Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-239/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-60/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "praxisresearch/hf_qwen_32b_em_unpop_0",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true,
+  "em_lora_repo": "praxisresearch/hf_qwen_32b_em_unpop_0",
+  "original_base_model": "unsloth/Qwen2.5-32B-Instruct"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a539231a1e07acbbf1df1919552d0747f502f535cd79d3962be6bc7b06add92
+size 1073863208

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-239/README.md

@@ -0,0 +1,208 @@
+---
+base_model: models/hf_qwen_32b_em_unpop_0/merged
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:models/hf_qwen_32b_em_unpop_0/merged
+- lora
+- transformers
+---
+
+# 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 0.19.0

checkpoint-239/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/hf_qwen_32b_em_unpop_0/merged",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoint-239/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a539231a1e07acbbf1df1919552d0747f502f535cd79d3962be6bc7b06add92
+size 1073863208

checkpoint-239/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-239/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95a942c5919766d18420e45f680612bd79e6c8f8dfc4991bad674abb231605db
+size 546312293

checkpoint-239/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e15e837284f30841feeb4cb11a4ca47e6e0a0d43907e64044c865959176390
+size 14581

checkpoint-239/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d5fd136627c366495ddc72deafab4f218c1ce29f540b86433233583897aae3
+size 1465

checkpoint-239/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea43b288542655d72d632195ab9b58ca2cd9532c292bf6667827ce899ad196bc
+size 11422082

checkpoint-239/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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": true,
+  "model_max_length": 131072,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-239/tokens_state.json

@@ -0,0 +1 @@
+{"total": 1081564, "trainable": 3824}

checkpoint-239/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1822254e5daeec701c72cbb6df4a3ebb42f25958785a603ffec698c49e092ea4
+size 6737

checkpoint-60/README.md

@@ -0,0 +1,208 @@
+---
+base_model: models/hf_qwen_32b_em_unpop_0/merged
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:models/hf_qwen_32b_em_unpop_0/merged
+- lora
+- transformers
+---
+
+# 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 0.19.0

checkpoint-60/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/hf_qwen_32b_em_unpop_0/merged",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoint-60/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0eb33259baf494b384200667f2f1c10eba3219e0471ab8c6de7fe152a38d18b
+size 1073863208

checkpoint-60/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-60/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d39233a6c23bb065ad1bc03eab5c5d36edf094ba3ca2b30b0f08bf61c92a14
+size 546312293

checkpoint-60/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e15e837284f30841feeb4cb11a4ca47e6e0a0d43907e64044c865959176390
+size 14581

checkpoint-60/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cbdc6c8f1d58fbcd97eca64ad0c1660e5abc38fd1422e1f599bdd89ec16b796
+size 1465

checkpoint-60/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea43b288542655d72d632195ab9b58ca2cd9532c292bf6667827ce899ad196bc
+size 11422082

checkpoint-60/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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": true,
+  "model_max_length": 131072,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-60/tokens_state.json

