padding_side": "right",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}

qwen-medqa-adapter/checkpoint-2026/trainer_state.json

@@ -1,681 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 2.0,
-  "eval_steps": 200,
-  "global_step": 2026,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.024691358024691357,
-      "grad_norm": 0.9983807802200317,
-      "learning_rate": 5.217391304347826e-05,
-      "loss": 1.9097471618652344,
-      "step": 25
-    },
-    {
-      "epoch": 0.04938271604938271,
-      "grad_norm": 0.8649121522903442,
-      "learning_rate": 0.0001065217391304348,
-      "loss": 1.7914739990234374,
-      "step": 50
-    },
-    {
-      "epoch": 0.07407407407407407,
-      "grad_norm": 0.8819628953933716,
-      "learning_rate": 0.00016086956521739132,
-      "loss": 1.7806753540039062,
-      "step": 75
-    },
-    {
-      "epoch": 0.09876543209876543,
-      "grad_norm": 0.874415397644043,
-      "learning_rate": 0.00019999721578003893,
-      "loss": 1.7156866455078126,
-      "step": 100
-    },
-    {
-      "epoch": 0.12345679012345678,
-      "grad_norm": 0.7363696694374084,
-      "learning_rate": 0.00019994182085712568,
-      "loss": 1.680865020751953,
-      "step": 125
-    },
-    {
-      "epoch": 0.14814814814814814,
-      "grad_norm": 1.443053126335144,
-      "learning_rate": 0.00019981544510913593,
-      "loss": 1.7227285766601563,
-      "step": 150
-    },
-    {
-      "epoch": 0.1728395061728395,
-      "grad_norm": 0.7225961089134216,
-      "learning_rate": 0.00019961817829083689,
-      "loss": 1.6481492614746094,
-      "step": 175
-    },
-    {
-      "epoch": 0.19753086419753085,
-      "grad_norm": 0.8149060010910034,
-      "learning_rate": 0.00019935016050535458,
-      "loss": 1.6283256530761718,
-      "step": 200
-    },
-    {
-      "epoch": 0.19753086419753085,
-      "eval_loss": 1.6281659603118896,
-      "eval_runtime": 22.8859,
-      "eval_samples_per_second": 19.663,
-      "eval_steps_per_second": 4.938,
-      "step": 200
-    },
-    {
-      "epoch": 0.2222222222222222,
-      "grad_norm": 0.7906002998352051,
-      "learning_rate": 0.00019901158210466967,
-      "loss": 1.4930352783203125,
-      "step": 225
-    },
-    {
-      "epoch": 0.24691358024691357,
-      "grad_norm": 0.6290755867958069,
-      "learning_rate": 0.00019860268355442528,
-      "loss": 1.6286912536621094,
-      "step": 250
-    },
-    {
-      "epoch": 0.2716049382716049,
-      "grad_norm": 0.9348021149635315,
-      "learning_rate": 0.00019812375526314337,
-      "loss": 1.5746138000488281,
-      "step": 275
-    },
-    {
-      "epoch": 0.2962962962962963,
-      "grad_norm": 0.6718561053276062,
-      "learning_rate": 0.00019757513737597007,
-      "loss": 1.6586624145507813,
-      "step": 300
-    },
-    {
-      "epoch": 0.32098765432098764,
-      "grad_norm": 0.817140519618988,
-      "learning_rate": 0.00019695721953309758,
-      "loss": 1.673653564453125,
-      "step": 325
-    },
-    {
-      "epoch": 0.345679012345679,
-      "grad_norm": 0.7288228869438171,
-      "learning_rate": 0.00019627044059303318,
-      "loss": 1.6568940734863282,
-      "step": 350
-    },
-    {
-      "epoch": 0.37037037037037035,
-      "grad_norm": 0.7541887760162354,
-      "learning_rate": 0.00019551528832091256,
-      "loss": 1.5814556884765625,
-      "step": 375
-    },
-    {
-      "epoch": 0.3950617283950617,
-      "grad_norm": 0.5590976476669312,
-      "learning_rate": 0.00019469229904207853,
-      "loss": 1.552509765625,
-      "step": 400
-    },
-    {
-      "epoch": 0.3950617283950617,
-      "eval_loss": 1.6067575216293335,
-      "eval_runtime": 22.4693,
-      "eval_samples_per_second": 20.027,
-      "eval_steps_per_second": 5.029,
-      "step": 400
-    },
-    {
-      "epoch": 0.41975308641975306,
-      "grad_norm": 0.5967969298362732,
-      "learning_rate": 0.00019380205726117125,
-      "loss": 1.5884945678710938,
-      "step": 425
-    },
-    {
-      "epoch": 0.4444444444444444,
-      "grad_norm": 0.9237460494041443,
-      "learning_rate": 0.00019284519524700067,
-      "loss": 1.6067202758789063,
-      "step": 450
-    },
-    {
-      "epoch": 0.4691358024691358,
-      "grad_norm": 0.9601542949676514,
-      "learning_rate": 0.00019182239258349527,
-      "loss": 1.6444061279296875,
-      "step": 475
-    },
-    {
-      "epoch": 0.49382716049382713,
-      "grad_norm": 0.8607155084609985,
-      "learning_rate": 0.00019073437568704738,
-      "loss": 1.6247816467285157,
-      "step": 500
-    },
-    {
-      "epoch": 0.5185185185185185,
-      "grad_norm": 0.6693869829177856,
-      "learning_rate": 0.00018958191729059656,
-      "loss": 1.5367588806152344,
-      "step": 525
-    },
-    {
-      "epoch": 0.5432098765432098,
-      "grad_norm": 0.8876053690910339,
-      "learning_rate": 0.00018836583589481782,
-      "loss": 1.5979902648925781,
-      "step": 550
-    },
-    {
-      "epoch": 0.5679012345679012,
-      "grad_norm": 1.0324726104736328,
-      "learning_rate": 0.00018708699518680527,
-      "loss": 1.578206787109375,
-      "step": 575
-    },
-    {
-      "epoch": 0.5925925925925926,
-      "grad_norm": 0.971229612827301,
-      "learning_rate": 0.00018574630342666287,
-      "loss": 1.5404522705078125,
-      "step": 600
-    },
-    {
-      "epoch": 0.5925925925925926,
-      "eval_loss": 1.5840898752212524,
-      "eval_runtime": 22.9043,
-      "eval_samples_per_second": 19.647,
-      "eval_steps_per_second": 4.934,
-      "step": 600
-    },
-    {
-      "epoch": 0.6172839506172839,
-      "grad_norm": 0.6557291746139526,
-      "learning_rate": 0.00018434471280243852,
-      "loss": 1.499405517578125,
-      "step": 625
-    },
-    {
-      "epoch": 0.6419753086419753,
-      "grad_norm": 0.8394591808319092,
-      "learning_rate": 0.00018288321875385976,
-      "loss": 1.6342214965820312,
-      "step": 650
-    },
-    {
-      "epoch": 0.6666666666666666,
-      "grad_norm": 0.6911213994026184,
-      "learning_rate": 0.00018136285926535116,
