Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,9 @@ 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-122/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-183/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-244/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-305/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-61/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

added_tokens.json

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

checkpoint-122/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-122/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-122/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86c3e11d8f5942f9b2c882ababc848fe76d0dbe193723403d19cecc8c00b54b7
+size 1291899552

checkpoint-122/added_tokens.json

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

checkpoint-122/global_step121/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43d3ff593a33db9d00af920c05d4981441e36bd308ad6d2a86d8ac3fb487c47
+size 7751120668

checkpoint-122/global_step121/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c5f7eb02b7278cf6b3af4ee4a04cd18b957b8275704197acf345dbf9dd2ee5
+size 1396311192

checkpoint-122/latest

@@ -0,0 +1 @@
+global_step121

checkpoint-122/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53c42d1dfb8f91dd99fc98206d3b977c631968894b3844ac69a00b54336b72c5
+size 14244

checkpoint-122/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:888fd97ed86ec79d32749f41b60052b780850ebdef2267edee04b642afcac14a
+size 1064

checkpoint-122/special_tokens_map.json

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

checkpoint-122/tokenizer.json

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

checkpoint-122/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-122/trainer_state.json

@@ -0,0 +1,887 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9782608695652173,
+  "eval_steps": 500,
+  "global_step": 122,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016304347826086956,
+      "grad_norm": 45.78702163696289,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 4.8845,
+      "step": 1
+    },
+    {
+      "epoch": 0.03260869565217391,
+      "grad_norm": 45.26464080810547,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 4.8307,
+      "step": 2
+    },
+    {
+      "epoch": 0.04891304347826087,
+      "grad_norm": 45.96015167236328,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 4.8322,
+      "step": 3
+    },
+    {
+      "epoch": 0.06521739130434782,
+      "grad_norm": 45.86792755126953,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 4.8841,
+      "step": 4
+    },
+    {
+      "epoch": 0.08152173913043478,
+      "grad_norm": 44.19926071166992,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 4.8013,
+      "step": 5
+    },
+    {
+      "epoch": 0.09782608695652174,
+      "grad_norm": 45.76038360595703,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 4.8112,
+      "step": 6
+    },
+    {
+      "epoch": 0.11413043478260869,
+      "grad_norm": 45.73483657836914,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 4.8235,
+      "step": 7
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "grad_norm": 46.2863655090332,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 4.895,
+      "step": 8
+    },
+    {
+      "epoch": 0.14673913043478262,
+      "grad_norm": 44.06720733642578,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 4.7696,
+      "step": 9
+    },
+    {
+      "epoch": 0.16304347826086957,
+      "grad_norm": 43.8859977722168,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 4.7098,
+      "step": 10
+    },
+    {
+      "epoch": 0.1793478260869565,
+      "grad_norm": 44.059043884277344,
+      "learning_rate": 5.5e-07,
+      "loss": 4.7519,
+      "step": 11
+    },
+    {
+      "epoch": 0.1956521739130435,
+      "grad_norm": 43.980201721191406,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 4.7465,
+      "step": 12
+    },
+    {
+      "epoch": 0.21195652173913043,
+      "grad_norm": 40.88735580444336,
+      "learning_rate": 6.5e-07,
+      "loss": 4.5416,
+      "step": 13
+    },
+    {
+      "epoch": 0.22826086956521738,
+      "grad_norm": 39.40138244628906,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 4.5273,
+      "step": 14
+    },
+    {
+      "epoch": 0.24456521739130435,
+      "grad_norm": 37.21616744995117,
+      "learning_rate": 7.5e-07,
+      "loss": 4.4206,
+      "step": 15
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 35.060447692871094,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 4.3318,
+      "step": 16
+    },
+    {
+      "epoch": 0.27717391304347827,
+      "grad_norm": 30.492183685302734,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 4.0841,
+      "step": 17
+    },
+    {
+      "epoch": 0.29347826086956524,
+      "grad_norm": 28.49239730834961,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 4.0979,
+      "step": 18
+    },
+    {
+      "epoch": 0.30978260869565216,
+      "grad_norm": 24.898632049560547,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 3.8752,
+      "step": 19
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": 22.521434783935547,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 3.77,
+      "step": 20
+    },
+    {
+      "epoch": 0.3423913043478261,
+      "grad_norm": 20.311031341552734,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 3.5973,
+      "step": 21
+    },
+    {
+      "epoch": 0.358695652173913,
+      "grad_norm": 19.707839965820312,
+      "learning_rate": 1.1e-06,
+      "loss": 3.6102,
+      "step": 22
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 18.431489944458008,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 3.4147,
+      "step": 23
+    },
+    {
+      "epoch": 0.391304347826087,
+      "grad_norm": 17.78904151916504,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 3.2665,
+      "step": 24
+    },
+    {
+      "epoch": 0.4076086956521739,
+      "grad_norm": 18.014617919921875,
+      "learning_rate": 1.25e-06,
+      "loss": 3.1941,
+      "step": 25
+    },
+    {
+      "epoch": 0.42391304347826086,
+      "grad_norm": 17.8990478515625,
+      "learning_rate": 1.3e-06,
+      "loss": 3.0377,
+      "step": 26
+    },
+    {
+      "epoch": 0.44021739130434784,
+      "grad_norm": 18.60847282409668,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 2.8489,
+      "step": 27
+    },
+    {
+      "epoch": 0.45652173913043476,
+      "grad_norm": 18.562536239624023,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 2.6229,
+      "step": 28
+    },
+    {
+      "epoch": 0.47282608695652173,
+      "grad_norm": 19.00884246826172,
+      "learning_rate": 1.45e-06,
+      "loss": 2.4521,
+      "step": 29
+    },
+    {
+      "epoch": 0.4891304347826087,
+      "grad_norm": 20.419940948486328,
+      "learning_rate": 1.5e-06,
+      "loss": 2.3907,
+      "step": 30
+    },
+    {
+      "epoch": 0.5054347826086957,
+      "grad_norm": 21.181713104248047,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 2.2032,
+      "step": 31
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 20.592416763305664,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 2.004,
+      "step": 32
+    },
+    {
+      "epoch": 0.5380434782608695,
+      "grad_norm": 20.40924835205078,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 1.8373,
+      "step": 33
+    },
+    {
+      "epoch": 0.5543478260869565,
+      "grad_norm": 18.38524627685547,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 1.6218,
+      "step": 34
+    },
+    {