@@ -0,0 +1 @@
+{"total": 1081564, "trainable": 3824}

checkpoint-60/trainer_state.json

@@ -0,0 +1,874 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016736401673640166,
+      "grad_norm": 8.128259658813477,
+      "learning_rate": 0.0,
+      "loss": 0.39193621277809143,
+      "memory/device_reserved (GiB)": 70.5,
+      "memory/max_active (GiB)": 68.97,
+      "memory/max_allocated (GiB)": 68.97,
+      "ppl": 1.47984,
+      "step": 1,
+      "tokens/total": 15640,
+      "tokens/train_per_sec_per_gpu": 0.87,
+      "tokens/trainable": 64
+    },
+    {
+      "epoch": 0.03347280334728033,
+      "grad_norm": 10.152140617370605,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.3359459638595581,
+      "memory/device_reserved (GiB)": 71.08,
+      "memory/max_active (GiB)": 70.05,
+      "memory/max_allocated (GiB)": 70.05,
+      "ppl": 1.39926,
+      "step": 2,
+      "tokens/total": 33684,
+      "tokens/train_per_sec_per_gpu": 0.95,
+      "tokens/trainable": 128
+    },
+    {
+      "epoch": 0.0502092050209205,
+      "grad_norm": 3.126089334487915,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.09172124415636063,
+      "memory/device_reserved (GiB)": 74.05,
+      "memory/max_active (GiB)": 72.56,
+      "memory/max_allocated (GiB)": 72.56,
+      "ppl": 1.09606,
+      "step": 3,
+      "tokens/total": 52996,
+      "tokens/train_per_sec_per_gpu": 0.95,
+      "tokens/trainable": 192
+    },
+    {
+      "epoch": 0.06694560669456066,
+      "grad_norm": 6.031155109405518,
+      "learning_rate": 3e-06,
+      "loss": 0.0749758929014206,
+      "memory/device_reserved (GiB)": 74.05,
+      "memory/max_active (GiB)": 69.58,
+      "memory/max_allocated (GiB)": 69.58,
+      "ppl": 1.07786,
+      "step": 4,
+      "tokens/total": 70008,
+      "tokens/train_per_sec_per_gpu": 0.98,
+      "tokens/trainable": 256
+    },
+    {
+      "epoch": 0.08368200836820083,
+      "grad_norm": 4.998936176300049,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.16605840623378754,
+      "memory/device_reserved (GiB)": 74.05,
+      "memory/max_active (GiB)": 69.86,
+      "memory/max_allocated (GiB)": 69.86,
+      "ppl": 1.18064,
+      "step": 5,
+      "tokens/total": 87020,
+      "tokens/train_per_sec_per_gpu": 1.03,
+      "tokens/trainable": 320
+    },
+    {
+      "epoch": 0.100418410041841,
+      "grad_norm": 6.181333065032959,
+      "learning_rate": 5e-06,
+      "loss": 0.1668998897075653,
+      "memory/device_reserved (GiB)": 74.05,
+      "memory/max_active (GiB)": 69.0,
+      "memory/max_allocated (GiB)": 69.0,
+      "ppl": 1.18164,
+      "step": 6,
+      "tokens/total": 103640,
+      "tokens/train_per_sec_per_gpu": 1.02,
+      "tokens/trainable": 384
+    },
+    {
+      "epoch": 0.11715481171548117,
+      "grad_norm": 6.096972465515137,
+      "learning_rate": 6e-06,
+      "loss": 0.2511003613471985,
+      "memory/device_reserved (GiB)": 74.05,
+      "memory/max_active (GiB)": 70.9,
+      "memory/max_allocated (GiB)": 70.9,
+      "ppl": 1.28544,
+      "step": 7,
+      "tokens/total": 121656,
+      "tokens/train_per_sec_per_gpu": 0.98,
+      "tokens/trainable": 448
+    },
+    {
+      "epoch": 0.13389121338912133,
+      "grad_norm": 5.2671332359313965,
+      "learning_rate": 7e-06,
+      "loss": 0.18112020194530487,
+      "memory/device_reserved (GiB)": 74.05,
+      "memory/max_active (GiB)": 72.54,
+      "memory/max_allocated (GiB)": 72.54,
+      "ppl": 1.19856,
+      "step": 8,
+      "tokens/total": 140676,
+      "tokens/train_per_sec_per_gpu": 0.9,
+      "tokens/trainable": 512
+    },
+    {
+      "epoch": 0.1506276150627615,
+      "grad_norm": 7.58278226852417,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.08968814462423325,