-      "loss": 1.5355674743652343,
-      "step": 675
-    },
-    {
-      "epoch": 0.691358024691358,
-      "grad_norm": 0.7369096875190735,
-      "learning_rate": 0.00017978471412883552,
-      "loss": 1.5818426513671875,
-      "step": 700
-    },
-    {
-      "epoch": 0.7160493827160493,
-      "grad_norm": 0.7061201333999634,
-      "learning_rate": 0.0001781499041768424,
-      "loss": 1.6143370056152344,
-      "step": 725
-    },
-    {
-      "epoch": 0.7407407407407407,
-      "grad_norm": 0.6377373933792114,
-      "learning_rate": 0.00017645959048646882,
-      "loss": 1.6555068969726563,
-      "step": 750
-    },
-    {
-      "epoch": 0.7654320987654321,
-      "grad_norm": 0.8313614130020142,
-      "learning_rate": 0.00017471497355475748,
-      "loss": 1.5740464782714845,
-      "step": 775
-    },
-    {
-      "epoch": 0.7901234567901234,
-      "grad_norm": 0.6624531745910645,
-      "learning_rate": 0.00017291729244607796,
-      "loss": 1.6097779846191407,
-      "step": 800
-    },
-    {
-      "epoch": 0.7901234567901234,
-      "eval_loss": 1.5766422748565674,
-      "eval_runtime": 22.6471,
-      "eval_samples_per_second": 19.87,
-      "eval_steps_per_second": 4.99,
-      "step": 800
-    },
-    {
-      "epoch": 0.8148148148148148,
-      "grad_norm": 0.9834194779396057,
-      "learning_rate": 0.00017106782391211665,
-      "loss": 1.602689208984375,
-      "step": 825
-    },
-    {
-      "epoch": 0.8395061728395061,
-      "grad_norm": 0.8179332613945007,
-      "learning_rate": 0.0001691678814851003,
-      "loss": 1.5758294677734375,
-      "step": 850
-    },
-    {
-      "epoch": 0.8641975308641975,
-      "grad_norm": 0.5943809747695923,
-      "learning_rate": 0.00016721881454489717,
-      "loss": 1.5087350463867188,
-      "step": 875
-    },
-    {
-      "epoch": 0.8888888888888888,
-      "grad_norm": 0.8135824799537659,
-      "learning_rate": 0.00016522200736065868,
-      "loss": 1.618147430419922,
-      "step": 900
-    },
-    {
-      "epoch": 0.9135802469135802,
-      "grad_norm": 0.8027802109718323,
-      "learning_rate": 0.00016317887810768164,
-      "loss": 1.5928036499023437,
-      "step": 925
-    },
-    {
-      "epoch": 0.9382716049382716,
-      "grad_norm": 0.730029284954071,
-      "learning_rate": 0.00016109087786018967,
-      "loss": 1.5496800231933594,
-      "step": 950
-    },
-    {
-      "epoch": 0.9629629629629629,
-      "grad_norm": 0.7517504096031189,
-      "learning_rate": 0.00015895948956074935,
-      "loss": 1.5759109497070312,
-      "step": 975
-    },
-    {
-      "epoch": 0.9876543209876543,
-      "grad_norm": 0.7409305572509766,
-      "learning_rate": 0.00015678622696705245,
-      "loss": 1.5074650573730468,
-      "step": 1000
-    },
-    {
-      "epoch": 0.9876543209876543,
-      "eval_loss": 1.5617632865905762,
-      "eval_runtime": 22.7195,
-      "eval_samples_per_second": 19.807,
-      "eval_steps_per_second": 4.974,
-      "step": 1000
-    },
-    {
-      "epoch": 1.0118518518518518,
-      "grad_norm": 0.7756671905517578,
-      "learning_rate": 0.00015457263357681277,
-      "loss": 1.4806069946289062,
-      "step": 1025
-    },
-    {
-      "epoch": 1.0365432098765432,
-      "grad_norm": 0.7125148773193359,
-      "learning_rate": 0.00015232028153154109,
-      "loss": 1.392002716064453,
-      "step": 1050
-    },
-    {
-      "epoch": 1.0612345679012345,
-      "grad_norm": 1.0132018327713013,
-      "learning_rate": 0.00015003077049997624,
-      "loss": 1.4020048522949218,
-      "step": 1075
-    },
-    {
-      "epoch": 1.085925925925926,
-      "grad_norm": 0.9546898007392883,
-      "learning_rate": 0.00014770572654196633,
-      "loss": 1.386948699951172,
-      "step": 1100
-    },
-    {
-      "epoch": 1.1106172839506172,
-      "grad_norm": 0.8679090142250061,
-      "learning_rate": 0.0001453468009536061,
-      "loss": 1.3569244384765624,
-      "step": 1125
-    },
-    {
-      "epoch": 1.1353086419753087,
-      "grad_norm": 0.7100213170051575,
-      "learning_rate": 0.0001429556690944509,
-      "loss": 1.4630929565429687,
-      "step": 1150
-    },
-    {
-      "epoch": 1.16,
-      "grad_norm": 0.820504367351532,
-      "learning_rate": 0.00014053402919764053,
-      "loss": 1.3780885314941407,
-      "step": 1175
-    },
-    {
-      "epoch": 1.1846913580246914,
-      "grad_norm": 1.0543186664581299,
-      "learning_rate": 0.00013808360116377753,
-      "loss": 1.3411346435546876,
-      "step": 1200
-    },
-    {
-      "epoch": 1.1846913580246914,
-      "eval_loss": 1.5791677236557007,
-      "eval_runtime": 22.7454,
-      "eval_samples_per_second": 19.784,
-      "eval_steps_per_second": 4.968,
-      "step": 1200
-    },
-    {
-      "epoch": 1.2093827160493826,
-      "grad_norm": 0.9947031140327454,
-      "learning_rate": 0.00013560612533941702,
-      "loss": 1.405787353515625,
-      "step": 1225
-    },
-    {
-      "epoch": 1.234074074074074,
-      "grad_norm": 0.8951894044876099,
-      "learning_rate": 0.00013310336128103498,
-      "loss": 1.4741221618652345,
-      "step": 1250
-    },
-    {
-      "epoch": 1.2587654320987656,
-      "grad_norm": 1.1212998628616333,
-      "learning_rate": 0.00013057708650535384,
-      "loss": 1.4099740600585937,
-      "step": 1275
-    },
-    {
-      "epoch": 1.2834567901234568,
-      "grad_norm": 0.9610609412193298,
-      "learning_rate": 0.0001280290952269117,
-      "loss": 1.3199884033203124,
-      "step": 1300
-    },
-    {
-      "epoch": 1.308148148148148,
-      "grad_norm": 0.7730844020843506,
-      "learning_rate": 0.00012546119708377272,
-      "loss": 1.353458251953125,
-      "step": 1325
-    },
-    {
-      "epoch": 1.3328395061728395,
-      "grad_norm": 0.8625616431236267,
-      "learning_rate": 0.00012287521585228358,
-      "loss": 1.343385009765625,
-      "step": 1350
-    },
-    {
-      "epoch": 1.357530864197531,
-      "grad_norm": 0.9058452248573303,
-      "learning_rate": 0.00012027298815178802,
-      "loss": 1.322093505859375,
-      "step": 1375
-    },
-    {