+      "epoch": 0.5706521739130435,
+      "grad_norm": 18.922391891479492,
+      "learning_rate": 1.75e-06,
+      "loss": 1.4708,
+      "step": 35
+    },
+    {
+      "epoch": 0.5869565217391305,
+      "grad_norm": 20.200698852539062,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 1.3044,
+      "step": 36
+    },
+    {
+      "epoch": 0.6032608695652174,
+      "grad_norm": 20.70162582397461,
+      "learning_rate": 1.85e-06,
+      "loss": 1.1445,
+      "step": 37
+    },
+    {
+      "epoch": 0.6195652173913043,
+      "grad_norm": 18.18869400024414,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.9504,
+      "step": 38
+    },
+    {
+      "epoch": 0.6358695652173914,
+      "grad_norm": 15.211593627929688,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.8083,
+      "step": 39
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 12.71890640258789,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.6981,
+      "step": 40
+    },
+    {
+      "epoch": 0.6684782608695652,
+      "grad_norm": 10.869053840637207,
+      "learning_rate": 2.05e-06,
+      "loss": 0.6018,
+      "step": 41
+    },
+    {
+      "epoch": 0.6847826086956522,
+      "grad_norm": 9.5787353515625,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 0.4899,
+      "step": 42
+    },
+    {
+      "epoch": 0.7010869565217391,
+      "grad_norm": 9.319293975830078,
+      "learning_rate": 2.15e-06,
+      "loss": 0.3986,
+      "step": 43
+    },
+    {
+      "epoch": 0.717391304347826,
+      "grad_norm": 9.404044151306152,
+      "learning_rate": 2.2e-06,
+      "loss": 0.3084,
+      "step": 44
+    },
+    {
+      "epoch": 0.7336956521739131,
+      "grad_norm": 7.995025634765625,
+      "learning_rate": 2.25e-06,
+      "loss": 0.2373,
+      "step": 45
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.505397319793701,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 0.1527,
+      "step": 46
+    },
+    {
+      "epoch": 0.7663043478260869,
+      "grad_norm": 2.5063579082489014,
+      "learning_rate": 2.35e-06,
+      "loss": 0.1097,
+      "step": 47
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 1.5846028327941895,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.102,
+      "step": 48
+    },
+    {
+      "epoch": 0.7989130434782609,
+      "grad_norm": 1.1286852359771729,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.093,
+      "step": 49
+    },
+    {
+      "epoch": 0.8152173913043478,
+      "grad_norm": 1.0311343669891357,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0778,
+      "step": 50
+    },
+    {
+      "epoch": 0.8315217391304348,
+      "grad_norm": 0.6458576917648315,
+      "learning_rate": 2.55e-06,
+      "loss": 0.0883,
+      "step": 51
+    },
+    {
+      "epoch": 0.8478260869565217,
+      "grad_norm": 0.727554202079773,
+      "learning_rate": 2.6e-06,
+      "loss": 0.0852,
+      "step": 52
+    },
+    {
+      "epoch": 0.8641304347826086,
+      "grad_norm": 0.619137167930603,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 0.0697,
+      "step": 53
+    },
+    {
+      "epoch": 0.8804347826086957,
+      "grad_norm": 0.38241881132125854,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.0665,
+      "step": 54
+    },
+    {
+      "epoch": 0.8967391304347826,
+      "grad_norm": 0.541621744632721,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.0658,
+      "step": 55
+    },
+    {
+      "epoch": 0.9130434782608695,
+      "grad_norm": 0.3869657516479492,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.0728,
+      "step": 56
+    },
+    {
+      "epoch": 0.9293478260869565,
+      "grad_norm": 0.3768727481365204,
+      "learning_rate": 2.85e-06,
+      "loss": 0.0741,
+      "step": 57
+    },
+    {
+      "epoch": 0.9456521739130435,
+      "grad_norm": 0.31400591135025024,
+      "learning_rate": 2.9e-06,
+      "loss": 0.0682,
+      "step": 58
+    },
+    {
+      "epoch": 0.9619565217391305,
+      "grad_norm": 0.3604981303215027,
+      "learning_rate": 2.95e-06,
+      "loss": 0.0652,
+      "step": 59
+    },
+    {
+      "epoch": 0.9782608695652174,
+      "grad_norm": 0.4383264482021332,
+      "learning_rate": 3e-06,
+      "loss": 0.0703,
+      "step": 60
+    },
+    {
+      "epoch": 0.9945652173913043,
+      "grad_norm": 0.310332328081131,
+      "learning_rate": 3.05e-06,
+      "loss": 0.0664,
+      "step": 61
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.310332328081131,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.0509,
+      "step": 62
+    },
+    {
+      "epoch": 1.016304347826087,
+      "grad_norm": 0.665212869644165,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 0.0633,
+      "step": 63
+    },
+    {
+      "epoch": 1.0326086956521738,
+      "grad_norm": 0.3108278512954712,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.0648,
+      "step": 64
+    },
+    {
+      "epoch": 1.048913043478261,
+      "grad_norm": 0.5986258387565613,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.0769,
+      "step": 65
+    },
+    {
+      "epoch": 1.065217391304348,
+      "grad_norm": 0.6987417936325073,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.0728,
+      "step": 66
+    },
+    {
+      "epoch": 1.0815217391304348,
+      "grad_norm": 0.36069774627685547,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 0.0647,
+      "step": 67
+    },
+    {
+      "epoch": 1.0978260869565217,
+      "grad_norm": 0.37604954838752747,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.0571,
+      "step": 68
+    },
+    {
+      "epoch": 1.1141304347826086,
+      "grad_norm": 0.2985791862010956,
+      "learning_rate": 3.45e-06,
+      "loss": 0.0629,
+      "step": 69
+    },
+    {
+      "epoch": 1.1304347826086956,
+      "grad_norm": 0.3454388380050659,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0644,
+      "step": 70
+    },
+    {
+      "epoch": 1.1467391304347827,
+      "grad_norm": 0.3371462821960449,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 0.0645,
+      "step": 71
+    },
+    {
+      "epoch": 1.1630434782608696,
+      "grad_norm": 0.27834194898605347,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.0678,
+      "step": 72
+    },
+    {
+      "epoch": 1.1793478260869565,
+      "grad_norm": 0.26285555958747864,
+      "learning_rate": 3.65e-06,
+      "loss": 0.0586,
+      "step": 73
+    },
+    {
+      "epoch": 1.1956521739130435,
+      "grad_norm": 0.34152188897132874,
+      "learning_rate": 3.7e-06,
+      "loss": 0.061,
+      "step": 74
+    },
+    {
+      "epoch": 1.2119565217391304,
+      "grad_norm": 0.2939279079437256,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0643,
+      "step": 75
+    },
+    {
+      "epoch": 1.2282608695652173,
+      "grad_norm": 0.395220547914505,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.0644,
+      "step": 76
+    },
+    {
+      "epoch": 1.2445652173913044,
+      "grad_norm": 0.29400259256362915,
+      "learning_rate": 3.85e-06,
+      "loss": 0.0562,
+      "step": 77
+    },
+    {
+      "epoch": 1.2608695652173914,
+      "grad_norm": 0.25938117504119873,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.0658,
+      "step": 78
+    },
+    {
+      "epoch": 1.2771739130434783,
+      "grad_norm": 0.36941587924957275,
+      "learning_rate": 3.95e-06,
+      "loss": 0.0678,
+      "step": 79
+    },
+    {
+      "epoch": 1.2934782608695652,
+      "grad_norm": 0.26572781801223755,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0588,
+      "step": 80
+    },
+    {
+      "epoch": 1.309782608695652,
