Upload folder using huggingface_hub

checkpoint-234/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: unsloth/Qwen2.5-Coder-1.5B-Instruct
+---
+
+# 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 0.11.1

checkpoint-234/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-1.5B-Instruct",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-234/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5beab5e854d46fce47b6fb8484cfdfe9d5272042e6068194759f9d2369c7b47e
+size 147770496

checkpoint-234/added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
+  "<|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-234/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8db4e8684b1745ddfe2536225909adfc32e8c15ba910f3d109ad58867aaa58a0
+size 74435636

checkpoint-234/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4cd1fe86b1a7fb5088d7a2906b0cb61e4869d95fbfc7c20d29a1bd855a63719
+size 14960

checkpoint-234/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e44ed27029ad3cf3656b178a6c84f721991870fb9a317c715ab29a6df0afe6
+size 14960

checkpoint-234/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28ef82cbdbb129628fa88ac1116ee60fba55ca82a377b960594fe9a61f79623f
+size 14960

checkpoint-234/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed77a6df1b46cdd66183daa169caddec8f852f9e21784484fac807401feda775
+size 14960

checkpoint-234/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ede7b1423721cae7c5a3bccce2b3f83abcf842665a4c5b368aefc719a462de
+size 1064

checkpoint-234/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": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-234/tokenizer_config.json

@@ -0,0 +1,216 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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",
+  "model_max_length": 131072,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-234/trainer_state.json