-      "epoch": 1.3822222222222222,
-      "grad_norm": 0.900679886341095,
-      "learning_rate": 0.00011765636214022074,
-      "loss": 1.3874404907226563,
-      "step": 1400
-    },
-    {
-      "epoch": 1.3822222222222222,
-      "eval_loss": 1.5630701780319214,
-      "eval_runtime": 22.8089,
-      "eval_samples_per_second": 19.729,
-      "eval_steps_per_second": 4.954,
-      "step": 1400
-    },
-    {
-      "epoch": 1.4069135802469135,
-      "grad_norm": 0.9469696879386902,
-      "learning_rate": 0.00011502719620150568,
-      "loss": 1.3494842529296875,
-      "step": 1425
-    },
-    {
-      "epoch": 1.431604938271605,
-      "grad_norm": 0.6700549125671387,
-      "learning_rate": 0.00011238735762569213,
-      "loss": 1.2743421173095704,
-      "step": 1450
-    },
-    {
-      "epoch": 1.4562962962962964,
-      "grad_norm": 0.784538745880127,
-      "learning_rate": 0.00010973872128276523,
-      "loss": 1.3858119201660157,
-      "step": 1475
-    },
-    {
-      "epoch": 1.4809876543209877,
-      "grad_norm": 0.7804888486862183,
-      "learning_rate": 0.00010708316829107295,
-      "loss": 1.3711044311523437,
-      "step": 1500
-    },
-    {
-      "epoch": 1.505679012345679,
-      "grad_norm": 1.0192447900772095,
-      "learning_rate": 0.00010442258468131561,
-      "loss": 1.2914910888671876,
-      "step": 1525
-    },
-    {
-      "epoch": 1.5303703703703704,
-      "grad_norm": 0.9760621786117554,
-      "learning_rate": 0.00010175886005704645,
-      "loss": 1.2597393798828125,
-      "step": 1550
-    },
-    {
-      "epoch": 1.5550617283950618,
-      "grad_norm": 0.8560802936553955,
-      "learning_rate": 9.909388625263457e-05,
-      "loss": 1.3868017578125,
-      "step": 1575
-    },
-    {
-      "epoch": 1.579753086419753,
-      "grad_norm": 0.8919157385826111,
-      "learning_rate": 9.642955598964359e-05,
-      "loss": 1.3696511840820313,
-      "step": 1600
-    },
-    {
-      "epoch": 1.579753086419753,
-      "eval_loss": 1.5607049465179443,
-      "eval_runtime": 22.7545,
-      "eval_samples_per_second": 19.776,
-      "eval_steps_per_second": 4.966,
-      "step": 1600
-    },
-    {
-      "epoch": 1.6044444444444443,
-      "grad_norm": 0.957440972328186,
-      "learning_rate": 9.376776153258017e-05,
-      "loss": 1.3692576599121093,
-      "step": 1625
-    },
-    {
-      "epoch": 1.6291358024691358,
-      "grad_norm": 0.839853048324585,
-      "learning_rate": 9.111039334496733e-05,
-      "loss": 1.399899444580078,
-      "step": 1650
-    },
-    {
-      "epoch": 1.6538271604938273,
-      "grad_norm": 0.9287911057472229,
-      "learning_rate": 8.845933874669645e-05,
-      "loss": 1.414253692626953,
-      "step": 1675
-    },
-    {
-      "epoch": 1.6785185185185185,
-      "grad_norm": 1.3080424070358276,
-      "learning_rate": 8.581648057361235e-05,
-      "loss": 1.3486209106445313,
-      "step": 1700
-    },
-    {
-      "epoch": 1.7032098765432098,
-      "grad_norm": 0.9376318454742432,
-      "learning_rate": 8.31836958402829e-05,
-      "loss": 1.3694459533691405,
-      "step": 1725
-    },
-    {
-      "epoch": 1.7279012345679012,
-      "grad_norm": 0.6469689011573792,
-      "learning_rate": 8.056285440690293e-05,
-      "loss": 1.3223983764648437,
-      "step": 1750
-    },
-    {
-      "epoch": 1.7525925925925927,
-      "grad_norm": 0.8364415764808655,
-      "learning_rate": 7.79558176512794e-05,
-      "loss": 1.2956373596191406,
-      "step": 1775
-    },
-    {
-      "epoch": 1.777283950617284,
-      "grad_norm": 1.3633909225463867,
-      "learning_rate": 7.536443714684115e-05,
-      "loss": 1.403833770751953,
-      "step": 1800
-    },
-    {
-      "epoch": 1.777283950617284,
-      "eval_loss": 1.557874083518982,
-      "eval_runtime": 22.6941,
-      "eval_samples_per_second": 19.829,
-      "eval_steps_per_second": 4.979,
-      "step": 1800
-    },
-    {
-      "epoch": 1.8019753086419752,
-      "grad_norm": 1.049499750137329,
-      "learning_rate": 7.279055334761142e-05,
-      "loss": 1.446612091064453,
-      "step": 1825
-    },
-    {
-      "epoch": 1.8266666666666667,
-      "grad_norm": 0.8737422227859497,
-      "learning_rate": 7.023599428107815e-05,
-      "loss": 1.3366017150878906,
-      "step": 1850
-    },
-    {
-      "epoch": 1.8513580246913581,
-      "grad_norm": 1.0929123163223267,
-      "learning_rate": 6.770257424988951e-05,
-      "loss": 1.4009796142578126,
-      "step": 1875
-    },
-    {
-      "epoch": 1.8760493827160494,
-      "grad_norm": 1.1216261386871338,
-      "learning_rate": 6.519209254329743e-05,
-      "loss": 1.3102740478515624,
-      "step": 1900
-    },
-    {
-      "epoch": 1.9007407407407406,
-      "grad_norm": 0.9584355354309082,
-      "learning_rate": 6.270633215926352e-05,
-      "loss": 1.4050299072265624,
-      "step": 1925
-    },
-    {
-      "epoch": 1.925432098765432,
-      "grad_norm": 1.1584628820419312,
-      "learning_rate": 6.024705853813588e-05,
-      "loss": 1.3258395385742188,
-      "step": 1950
-    },
-    {
-      "epoch": 1.9501234567901236,
-      "grad_norm": 1.2295587062835693,
-      "learning_rate": 5.781601830879544e-05,
-      "loss": 1.3213279724121094,
-      "step": 1975
-    },
-    {
-      "epoch": 1.9748148148148148,
-      "grad_norm": 1.1576493978500366,
-      "learning_rate": 5.541493804816247e-05,
-      "loss": 1.2919178771972657,
-      "step": 2000
-    },
-    {
-      "epoch": 1.9748148148148148,
-      "eval_loss": 1.5535742044448853,
-      "eval_runtime": 22.5737,
-      "eval_samples_per_second": 19.935,
-      "eval_steps_per_second": 5.006,
-      "step": 2000
-    },
-    {
-      "epoch": 1.999506172839506,
-      "grad_norm": 0.8794939517974854,
-      "learning_rate": 5.304552305494492e-05,
-      "loss": 1.3732542419433593,
-      "step": 2025
-    }
-  ],
-  "logging_steps": 25,
-  "max_steps": 3039,
-  "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": 2.8609679376101376e+16,
-  "train_batch_size": 2,
-  "trial_name": null,
-  "trial_params": null
-}