+      "grad_norm": 0.22964634001255035,
+      "learning_rate": 4.05e-06,
+      "loss": 0.0612,
+      "step": 81
+    },
+    {
+      "epoch": 1.3260869565217392,
+      "grad_norm": 0.24455289542675018,
+      "learning_rate": 4.1e-06,
+      "loss": 0.059,
+      "step": 82
+    },
+    {
+      "epoch": 1.3423913043478262,
+      "grad_norm": 0.3925253748893738,
+      "learning_rate": 4.15e-06,
+      "loss": 0.0648,
+      "step": 83
+    },
+    {
+      "epoch": 1.358695652173913,
+      "grad_norm": 0.24822917580604553,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.0618,
+      "step": 84
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 0.2522635757923126,
+      "learning_rate": 4.25e-06,
+      "loss": 0.0568,
+      "step": 85
+    },
+    {
+      "epoch": 1.391304347826087,
+      "grad_norm": 0.2465311586856842,
+      "learning_rate": 4.3e-06,
+      "loss": 0.0613,
+      "step": 86
+    },
+    {
+      "epoch": 1.4076086956521738,
+      "grad_norm": 0.2514893412590027,
+      "learning_rate": 4.350000000000001e-06,
+      "loss": 0.0574,
+      "step": 87
+    },
+    {
+      "epoch": 1.4239130434782608,
+      "grad_norm": 0.2320777177810669,
+      "learning_rate": 4.4e-06,
+      "loss": 0.0502,
+      "step": 88
+    },
+    {
+      "epoch": 1.440217391304348,
+      "grad_norm": 0.2494516372680664,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 0.0685,
+      "step": 89
+    },
+    {
+      "epoch": 1.4565217391304348,
+      "grad_norm": 0.244571715593338,
+      "learning_rate": 4.5e-06,
+      "loss": 0.0588,
+      "step": 90
+    },
+    {
+      "epoch": 1.4728260869565217,
+      "grad_norm": 0.22765810787677765,
+      "learning_rate": 4.5500000000000005e-06,
+      "loss": 0.0591,
+      "step": 91
+    },
+    {
+      "epoch": 1.4891304347826086,
+      "grad_norm": 0.2349582016468048,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.0572,
+      "step": 92
+    },
+    {
+      "epoch": 1.5054347826086958,
+      "grad_norm": 0.228654682636261,
+      "learning_rate": 4.65e-06,
+      "loss": 0.0593,
+      "step": 93
+    },
+    {
+      "epoch": 1.5217391304347827,
+      "grad_norm": 0.3090372681617737,
+      "learning_rate": 4.7e-06,
+      "loss": 0.0592,
+      "step": 94
+    },
+    {
+      "epoch": 1.5380434782608696,
+      "grad_norm": 0.2116968333721161,
+      "learning_rate": 4.75e-06,
+      "loss": 0.0575,
+      "step": 95
+    },
+    {
+      "epoch": 1.5543478260869565,
+      "grad_norm": 0.32294484972953796,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.062,
+      "step": 96
+    },
+    {
+      "epoch": 1.5706521739130435,
+      "grad_norm": 0.35240596532821655,
+      "learning_rate": 4.85e-06,
+      "loss": 0.0561,
+      "step": 97
+    },
+    {
+      "epoch": 1.5869565217391304,
+      "grad_norm": 0.24272935092449188,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.0591,
+      "step": 98
+    },
+    {
+      "epoch": 1.6032608695652173,
+      "grad_norm": 0.26952850818634033,
+      "learning_rate": 4.95e-06,
+      "loss": 0.0557,
+      "step": 99
+    },
+    {
+      "epoch": 1.6195652173913042,
+      "grad_norm": 0.2775789201259613,
+      "learning_rate": 5e-06,
+      "loss": 0.0624,
+      "step": 100
+    },
+    {
+      "epoch": 1.6358695652173914,
+      "grad_norm": 0.2162039428949356,
+      "learning_rate": 4.999825642177387e-06,
+      "loss": 0.0582,
+      "step": 101
+    },
+    {
+      "epoch": 1.6521739130434783,
+      "grad_norm": 0.38436195254325867,
+      "learning_rate": 4.999302593030069e-06,
+      "loss": 0.0618,
+      "step": 102
+    },
+    {
+      "epoch": 1.6684782608695652,
+      "grad_norm": 0.2860764265060425,
+      "learning_rate": 4.998430925516213e-06,
+      "loss": 0.0637,
+      "step": 103
+    },
+    {
+      "epoch": 1.6847826086956523,
+      "grad_norm": 0.2180222123861313,
+      "learning_rate": 4.99721076122146e-06,
+      "loss": 0.0565,
+      "step": 104
+    },
+    {
+      "epoch": 1.7010869565217392,
+      "grad_norm": 0.30026087164878845,
+      "learning_rate": 4.995642270341961e-06,
+      "loss": 0.0615,
+      "step": 105
+    },
+    {
+      "epoch": 1.7173913043478262,
+      "grad_norm": 0.27657821774482727,
+      "learning_rate": 4.99372567166064e-06,
+      "loss": 0.0661,
+      "step": 106
+    },
+    {
+      "epoch": 1.733695652173913,
+      "grad_norm": 0.23324432969093323,
+      "learning_rate": 4.991461232516675e-06,
+      "loss": 0.0563,
+      "step": 107
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.2670609951019287,
+      "learning_rate": 4.98884926876821e-06,
+      "loss": 0.0671,
+      "step": 108
+    },
+    {
+      "epoch": 1.766304347826087,
+      "grad_norm": 0.2405894696712494,
+      "learning_rate": 4.9858901447482924e-06,
+      "loss": 0.0571,
+      "step": 109
+    },
+    {
+      "epoch": 1.7826086956521738,
+      "grad_norm": 0.23271754384040833,
+      "learning_rate": 4.982584273214061e-06,
+      "loss": 0.0598,
+      "step": 110
+    },
+    {
+      "epoch": 1.7989130434782608,
+      "grad_norm": 0.21662941575050354,
+      "learning_rate": 4.978932115289165e-06,
+      "loss": 0.0562,
+      "step": 111
+    },
+    {
+      "epoch": 1.8152173913043477,
+      "grad_norm": 0.27656564116477966,
+      "learning_rate": 4.974934180399447e-06,
+      "loss": 0.0531,
+      "step": 112
+    },
+    {
+      "epoch": 1.8315217391304348,
+      "grad_norm": 0.3287908434867859,
+      "learning_rate": 4.970591026201884e-06,
+      "loss": 0.0522,
+      "step": 113
+    },
+    {
+      "epoch": 1.8478260869565217,
+      "grad_norm": 0.1879669576883316,
+      "learning_rate": 4.965903258506806e-06,
+      "loss": 0.0625,
+      "step": 114
+    },
+    {
+      "epoch": 1.8641304347826086,
+      "grad_norm": 0.2798942029476166,
+      "learning_rate": 4.9608715311933865e-06,
+      "loss": 0.0546,
+      "step": 115
+    },
+    {
+      "epoch": 1.8804347826086958,
+      "grad_norm": 0.31130167841911316,
+      "learning_rate": 4.955496546118439e-06,
+      "loss": 0.0576,
+      "step": 116
+    },
+    {
+      "epoch": 1.8967391304347827,
+      "grad_norm": 0.23934200406074524,
+      "learning_rate": 4.949779053018519e-06,
+      "loss": 0.0522,
+      "step": 117
+    },
+    {
+      "epoch": 1.9130434782608696,
+      "grad_norm": 0.2684226632118225,
+      "learning_rate": 4.943719849405347e-06,
+      "loss": 0.0596,
+      "step": 118
+    },
+    {
+      "epoch": 1.9293478260869565,
+      "grad_norm": 0.31276896595954895,
+      "learning_rate": 4.937319780454559e-06,
+      "loss": 0.0609,
+      "step": 119
+    },
+    {
+      "epoch": 1.9456521739130435,
+      "grad_norm": 0.2928497791290283,
+      "learning_rate": 4.930579738887827e-06,
+      "loss": 0.0515,
+      "step": 120
+    },
+    {
+      "epoch": 1.9619565217391304,
+      "grad_norm": 0.25487199425697327,
+      "learning_rate": 4.923500664848327e-06,
+      "loss": 0.0565,
+      "step": 121
+    },
+    {
+      "epoch": 1.9782608695652173,
+      "grad_norm": 0.19076956808567047,
+      "learning_rate": 4.9160835457696075e-06,
+      "loss": 0.0541,
+      "step": 122
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 366,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 61,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.7161733923602432e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-122/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4bdf3f34ad3174d7ffb541641f906b4ea87bd3f0ed6dc8fb586e66791457854
+size 7992