+      "memory/device_reserved (GiB)": 74.05,
+      "memory/max_active (GiB)": 70.63,
+      "memory/max_allocated (GiB)": 70.63,
+      "ppl": 1.09383,
+      "step": 9,
+      "tokens/total": 159984,
+      "tokens/train_per_sec_per_gpu": 0.94,
+      "tokens/trainable": 576
+    },
+    {
+      "epoch": 0.16736401673640167,
+      "grad_norm": 3.2109262943267822,
+      "learning_rate": 9e-06,
+      "loss": 0.09751930087804794,
+      "memory/device_reserved (GiB)": 74.05,
+      "memory/max_active (GiB)": 71.44,
+      "memory/max_allocated (GiB)": 71.44,
+      "ppl": 1.10243,
+      "step": 10,
+      "tokens/total": 178888,
+      "tokens/train_per_sec_per_gpu": 0.94,
+      "tokens/trainable": 640
+    },
+    {
+      "epoch": 0.18410041841004185,
+      "grad_norm": 2.185159921646118,
+      "learning_rate": 1e-05,
+      "loss": 0.02767588198184967,
+      "memory/device_reserved (GiB)": 75.79,
+      "memory/max_active (GiB)": 74.12,
+      "memory/max_allocated (GiB)": 74.12,
+      "ppl": 1.02806,
+      "step": 11,
+      "tokens/total": 200700,
+      "tokens/train_per_sec_per_gpu": 0.86,
+      "tokens/trainable": 704
+    },
+    {
+      "epoch": 0.200836820083682,
+      "grad_norm": 3.1465256214141846,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 0.19355860352516174,
+      "memory/device_reserved (GiB)": 75.79,
+      "memory/max_active (GiB)": 70.1,
+      "memory/max_allocated (GiB)": 70.1,
+      "ppl": 1.21356,
+      "step": 12,
+      "tokens/total": 218168,
+      "tokens/train_per_sec_per_gpu": 0.98,
+      "tokens/trainable": 768
+    },
+    {
+      "epoch": 0.2175732217573222,
+      "grad_norm": 4.955603122711182,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 0.2472325563430786,
+      "memory/device_reserved (GiB)": 75.79,
+      "memory/max_active (GiB)": 69.33,
+      "memory/max_allocated (GiB)": 69.33,
+      "ppl": 1.28048,
+      "step": 13,
+      "tokens/total": 233908,
+      "tokens/train_per_sec_per_gpu": 1.1,
+      "tokens/trainable": 832
+    },
+    {
+      "epoch": 0.23430962343096234,
+      "grad_norm": 5.264505386352539,
+      "learning_rate": 9.4e-06,
+      "loss": 0.25922638177871704,
+      "memory/device_reserved (GiB)": 75.79,
+      "memory/max_active (GiB)": 70.2,
+      "memory/max_allocated (GiB)": 70.2,
+      "ppl": 1.29593,
+      "step": 14,
+      "tokens/total": 251440,
+      "tokens/train_per_sec_per_gpu": 1.02,
+      "tokens/trainable": 896
+    },
+    {
+      "epoch": 0.2510460251046025,
+      "grad_norm": 3.7549469470977783,
+      "learning_rate": 9.200000000000002e-06,
+      "loss": 0.1895458996295929,
+      "memory/device_reserved (GiB)": 75.79,
+      "memory/max_active (GiB)": 69.57,
+      "memory/max_allocated (GiB)": 69.57,
+      "ppl": 1.2087,
+      "step": 15,
+      "tokens/total": 267920,
+      "tokens/train_per_sec_per_gpu": 1.04,
+      "tokens/trainable": 960
+    },
+    {
+      "epoch": 0.26778242677824265,
+      "grad_norm": 5.312631130218506,
+      "learning_rate": 9e-06,
+      "loss": 0.10376565158367157,
+      "memory/device_reserved (GiB)": 75.79,
+      "memory/max_active (GiB)": 70.19,
+      "memory/max_allocated (GiB)": 70.19,
+      "ppl": 1.10934,
+      "step": 16,
+      "tokens/total": 285952,
+      "tokens/train_per_sec_per_gpu": 1.0,
+      "tokens/trainable": 1024
+    },
+    {
+      "epoch": 0.28451882845188287,
+      "grad_norm": 4.028632640838623,
+      "learning_rate": 8.8e-06,
+      "loss": 0.26162976026535034,
+      "memory/device_reserved (GiB)": 75.79,
+      "memory/max_active (GiB)": 72.63,
+      "memory/max_allocated (GiB)": 72.63,
+      "ppl": 1.29905,
+      "step": 17,
+      "tokens/total": 303764,