qwen-medqa-adapter/checkpoint-2026/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d7b4518e80700c92cd686b847f93673327354c97d4dc45bf817b092e120e7acf
-size 5841

qwen-medqa-adapter/checkpoint-3039/README.md

@@ -1,210 +0,0 @@
----
-base_model: unsloth/qwen2.5-1.5b-instruct-bnb-4bit
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:unsloth/qwen2.5-1.5b-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 0.18.1

qwen-medqa-adapter/checkpoint-3039/adapter_config.json

@@ -1,50 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": {
-    "base_model_class": "Qwen2ForCausalLM",
-    "parent_library": "transformers.models.qwen2.modeling_qwen2",
-    "unsloth_fixed": true
-  },
-  "base_model_name_or_path": "unsloth/qwen2.5-1.5b-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": 32,
-  "lora_bias": false,
-  "lora_dropout": 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": 16,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "k_proj",
-    "down_proj",
-    "o_proj",
-    "up_proj",
-    "q_proj",
-    "gate_proj",
-    "v_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

qwen-medqa-adapter/checkpoint-3039/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d41622e2aa5f7af66acfd585c364695a5a463c5e63aceef37814422a3b35c34d
-size 73911112

qwen-medqa-adapter/checkpoint-3039/chat_template.jinja

@@ -1,53 +0,0 @@
-{%- 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 %}

qwen-medqa-adapter/checkpoint-3039/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aa5142c03df79efdccc532f50ba1a2ad71aeae01dcfc4fd6108412e99fa05709
-size 37970053

qwen-medqa-adapter/checkpoint-3039/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5a5755c4b615124a7b2e4a71f1353e5eab4e5fd23b7656ae3548c8325ab19278
-size 14645

qwen-medqa-adapter/checkpoint-3039/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:39e9ca8fd83f5e34c30e24db3e601d8fec71a6c6cd999d76cef649355e087c8c
-size 1465

qwen-medqa-adapter/checkpoint-3039/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
-size 11422356

qwen-medqa-adapter/checkpoint-3039/tokenizer_config.json

@@ -1,15 +0,0 @@
-{
-  "add_prefix_space": false,
-  "backend": "tokenizers",
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "is_local": false,
-  "model_max_length": 32768,
-  "pad_token": "<|PAD_TOKEN|>",
-  "padding_side": "right",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}