checkpoint-122/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

checkpoint-183/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-183/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-183/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65b3191d1c0e93ac6a42bb660833e5a94c5ebc4286dbca12ba6e139b428567c4
+size 1291899552

checkpoint-183/added_tokens.json

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

checkpoint-183/global_step181/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16c2a176aa5ae8a70df65ca77612de44d98d485d5e6a14944767e2afc21fbdbc
+size 7751120668

checkpoint-183/global_step181/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:092312dd458f672436baed471261e7038eeab6a8ed22f0fd6b492952ed732961
+size 1396311192

checkpoint-183/latest

@@ -0,0 +1 @@
+global_step181

checkpoint-183/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49b91b35605b5d98cd3c4bddce155e450de25b5e628a48fcc12525dec0659509
+size 14244

checkpoint-183/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:638be0ea97d5ae33636c6687142a00e0c87ea82a700820d19a9873974009b8e8
+size 1064

checkpoint-183/special_tokens_map.json

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

checkpoint-183/tokenizer.json

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

checkpoint-183/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-183/trainer_state.json

@@ -0,0 +1,1314 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9619565217391304,
+  "eval_steps": 500,
+  "global_step": 183,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016304347826086956,
+      "grad_norm": 45.78702163696289,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 4.8845,
+      "step": 1
+    },
+    {
+      "epoch": 0.03260869565217391,
+      "grad_norm": 45.26464080810547,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 4.8307,
+      "step": 2
+    },
+    {
+      "epoch": 0.04891304347826087,
+      "grad_norm": 45.96015167236328,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 4.8322,
+      "step": 3
+    },
+    {
+      "epoch": 0.06521739130434782,
+      "grad_norm": 45.86792755126953,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 4.8841,
+      "step": 4
+    },
+    {
+      "epoch": 0.08152173913043478,
+      "grad_norm": 44.19926071166992,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 4.8013,
+      "step": 5
+    },
+    {
+      "epoch": 0.09782608695652174,
+      "grad_norm": 45.76038360595703,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 4.8112,
+      "step": 6
+    },
+    {
+      "epoch": 0.11413043478260869,
+      "grad_norm": 45.73483657836914,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 4.8235,
+      "step": 7
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "grad_norm": 46.2863655090332,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 4.895,
+      "step": 8
+    },
+    {
+      "epoch": 0.14673913043478262,
+      "grad_norm": 44.06720733642578,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 4.7696,
+      "step": 9
+    },
+    {
+      "epoch": 0.16304347826086957,
+      "grad_norm": 43.8859977722168,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 4.7098,
+      "step": 10
+    },
+    {
+      "epoch": 0.1793478260869565,
+      "grad_norm": 44.059043884277344,
+      "learning_rate": 5.5e-07,
+      "loss": 4.7519,
+      "step": 11
+    },
+    {
+      "epoch": 0.1956521739130435,
+      "grad_norm": 43.980201721191406,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 4.7465,
+      "step": 12
+    },
+    {
+      "epoch": 0.21195652173913043,
+      "grad_norm": 40.88735580444336,
+      "learning_rate": 6.5e-07,
+      "loss": 4.5416,
+      "step": 13
+    },
+    {
+      "epoch": 0.22826086956521738,
+      "grad_norm": 39.40138244628906,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 4.5273,
+      "step": 14
+    },
+    {
+      "epoch": 0.24456521739130435,
+      "grad_norm": 37.21616744995117,
+      "learning_rate": 7.5e-07,
+      "loss": 4.4206,
+      "step": 15
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 35.060447692871094,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 4.3318,
+      "step": 16
+    },
+    {
+      "epoch": 0.27717391304347827,
+      "grad_norm": 30.492183685302734,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 4.0841,
+      "step": 17
+    },
+    {
+      "epoch": 0.29347826086956524,
+      "grad_norm": 28.49239730834961,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 4.0979,
+      "step": 18
+    },
+    {
+      "epoch": 0.30978260869565216,
+      "grad_norm": 24.898632049560547,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 3.8752,
+      "step": 19
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": 22.521434783935547,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 3.77,
+      "step": 20
+    },
+    {
+      "epoch": 0.3423913043478261,
+      "grad_norm": 20.311031341552734,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 3.5973,
+      "step": 21
+    },
+    {
+      "epoch": 0.358695652173913,
+      "grad_norm": 19.707839965820312,
+      "learning_rate": 1.1e-06,
+      "loss": 3.6102,
+      "step": 22
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 18.431489944458008,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 3.4147,
+      "step": 23
+    },
+    {
+      "epoch": 0.391304347826087,
+      "grad_norm": 17.78904151916504,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 3.2665,
+      "step": 24
+    },
+    {
+      "epoch": 0.4076086956521739,
+      "grad_norm": 18.014617919921875,
+      "learning_rate": 1.25e-06,
+      "loss": 3.1941,
+      "step": 25
+    },
+    {
+      "epoch": 0.42391304347826086,
+      "grad_norm": 17.8990478515625,
+      "learning_rate": 1.3e-06,
+      "loss": 3.0377,
+      "step": 26
+    },
+    {
+      "epoch": 0.44021739130434784,
+      "grad_norm": 18.60847282409668,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 2.8489,
+      "step": 27
+    },
+    {
+      "epoch": 0.45652173913043476,
+      "grad_norm": 18.562536239624023,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 2.6229,
+      "step": 28
+    },
+    {
+      "epoch": 0.47282608695652173,
+      "grad_norm": 19.00884246826172,
+      "learning_rate": 1.45e-06,
+      "loss": 2.4521,
+      "step": 29
+    },
+    {
+      "epoch": 0.4891304347826087,
+      "grad_norm": 20.419940948486328,
+      "learning_rate": 1.5e-06,
+      "loss": 2.3907,
+      "step": 30
+    },
+    {
+      "epoch": 0.5054347826086957,
+      "grad_norm": 21.181713104248047,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 2.2032,
+      "step": 31
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 20.592416763305664,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 2.004,
+      "step": 32
+    },
+    {
+      "epoch": 0.5380434782608695,
+      "grad_norm": 20.40924835205078,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 1.8373,