@@ -0,0 +1,1703 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9968051118210862,
+  "eval_steps": 59,
+  "global_step": 234,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004259850905218318,
+      "grad_norm": 0.42660918831825256,
+      "learning_rate": 2e-05,
+      "loss": 1.4194,
+      "step": 1
+    },
+    {
+      "epoch": 0.004259850905218318,
+      "eval_loss": 1.3981385231018066,
+      "eval_runtime": 17.5749,
+      "eval_samples_per_second": 22.475,
+      "eval_steps_per_second": 2.845,
+      "step": 1
+    },
+    {
+      "epoch": 0.008519701810436636,
+      "grad_norm": 0.38132771849632263,
+      "learning_rate": 4e-05,
+      "loss": 1.4291,
+      "step": 2
+    },
+    {
+      "epoch": 0.012779552715654952,
+      "grad_norm": 0.4677501916885376,
+      "learning_rate": 6e-05,
+      "loss": 1.606,
+      "step": 3
+    },
+    {
+      "epoch": 0.01703940362087327,
+      "grad_norm": 0.4839603900909424,
+      "learning_rate": 8e-05,
+      "loss": 1.5193,
+      "step": 4
+    },
+    {
+      "epoch": 0.021299254526091587,
+      "grad_norm": 0.52900630235672,
+      "learning_rate": 0.0001,
+      "loss": 1.7253,
+      "step": 5
+    },
+    {
+      "epoch": 0.025559105431309903,
+      "grad_norm": 0.4611320495605469,
+      "learning_rate": 0.00012,
+      "loss": 1.4042,
+      "step": 6
+    },
+    {
+      "epoch": 0.029818956336528223,
+      "grad_norm": 0.5078997611999512,
+      "learning_rate": 0.00014,
+      "loss": 1.8641,
+      "step": 7
+    },
+    {
+      "epoch": 0.03407880724174654,
+      "grad_norm": 0.5692968368530273,
+      "learning_rate": 0.00016,
+      "loss": 1.0603,
+      "step": 8
+    },
+    {
+      "epoch": 0.038338658146964855,
+      "grad_norm": 0.5424911379814148,
+      "learning_rate": 0.00018,
+      "loss": 0.9217,
+      "step": 9
+    },
+    {
+      "epoch": 0.042598509052183174,
+      "grad_norm": 0.6595712304115295,
+      "learning_rate": 0.0002,
+      "loss": 1.0443,
+      "step": 10
+    },
+    {
+      "epoch": 0.046858359957401494,
+      "grad_norm": 0.552948534488678,
+      "learning_rate": 0.00019999016517595753,
+      "loss": 0.9727,
+      "step": 11
+    },
+    {
+      "epoch": 0.051118210862619806,
+      "grad_norm": 0.523713231086731,
+      "learning_rate": 0.00019996066263830531,
+      "loss": 1.0042,
+      "step": 12
+    },
+    {
+      "epoch": 0.055378061767838126,
+      "grad_norm": 0.3326718807220459,
+      "learning_rate": 0.0001999114981900887,
+      "loss": 0.6851,
+      "step": 13
+    },
+    {
+      "epoch": 0.059637912673056445,
+      "grad_norm": 0.40246546268463135,
+      "learning_rate": 0.00019984268150178167,
+      "loss": 0.6865,
+      "step": 14
+    },
+    {
+      "epoch": 0.06389776357827476,
+      "grad_norm": 0.3299888074398041,
+      "learning_rate": 0.00019975422610938462,
+      "loss": 0.6413,
+      "step": 15
+    },
+    {
+      "epoch": 0.06815761448349308,
+      "grad_norm": 0.321532666683197,
+      "learning_rate": 0.00019964614941176195,
+      "loss": 0.6425,
+      "step": 16
+    },
+    {
+      "epoch": 0.0724174653887114,
+      "grad_norm": 0.30551549792289734,
+      "learning_rate": 0.0001995184726672197,
+      "loss": 0.6573,
+      "step": 17
+    },
+    {
+      "epoch": 0.07667731629392971,
+      "grad_norm": 0.3162730932235718,
+      "learning_rate": 0.00019937122098932428,
+      "loss": 0.7957,
+      "step": 18
+    },
+    {
+      "epoch": 0.08093716719914804,
+      "grad_norm": 0.2646523714065552,
+      "learning_rate": 0.00019920442334196248,
+      "loss": 0.6842,
+      "step": 19
+    },
+    {
+      "epoch": 0.08519701810436635,
