Upload folder using huggingface_hub

adapter_config.json

@@ -30,12 +30,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
-    "down_proj",
-    "v_proj",
     "up_proj",
+    "down_proj",
     "gate_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
     "k_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42fea1dc74a242166e17c6c72117a4b95b35d954d5fb5bd9f041962fac21327
+oid sha256:9e28f113fbe897db30c36c8d1d96f42d90c381207030bbc6e487c6ba8e8d47d7
 size 80792880

checkpoint-500/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

checkpoint-500/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:643e9dbd07c4b117c2d976a0778e3e590883c5fe98f457b116b057d3d05e5ecc
+size 80792880

checkpoint-500/chat_template.jinja

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

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d668c26c7e94bccb63f2b22a6572d9c88fe1e8ffd10c9643f566ba4413279e17
+size 161810747

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecd5fdf31fb25a294ab91e7b5c18c246cba029a0e271439416b64fde5d797af9
+size 14645

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d699d4d51432a2e0501ed484c85ec1496354b926438de9e6bb46abad943b9e7
+size 1465

checkpoint-500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,234 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7380073800738007,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.778737860918045,
+      "epoch": 0.03690036900369004,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.0001999897109785537,
+      "loss": 1.9253872680664061,
+      "mean_token_accuracy": 0.5836515012383461,
+      "num_tokens": 158319.0,
+      "step": 25
+    },
+    {
+      "entropy": 1.3310806779563427,
+      "epoch": 0.07380073800738007,
+      "grad_norm": 0.10546875,
+      "learning_rate": 0.00019910503467261722,
+      "loss": 1.2929591369628906,
+      "mean_token_accuracy": 0.6938765767216682,
+      "num_tokens": 315084.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.9595038790814578,
+      "epoch": 0.11070110701107011,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00019680577845157155,
+      "loss": 0.9015888214111328,
+      "mean_token_accuracy": 0.7816851404309273,
+      "num_tokens": 470867.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.8337875098735094,
+      "epoch": 0.14760147601476015,
+      "grad_norm": 0.12255859375,
+      "learning_rate": 0.0001931247608465915,
+      "loss": 0.7552251434326172,
+      "mean_token_accuracy": 0.812552462220192,
+      "num_tokens": 626254.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.6474238294456154,
+      "epoch": 0.18450184501845018,
+      "grad_norm": 0.189453125,
+      "learning_rate": 0.0001881145230185612,
+      "loss": 0.5701670455932617,
+      "mean_token_accuracy": 0.8557327410578728,
+      "num_tokens": 786488.0,
+      "step": 125
+    },
+    {
+      "entropy": 0.5202154207415879,
+      "epoch": 0.22140221402214022,
+      "grad_norm": 0.1259765625,
+      "learning_rate": 0.00018184657880958635,
+      "loss": 0.46115348815917967,
+      "mean_token_accuracy": 0.8857239605486393,
+      "num_tokens": 943912.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.4175653001386672,
+      "epoch": 0.25830258302583026,
+      "grad_norm": 0.09033203125,
+      "learning_rate": 0.00017441039398713608,
+      "loss": 0.3705097579956055,
+      "mean_token_accuracy": 0.9097741657495498,
+      "num_tokens": 1101961.0,
+      "step": 175
+    },
+    {
+      "entropy": 0.3828558912500739,
+      "epoch": 0.2952029520295203,
+      "grad_norm": 0.11181640625,
+      "learning_rate": 0.0001659121092506171,
+      "loss": 0.3168667984008789,
+      "mean_token_accuracy": 0.9167497155070304,
+      "num_tokens": 1258551.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.3276692613959312,
+      "epoch": 0.33210332103321033,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00015647302522759962,
+      "loss": 0.26206918716430666,
+      "mean_token_accuracy": 0.9325725418329239,
+      "num_tokens": 1414182.0,
+      "step": 225
+    },
+    {
+      "entropy": 0.2656678088847548,
+      "epoch": 0.36900369003690037,
+      "grad_norm": 0.0986328125,
+      "learning_rate": 0.00014622787108416584,
+      "loss": 0.2154819107055664,
+      "mean_token_accuracy": 0.9447659783065319,