+      "step": 33
+    },
+    {
+      "epoch": 0.5543478260869565,
+      "grad_norm": 18.38524627685547,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 1.6218,
+      "step": 34
+    },
+    {
+      "epoch": 0.5706521739130435,
+      "grad_norm": 18.922391891479492,
+      "learning_rate": 1.75e-06,
+      "loss": 1.4708,
+      "step": 35
+    },
+    {
+      "epoch": 0.5869565217391305,
+      "grad_norm": 20.200698852539062,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 1.3044,
+      "step": 36
+    },
+    {
+      "epoch": 0.6032608695652174,
+      "grad_norm": 20.70162582397461,
+      "learning_rate": 1.85e-06,
+      "loss": 1.1445,
+      "step": 37
+    },
+    {
+      "epoch": 0.6195652173913043,
+      "grad_norm": 18.18869400024414,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.9504,
+      "step": 38
+    },
+    {
+      "epoch": 0.6358695652173914,
+      "grad_norm": 15.211593627929688,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.8083,
+      "step": 39
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 12.71890640258789,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.6981,
+      "step": 40
+    },
+    {
+      "epoch": 0.6684782608695652,
+      "grad_norm": 10.869053840637207,
+      "learning_rate": 2.05e-06,
+      "loss": 0.6018,
+      "step": 41
+    },
+    {
+      "epoch": 0.6847826086956522,
+      "grad_norm": 9.5787353515625,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 0.4899,
+      "step": 42
+    },
+    {
+      "epoch": 0.7010869565217391,
+      "grad_norm": 9.319293975830078,
+      "learning_rate": 2.15e-06,
+      "loss": 0.3986,
+      "step": 43
+    },
+    {
+      "epoch": 0.717391304347826,
+      "grad_norm": 9.404044151306152,
+      "learning_rate": 2.2e-06,
+      "loss": 0.3084,
+      "step": 44
+    },
+    {
+      "epoch": 0.7336956521739131,
+      "grad_norm": 7.995025634765625,
+      "learning_rate": 2.25e-06,
+      "loss": 0.2373,
+      "step": 45
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.505397319793701,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 0.1527,
+      "step": 46
+    },
+    {
+      "epoch": 0.7663043478260869,
+      "grad_norm": 2.5063579082489014,
+      "learning_rate": 2.35e-06,
+      "loss": 0.1097,
+      "step": 47
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 1.5846028327941895,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.102,
+      "step": 48
+    },
+    {
+      "epoch": 0.7989130434782609,
+      "grad_norm": 1.1286852359771729,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.093,
+      "step": 49
+    },
+    {
+      "epoch": 0.8152173913043478,
+      "grad_norm": 1.0311343669891357,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0778,
+      "step": 50
+    },
+    {
+      "epoch": 0.8315217391304348,
+      "grad_norm": 0.6458576917648315,
+      "learning_rate": 2.55e-06,
+      "loss": 0.0883,
+      "step": 51
+    },
+    {
+      "epoch": 0.8478260869565217,
+      "grad_norm": 0.727554202079773,
+      "learning_rate": 2.6e-06,
+      "loss": 0.0852,
+      "step": 52
+    },
+    {
+      "epoch": 0.8641304347826086,
+      "grad_norm": 0.619137167930603,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 0.0697,
+      "step": 53
+    },
+    {
+      "epoch": 0.8804347826086957,
+      "grad_norm": 0.38241881132125854,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.0665,
+      "step": 54
+    },
+    {
+      "epoch": 0.8967391304347826,
+      "grad_norm": 0.541621744632721,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.0658,
+      "step": 55
+    },
+    {
+      "epoch": 0.9130434782608695,
+      "grad_norm": 0.3869657516479492,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.0728,
+      "step": 56
+    },
+    {
+      "epoch": 0.9293478260869565,
+      "grad_norm": 0.3768727481365204,
+      "learning_rate": 2.85e-06,
+      "loss": 0.0741,
+      "step": 57
+    },
+    {
+      "epoch": 0.9456521739130435,
+      "grad_norm": 0.31400591135025024,
+      "learning_rate": 2.9e-06,
+      "loss": 0.0682,
+      "step": 58
+    },
+    {
+      "epoch": 0.9619565217391305,
+      "grad_norm": 0.3604981303215027,
+      "learning_rate": 2.95e-06,
+      "loss": 0.0652,
+      "step": 59
+    },
+    {
+      "epoch": 0.9782608695652174,
+      "grad_norm": 0.4383264482021332,
+      "learning_rate": 3e-06,
+      "loss": 0.0703,
+      "step": 60
+    },
+    {
+      "epoch": 0.9945652173913043,
+      "grad_norm": 0.310332328081131,
+      "learning_rate": 3.05e-06,
+      "loss": 0.0664,
+      "step": 61
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.310332328081131,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.0509,
+      "step": 62
+    },
+    {
+      "epoch": 1.016304347826087,
+      "grad_norm": 0.665212869644165,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 0.0633,
+      "step": 63
+    },
+    {
+      "epoch": 1.0326086956521738,
+      "grad_norm": 0.3108278512954712,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.0648,
+      "step": 64
+    },
+    {
+      "epoch": 1.048913043478261,
+      "grad_norm": 0.5986258387565613,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.0769,
+      "step": 65
+    },
+    {
+      "epoch": 1.065217391304348,
+      "grad_norm": 0.6987417936325073,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.0728,
+      "step": 66
+    },
+    {
+      "epoch": 1.0815217391304348,
+      "grad_norm": 0.36069774627685547,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 0.0647,
+      "step": 67
+    },
+    {
+      "epoch": 1.0978260869565217,
+      "grad_norm": 0.37604954838752747,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.0571,
+      "step": 68
+    },
+    {
+      "epoch": 1.1141304347826086,
+      "grad_norm": 0.2985791862010956,
+      "learning_rate": 3.45e-06,
+      "loss": 0.0629,
+      "step": 69
+    },
+    {
+      "epoch": 1.1304347826086956,
+      "grad_norm": 0.3454388380050659,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0644,
+      "step": 70
+    },
+    {
+      "epoch": 1.1467391304347827,
+      "grad_norm": 0.3371462821960449,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 0.0645,
+      "step": 71
+    },
+    {
+      "epoch": 1.1630434782608696,
+      "grad_norm": 0.27834194898605347,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.0678,
+      "step": 72
+    },
+    {
+      "epoch": 1.1793478260869565,
+      "grad_norm": 0.26285555958747864,
+      "learning_rate": 3.65e-06,
+      "loss": 0.0586,
+      "step": 73
+    },
+    {
+      "epoch": 1.1956521739130435,
+      "grad_norm": 0.34152188897132874,
+      "learning_rate": 3.7e-06,
+      "loss": 0.061,
+      "step": 74
+    },
+    {
+      "epoch": 1.2119565217391304,
+      "grad_norm": 0.2939279079437256,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0643,