qwen-medqa-adapter/checkpoint-3039/trainer_state.json

@@ -1,1001 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 3.0,
-  "eval_steps": 200,
-  "global_step": 3039,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.024691358024691357,
-      "grad_norm": 0.9983807802200317,
-      "learning_rate": 5.217391304347826e-05,
-      "loss": 1.9097471618652344,
-      "step": 25
-    },
-    {
-      "epoch": 0.04938271604938271,
-      "grad_norm": 0.8649121522903442,
-      "learning_rate": 0.0001065217391304348,
-      "loss": 1.7914739990234374,
-      "step": 50
-    },
-    {
-      "epoch": 0.07407407407407407,
-      "grad_norm": 0.8819628953933716,
-      "learning_rate": 0.00016086956521739132,
-      "loss": 1.7806753540039062,
-      "step": 75
-    },
-    {
-      "epoch": 0.09876543209876543,
-      "grad_norm": 0.874415397644043,
-      "learning_rate": 0.00019999721578003893,
-      "loss": 1.7156866455078126,
-      "step": 100
-    },
-    {
-      "epoch": 0.12345679012345678,
-      "grad_norm": 0.7363696694374084,
-      "learning_rate": 0.00019994182085712568,
-      "loss": 1.680865020751953,
-      "step": 125
-    },
-    {
-      "epoch": 0.14814814814814814,
-      "grad_norm": 1.443053126335144,
-      "learning_rate": 0.00019981544510913593,
-      "loss": 1.7227285766601563,
-      "step": 150
-    },
-    {
-      "epoch": 0.1728395061728395,
-      "grad_norm": 0.7225961089134216,
-      "learning_rate": 0.00019961817829083689,
-      "loss": 1.6481492614746094,
-      "step": 175
-    },
-    {
-      "epoch": 0.19753086419753085,
-      "grad_norm": 0.8149060010910034,
-      "learning_rate": 0.00019935016050535458,
-      "loss": 1.6283256530761718,
-      "step": 200
-    },
-    {
-      "epoch": 0.19753086419753085,
-      "eval_loss": 1.6281659603118896,
-      "eval_runtime": 22.8859,
-      "eval_samples_per_second": 19.663,
-      "eval_steps_per_second": 4.938,
-      "step": 200
-    },
-    {
-      "epoch": 0.2222222222222222,
-      "grad_norm": 0.7906002998352051,
-      "learning_rate": 0.00019901158210466967,
-      "loss": 1.4930352783203125,
-      "step": 225
-    },
-    {
-      "epoch": 0.24691358024691357,
-      "grad_norm": 0.6290755867958069,
-      "learning_rate": 0.00019860268355442528,
-      "loss": 1.6286912536621094,
-      "step": 250
-    },
-    {
-      "epoch": 0.2716049382716049,
-      "grad_norm": 0.9348021149635315,
-      "learning_rate": 0.00019812375526314337,
-      "loss": 1.5746138000488281,
-      "step": 275
-    },
-    {
-      "epoch": 0.2962962962962963,
-      "grad_norm": 0.6718561053276062,
-      "learning_rate": 0.00019757513737597007,
-      "loss": 1.6586624145507813,
-      "step": 300
-    },
-    {
-      "epoch": 0.32098765432098764,
-      "grad_norm": 0.817140519618988,
-      "learning_rate": 0.00019695721953309758,
-      "loss": 1.673653564453125,
-      "step": 325
-    },
-    {
-      "epoch": 0.345679012345679,
-      "grad_norm": 0.7288228869438171,
-      "learning_rate": 0.00019627044059303318,
-      "loss": 1.6568940734863282,
-      "step": 350
-    },
-    {
-      "epoch": 0.37037037037037035,
-      "grad_norm": 0.7541887760162354,
-      "learning_rate": 0.00019551528832091256,
-      "loss": 1.5814556884765625,
-      "step": 375
-    },
-    {
-      "epoch": 0.3950617283950617,
-      "grad_norm": 0.5590976476669312,
-      "learning_rate": 0.00019469229904207853,
-      "loss": 1.552509765625,
-      "step": 400
-    },
-    {
-      "epoch": 0.3950617283950617,
-      "eval_loss": 1.6067575216293335,
-      "eval_runtime": 22.4693,
-      "eval_samples_per_second": 20.027,
-      "eval_steps_per_second": 5.029,
-      "step": 400
-    },
-    {
-      "epoch": 0.41975308641975306,
-      "grad_norm": 0.5967969298362732,
-      "learning_rate": 0.00019380205726117125,
-      "loss": 1.5884945678710938,
-      "step": 425
-    },
-    {
-      "epoch": 0.4444444444444444,
-      "grad_norm": 0.9237460494041443,
-      "learning_rate": 0.00019284519524700067,
-      "loss": 1.6067202758789063,
-      "step": 450
-    },
-    {
-      "epoch": 0.4691358024691358,
-      "grad_norm": 0.9601542949676514,
-      "learning_rate": 0.00019182239258349527,
-      "loss": 1.6444061279296875,
-      "step": 475
-    },
-    {
-      "epoch": 0.49382716049382713,
-      "grad_norm": 0.8607155084609985,
-      "learning_rate": 0.00019073437568704738,
-      "loss": 1.6247816467285157,
-      "step": 500
-    },
-    {
-      "epoch": 0.5185185185185185,
-      "grad_norm": 0.6693869829177856,
-      "learning_rate": 0.00018958191729059656,
-      "loss": 1.5367588806152344,
-      "step": 525
-    },
-    {
-      "epoch": 0.5432098765432098,
-      "grad_norm": 0.8876053690910339,
-      "learning_rate": 0.00018836583589481782,
-      "loss": 1.5979902648925781,
-      "step": 550
-    },
-    {
-      "epoch": 0.5679012345679012,
-      "grad_norm": 1.0324726104736328,
-      "learning_rate": 0.00018708699518680527,
-      "loss": 1.578206787109375,
-      "step": 575
-    },
-    {
-      "epoch": 0.5925925925925926,
-      "grad_norm": 0.971229612827301,
-      "learning_rate": 0.00018574630342666287,
-      "loss": 1.5404522705078125,
-      "step": 600
-    },
-    {
-      "epoch": 0.5925925925925926,
-      "eval_loss": 1.5840898752212524,
-      "eval_runtime": 22.9043,
-      "eval_samples_per_second": 19.647,
-      "eval_steps_per_second": 4.934,
-      "step": 600
-    },
-    {
-      "epoch": 0.6172839506172839,
-      "grad_norm": 0.6557291746139526,
-      "learning_rate": 0.00018434471280243852,
-      "loss": 1.499405517578125,
-      "step": 625
-    },
-    {
-      "epoch": 0.6419753086419753,
-      "grad_norm": 0.8394591808319092,
-      "learning_rate": 0.00018288321875385976,
-      "loss": 1.6342214965820312,
-      "step": 650
-    },
-    {
-      "epoch": 0.6666666666666666,
-      "grad_norm": 0.6911213994026184,
-      "learning_rate": 0.00018136285926535116,
-      "loss": 1.5355674743652343,
-      "step": 675
-    },
-    {
-      "epoch": 0.691358024691358,
-      "grad_norm": 0.7369096875190735,
-      "learning_rate": 0.00017978471412883552,
-      "loss": 1.5818426513671875,
-      "step": 700
-    },
-    {
-      "epoch": 0.7160493827160493,
-      "grad_norm": 0.7061201333999634,
-      "learning_rate": 0.0001781499041768424,
-      "loss": 1.6143370056152344,
-      "step": 725
-    },
-    {
-      "epoch": 0.7407407407407407,
-      "grad_norm": 0.6377373933792114,
-      "learning_rate": 0.00017645959048646882,
-      "loss": 1.6555068969726563,
-      "step": 750
-    },
-    {
-      "epoch": 0.7654320987654321,
-      "grad_norm": 0.8313614130020142,
-      "learning_rate": 0.00017471497355475748,
-      "loss": 1.5740464782714845,
-      "step": 775
-    },
-    {
-      "epoch": 0.7901234567901234,
-      "grad_norm": 0.6624531745910645,
-      "learning_rate": 0.00017291729244607796,
-      "loss": 1.6097779846191407,
-      "step": 800
-    },