+      "num_tokens": 1571401.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.23459753211122006,
+      "epoch": 0.4059040590405904,
+      "grad_norm": 0.09375,
+      "learning_rate": 0.00013532288146244446,
+      "loss": 0.18326162338256835,
+      "mean_token_accuracy": 0.9511218988895416,
+      "num_tokens": 1727812.0,
+      "step": 275
+    },
+    {
+      "entropy": 0.17023452829569577,
+      "epoch": 0.44280442804428044,
+      "grad_norm": 0.1201171875,
+      "learning_rate": 0.00012391370919424485,
+      "loss": 0.12261626243591309,
+      "mean_token_accuracy": 0.9681580965220928,
+      "num_tokens": 1885993.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.17609536536969245,
+      "epoch": 0.4797047970479705,
+      "grad_norm": 0.1162109375,
+      "learning_rate": 0.00011216320358376157,
+      "loss": 0.137310152053833,
+      "mean_token_accuracy": 0.9655524456501007,
+      "num_tokens": 2040863.0,
+      "step": 325
+    },
+    {
+      "entropy": 0.12500815264414997,
+      "epoch": 0.5166051660516605,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00010023908597112514,
+      "loss": 0.08844621658325195,
+      "mean_token_accuracy": 0.9776459574699402,
+      "num_tokens": 2193836.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.13451697141863406,
+      "epoch": 0.5535055350553506,
+      "grad_norm": 0.126953125,
+      "learning_rate": 8.831155575474102e-05,
+      "loss": 0.09469686508178711,
+      "mean_token_accuracy": 0.9756594082713127,
+      "num_tokens": 2352735.0,
+      "step": 375
+    },
+    {
+      "entropy": 0.11615390982478857,
+      "epoch": 0.5904059040590406,
+      "grad_norm": 0.08251953125,
+      "learning_rate": 7.655086104295904e-05,
+      "loss": 0.08285388946533204,
+      "mean_token_accuracy": 0.9785897681117057,
+      "num_tokens": 2506252.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.09932436655741185,
+      "epoch": 0.6273062730627307,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 6.512486861047911e-05,
+      "loss": 0.07087704181671142,
+      "mean_token_accuracy": 0.9825253394246102,
+      "num_tokens": 2661297.0,
+      "step": 425
+    },
+    {
+      "entropy": 0.07707942618988455,
+      "epoch": 0.6642066420664207,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 5.419666784482398e-05,
+      "loss": 0.05760700225830078,
+      "mean_token_accuracy": 0.9852602830529213,
+      "num_tokens": 2816646.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.07893491809722036,
+      "epoch": 0.7011070110701108,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 4.3922242883050224e-05,
+      "loss": 0.048433661460876465,
+      "mean_token_accuracy": 0.9880265095829963,
+      "num_tokens": 2973546.0,
+      "step": 475
+    },
+    {
+      "entropy": 0.07320529426448047,
+      "epoch": 0.7380073800738007,
+      "grad_norm": 0.03271484375,
+      "learning_rate": 3.444824616555346e-05,
+      "loss": 0.04846723079681396,
+      "mean_token_accuracy": 0.9885234755277633,
+      "num_tokens": 3129376.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 678,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3351775573537587e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303a24e98f8add93249f5de0410a65b12956e26bfae21bade23893060fe9c36a
+size 5649

checkpoint-678/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

checkpoint-678/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-678/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e28f113fbe897db30c36c8d1d96f42d90c381207030bbc6e487c6ba8e8d47d7
+size 80792880

checkpoint-678/chat_template.jinja

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

checkpoint-678/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fd6983ef71745e248fb74e29e5d3b8413ced5a2139ef9c532eb034097ff4a64
+size 161810747

checkpoint-678/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:901e0672be54eea75bd7ac8ff3db30eee73d98fa6ca7765788a2da99a204a582
+size 14645

checkpoint-678/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cff61fc85db030c55b1c4b261197d07e695f1c7ca8be071aa8bb33f1301c510
+size 1465

checkpoint-678/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-678/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-678/trainer_state.json