+      "tokens/train_per_sec_per_gpu": 0.97,
+      "tokens/trainable": 1088
+    },
+    {
+      "epoch": 0.301255230125523,
+      "grad_norm": 2.946964979171753,
+      "learning_rate": 8.6e-06,
+      "loss": 0.07303209602832794,
+      "memory/device_reserved (GiB)": 75.79,
+      "memory/max_active (GiB)": 69.51,
+      "memory/max_allocated (GiB)": 69.51,
+      "ppl": 1.07577,
+      "step": 18,
+      "tokens/total": 320944,
+      "tokens/train_per_sec_per_gpu": 1.02,
+      "tokens/trainable": 1152
+    },
+    {
+      "epoch": 0.3179916317991632,
+      "grad_norm": 2.8597347736358643,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 0.14552569389343262,
+      "memory/device_reserved (GiB)": 75.79,
+      "memory/max_active (GiB)": 73.12,
+      "memory/max_allocated (GiB)": 73.12,
+      "ppl": 1.15665,
+      "step": 19,
+      "tokens/total": 341232,
+      "tokens/train_per_sec_per_gpu": 0.87,
+      "tokens/trainable": 1216
+    },
+    {
+      "epoch": 0.33472803347280333,
+      "grad_norm": 3.6591947078704834,
+      "learning_rate": 8.2e-06,
+      "loss": 0.15546177327632904,
+      "memory/device_reserved (GiB)": 75.79,
+      "memory/max_active (GiB)": 69.01,
+      "memory/max_allocated (GiB)": 69.01,
+      "ppl": 1.1682,
+      "step": 20,
+      "tokens/total": 356940,
+      "tokens/train_per_sec_per_gpu": 1.09,
+      "tokens/trainable": 1280
+    },
+    {
+      "epoch": 0.3514644351464435,
+      "grad_norm": 3.0281717777252197,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.09110970795154572,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 75.72,
+      "memory/max_allocated (GiB)": 75.72,
+      "ppl": 1.09539,
+      "step": 21,
+      "tokens/total": 376412,
+      "tokens/train_per_sec_per_gpu": 0.89,
+      "tokens/trainable": 1344
+    },
+    {
+      "epoch": 0.3682008368200837,
+      "grad_norm": 4.838003158569336,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 0.16041593253612518,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 69.12,
+      "memory/max_allocated (GiB)": 69.12,
+      "ppl": 1.174,
+      "step": 22,
+      "tokens/total": 392588,
+      "tokens/train_per_sec_per_gpu": 1.06,
+      "tokens/trainable": 1408
+    },
+    {
+      "epoch": 0.38493723849372385,
+      "grad_norm": 2.350078582763672,
+      "learning_rate": 7.600000000000001e-06,
+      "loss": 0.08050499856472015,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 72.63,
+      "memory/max_allocated (GiB)": 72.63,
+      "ppl": 1.08383,
+      "step": 23,
+      "tokens/total": 411740,
+      "tokens/train_per_sec_per_gpu": 0.92,
+      "tokens/trainable": 1472
+    },
+    {
+      "epoch": 0.401673640167364,
+      "grad_norm": 6.2735419273376465,
+      "learning_rate": 7.4e-06,
+      "loss": 0.17845900356769562,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 71.21,
+      "memory/max_allocated (GiB)": 71.21,
+      "ppl": 1.19537,
+      "step": 24,
+      "tokens/total": 429660,
+      "tokens/train_per_sec_per_gpu": 0.99,
+      "tokens/trainable": 1536
+    },
+    {
+      "epoch": 0.41841004184100417,
+      "grad_norm": 4.327482223510742,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.2505568861961365,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 71.94,
+      "memory/max_allocated (GiB)": 71.94,
+      "ppl": 1.28474,
+      "step": 25,
+      "tokens/total": 447356,
+      "tokens/train_per_sec_per_gpu": 0.97,
+      "tokens/trainable": 1600
+    },
+    {
+      "epoch": 0.4351464435146444,
+      "grad_norm": 2.954861640930176,
+      "learning_rate": 7e-06,
+      "loss": 0.21243004500865936,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 70.72,
+      "memory/max_allocated (GiB)": 70.72,