+      "step": 75
+    },
+    {
+      "epoch": 1.2282608695652173,
+      "grad_norm": 0.395220547914505,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.0644,
+      "step": 76
+    },
+    {
+      "epoch": 1.2445652173913044,
+      "grad_norm": 0.29400259256362915,
+      "learning_rate": 3.85e-06,
+      "loss": 0.0562,
+      "step": 77
+    },
+    {
+      "epoch": 1.2608695652173914,
+      "grad_norm": 0.25938117504119873,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.0658,
+      "step": 78
+    },
+    {
+      "epoch": 1.2771739130434783,
+      "grad_norm": 0.36941587924957275,
+      "learning_rate": 3.95e-06,
+      "loss": 0.0678,
+      "step": 79
+    },
+    {
+      "epoch": 1.2934782608695652,
+      "grad_norm": 0.26572781801223755,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0588,
+      "step": 80
+    },
+    {
+      "epoch": 1.309782608695652,
+      "grad_norm": 0.22964634001255035,
+      "learning_rate": 4.05e-06,
+      "loss": 0.0612,
+      "step": 81
+    },
+    {
+      "epoch": 1.3260869565217392,
+      "grad_norm": 0.24455289542675018,
+      "learning_rate": 4.1e-06,
+      "loss": 0.059,
+      "step": 82
+    },
+    {
+      "epoch": 1.3423913043478262,
+      "grad_norm": 0.3925253748893738,
+      "learning_rate": 4.15e-06,
+      "loss": 0.0648,
+      "step": 83
+    },
+    {
+      "epoch": 1.358695652173913,
+      "grad_norm": 0.24822917580604553,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.0618,
+      "step": 84
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 0.2522635757923126,
+      "learning_rate": 4.25e-06,
+      "loss": 0.0568,
+      "step": 85
+    },
+    {
+      "epoch": 1.391304347826087,
+      "grad_norm": 0.2465311586856842,
+      "learning_rate": 4.3e-06,
+      "loss": 0.0613,
+      "step": 86
+    },
+    {
+      "epoch": 1.4076086956521738,
+      "grad_norm": 0.2514893412590027,
+      "learning_rate": 4.350000000000001e-06,
+      "loss": 0.0574,
+      "step": 87
+    },
+    {
+      "epoch": 1.4239130434782608,
+      "grad_norm": 0.2320777177810669,
+      "learning_rate": 4.4e-06,
+      "loss": 0.0502,
+      "step": 88
+    },
+    {
+      "epoch": 1.440217391304348,
+      "grad_norm": 0.2494516372680664,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 0.0685,
+      "step": 89
+    },
+    {
+      "epoch": 1.4565217391304348,
+      "grad_norm": 0.244571715593338,
+      "learning_rate": 4.5e-06,
+      "loss": 0.0588,
+      "step": 90
+    },
+    {
+      "epoch": 1.4728260869565217,
+      "grad_norm": 0.22765810787677765,
+      "learning_rate": 4.5500000000000005e-06,
+      "loss": 0.0591,
+      "step": 91
+    },
+    {
+      "epoch": 1.4891304347826086,
+      "grad_norm": 0.2349582016468048,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.0572,
+      "step": 92
+    },
+    {
+      "epoch": 1.5054347826086958,
+      "grad_norm": 0.228654682636261,
+      "learning_rate": 4.65e-06,
+      "loss": 0.0593,
+      "step": 93
+    },
+    {
+      "epoch": 1.5217391304347827,
+      "grad_norm": 0.3090372681617737,
+      "learning_rate": 4.7e-06,
+      "loss": 0.0592,
+      "step": 94
+    },
+    {
+      "epoch": 1.5380434782608696,
+      "grad_norm": 0.2116968333721161,
+      "learning_rate": 4.75e-06,
+      "loss": 0.0575,
+      "step": 95
+    },
+    {
+      "epoch": 1.5543478260869565,
+      "grad_norm": 0.32294484972953796,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.062,
+      "step": 96
+    },
+    {
+      "epoch": 1.5706521739130435,
+      "grad_norm": 0.35240596532821655,
+      "learning_rate": 4.85e-06,
+      "loss": 0.0561,
+      "step": 97
+    },
+    {
+      "epoch": 1.5869565217391304,
+      "grad_norm": 0.24272935092449188,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.0591,
+      "step": 98
+    },
+    {
+      "epoch": 1.6032608695652173,
+      "grad_norm": 0.26952850818634033,
+      "learning_rate": 4.95e-06,
+      "loss": 0.0557,
+      "step": 99
+    },
+    {
+      "epoch": 1.6195652173913042,
+      "grad_norm": 0.2775789201259613,
+      "learning_rate": 5e-06,
+      "loss": 0.0624,
+      "step": 100
+    },
+    {
+      "epoch": 1.6358695652173914,
+      "grad_norm": 0.2162039428949356,
+      "learning_rate": 4.999825642177387e-06,
+      "loss": 0.0582,
+      "step": 101
+    },
+    {
+      "epoch": 1.6521739130434783,
+      "grad_norm": 0.38436195254325867,
+      "learning_rate": 4.999302593030069e-06,
+      "loss": 0.0618,
+      "step": 102
+    },
+    {
+      "epoch": 1.6684782608695652,
+      "grad_norm": 0.2860764265060425,
+      "learning_rate": 4.998430925516213e-06,
+      "loss": 0.0637,
+      "step": 103
+    },
+    {
+      "epoch": 1.6847826086956523,
+      "grad_norm": 0.2180222123861313,
+      "learning_rate": 4.99721076122146e-06,
+      "loss": 0.0565,
+      "step": 104
+    },
+    {
+      "epoch": 1.7010869565217392,
+      "grad_norm": 0.30026087164878845,
+      "learning_rate": 4.995642270341961e-06,
+      "loss": 0.0615,
+      "step": 105
+    },
+    {
+      "epoch": 1.7173913043478262,
+      "grad_norm": 0.27657821774482727,
+      "learning_rate": 4.99372567166064e-06,
+      "loss": 0.0661,
+      "step": 106
+    },
+    {
+      "epoch": 1.733695652173913,
+      "grad_norm": 0.23324432969093323,
+      "learning_rate": 4.991461232516675e-06,
+      "loss": 0.0563,
+      "step": 107
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.2670609951019287,
+      "learning_rate": 4.98884926876821e-06,
+      "loss": 0.0671,
+      "step": 108
+    },
+    {
+      "epoch": 1.766304347826087,
+      "grad_norm": 0.2405894696712494,
+      "learning_rate": 4.9858901447482924e-06,
+      "loss": 0.0571,
+      "step": 109
+    },
+    {
+      "epoch": 1.7826086956521738,
+      "grad_norm": 0.23271754384040833,
+      "learning_rate": 4.982584273214061e-06,
+      "loss": 0.0598,
+      "step": 110
+    },
+    {
+      "epoch": 1.7989130434782608,
+      "grad_norm": 0.21662941575050354,
+      "learning_rate": 4.978932115289165e-06,
+      "loss": 0.0562,
+      "step": 111
+    },
+    {
+      "epoch": 1.8152173913043477,
+      "grad_norm": 0.27656564116477966,
+      "learning_rate": 4.974934180399447e-06,
+      "loss": 0.0531,
+      "step": 112
+    },
+    {
+      "epoch": 1.8315217391304348,
+      "grad_norm": 0.3287908434867859,
+      "learning_rate": 4.970591026201884e-06,
+      "loss": 0.0522,
+      "step": 113
+    },
+    {
+      "epoch": 1.8478260869565217,
+      "grad_norm": 0.1879669576883316,
+      "learning_rate": 4.965903258506806e-06,
+      "loss": 0.0625,
+      "step": 114
+    },
+    {
+      "epoch": 1.8641304347826086,
+      "grad_norm": 0.2798942029476166,
+      "learning_rate": 4.9608715311933865e-06,
+      "loss": 0.0546,
+      "step": 115
+    },
+    {
+      "epoch": 1.8804347826086958,