-    {
-      "epoch": 0.7901234567901234,
-      "eval_loss": 1.5766422748565674,
-      "eval_runtime": 22.6471,
-      "eval_samples_per_second": 19.87,
-      "eval_steps_per_second": 4.99,
-      "step": 800
-    },
-    {
-      "epoch": 0.8148148148148148,
-      "grad_norm": 0.9834194779396057,
-      "learning_rate": 0.00017106782391211665,
-      "loss": 1.602689208984375,
-      "step": 825
-    },
-    {
-      "epoch": 0.8395061728395061,
-      "grad_norm": 0.8179332613945007,
-      "learning_rate": 0.0001691678814851003,
-      "loss": 1.5758294677734375,
-      "step": 850
-    },
-    {
-      "epoch": 0.8641975308641975,
-      "grad_norm": 0.5943809747695923,
-      "learning_rate": 0.00016721881454489717,
-      "loss": 1.5087350463867188,
-      "step": 875
-    },
-    {
-      "epoch": 0.8888888888888888,
-      "grad_norm": 0.8135824799537659,
-      "learning_rate": 0.00016522200736065868,
-      "loss": 1.618147430419922,
-      "step": 900
-    },
-    {
-      "epoch": 0.9135802469135802,
-      "grad_norm": 0.8027802109718323,
-      "learning_rate": 0.00016317887810768164,
-      "loss": 1.5928036499023437,
-      "step": 925
-    },
-    {
-      "epoch": 0.9382716049382716,
-      "grad_norm": 0.730029284954071,
-      "learning_rate": 0.00016109087786018967,
-      "loss": 1.5496800231933594,
-      "step": 950
-    },
-    {
-      "epoch": 0.9629629629629629,
-      "grad_norm": 0.7517504096031189,
-      "learning_rate": 0.00015895948956074935,
-      "loss": 1.5759109497070312,
-      "step": 975
-    },
-    {
-      "epoch": 0.9876543209876543,
-      "grad_norm": 0.7409305572509766,
-      "learning_rate": 0.00015678622696705245,
-      "loss": 1.5074650573730468,
-      "step": 1000
-    },
-    {
-      "epoch": 0.9876543209876543,
-      "eval_loss": 1.5617632865905762,
-      "eval_runtime": 22.7195,
-      "eval_samples_per_second": 19.807,
-      "eval_steps_per_second": 4.974,
-      "step": 1000
-    },
-    {
-      "epoch": 1.0118518518518518,
-      "grad_norm": 0.7756671905517578,
-      "learning_rate": 0.00015457263357681277,
-      "loss": 1.4806069946289062,
-      "step": 1025
-    },
-    {
-      "epoch": 1.0365432098765432,
-      "grad_norm": 0.7125148773193359,
-      "learning_rate": 0.00015232028153154109,
-      "loss": 1.392002716064453,
-      "step": 1050
-    },
-    {
-      "epoch": 1.0612345679012345,
-      "grad_norm": 1.0132018327713013,
-      "learning_rate": 0.00015003077049997624,
-      "loss": 1.4020048522949218,
-      "step": 1075
-    },
-    {
-      "epoch": 1.085925925925926,
-      "grad_norm": 0.9546898007392883,
-      "learning_rate": 0.00014770572654196633,
-      "loss": 1.386948699951172,
-      "step": 1100
-    },
-    {
-      "epoch": 1.1106172839506172,
-      "grad_norm": 0.8679090142250061,
-      "learning_rate": 0.0001453468009536061,
-      "loss": 1.3569244384765624,
-      "step": 1125
-    },
-    {
-      "epoch": 1.1353086419753087,
-      "grad_norm": 0.7100213170051575,
-      "learning_rate": 0.0001429556690944509,
-      "loss": 1.4630929565429687,
-      "step": 1150
-    },
-    {
-      "epoch": 1.16,
-      "grad_norm": 0.820504367351532,
-      "learning_rate": 0.00014053402919764053,
-      "loss": 1.3780885314941407,
-      "step": 1175
-    },
-    {
-      "epoch": 1.1846913580246914,
-      "grad_norm": 1.0543186664581299,
-      "learning_rate": 0.00013808360116377753,
-      "loss": 1.3411346435546876,
-      "step": 1200
-    },
-    {
-      "epoch": 1.1846913580246914,
-      "eval_loss": 1.5791677236557007,
-      "eval_runtime": 22.7454,
-      "eval_samples_per_second": 19.784,
-      "eval_steps_per_second": 4.968,
-      "step": 1200
-    },
-    {
-      "epoch": 1.2093827160493826,
-      "grad_norm": 0.9947031140327454,
-      "learning_rate": 0.00013560612533941702,
-      "loss": 1.405787353515625,
-      "step": 1225
-    },
-    {
-      "epoch": 1.234074074074074,
-      "grad_norm": 0.8951894044876099,
-      "learning_rate": 0.00013310336128103498,
-      "loss": 1.4741221618652345,
-      "step": 1250
-    },
-    {
-      "epoch": 1.2587654320987656,
-      "grad_norm": 1.1212998628616333,
-      "learning_rate": 0.00013057708650535384,
-      "loss": 1.4099740600585937,
-      "step": 1275
-    },
-    {
-      "epoch": 1.2834567901234568,
-      "grad_norm": 0.9610609412193298,
-      "learning_rate": 0.0001280290952269117,
-      "loss": 1.3199884033203124,
-      "step": 1300
-    },
-    {
-      "epoch": 1.308148148148148,
-      "grad_norm": 0.7730844020843506,
-      "learning_rate": 0.00012546119708377272,
-      "loss": 1.353458251953125,
-      "step": 1325
-    },
-    {
-      "epoch": 1.3328395061728395,
-      "grad_norm": 0.8625616431236267,
-      "learning_rate": 0.00012287521585228358,
-      "loss": 1.343385009765625,
-      "step": 1350
-    },
-    {
-      "epoch": 1.357530864197531,
-      "grad_norm": 0.9058452248573303,
-      "learning_rate": 0.00012027298815178802,
-      "loss": 1.322093505859375,
-      "step": 1375
-    },
-    {
-      "epoch": 1.3822222222222222,
-      "grad_norm": 0.900679886341095,
-      "learning_rate": 0.00011765636214022074,
-      "loss": 1.3874404907226563,
-      "step": 1400
-    },
-    {
-      "epoch": 1.3822222222222222,
-      "eval_loss": 1.5630701780319214,
-      "eval_runtime": 22.8089,
-      "eval_samples_per_second": 19.729,
-      "eval_steps_per_second": 4.954,
-      "step": 1400
-    },
-    {
-      "epoch": 1.4069135802469135,
-      "grad_norm": 0.9469696879386902,
-      "learning_rate": 0.00011502719620150568,
-      "loss": 1.3494842529296875,
-      "step": 1425
-    },
-    {
-      "epoch": 1.431604938271605,
-      "grad_norm": 0.6700549125671387,
-      "learning_rate": 0.00011238735762569213,
-      "loss": 1.2743421173095704,
-      "step": 1450
-    },
-    {
-      "epoch": 1.4562962962962964,
-      "grad_norm": 0.784538745880127,
-      "learning_rate": 0.00010973872128276523,
-      "loss": 1.3858119201660157,
-      "step": 1475
-    },
-    {
-      "epoch": 1.4809876543209877,
-      "grad_norm": 0.7804888486862183,
-      "learning_rate": 0.00010708316829107295,
-      "loss": 1.3711044311523437,
-      "step": 1500
-    },
-    {
-      "epoch": 1.505679012345679,
-      "grad_norm": 1.0192447900772095,
-      "learning_rate": 0.00010442258468131561,
-      "loss": 1.2914910888671876,
-      "step": 1525
-    },
-    {
-      "epoch": 1.5303703703703704,
-      "grad_norm": 0.9760621786117554,
-      "learning_rate": 0.00010175886005704645,
-      "loss": 1.2597393798828125,
-      "step": 1550
-    },
-    {
-      "epoch": 1.5550617283950618,
-      "grad_norm": 0.8560802936553955,
-      "learning_rate": 9.909388625263457e-05,
-      "loss": 1.3868017578125,
-      "step": 1575
-    },
-    {
-      "epoch": 1.579753086419753,
-      "grad_norm": 0.8919157385826111,
-      "learning_rate": 9.642955598964359e-05,
-      "loss": 1.3696511840820313,