+      "ppl": 1.23668,
+      "step": 26,
+      "tokens/total": 463480,
+      "tokens/train_per_sec_per_gpu": 1.06,
+      "tokens/trainable": 1664
+    },
+    {
+      "epoch": 0.45188284518828453,
+      "grad_norm": 3.397681474685669,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 0.12888659536838531,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 71.77,
+      "memory/max_allocated (GiB)": 71.77,
+      "ppl": 1.13756,
+      "step": 27,
+      "tokens/total": 484208,
+      "tokens/train_per_sec_per_gpu": 0.86,
+      "tokens/trainable": 1728
+    },
+    {
+      "epoch": 0.4686192468619247,
+      "grad_norm": 2.7010715007781982,
+      "learning_rate": 6.600000000000001e-06,
+      "loss": 0.07128126174211502,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 70.9,
+      "memory/max_allocated (GiB)": 70.9,
+      "ppl": 1.07388,
+      "step": 28,
+      "tokens/total": 501932,
+      "tokens/train_per_sec_per_gpu": 0.98,
+      "tokens/trainable": 1792
+    },
+    {
+      "epoch": 0.48535564853556484,
+      "grad_norm": 4.152257442474365,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.2603352963924408,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 69.26,
+      "memory/max_allocated (GiB)": 69.26,
+      "ppl": 1.29737,
+      "step": 29,
+      "tokens/total": 518156,
+      "tokens/train_per_sec_per_gpu": 1.01,
+      "tokens/trainable": 1856
+    },
+    {
+      "epoch": 0.502092050209205,
+      "grad_norm": 4.530823707580566,
+      "learning_rate": 6.200000000000001e-06,
+      "loss": 0.3304905593395233,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 71.61,
+      "memory/max_allocated (GiB)": 71.61,
+      "ppl": 1.39165,
+      "step": 30,
+      "tokens/total": 535864,
+      "tokens/train_per_sec_per_gpu": 1.01,
+      "tokens/trainable": 1920
+    },
+    {
+      "epoch": 0.5188284518828452,
+      "grad_norm": 2.317944049835205,
+      "learning_rate": 6e-06,
+      "loss": 0.05913675203919411,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 71.14,
+      "memory/max_allocated (GiB)": 71.14,
+      "ppl": 1.06092,
+      "step": 31,
+      "tokens/total": 555492,
+      "tokens/train_per_sec_per_gpu": 0.89,
+      "tokens/trainable": 1984
+    },
+    {
+      "epoch": 0.5355648535564853,
+      "grad_norm": 2.4664571285247803,
+      "learning_rate": 5.8e-06,
+      "loss": 0.1651962250471115,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 72.9,
+      "memory/max_allocated (GiB)": 72.9,
+      "ppl": 1.17962,
+      "step": 32,
+      "tokens/total": 572804,
+      "tokens/train_per_sec_per_gpu": 1.01,
+      "tokens/trainable": 2048
+    },
+    {
+      "epoch": 0.5523012552301255,
+      "grad_norm": 10.276764869689941,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 0.2797020673751831,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 69.29,
+      "memory/max_allocated (GiB)": 69.29,
+      "ppl": 1.32274,
+      "step": 33,
+      "tokens/total": 590456,
+      "tokens/train_per_sec_per_gpu": 0.97,
+      "tokens/trainable": 2112
+    },
+    {
+      "epoch": 0.5690376569037657,
+      "grad_norm": 3.641462802886963,
+      "learning_rate": 5.400000000000001e-06,
+      "loss": 0.12429427355527878,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 69.39,
+      "memory/max_allocated (GiB)": 69.39,
+      "ppl": 1.13235,
+      "step": 34,
+      "tokens/total": 607664,
+      "tokens/train_per_sec_per_gpu": 1.02,
+      "tokens/trainable": 2176
+    },
+    {
+      "epoch": 0.5857740585774058,
+      "grad_norm": 5.973912239074707,
+      "learning_rate": 5.2e-06,
+      "loss": 0.13799738883972168,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 70.6,