+      "grad_norm": 0.31130167841911316,
+      "learning_rate": 4.955496546118439e-06,
+      "loss": 0.0576,
+      "step": 116
+    },
+    {
+      "epoch": 1.8967391304347827,
+      "grad_norm": 0.23934200406074524,
+      "learning_rate": 4.949779053018519e-06,
+      "loss": 0.0522,
+      "step": 117
+    },
+    {
+      "epoch": 1.9130434782608696,
+      "grad_norm": 0.2684226632118225,
+      "learning_rate": 4.943719849405347e-06,
+      "loss": 0.0596,
+      "step": 118
+    },
+    {
+      "epoch": 1.9293478260869565,
+      "grad_norm": 0.31276896595954895,
+      "learning_rate": 4.937319780454559e-06,
+      "loss": 0.0609,
+      "step": 119
+    },
+    {
+      "epoch": 1.9456521739130435,
+      "grad_norm": 0.2928497791290283,
+      "learning_rate": 4.930579738887827e-06,
+      "loss": 0.0515,
+      "step": 120
+    },
+    {
+      "epoch": 1.9619565217391304,
+      "grad_norm": 0.25487199425697327,
+      "learning_rate": 4.923500664848327e-06,
+      "loss": 0.0565,
+      "step": 121
+    },
+    {
+      "epoch": 1.9782608695652173,
+      "grad_norm": 0.19076956808567047,
+      "learning_rate": 4.9160835457696075e-06,
+      "loss": 0.0541,
+      "step": 122
+    },
+    {
+      "epoch": 1.9945652173913042,
+      "grad_norm": 0.36202409863471985,
+      "learning_rate": 4.9083294162378545e-06,
+      "loss": 0.0572,
+      "step": 123
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.36202409863471985,
+      "learning_rate": 4.900239357847582e-06,
+      "loss": 0.0578,
+      "step": 124
+    },
+    {
+      "epoch": 2.016304347826087,
+      "grad_norm": 0.5418670177459717,
+      "learning_rate": 4.891814499050762e-06,
+      "loss": 0.0504,
+      "step": 125
+    },
+    {
+      "epoch": 2.032608695652174,
+      "grad_norm": 0.24317026138305664,
+      "learning_rate": 4.883056014999423e-06,
+      "loss": 0.0557,
+      "step": 126
+    },
+    {
+      "epoch": 2.0489130434782608,
+      "grad_norm": 0.23591496050357819,
+      "learning_rate": 4.873965127381734e-06,
+      "loss": 0.0567,
+      "step": 127
+    },
+    {
+      "epoch": 2.0652173913043477,
+      "grad_norm": 0.26839157938957214,
+      "learning_rate": 4.864543104251587e-06,
+      "loss": 0.0489,
+      "step": 128
+    },
+    {
+      "epoch": 2.0815217391304346,
+      "grad_norm": 0.23912706971168518,
+      "learning_rate": 4.854791259851735e-06,
+      "loss": 0.0519,
+      "step": 129
+    },
+    {
+      "epoch": 2.097826086956522,
+      "grad_norm": 0.22615790367126465,
+      "learning_rate": 4.844710954430464e-06,
+      "loss": 0.0533,
+      "step": 130
+    },
+    {
+      "epoch": 2.114130434782609,
+      "grad_norm": 0.18881212174892426,
+      "learning_rate": 4.834303594051854e-06,
+      "loss": 0.0509,
+      "step": 131
+    },
+    {
+      "epoch": 2.130434782608696,
+      "grad_norm": 0.20288890600204468,
+      "learning_rate": 4.823570630399665e-06,
+      "loss": 0.0515,
+      "step": 132
+    },
+    {
+      "epoch": 2.1467391304347827,
+      "grad_norm": 0.2495969533920288,
+      "learning_rate": 4.812513560574832e-06,
+      "loss": 0.0593,
+      "step": 133
+    },
+    {
+      "epoch": 2.1630434782608696,
+      "grad_norm": 0.25076112151145935,
+      "learning_rate": 4.8011339268866505e-06,
+      "loss": 0.0546,
+      "step": 134
+    },
+    {
+      "epoch": 2.1793478260869565,
+      "grad_norm": 0.26761433482170105,
+      "learning_rate": 4.789433316637644e-06,
+      "loss": 0.0494,
+      "step": 135
+    },
+    {
+      "epoch": 2.1956521739130435,
+      "grad_norm": 0.22908158600330353,
+      "learning_rate": 4.777413361902152e-06,
+      "loss": 0.0556,
+      "step": 136
+    },
+    {
+      "epoch": 2.2119565217391304,
+      "grad_norm": 0.24989894032478333,
+      "learning_rate": 4.765075739298683e-06,
+      "loss": 0.0457,
+      "step": 137
+    },
+    {
+      "epoch": 2.2282608695652173,
+      "grad_norm": 0.19970546662807465,
+      "learning_rate": 4.752422169756048e-06,
+      "loss": 0.0483,
+      "step": 138
+    },
+    {
+      "epoch": 2.244565217391304,
+      "grad_norm": 0.2547377347946167,
+      "learning_rate": 4.739454418273314e-06,
+      "loss": 0.0562,
+      "step": 139
+    },
+    {
+      "epoch": 2.260869565217391,
+      "grad_norm": 0.30050888657569885,
+      "learning_rate": 4.726174293673612e-06,
+      "loss": 0.0474,
+      "step": 140
+    },
+    {
+      "epoch": 2.2771739130434785,
+      "grad_norm": 0.20995593070983887,
+      "learning_rate": 4.712583648351827e-06,
+      "loss": 0.0486,
+      "step": 141
+    },
+    {
+      "epoch": 2.2934782608695654,
+      "grad_norm": 0.24649159610271454,
+      "learning_rate": 4.698684378016223e-06,
+      "loss": 0.0521,
+      "step": 142
+    },
+    {
+      "epoch": 2.3097826086956523,
+      "grad_norm": 0.23422546684741974,
+      "learning_rate": 4.684478421424007e-06,
+      "loss": 0.0521,
+      "step": 143
+    },
+    {
+      "epoch": 2.3260869565217392,
+      "grad_norm": 0.21018289029598236,
+      "learning_rate": 4.669967760110908e-06,
+      "loss": 0.0503,
+      "step": 144
+    },
+    {
+      "epoch": 2.342391304347826,
+      "grad_norm": 0.20515775680541992,
+      "learning_rate": 4.655154418114774e-06,
+      "loss": 0.0545,
+      "step": 145
+    },
+    {
+      "epoch": 2.358695652173913,
+      "grad_norm": 0.2237028032541275,
+      "learning_rate": 4.6400404616932505e-06,
+      "loss": 0.052,
+      "step": 146
+    },
+    {
+      "epoch": 2.375,
+      "grad_norm": 0.24619129300117493,
+      "learning_rate": 4.624627999035564e-06,
+      "loss": 0.059,
+      "step": 147
+    },
+    {
+      "epoch": 2.391304347826087,
+      "grad_norm": 0.20323814451694489,
+      "learning_rate": 4.608919179968457e-06,
+      "loss": 0.0534,
+      "step": 148
+    },
+    {
+      "epoch": 2.407608695652174,
+      "grad_norm": 0.21665000915527344,
+      "learning_rate": 4.592916195656322e-06,
+      "loss": 0.0505,
+      "step": 149
+    },
+    {
+      "epoch": 2.4239130434782608,
+      "grad_norm": 0.21209590137004852,
+      "learning_rate": 4.576621278295558e-06,
+      "loss": 0.055,
+      "step": 150
+    },
+    {
+      "epoch": 2.4402173913043477,
+      "grad_norm": 0.19232606887817383,
+      "learning_rate": 4.5600367008032135e-06,
+      "loss": 0.0533,
+      "step": 151
+    },
+    {
+      "epoch": 2.4565217391304346,
+      "grad_norm": 0.22477513551712036,
+      "learning_rate": 4.543164776499945e-06,
+      "loss": 0.0544,
+      "step": 152
+    },
+    {
+      "epoch": 2.4728260869565215,
+      "grad_norm": 0.21310777962207794,
+      "learning_rate": 4.5260078587873416e-06,
+      "loss": 0.0534,
+      "step": 153
+    },
+    {
+      "epoch": 2.489130434782609,
+      "grad_norm": 0.2207050621509552,
+      "learning_rate": 4.508568340819654e-06,
+      "loss": 0.0516,