+      "grad_norm": 0.35260164737701416,
+      "learning_rate": 0.00019901811253364456,
+      "loss": 0.7045,
+      "step": 20
+    },
+    {
+      "epoch": 0.08945686900958466,
+      "grad_norm": 0.36994901299476624,
+      "learning_rate": 0.00019881232521105089,
+      "loss": 0.7506,
+      "step": 21
+    },
+    {
+      "epoch": 0.09371671991480299,
+      "grad_norm": 0.3145638108253479,
+      "learning_rate": 0.0001985871018518236,
+      "loss": 0.6522,
+      "step": 22
+    },
+    {
+      "epoch": 0.0979765708200213,
+      "grad_norm": 0.28740495443344116,
+      "learning_rate": 0.00019834248675660486,
+      "loss": 0.5763,
+      "step": 23
+    },
+    {
+      "epoch": 0.10223642172523961,
+      "grad_norm": 0.29527685046195984,
+      "learning_rate": 0.00019807852804032305,
+      "loss": 0.8533,
+      "step": 24
+    },
+    {
+      "epoch": 0.10649627263045794,
+      "grad_norm": 0.3023378849029541,
+      "learning_rate": 0.00019779527762272877,
+      "loss": 0.738,
+      "step": 25
+    },
+    {
+      "epoch": 0.11075612353567625,
+      "grad_norm": 0.2749658524990082,
+      "learning_rate": 0.00019749279121818235,
+      "loss": 0.6354,
+      "step": 26
+    },
+    {
+      "epoch": 0.11501597444089456,
+      "grad_norm": 0.3914307951927185,
+      "learning_rate": 0.0001971711283246951,
+      "loss": 0.8604,
+      "step": 27
+    },
+    {
+      "epoch": 0.11927582534611289,
+      "grad_norm": 0.47873714566230774,
+      "learning_rate": 0.00019683035221222618,
+      "loss": 0.7972,
+      "step": 28
+    },
+    {
+      "epoch": 0.1235356762513312,
+      "grad_norm": 0.22174575924873352,
+      "learning_rate": 0.0001964705299102376,
+      "loss": 0.4385,
+      "step": 29
+    },
+    {
+      "epoch": 0.12779552715654952,
+      "grad_norm": 0.244963139295578,
+      "learning_rate": 0.00019609173219450998,
+      "loss": 0.7168,
+      "step": 30
+    },
+    {
+      "epoch": 0.13205537806176784,
+      "grad_norm": 0.32758575677871704,
+      "learning_rate": 0.0001956940335732209,
+      "loss": 0.7231,
+      "step": 31
+    },
+    {
+      "epoch": 0.13631522896698617,
+      "grad_norm": 0.21992172300815582,
+      "learning_rate": 0.00019527751227228963,
+      "loss": 0.662,
+      "step": 32
+    },
+    {
+      "epoch": 0.14057507987220447,
+      "grad_norm": 0.2899262309074402,
+      "learning_rate": 0.0001948422502199903,
+      "loss": 0.4651,
+      "step": 33
+    },
+    {
+      "epoch": 0.1448349307774228,
+      "grad_norm": 0.23878340423107147,
+      "learning_rate": 0.00019438833303083678,
+      "loss": 0.5367,
+      "step": 34
+    },
+    {
+      "epoch": 0.14909478168264112,
+      "grad_norm": 0.20475314557552338,
+      "learning_rate": 0.0001939158499887428,
+      "loss": 0.4024,
+      "step": 35
+    },
+    {
+      "epoch": 0.15335463258785942,
+      "grad_norm": 0.25068745017051697,
+      "learning_rate": 0.00019342489402945998,
+      "loss": 0.6575,
+      "step": 36
+    },
+    {
+      "epoch": 0.15761448349307774,
+      "grad_norm": 0.3811924159526825,
+      "learning_rate": 0.00019291556172229785,
+      "loss": 0.6405,
+      "step": 37
+    },
+    {
+      "epoch": 0.16187433439829607,
+      "grad_norm": 0.2627577483654022,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 0.6961,
+      "step": 38
+    },
+    {
+      "epoch": 0.16613418530351437,
+      "grad_norm": 0.32665154337882996,
+      "learning_rate": 0.00019184217239468212,
+      "loss": 0.6983,
+      "step": 39
+    },
+    {
+      "epoch": 0.1703940362087327,
+      "grad_norm": 0.24597743153572083,
+      "learning_rate": 0.00019127832650613189,