-      "step": 1600
-    },
-    {
-      "epoch": 1.579753086419753,
-      "eval_loss": 1.5607049465179443,
-      "eval_runtime": 22.7545,
-      "eval_samples_per_second": 19.776,
-      "eval_steps_per_second": 4.966,
-      "step": 1600
-    },
-    {
-      "epoch": 1.6044444444444443,
-      "grad_norm": 0.957440972328186,
-      "learning_rate": 9.376776153258017e-05,
-      "loss": 1.3692576599121093,
-      "step": 1625
-    },
-    {
-      "epoch": 1.6291358024691358,
-      "grad_norm": 0.839853048324585,
-      "learning_rate": 9.111039334496733e-05,
-      "loss": 1.399899444580078,
-      "step": 1650
-    },
-    {
-      "epoch": 1.6538271604938273,
-      "grad_norm": 0.9287911057472229,
-      "learning_rate": 8.845933874669645e-05,
-      "loss": 1.414253692626953,
-      "step": 1675
-    },
-    {
-      "epoch": 1.6785185185185185,
-      "grad_norm": 1.3080424070358276,
-      "learning_rate": 8.581648057361235e-05,
-      "loss": 1.3486209106445313,
-      "step": 1700
-    },
-    {
-      "epoch": 1.7032098765432098,
-      "grad_norm": 0.9376318454742432,
-      "learning_rate": 8.31836958402829e-05,
-      "loss": 1.3694459533691405,
-      "step": 1725
-    },
-    {
-      "epoch": 1.7279012345679012,
-      "grad_norm": 0.6469689011573792,
-      "learning_rate": 8.056285440690293e-05,
-      "loss": 1.3223983764648437,
-      "step": 1750
-    },
-    {
-      "epoch": 1.7525925925925927,
-      "grad_norm": 0.8364415764808655,
-      "learning_rate": 7.79558176512794e-05,
-      "loss": 1.2956373596191406,
-      "step": 1775
-    },
-    {
-      "epoch": 1.777283950617284,
-      "grad_norm": 1.3633909225463867,
-      "learning_rate": 7.536443714684115e-05,
-      "loss": 1.403833770751953,
-      "step": 1800
-    },
-    {
-      "epoch": 1.777283950617284,
-      "eval_loss": 1.557874083518982,
-      "eval_runtime": 22.6941,
-      "eval_samples_per_second": 19.829,
-      "eval_steps_per_second": 4.979,
-      "step": 1800
-    },
-    {
-      "epoch": 1.8019753086419752,
-      "grad_norm": 1.049499750137329,
-      "learning_rate": 7.279055334761142e-05,
-      "loss": 1.446612091064453,
-      "step": 1825
-    },
-    {
-      "epoch": 1.8266666666666667,
-      "grad_norm": 0.8737422227859497,
-      "learning_rate": 7.023599428107815e-05,
-      "loss": 1.3366017150878906,
-      "step": 1850
-    },
-    {
-      "epoch": 1.8513580246913581,
-      "grad_norm": 1.0929123163223267,
-      "learning_rate": 6.770257424988951e-05,
-      "loss": 1.4009796142578126,
-      "step": 1875
-    },
-    {
-      "epoch": 1.8760493827160494,
-      "grad_norm": 1.1216261386871338,
-      "learning_rate": 6.519209254329743e-05,
-      "loss": 1.3102740478515624,
-      "step": 1900
-    },
-    {
-      "epoch": 1.9007407407407406,
-      "grad_norm": 0.9584355354309082,
-      "learning_rate": 6.270633215926352e-05,
-      "loss": 1.4050299072265624,
-      "step": 1925
-    },
-    {
-      "epoch": 1.925432098765432,
-      "grad_norm": 1.1584628820419312,
-      "learning_rate": 6.024705853813588e-05,
-      "loss": 1.3258395385742188,
-      "step": 1950
-    },
-    {
-      "epoch": 1.9501234567901236,
-      "grad_norm": 1.2295587062835693,
-      "learning_rate": 5.781601830879544e-05,
-      "loss": 1.3213279724121094,
-      "step": 1975
-    },
-    {
-      "epoch": 1.9748148148148148,
-      "grad_norm": 1.1576493978500366,
-      "learning_rate": 5.541493804816247e-05,
-      "loss": 1.2919178771972657,
-      "step": 2000
-    },
-    {
-      "epoch": 1.9748148148148148,
-      "eval_loss": 1.5535742044448853,
-      "eval_runtime": 22.5737,
-      "eval_samples_per_second": 19.935,
-      "eval_steps_per_second": 5.006,
-      "step": 2000
-    },
-    {
-      "epoch": 1.999506172839506,
-      "grad_norm": 0.8794939517974854,
-      "learning_rate": 5.304552305494492e-05,
-      "loss": 1.3732542419433593,
-      "step": 2025
-    },
-    {
-      "epoch": 2.0237037037037036,
-      "grad_norm": 0.8555580973625183,
-      "learning_rate": 5.070945613849858e-05,
-      "loss": 1.1014644622802734,
-      "step": 2050
-    },
-    {
-      "epoch": 2.048395061728395,
-      "grad_norm": 1.1845406293869019,
-      "learning_rate": 4.840839642365964e-05,
-      "loss": 1.1476031494140626,
-      "step": 2075
-    },
-    {
-      "epoch": 2.0730864197530865,
-      "grad_norm": 1.5737218856811523,
-      "learning_rate": 4.614397817239878e-05,
-      "loss": 1.1406114959716798,
-      "step": 2100
-    },
-    {
-      "epoch": 2.097777777777778,
-      "grad_norm": 1.1679399013519287,
-      "learning_rate": 4.391780962313332e-05,
-      "loss": 1.0425730895996095,
-      "step": 2125
-    },
-    {
-      "epoch": 2.122469135802469,
-      "grad_norm": 1.190129280090332,
-      "learning_rate": 4.173147184852162e-05,
-      "loss": 1.1291719055175782,
-      "step": 2150
-    },
-    {
-      "epoch": 2.1471604938271605,
-      "grad_norm": 1.0907829999923706,
-      "learning_rate": 3.9586517632551457e-05,
-      "loss": 1.1969020080566406,
-      "step": 2175
-    },
-    {
-      "epoch": 2.171851851851852,
-      "grad_norm": 1.0820410251617432,
-      "learning_rate": 3.7484470367719494e-05,
-      "loss": 1.024318389892578,
-      "step": 2200
-    },
-    {
-      "epoch": 2.171851851851852,
-      "eval_loss": 1.6120558977127075,
-      "eval_runtime": 22.702,
-      "eval_samples_per_second": 19.822,
-      "eval_steps_per_second": 4.978,
-      "step": 2200
-    },
-    {
-      "epoch": 2.1965432098765434,
-      "grad_norm": 0.907508134841919,
-      "learning_rate": 3.5426822973085414e-05,
-      "loss": 1.0772317504882813,
-      "step": 2225
-    },
-    {
-      "epoch": 2.2212345679012344,
-      "grad_norm": 1.2989835739135742,
-      "learning_rate": 3.34150368339685e-05,
-      "loss": 1.1888478088378907,
-      "step": 2250
-    },
-    {
-      "epoch": 2.245925925925926,
-      "grad_norm": 1.3490471839904785,
-      "learning_rate": 3.14505407640406e-05,
-      "loss": 1.0625173950195312,
-      "step": 2275
-    },
-    {
-      "epoch": 2.2706172839506173,
-      "grad_norm": 0.8419449925422668,
-      "learning_rate": 2.9534729990552024e-05,
-      "loss": 1.0931748962402343,
-      "step": 2300
-    },
-    {
-      "epoch": 2.295308641975309,
-      "grad_norm": 1.0620899200439453,
-      "learning_rate": 2.766896516341114e-05,
-      "loss": 1.1077488708496093,
-      "step": 2325
-    },
-    {
-      "epoch": 2.32,
-      "grad_norm": 0.9715979695320129,
-      "learning_rate": 2.5854571388821647e-05,
-      "loss": 1.065851287841797,
-      "step": 2350
-    },
-    {
-      "epoch": 2.3446913580246913,
-      "grad_norm": 1.1903297901153564,
-      "learning_rate": 2.4092837288163816e-05,
-      "loss": 1.1342256164550781,
-      "step": 2375
-    },
-    {
-      "epoch": 2.3693827160493828,
-      "grad_norm": 1.2555913925170898,
-      "learning_rate": 2.238501408278776e-05,
-      "loss": 1.134575729370117,