+      "step": 154
+    },
+    {
+      "epoch": 2.505434782608696,
+      "grad_norm": 0.22430899739265442,
+      "learning_rate": 4.490848655169986e-06,
+      "loss": 0.0552,
+      "step": 155
+    },
+    {
+      "epoch": 2.5217391304347827,
+      "grad_norm": 0.2665068805217743,
+      "learning_rate": 4.472851273490985e-06,
+      "loss": 0.0517,
+      "step": 156
+    },
+    {
+      "epoch": 2.5380434782608696,
+      "grad_norm": 0.20904089510440826,
+      "learning_rate": 4.454578706170075e-06,
+      "loss": 0.0477,
+      "step": 157
+    },
+    {
+      "epoch": 2.5543478260869565,
+      "grad_norm": 0.21974575519561768,
+      "learning_rate": 4.436033501979299e-06,
+      "loss": 0.0465,
+      "step": 158
+    },
+    {
+      "epoch": 2.5706521739130435,
+      "grad_norm": 0.2737596333026886,
+      "learning_rate": 4.417218247719794e-06,
+      "loss": 0.0443,
+      "step": 159
+    },
+    {
+      "epoch": 2.5869565217391304,
+      "grad_norm": 0.19713006913661957,
+      "learning_rate": 4.398135567860972e-06,
+      "loss": 0.0565,
+      "step": 160
+    },
+    {
+      "epoch": 2.6032608695652173,
+      "grad_norm": 0.24970802664756775,
+      "learning_rate": 4.378788124174441e-06,
+      "loss": 0.0473,
+      "step": 161
+    },
+    {
+      "epoch": 2.619565217391304,
+      "grad_norm": 0.20846787095069885,
+      "learning_rate": 4.359178615362725e-06,
+      "loss": 0.0511,
+      "step": 162
+    },
+    {
+      "epoch": 2.6358695652173916,
+      "grad_norm": 0.33354219794273376,
+      "learning_rate": 4.33930977668283e-06,
+      "loss": 0.0541,
+      "step": 163
+    },
+    {
+      "epoch": 2.6521739130434785,
+      "grad_norm": 0.23585955798625946,
+      "learning_rate": 4.319184379564716e-06,
+      "loss": 0.0534,
+      "step": 164
+    },
+    {
+      "epoch": 2.6684782608695654,
+      "grad_norm": 0.26923519372940063,
+      "learning_rate": 4.298805231224721e-06,
+      "loss": 0.052,
+      "step": 165
+    },
+    {
+      "epoch": 2.6847826086956523,
+      "grad_norm": 0.20466569066047668,
+      "learning_rate": 4.278175174273989e-06,
+      "loss": 0.0532,
+      "step": 166
+    },
+    {
+      "epoch": 2.7010869565217392,
+      "grad_norm": 0.27908194065093994,
+      "learning_rate": 4.257297086321967e-06,
+      "loss": 0.0497,
+      "step": 167
+    },
+    {
+      "epoch": 2.717391304347826,
+      "grad_norm": 0.29970937967300415,
+      "learning_rate": 4.236173879575022e-06,
+      "loss": 0.0502,
+      "step": 168
+    },
+    {
+      "epoch": 2.733695652173913,
+      "grad_norm": 0.2322796732187271,
+      "learning_rate": 4.2148085004302205e-06,
+      "loss": 0.054,
+      "step": 169
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.1984764039516449,
+      "learning_rate": 4.1932039290643534e-06,
+      "loss": 0.0491,
+      "step": 170
+    },
+    {
+      "epoch": 2.766304347826087,
+      "grad_norm": 0.20822829008102417,
+      "learning_rate": 4.1713631790182366e-06,
+      "loss": 0.0555,
+      "step": 171
+    },
+    {
+      "epoch": 2.782608695652174,
+      "grad_norm": 0.2537862956523895,
+      "learning_rate": 4.149289296776369e-06,
+      "loss": 0.0479,
+      "step": 172
+    },
+    {
+      "epoch": 2.7989130434782608,
+      "grad_norm": 0.20386171340942383,
+      "learning_rate": 4.126985361341984e-06,
+      "loss": 0.049,
+      "step": 173
+    },
+    {
+      "epoch": 2.8152173913043477,
+      "grad_norm": 0.28424644470214844,
+      "learning_rate": 4.104454483807579e-06,
+      "loss": 0.0481,
+      "step": 174
+    },
+    {
+      "epoch": 2.8315217391304346,
+      "grad_norm": 0.2668056786060333,
+      "learning_rate": 4.0816998069209516e-06,
+      "loss": 0.0528,
+      "step": 175
+    },
+    {
+      "epoch": 2.8478260869565215,
+      "grad_norm": 0.2771640419960022,
+      "learning_rate": 4.058724504646834e-06,
+      "loss": 0.0673,
+      "step": 176
+    },
+    {
+      "epoch": 2.8641304347826084,
+      "grad_norm": 0.26568353176116943,
+      "learning_rate": 4.0355317817241705e-06,
+      "loss": 0.0438,
+      "step": 177
+    },
+    {
+      "epoch": 2.880434782608696,
+      "grad_norm": 0.21058987081050873,
+      "learning_rate": 4.012124873219094e-06,
+      "loss": 0.0499,
+      "step": 178
+    },
+    {
+      "epoch": 2.8967391304347827,
+      "grad_norm": 0.27742889523506165,
+      "learning_rate": 3.988507044073687e-06,
+      "loss": 0.047,
+      "step": 179
+    },
+    {
+      "epoch": 2.9130434782608696,
+      "grad_norm": 0.21633900701999664,
+      "learning_rate": 3.964681588650562e-06,
+      "loss": 0.0485,
+      "step": 180
+    },
+    {
+      "epoch": 2.9293478260869565,
+      "grad_norm": 0.21723268926143646,
+      "learning_rate": 3.940651830273342e-06,
+      "loss": 0.0535,
+      "step": 181
+    },
+    {
+      "epoch": 2.9456521739130435,
+      "grad_norm": 0.21648381650447845,
+      "learning_rate": 3.916421120763106e-06,
+      "loss": 0.0469,
+      "step": 182
+    },
+    {
+      "epoch": 2.9619565217391304,
+      "grad_norm": 0.2256888449192047,
+      "learning_rate": 3.891992839970855e-06,
+      "loss": 0.0469,
+      "step": 183
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 366,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 61,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.065859552275333e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-183/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4bdf3f34ad3174d7ffb541641f906b4ea87bd3f0ed6dc8fb586e66791457854
+size 7992

checkpoint-183/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

checkpoint-244/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-244/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-244/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa54d9d69d910103ae897a63a4685f2d2e652f66aabbcfc03c3e331c911fbbd
+size 1291899552

checkpoint-244/added_tokens.json

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

checkpoint-244/global_step242/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10adadfccde736dd8e498de869dac111ab4ff851ea2fe70cc03cc12bb4bd707f
+size 7751120668

checkpoint-244/global_step242/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e3a7b1b426030ead819ed56e78d54c8d1cf38e55da815a67256638a2422ac9e
+size 1396311192

checkpoint-244/latest

@@ -0,0 +1 @@
+global_step242

checkpoint-244/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:667d16212f563863a9889d9dc66bf12b93f83cc5f70a23b485de50f564039849
+size 14244

checkpoint-244/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0846800f5bb7abb340a8341a16a086f1a97a0c762bfaed049cccff6bf7bea00d
+size 1064

checkpoint-244/special_tokens_map.json

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

checkpoint-244/tokenizer.json

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

checkpoint-244/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}