+      "loss": 0.54,
+      "step": 40
+    },
+    {
+      "epoch": 0.17465388711395102,
+      "grad_norm": 0.2611660361289978,
+      "learning_rate": 0.00019069652649198005,
+      "loss": 0.6281,
+      "step": 41
+    },
+    {
+      "epoch": 0.17891373801916932,
+      "grad_norm": 0.2969326078891754,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 0.6817,
+      "step": 42
+    },
+    {
+      "epoch": 0.18317358892438765,
+      "grad_norm": 0.27561935782432556,
+      "learning_rate": 0.00018947952534793661,
+      "loss": 0.626,
+      "step": 43
+    },
+    {
+      "epoch": 0.18743343982960597,
+      "grad_norm": 0.33468887209892273,
+      "learning_rate": 0.00018884456359788724,
+      "loss": 0.7383,
+      "step": 44
+    },
+    {
+      "epoch": 0.19169329073482427,
+      "grad_norm": 0.2937297224998474,
+      "learning_rate": 0.0001881921264348355,
+      "loss": 0.6972,
+      "step": 45
+    },
+    {
+      "epoch": 0.1959531416400426,
+      "grad_norm": 0.33218011260032654,
+      "learning_rate": 0.00018752234219087538,
+      "loss": 0.6749,
+      "step": 46
+    },
+    {
+      "epoch": 0.20021299254526093,
+      "grad_norm": 0.2661404311656952,
+      "learning_rate": 0.00018683534261021057,
+      "loss": 0.4882,
+      "step": 47
+    },
+    {
+      "epoch": 0.20447284345047922,
+      "grad_norm": 0.2451002150774002,
+      "learning_rate": 0.00018613126282324092,
+      "loss": 0.637,
+      "step": 48
+    },
+    {
+      "epoch": 0.20873269435569755,
+      "grad_norm": 0.27517661452293396,
+      "learning_rate": 0.00018541024131998274,
+      "loss": 0.5483,
+      "step": 49
+    },
+    {
+      "epoch": 0.21299254526091588,
+      "grad_norm": 0.24373459815979004,
+      "learning_rate": 0.00018467241992282843,
+      "loss": 0.5112,
+      "step": 50
+    },
+    {
+      "epoch": 0.21725239616613418,
+      "grad_norm": 0.3239864408969879,
+      "learning_rate": 0.00018391794375865024,
+      "loss": 0.8005,
+      "step": 51
+    },
+    {
+      "epoch": 0.2215122470713525,
+      "grad_norm": 0.29262682795524597,
+      "learning_rate": 0.00018314696123025454,
+      "loss": 0.6769,
+      "step": 52
+    },
+    {
+      "epoch": 0.22577209797657083,
+      "grad_norm": 0.28277888894081116,
+      "learning_rate": 0.00018235962398719147,
+      "loss": 0.6892,
+      "step": 53
+    },
+    {
+      "epoch": 0.23003194888178913,
+      "grad_norm": 0.41741546988487244,
+      "learning_rate": 0.00018155608689592604,
+      "loss": 0.6763,
+      "step": 54
+    },
+    {
+      "epoch": 0.23429179978700745,
+      "grad_norm": 0.2734082043170929,
+      "learning_rate": 0.00018073650800937624,
+      "loss": 0.697,
+      "step": 55
+    },
+    {
+      "epoch": 0.23855165069222578,
+      "grad_norm": 0.2646290957927704,
+      "learning_rate": 0.00017990104853582493,
+      "loss": 0.5936,
+      "step": 56
+    },
+    {
+      "epoch": 0.24281150159744408,
+      "grad_norm": 0.27723610401153564,
+      "learning_rate": 0.00017904987280721035,
+      "loss": 0.5875,
+      "step": 57
+    },
+    {
+      "epoch": 0.2470713525026624,
+      "grad_norm": 0.2668153643608093,
+      "learning_rate": 0.000178183148246803,
+      "loss": 0.5219,
+      "step": 58
+    },
+    {
+      "epoch": 0.25133120340788073,
+      "grad_norm": 0.29033368825912476,
+      "learning_rate": 0.0001773010453362737,
+      "loss": 0.5997,
+      "step": 59
+    },
+    {
+      "epoch": 0.25133120340788073,
+      "eval_loss": 0.5784963965415955,
+      "eval_runtime": 17.4317,
+      "eval_samples_per_second": 22.66,
+      "eval_steps_per_second": 2.868,
+      "step": 59