+      "memory/max_allocated (GiB)": 70.6,
+      "ppl": 1.14797,
+      "step": 35,
+      "tokens/total": 626896,
+      "tokens/train_per_sec_per_gpu": 0.91,
+      "tokens/trainable": 2240
+    },
+    {
+      "epoch": 0.602510460251046,
+      "grad_norm": 4.914763450622559,
+      "learning_rate": 5e-06,
+      "loss": 0.1138860359787941,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 70.33,
+      "memory/max_allocated (GiB)": 70.33,
+      "ppl": 1.12062,
+      "step": 36,
+      "tokens/total": 644568,
+      "tokens/train_per_sec_per_gpu": 1.0,
+      "tokens/trainable": 2304
+    },
+    {
+      "epoch": 0.6192468619246861,
+      "grad_norm": 4.411563873291016,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.17296995222568512,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 69.9,
+      "memory/max_allocated (GiB)": 69.9,
+      "ppl": 1.18883,
+      "step": 37,
+      "tokens/total": 661036,
+      "tokens/train_per_sec_per_gpu": 1.03,
+      "tokens/trainable": 2368
+    },
+    {
+      "epoch": 0.6359832635983264,
+      "grad_norm": 2.9458227157592773,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.2226925939321518,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 70.18,
+      "memory/max_allocated (GiB)": 70.18,
+      "ppl": 1.24944,
+      "step": 38,
+      "tokens/total": 678704,
+      "tokens/train_per_sec_per_gpu": 1.0,
+      "tokens/trainable": 2432
+    },
+    {
+      "epoch": 0.6527196652719666,
+      "grad_norm": 3.683631181716919,
+      "learning_rate": 4.4e-06,
+      "loss": 0.21397189795970917,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 70.0,
+      "memory/max_allocated (GiB)": 70.0,
+      "ppl": 1.23859,
+      "step": 39,
+      "tokens/total": 697700,
+      "tokens/train_per_sec_per_gpu": 0.92,
+      "tokens/trainable": 2496
+    },
+    {
+      "epoch": 0.6694560669456067,
+      "grad_norm": 2.96964693069458,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.1635679453611374,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 71.54,
+      "memory/max_allocated (GiB)": 71.54,
+      "ppl": 1.17771,
+      "step": 40,
+      "tokens/total": 718204,
+      "tokens/train_per_sec_per_gpu": 0.89,
+      "tokens/trainable": 2560
+    },
+    {
+      "epoch": 0.6861924686192469,
+      "grad_norm": 3.370025634765625,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.11609481275081635,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 72.96,
+      "memory/max_allocated (GiB)": 72.96,
+      "ppl": 1.1231,
+      "step": 41,
+      "tokens/total": 736764,
+      "tokens/train_per_sec_per_gpu": 0.92,
+      "tokens/trainable": 2624
+    },
+    {
+      "epoch": 0.702928870292887,
+      "grad_norm": 2.4330062866210938,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.11920055747032166,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 70.79,
+      "memory/max_allocated (GiB)": 70.79,
+      "ppl": 1.1266,
+      "step": 42,
+      "tokens/total": 755480,
+      "tokens/train_per_sec_per_gpu": 0.96,
+      "tokens/trainable": 2688
+    },
+    {
+      "epoch": 0.7196652719665272,
+      "grad_norm": 3.1380691528320312,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.11467825621366501,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 70.4,
+      "memory/max_allocated (GiB)": 70.4,
+      "ppl": 1.12151,
+      "step": 43,
+      "tokens/total": 773232,
+      "tokens/train_per_sec_per_gpu": 0.98,
+      "tokens/trainable": 2752
+    },
+    {
+      "epoch": 0.7364016736401674,
+      "grad_norm": 3.144101858139038,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.21014568209648132,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 68.59,
+      "memory/max_allocated (GiB)": 68.59,