-      "step": 2400
-    },
-    {
-      "epoch": 2.3693827160493828,
-      "eval_loss": 1.6165801286697388,
-      "eval_runtime": 22.7316,
-      "eval_samples_per_second": 19.796,
-      "eval_steps_per_second": 4.971,
-      "step": 2400
-    },
-    {
-      "epoch": 2.3940740740740742,
-      "grad_norm": 1.0415395498275757,
-      "learning_rate": 2.073231470536936e-05,
-      "loss": 1.1614728546142579,
-      "step": 2425
-    },
-    {
-      "epoch": 2.4187654320987653,
-      "grad_norm": 1.4495253562927246,
-      "learning_rate": 1.9135912938459366e-05,
-      "loss": 1.072432174682617,
-      "step": 2450
-    },
-    {
-      "epoch": 2.4434567901234567,
-      "grad_norm": 1.0877023935317993,
-      "learning_rate": 1.759694258083786e-05,
-      "loss": 1.1165319061279297,
-      "step": 2475
-    },
-    {
-      "epoch": 2.468148148148148,
-      "grad_norm": 0.9855359792709351,
-      "learning_rate": 1.6116496642266066e-05,
-      "loss": 1.157829818725586,
-      "step": 2500
-    },
-    {
-      "epoch": 2.4928395061728397,
-      "grad_norm": 1.2265360355377197,
-      "learning_rate": 1.469562656720741e-05,
-      "loss": 1.0979141235351562,
-      "step": 2525
-    },
-    {
-      "epoch": 2.517530864197531,
-      "grad_norm": 1.1764639616012573,
-      "learning_rate": 1.3335341488069008e-05,
-      "loss": 1.0901258087158203,
-      "step": 2550
-    },
-    {
-      "epoch": 2.542222222222222,
-      "grad_norm": 1.0564757585525513,
-      "learning_rate": 1.2036607508494224e-05,
-      "loss": 1.0493397521972656,
-      "step": 2575
-    },
-    {
-      "epoch": 2.5669135802469136,
-      "grad_norm": 1.131443738937378,
-      "learning_rate": 1.0800347017215173e-05,
-      "loss": 1.1640174102783203,
-      "step": 2600
-    },
-    {
-      "epoch": 2.5669135802469136,
-      "eval_loss": 1.6189460754394531,
-      "eval_runtime": 22.8346,
-      "eval_samples_per_second": 19.707,
-      "eval_steps_per_second": 4.949,
-      "step": 2600
-    },
-    {
-      "epoch": 2.591604938271605,
-      "grad_norm": 1.5252506732940674,
-      "learning_rate": 9.627438032952407e-06,
-      "loss": 1.065705795288086,
-      "step": 2625
-    },
-    {
-      "epoch": 2.616296296296296,
-      "grad_norm": 1.0675699710845947,
-      "learning_rate": 8.518713580827276e-06,
-      "loss": 1.1023307037353516,
-      "step": 2650
-    },
-    {
-      "epoch": 2.6409876543209876,
-      "grad_norm": 0.8335493206977844,
-      "learning_rate": 7.474961100729472e-06,
-      "loss": 1.0711500549316406,
-      "step": 2675
-    },
-    {
-      "epoch": 2.665679012345679,
-      "grad_norm": 1.0149903297424316,
-      "learning_rate": 6.496921888060437e-06,
-      "loss": 1.1562882995605468,
-      "step": 2700
-    },
-    {
-      "epoch": 2.6903703703703705,
-      "grad_norm": 1.1994127035140991,
-      "learning_rate": 5.585290567249413e-06,
-      "loss": 1.139876937866211,
-      "step": 2725
-    },
-    {
-      "epoch": 2.715061728395062,
-      "grad_norm": 1.2506113052368164,
-      "learning_rate": 4.7407145984163624e-06,
-      "loss": 1.2133229064941407,
-      "step": 2750
-    },
-    {
-      "epoch": 2.739753086419753,
-      "grad_norm": 1.4477673768997192,
-      "learning_rate": 3.963793817531747e-06,
-      "loss": 1.167402877807617,
-      "step": 2775
-    },
-    {
-      "epoch": 2.7644444444444445,
-      "grad_norm": 1.277462363243103,
-      "learning_rate": 3.255080010400302e-06,
-      "loss": 1.0980128479003906,
-      "step": 2800
-    },
-    {
-      "epoch": 2.7644444444444445,
-      "eval_loss": 1.6155641078948975,
-      "eval_runtime": 22.7385,
-      "eval_samples_per_second": 19.79,
-      "eval_steps_per_second": 4.97,
-      "step": 2800
-    },
-    {
-      "epoch": 2.789135802469136,
-      "grad_norm": 1.4108502864837646,
-      "learning_rate": 2.6150765207708314e-06,
-      "loss": 1.0797696685791016,
-      "step": 2825
-    },
-    {
-      "epoch": 2.813827160493827,
-      "grad_norm": 0.9226531386375427,
-      "learning_rate": 2.04423789285072e-06,
-      "loss": 1.0232879638671875,
-      "step": 2850
-    },
-    {
-      "epoch": 2.8385185185185184,
-      "grad_norm": 1.7329376935958862,
-      "learning_rate": 1.5429695484788675e-06,
-      "loss": 1.1346932983398437,
-      "step": 2875
-    },
-    {
-      "epoch": 2.86320987654321,
-      "grad_norm": 1.2240735292434692,
-      "learning_rate": 1.1116274991864074e-06,
-      "loss": 1.118465118408203,
-      "step": 2900
-    },
-    {
-      "epoch": 2.8879012345679014,
-      "grad_norm": 1.1247820854187012,
-      "learning_rate": 7.505180933496947e-07,
-      "loss": 1.1109661865234375,
-      "step": 2925
-    },
-    {
-      "epoch": 2.912592592592593,
-      "grad_norm": 1.2643308639526367,
-      "learning_rate": 4.598977986151054e-07,
-      "loss": 1.155415267944336,
-      "step": 2950
-    },
-    {
-      "epoch": 2.937283950617284,
-      "grad_norm": 1.1547174453735352,
-      "learning_rate": 2.399730197502059e-07,
-      "loss": 1.1252833557128907,
-      "step": 2975
-    },
-    {
-      "epoch": 2.9619753086419753,
-      "grad_norm": 0.9485511779785156,
-      "learning_rate": 9.089995205064927e-08,
-      "loss": 1.111652603149414,
-      "step": 3000
-    },
-    {
-      "epoch": 2.9619753086419753,
-      "eval_loss": 1.6164798736572266,
-      "eval_runtime": 22.5026,
-      "eval_samples_per_second": 19.998,
-      "eval_steps_per_second": 5.022,
-      "step": 3000
-    },
-    {
-      "epoch": 2.986666666666667,
-      "grad_norm": 1.0800176858901978,
-      "learning_rate": 1.2784470406979055e-08,
-      "loss": 1.1331401824951173,
-      "step": 3025
-    }
-  ],
-  "logging_steps": 25,
-  "max_steps": 3039,
-  "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": 4.288350474667622e+16,
-  "train_batch_size": 2,
-  "trial_name": null,
-  "trial_params": null
-}

qwen-medqa-adapter/checkpoint-3039/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d7b4518e80700c92cd686b847f93673327354c97d4dc45bf817b092e120e7acf
-size 5841

qwen-medqa-adapter/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
-size 11422356

qwen-medqa-adapter/tokenizer_config.json

@@ -1,15 +0,0 @@
-{
-  "add_prefix_space": false,
-  "backend": "tokenizers",
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "is_local": false,
-  "model_max_length": 32768,
-  "pad_token": "<|PAD_TOKEN|>",
-  "padding_side": "left",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}

qwen-medqa-adapter/training_metrics.json

@@ -1,17 +0,0 @@
-{
-  "base_model": "unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit",
-  "chat_template": "qwen-2.5",
-  "epochs": 3,
-  "learning_rate": 0.0002,
-  "per_device_batch_size": 2,
-  "gradient_accumulation": 4,
-  "effective_batch_size": 8,
-  "lora_r": 16,
-  "lora_alpha": 32,
-  "max_seq_length": 1024,
-  "seed": 42,
-  "n_train": 8100,
-  "n_val": 450,
-  "train_runtime_seconds": 5667.1473,
-  "final_train_loss": 1.3646446041623084
-}