+    },
+    {
+      "epoch": 0.25559105431309903,
+      "grad_norm": 0.2783537209033966,
+      "learning_rate": 0.00017640373758216077,
+      "loss": 0.483,
+      "step": 60
+    },
+    {
+      "epoch": 0.2598509052183174,
+      "grad_norm": 0.31082215905189514,
+      "learning_rate": 0.0001754914014817416,
+      "loss": 0.6473,
+      "step": 61
+    },
+    {
+      "epoch": 0.2641107561235357,
+      "grad_norm": 0.3206618130207062,
+      "learning_rate": 0.00017456421648831655,
+      "loss": 0.6289,
+      "step": 62
+    },
+    {
+      "epoch": 0.268370607028754,
+      "grad_norm": 0.2875254154205322,
+      "learning_rate": 0.00017362236497591094,
+      "loss": 0.594,
+      "step": 63
+    },
+    {
+      "epoch": 0.27263045793397234,
+      "grad_norm": 0.22950579226016998,
+      "learning_rate": 0.0001726660322034027,
+      "loss": 0.3886,
+      "step": 64
+    },
+    {
+      "epoch": 0.27689030883919064,
+      "grad_norm": 0.24293649196624756,
+      "learning_rate": 0.00017169540627808274,
+      "loss": 0.6129,
+      "step": 65
+    },
+    {
+      "epoch": 0.28115015974440893,
+      "grad_norm": 0.2611636519432068,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.6891,
+      "step": 66
+    },
+    {
+      "epoch": 0.2854100106496273,
+      "grad_norm": 0.284407377243042,
+      "learning_rate": 0.00016971204141768233,
+      "loss": 0.516,
+      "step": 67
+    },
+    {
+      "epoch": 0.2896698615548456,
+      "grad_norm": 0.21485944092273712,
+      "learning_rate": 0.00016869969260349018,
+      "loss": 0.3826,
+      "step": 68
+    },
+    {
+      "epoch": 0.2939297124600639,
+      "grad_norm": 0.29337963461875916,
+      "learning_rate": 0.00016767383080152742,
+      "loss": 0.5696,
+      "step": 69
+    },
+    {
+      "epoch": 0.29818956336528224,
+      "grad_norm": 0.27099764347076416,
+      "learning_rate": 0.0001666346577952004,
+      "loss": 0.4708,
+      "step": 70
+    },
+    {
+      "epoch": 0.30244941427050054,
+      "grad_norm": 0.29055824875831604,
+      "learning_rate": 0.00016558237798618245,
+      "loss": 0.5844,
+      "step": 71
+    },
+    {
+      "epoch": 0.30670926517571884,
+      "grad_norm": 0.22874757647514343,
+      "learning_rate": 0.00016451719835420877,
+      "loss": 0.4412,
+      "step": 72
+    },
+    {
+      "epoch": 0.3109691160809372,
+      "grad_norm": 0.2926221489906311,
+      "learning_rate": 0.00016343932841636456,
+      "loss": 0.5757,
+      "step": 73
+    },
+    {
+      "epoch": 0.3152289669861555,
+      "grad_norm": 0.30070438981056213,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 0.6063,
+      "step": 74
+    },
+    {
+      "epoch": 0.3194888178913738,
+      "grad_norm": 0.2475481927394867,
+      "learning_rate": 0.00016124636813039502,
+      "loss": 0.5056,
+      "step": 75
+    },
+    {
+      "epoch": 0.32374866879659214,
+      "grad_norm": 0.2851349711418152,
+      "learning_rate": 0.00016013170912984058,
+      "loss": 0.7547,
+      "step": 76
+    },
+    {
+      "epoch": 0.32800851970181044,
+      "grad_norm": 0.25569260120391846,
+      "learning_rate": 0.00015900522243371282,
+      "loss": 0.5168,
+      "step": 77
+    },
+    {
+      "epoch": 0.33226837060702874,
+      "grad_norm": 0.3774610757827759,
+      "learning_rate": 0.0001578671296179806,
+      "loss": 0.6691,
+      "step": 78
+    },
+    {
+      "epoch": 0.3365282215122471,
+      "grad_norm": 0.2339468151330948,
+      "learning_rate": 0.00015671765454149559,
+      "loss": 0.5021,
+      "step": 79
+    },
+    {
+      "epoch": 0.3407880724174654,
+      "grad_norm": 0.3066350519657135,