+      "ppl": 1.23386,
+      "step": 44,
+      "tokens/total": 789336,
+      "tokens/train_per_sec_per_gpu": 1.07,
+      "tokens/trainable": 2816
+    },
+    {
+      "epoch": 0.7531380753138075,
+      "grad_norm": 1.7117499113082886,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.11406993865966797,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 70.24,
+      "memory/max_allocated (GiB)": 70.24,
+      "ppl": 1.12083,
+      "step": 45,
+      "tokens/total": 808700,
+      "tokens/train_per_sec_per_gpu": 0.94,
+      "tokens/trainable": 2880
+    },
+    {
+      "epoch": 0.7698744769874477,
+      "grad_norm": 2.418976068496704,
+      "learning_rate": 3e-06,
+      "loss": 0.17273403704166412,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 72.81,
+      "memory/max_allocated (GiB)": 72.81,
+      "ppl": 1.18855,
+      "step": 46,
+      "tokens/total": 826844,
+      "tokens/train_per_sec_per_gpu": 0.96,
+      "tokens/trainable": 2944
+    },
+    {
+      "epoch": 0.7866108786610879,
+      "grad_norm": 2.926837921142578,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.09684156626462936,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 72.77,
+      "memory/max_allocated (GiB)": 72.77,
+      "ppl": 1.10169,
+      "step": 47,
+      "tokens/total": 847184,
+      "tokens/train_per_sec_per_gpu": 0.9,
+      "tokens/trainable": 3008
+    },
+    {
+      "epoch": 0.803347280334728,
+      "grad_norm": 4.230413436889648,
+      "learning_rate": 2.6e-06,
+      "loss": 0.20862005650997162,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 74.1,
+      "memory/max_allocated (GiB)": 74.1,
+      "ppl": 1.23198,
+      "step": 48,
+      "tokens/total": 866560,
+      "tokens/train_per_sec_per_gpu": 0.92,
+      "tokens/trainable": 3072
+    },
+    {
+      "epoch": 0.8200836820083682,
+      "grad_norm": 3.337388753890991,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.1312025487422943,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 70.8,
+      "memory/max_allocated (GiB)": 70.8,
+      "ppl": 1.1402,
+      "step": 49,
+      "tokens/total": 884492,
+      "tokens/train_per_sec_per_gpu": 0.99,
+      "tokens/trainable": 3136
+    },
+    {
+      "epoch": 0.8368200836820083,
+      "grad_norm": 2.6060917377471924,
+      "learning_rate": 2.2e-06,
+      "loss": 0.16115999221801758,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 70.0,
+      "memory/max_allocated (GiB)": 70.0,
+      "ppl": 1.17487,
+      "step": 50,
+      "tokens/total": 902636,
+      "tokens/train_per_sec_per_gpu": 0.96,
+      "tokens/trainable": 3200
+    },
+    {
+      "epoch": 0.8535564853556485,
+      "grad_norm": 2.2493844032287598,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.12020273506641388,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 70.29,
+      "memory/max_allocated (GiB)": 70.29,
+      "ppl": 1.12773,
+      "step": 51,
+      "tokens/total": 919304,
+      "tokens/train_per_sec_per_gpu": 1.05,
+      "tokens/trainable": 3264
+    },
+    {
+      "epoch": 0.8702928870292888,
+      "grad_norm": 3.619042158126831,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.21237094700336456,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 73.31,
+      "memory/max_allocated (GiB)": 73.31,
+      "ppl": 1.23661,
+      "step": 52,
+      "tokens/total": 938428,
+      "tokens/train_per_sec_per_gpu": 0.92,
+      "tokens/trainable": 3328
+    },
+    {
+      "epoch": 0.8870292887029289,
+      "grad_norm": 2.1316707134246826,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.15599104762077332,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 69.09,
+      "memory/max_allocated (GiB)": 69.09,