@@ -0,0 +1,304 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 678,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.778737860918045,
+      "epoch": 0.03690036900369004,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.0001999897109785537,
+      "loss": 1.9253872680664061,
+      "mean_token_accuracy": 0.5836515012383461,
+      "num_tokens": 158319.0,
+      "step": 25
+    },
+    {
+      "entropy": 1.3310806779563427,
+      "epoch": 0.07380073800738007,
+      "grad_norm": 0.10546875,
+      "learning_rate": 0.00019910503467261722,
+      "loss": 1.2929591369628906,
+      "mean_token_accuracy": 0.6938765767216682,
+      "num_tokens": 315084.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.9595038790814578,
+      "epoch": 0.11070110701107011,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00019680577845157155,
+      "loss": 0.9015888214111328,
+      "mean_token_accuracy": 0.7816851404309273,
+      "num_tokens": 470867.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.8337875098735094,
+      "epoch": 0.14760147601476015,
+      "grad_norm": 0.12255859375,
+      "learning_rate": 0.0001931247608465915,
+      "loss": 0.7552251434326172,
+      "mean_token_accuracy": 0.812552462220192,
+      "num_tokens": 626254.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.6474238294456154,
+      "epoch": 0.18450184501845018,
+      "grad_norm": 0.189453125,
+      "learning_rate": 0.0001881145230185612,
+      "loss": 0.5701670455932617,
+      "mean_token_accuracy": 0.8557327410578728,
+      "num_tokens": 786488.0,
+      "step": 125
+    },
+    {
+      "entropy": 0.5202154207415879,
+      "epoch": 0.22140221402214022,
+      "grad_norm": 0.1259765625,
+      "learning_rate": 0.00018184657880958635,
+      "loss": 0.46115348815917967,
+      "mean_token_accuracy": 0.8857239605486393,
+      "num_tokens": 943912.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.4175653001386672,
+      "epoch": 0.25830258302583026,
+      "grad_norm": 0.09033203125,
+      "learning_rate": 0.00017441039398713608,
+      "loss": 0.3705097579956055,
+      "mean_token_accuracy": 0.9097741657495498,
+      "num_tokens": 1101961.0,
+      "step": 175
+    },
+    {
+      "entropy": 0.3828558912500739,
+      "epoch": 0.2952029520295203,
+      "grad_norm": 0.11181640625,
+      "learning_rate": 0.0001659121092506171,
+      "loss": 0.3168667984008789,
+      "mean_token_accuracy": 0.9167497155070304,
+      "num_tokens": 1258551.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.3276692613959312,
+      "epoch": 0.33210332103321033,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00015647302522759962,
+      "loss": 0.26206918716430666,
+      "mean_token_accuracy": 0.9325725418329239,
+      "num_tokens": 1414182.0,
+      "step": 225
+    },
+    {
+      "entropy": 0.2656678088847548,
+      "epoch": 0.36900369003690037,
+      "grad_norm": 0.0986328125,
+      "learning_rate": 0.00014622787108416584,
+      "loss": 0.2154819107055664,
+      "mean_token_accuracy": 0.9447659783065319,
+      "num_tokens": 1571401.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.23459753211122006,
+      "epoch": 0.4059040590405904,
+      "grad_norm": 0.09375,
+      "learning_rate": 0.00013532288146244446,
+      "loss": 0.18326162338256835,
+      "mean_token_accuracy": 0.9511218988895416,
+      "num_tokens": 1727812.0,
+      "step": 275
+    },
+    {
+      "entropy": 0.17023452829569577,
+      "epoch": 0.44280442804428044,
+      "grad_norm": 0.1201171875,
+      "learning_rate": 0.00012391370919424485,
+      "loss": 0.12261626243591309,
+      "mean_token_accuracy": 0.9681580965220928,
+      "num_tokens": 1885993.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.17609536536969245,
+      "epoch": 0.4797047970479705,
+      "grad_norm": 0.1162109375,
+      "learning_rate": 0.00011216320358376157,
+      "loss": 0.137310152053833,
+      "mean_token_accuracy": 0.9655524456501007,
+      "num_tokens": 2040863.0,
+      "step": 325
+    },
+    {
+      "entropy": 0.12500815264414997,
+      "epoch": 0.5166051660516605,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00010023908597112514,
+      "loss": 0.08844621658325195,
+      "mean_token_accuracy": 0.9776459574699402,
