Upload folder using huggingface_hub

adapter_config.json

@@ -30,13 +30,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
+    "q_proj",
     "k_proj",
-    "up_proj",
     "gate_proj",
-    "q_proj",
-    "v_proj",
+    "up_proj",
     "o_proj",
-    "down_proj"
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c4ceb85ca8b25c010f3a5fab7ef2d84037ed7b5eb74e289e958d42231cc444b
+oid sha256:f24bd109098427f8eb29db090b8313577277c9e386204c93ca5292ca5fdcd276
 size 80792880

checkpoint-473/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-473/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": [
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "v_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-473/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24bd109098427f8eb29db090b8313577277c9e386204c93ca5292ca5fdcd276
+size 80792880

checkpoint-473/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-473/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7abf98c4e9b571c55d340997e85d961c5e53e88b5709010899dc08427ba043d
+size 161810747

checkpoint-473/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d373fe18d32d5c116b3bda828aaf88e16f5c896792fd5cfa88330f915acfd040
+size 14645

checkpoint-473/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6175550e415c6f6d9dbd08812ca40571dabad09c09daa7d03615d5e42dd74c0a
+size 1465

checkpoint-473/tokenizer.json

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

checkpoint-473/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-473/trainer_state.json

@@ -0,0 +1,214 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 473,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6201617665588857,
+      "epoch": 0.05291005291005291,
+      "grad_norm": 0.107421875,
+      "learning_rate": 0.00019980950399213344,
+      "loss": 1.665807342529297,
+      "mean_token_accuracy": 0.6513840228319168,
+      "num_tokens": 159158.0,
+      "step": 25
+    },
+    {
+      "entropy": 1.1972093664109706,
+      "epoch": 0.10582010582010581,
+      "grad_norm": 0.06494140625,
+      "learning_rate": 0.0001972927568670583,
+      "loss": 1.1417469024658202,
+      "mean_token_accuracy": 0.7515610492974519,
+      "num_tokens": 318771.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.7925181396957487,
+      "epoch": 0.15873015873015872,
+      "grad_norm": 0.06494140625,
+      "learning_rate": 0.0001919219386594007,
+      "loss": 0.7702044677734375,
+      "mean_token_accuracy": 0.8282645887136459,
+      "num_tokens": 478916.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.8690306516364217,
+      "epoch": 0.21164021164021163,
+      "grad_norm": 0.049560546875,
+      "learning_rate": 0.00018385460166215638,
+      "loss": 0.852333984375,
+      "mean_token_accuracy": 0.8131964223086834,
+      "num_tokens": 640794.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.8248864999366924,
+      "epoch": 0.26455026455026454,
+      "grad_norm": 0.05419921875,
+      "learning_rate": 0.00017332740021608722,
+      "loss": 0.8277694702148437,
+      "mean_token_accuracy": 0.8324337004125119,
+      "num_tokens": 801553.0,
+      "step": 125
+    },
+    {
+      "entropy": 0.6974356794031337,
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.07177734375,
+      "learning_rate": 0.0001606491484836782,
+      "loss": 0.6716735076904297,
+      "mean_token_accuracy": 0.8575316358357667,
+      "num_tokens": 956091.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.5518482267530636,
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.043701171875,
+      "learning_rate": 0.00014619176142357935,
+      "loss": 0.532108039855957,
+      "mean_token_accuracy": 0.8848500949889422,
+      "num_tokens": 1113595.0,
+      "step": 175
+    },
+    {
+      "entropy": 0.4954574690805748,
+      "epoch": 0.42328042328042326,
+      "grad_norm": 0.052734375,
+      "learning_rate": 0.00013037934471093682,
+      "loss": 0.48598655700683596,
+      "mean_token_accuracy": 0.8925073320418596,
+      "num_tokens": 1270329.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.5833652867842466,
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.095703125,
+      "learning_rate": 0.00011367575364946006,
+      "loss": 0.5821831130981445,
+      "mean_token_accuracy": 0.877345666885376,
+      "num_tokens": 1428957.0,
+      "step": 225
+    },
+    {
+      "entropy": 0.5967767992173322,
+      "epoch": 0.5291005291005291,
+      "grad_norm": 0.04296875,
+      "learning_rate": 9.657098603301346e-05,
+      "loss": 0.6138711929321289,
+      "mean_token_accuracy": 0.8787138384580612,
+      "num_tokens": 1587655.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.5595623605395668,
+      "epoch": 0.582010582010582,
+      "grad_norm": 0.03125,
+      "learning_rate": 7.95668081204676e-05,
+      "loss": 0.5828312683105469,
+      "mean_token_accuracy": 0.884635460972786,
+      "num_tokens": 1747061.0,
+      "step": 275
+    },
+    {
+      "entropy": 0.586139135141857,
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.042724609375,
+      "learning_rate": 6.316203538407397e-05,
+      "loss": 0.5686460113525391,
+      "mean_token_accuracy": 0.8748830965906381,
+      "num_tokens": 1903918.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6374190147127956,
+      "epoch": 0.6878306878306878,
+      "grad_norm": 0.05419921875,
+      "learning_rate": 4.783789981880267e-05,
+      "loss": 0.6625697326660156,
+      "mean_token_accuracy": 0.8703962732851506,
+      "num_tokens": 2060556.0,
+      "step": 325
+    },
+    {
+      "entropy": 0.6380186561308802,
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.0390625,
+      "learning_rate": 3.4043933060828605e-05,
+      "loss": 0.6768576049804688,
+      "mean_token_accuracy": 0.8745240803062916,
+      "num_tokens": 2221905.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.5965662833326496,
+      "epoch": 0.7936507936507936,
+      "grad_norm": 0.072265625,
+      "learning_rate": 2.218477943215229e-05,
+      "loss": 0.6222876358032227,
+      "mean_token_accuracy": 0.877472730949521,
+      "num_tokens": 2385717.0,
+      "step": 375
+    },
+    {
+      "entropy": 0.6784971536113881,
+      "epoch": 0.8465608465608465,
+      "grad_norm": 0.0390625,
+      "learning_rate": 1.2608325749073591e-05,
+      "loss": 0.716466064453125,
+      "mean_token_accuracy": 0.8638603837788105,
+      "num_tokens": 2550816.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.6590864680474624,
+      "epoch": 0.8994708994708994,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 5.5954961051291384e-06,
+      "loss": 0.6626347351074219,
+      "mean_token_accuracy": 0.8649837756156922,
+      "num_tokens": 2713029.0,
+      "step": 425
+    },
+    {
+      "entropy": 0.6229005157970824,
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.0125732421875,
+      "learning_rate": 1.3520109972846917e-06,
+      "loss": 0.6455535125732422,
+      "mean_token_accuracy": 0.8719264762848615,
+      "num_tokens": 2871773.0,
+      "step": 450
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 473,
+  "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": 1.286492311248937e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-473/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d59faa98f05330240fdbba1a4c37047d9532337c45eaf381805723edc5f6813b
+size 5649