+      "ppl": 1.16882,
+      "step": 53,
+      "tokens/total": 954948,
+      "tokens/train_per_sec_per_gpu": 1.06,
+      "tokens/trainable": 3392
+    },
+    {
+      "epoch": 0.9037656903765691,
+      "grad_norm": 4.997905254364014,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.1855754852294922,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 70.4,
+      "memory/max_allocated (GiB)": 70.4,
+      "ppl": 1.20391,
+      "step": 54,
+      "tokens/total": 972044,
+      "tokens/train_per_sec_per_gpu": 1.01,
+      "tokens/trainable": 3456
+    },
+    {
+      "epoch": 0.9205020920502092,
+      "grad_norm": 4.500757694244385,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.2657952904701233,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 71.54,
+      "memory/max_allocated (GiB)": 71.54,
+      "ppl": 1.30447,
+      "step": 55,
+      "tokens/total": 992968,
+      "tokens/train_per_sec_per_gpu": 0.89,
+      "tokens/trainable": 3520
+    },
+    {
+      "epoch": 0.9372384937238494,
+      "grad_norm": 2.8300693035125732,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.10803321748971939,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 69.62,
+      "memory/max_allocated (GiB)": 69.62,
+      "ppl": 1.11408,
+      "step": 56,
+      "tokens/total": 1010324,
+      "tokens/train_per_sec_per_gpu": 1.0,
+      "tokens/trainable": 3584
+    },
+    {
+      "epoch": 0.9539748953974896,
+      "grad_norm": 2.5564687252044678,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 0.09892988950014114,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 72.96,
+      "memory/max_allocated (GiB)": 72.96,
+      "ppl": 1.10399,
+      "step": 57,
+      "tokens/total": 1031372,
+      "tokens/train_per_sec_per_gpu": 0.88,
+      "tokens/trainable": 3648
+    },
+    {
+      "epoch": 0.9707112970711297,
+      "grad_norm": 3.4302942752838135,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 0.18448004126548767,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 69.23,
+      "memory/max_allocated (GiB)": 69.23,
+      "ppl": 1.20259,
+      "step": 58,
+      "tokens/total": 1049420,
+      "tokens/train_per_sec_per_gpu": 0.96,
+      "tokens/trainable": 3712
+    },
+    {
+      "epoch": 0.9874476987447699,
+      "grad_norm": 3.7558505535125732,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 0.108936607837677,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 69.31,
+      "memory/max_allocated (GiB)": 69.31,
+      "ppl": 1.11509,
+      "step": 59,
+      "tokens/total": 1066468,
+      "tokens/train_per_sec_per_gpu": 1.04,
+      "tokens/trainable": 3776
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.990888833999634,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 0.23011130094528198,
+      "memory/device_reserved (GiB)": 78.04,
+      "memory/max_active (GiB)": 71.37,
+      "memory/max_allocated (GiB)": 71.37,
+      "ppl": 1.25874,
+      "step": 60,
+      "tokens/total": 1081564,
+      "tokens/train_per_sec_per_gpu": 1.2,
+      "tokens/trainable": 3824
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 60,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0930693108433715e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-60/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea58b52c163e70b8bb908a71f89911154bacdf54b8ddff0c1fa7ce4234c1c130
+size 6737

config.json

@@ -0,0 +1,97 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea43b288542655d72d632195ab9b58ca2cd9532c292bf6667827ce899ad196bc
+size 11422082

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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": true,
+  "model_max_length": 131072,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}