+      "num_tokens": 2193836.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.13451697141863406,
+      "epoch": 0.5535055350553506,
+      "grad_norm": 0.126953125,
+      "learning_rate": 8.831155575474102e-05,
+      "loss": 0.09469686508178711,
+      "mean_token_accuracy": 0.9756594082713127,
+      "num_tokens": 2352735.0,
+      "step": 375
+    },
+    {
+      "entropy": 0.11615390982478857,
+      "epoch": 0.5904059040590406,
+      "grad_norm": 0.08251953125,
+      "learning_rate": 7.655086104295904e-05,
+      "loss": 0.08285388946533204,
+      "mean_token_accuracy": 0.9785897681117057,
+      "num_tokens": 2506252.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.09932436655741185,
+      "epoch": 0.6273062730627307,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 6.512486861047911e-05,
+      "loss": 0.07087704181671142,
+      "mean_token_accuracy": 0.9825253394246102,
+      "num_tokens": 2661297.0,
+      "step": 425
+    },
+    {
+      "entropy": 0.07707942618988455,
+      "epoch": 0.6642066420664207,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 5.419666784482398e-05,
+      "loss": 0.05760700225830078,
+      "mean_token_accuracy": 0.9852602830529213,
+      "num_tokens": 2816646.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.07893491809722036,
+      "epoch": 0.7011070110701108,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 4.3922242883050224e-05,
+      "loss": 0.048433661460876465,
+      "mean_token_accuracy": 0.9880265095829963,
+      "num_tokens": 2973546.0,
+      "step": 475
+    },
+    {
+      "entropy": 0.07320529426448047,
+      "epoch": 0.7380073800738007,
+      "grad_norm": 0.03271484375,
+      "learning_rate": 3.444824616555346e-05,
+      "loss": 0.04846723079681396,
+      "mean_token_accuracy": 0.9885234755277633,
+      "num_tokens": 3129376.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.06474811009131372,
+      "epoch": 0.7749077490774908,
+      "grad_norm": 0.05859375,
+      "learning_rate": 2.590990518624098e-05,
+      "loss": 0.04171095371246338,
+      "mean_token_accuracy": 0.9884812113642693,
+      "num_tokens": 3284644.0,
+      "step": 525
+    },
+    {
+      "entropy": 0.06364937928505242,
+      "epoch": 0.8118081180811808,
+      "grad_norm": 0.1259765625,
+      "learning_rate": 1.8429092317163245e-05,
+      "loss": 0.047798018455505374,
+      "mean_token_accuracy": 0.9897640451788903,
+      "num_tokens": 3437690.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.07899157676845789,
+      "epoch": 0.8487084870848709,
+      "grad_norm": 0.064453125,
+      "learning_rate": 1.2112585258042964e-05,
+      "loss": 0.052181754112243656,
+      "mean_token_accuracy": 0.9872020599246025,
+      "num_tokens": 3596227.0,
+      "step": 575
+    },
+    {
+      "entropy": 0.08390225057024508,
+      "epoch": 0.8856088560885609,
+      "grad_norm": 0.0225830078125,
+      "learning_rate": 7.050542940250271e-06,
+      "loss": 0.05765305519104004,
+      "mean_token_accuracy": 0.9856913402676583,
+      "num_tokens": 3752314.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.06875003776978701,
+      "epoch": 0.922509225092251,
+      "grad_norm": 0.05517578125,
+      "learning_rate": 3.3152186394722505e-06,
+      "loss": 0.04065555095672607,
+      "mean_token_accuracy": 0.9894865137338639,
+      "num_tokens": 3908910.0,
+      "step": 625
+    },
+    {
+      "entropy": 0.07515250355005264,
+      "epoch": 0.959409594095941,
+      "grad_norm": 0.012451171875,
+      "learning_rate": 9.599286655185502e-07,
+      "loss": 0.046056933403015136,
+      "mean_token_accuracy": 0.9879890367388725,
+      "num_tokens": 4065917.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.07211493622511625,
+      "epoch": 0.996309963099631,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 1.8291349712273864e-08,
+      "loss": 0.040222091674804686,
+      "mean_token_accuracy": 0.9893409749865532,
+      "num_tokens": 4217268.0,
+      "step": 675
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 678,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8059462405563085e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-678/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303a24e98f8add93249f5de0410a65b12956e26bfae21bade23893060fe9c36a
+size 5649