+      "learning_rate": 0.00015555702330196023,
+      "loss": 0.6838,
+      "step": 80
+    },
+    {
+      "epoch": 0.3450479233226837,
+      "grad_norm": 0.271908164024353,
+      "learning_rate": 0.00015438546419145488,
+      "loss": 0.4837,
+      "step": 81
+    },
+    {
+      "epoch": 0.34930777422790205,
+      "grad_norm": 0.304290771484375,
+      "learning_rate": 0.00015320320765153367,
+      "loss": 0.6768,
+      "step": 82
+    },
+    {
+      "epoch": 0.35356762513312034,
+      "grad_norm": 0.25685280561447144,
+      "learning_rate": 0.00015201048622789747,
+      "loss": 0.4335,
+      "step": 83
+    },
+    {
+      "epoch": 0.35782747603833864,
+      "grad_norm": 0.3003567159175873,
+      "learning_rate": 0.00015080753452465296,
+      "loss": 0.5836,
+      "step": 84
+    },
+    {
+      "epoch": 0.362087326943557,
+      "grad_norm": 0.2585873007774353,
+      "learning_rate": 0.0001495945891581668,
+      "loss": 0.5391,
+      "step": 85
+    },
+    {
+      "epoch": 0.3663471778487753,
+      "grad_norm": 0.30791282653808594,
+      "learning_rate": 0.000148371888710524,
+      "loss": 0.5103,
+      "step": 86
+    },
+    {
+      "epoch": 0.3706070287539936,
+      "grad_norm": 0.23016773164272308,
+      "learning_rate": 0.0001471396736825998,
+      "loss": 0.4269,
+      "step": 87
+    },
+    {
+      "epoch": 0.37486687965921195,
+      "grad_norm": 0.3137454390525818,
+      "learning_rate": 0.00014589818644675378,
+      "loss": 0.5116,
+      "step": 88
+    },
+    {
+      "epoch": 0.37912673056443025,
+      "grad_norm": 0.28078484535217285,
+      "learning_rate": 0.00014464767119915629,
+      "loss": 0.4388,
+      "step": 89
+    },
+    {
+      "epoch": 0.38338658146964855,
+      "grad_norm": 0.3163893222808838,
+      "learning_rate": 0.00014338837391175582,
+      "loss": 0.6122,
+      "step": 90
+    },
+    {
+      "epoch": 0.3876464323748669,
+      "grad_norm": 0.34674668312072754,
+      "learning_rate": 0.0001421205422838971,
+      "loss": 0.7114,
+      "step": 91
+    },
+    {
+      "epoch": 0.3919062832800852,
+      "grad_norm": 0.2210942953824997,
+      "learning_rate": 0.00014084442569359964,
+      "loss": 0.3351,
+      "step": 92
+    },
+    {
+      "epoch": 0.3961661341853035,
+      "grad_norm": 0.30586308240890503,
+      "learning_rate": 0.0001395602751485059,
+      "loss": 0.4845,
+      "step": 93
+    },
+    {
+      "epoch": 0.40042598509052185,
+      "grad_norm": 0.2695784568786621,
+      "learning_rate": 0.000138268343236509,
+      "loss": 0.4992,
+      "step": 94
+    },
+    {
+      "epoch": 0.40468583599574015,
+      "grad_norm": 0.2989813983440399,
+      "learning_rate": 0.00013696888407606952,
+      "loss": 0.585,
+      "step": 95
+    },
+    {
+      "epoch": 0.40894568690095845,
+      "grad_norm": 0.2759920656681061,
+      "learning_rate": 0.0001356621532662313,
+      "loss": 0.4492,
+      "step": 96
+    },
+    {
+      "epoch": 0.4132055378061768,
+      "grad_norm": 0.33117353916168213,
+      "learning_rate": 0.0001343484078363461,
+      "loss": 0.5606,
+      "step": 97
+    },
+    {
+      "epoch": 0.4174653887113951,
+      "grad_norm": 0.24572253227233887,
+      "learning_rate": 0.00013302790619551674,
+      "loss": 0.3261,
+      "step": 98
+    },
+    {
+      "epoch": 0.4217252396166134,
+      "grad_norm": 0.322480171918869,
+      "learning_rate": 0.00013170090808176883,
+      "loss": 0.5527,
+      "step": 99
+    },
+    {
+      "epoch": 0.42598509052183176,
+      "grad_norm": 0.3101179301738739,
+      "learning_rate": 0.00013036767451096148,
+      "loss": 0.5419,
+      "step": 100
+    },
+    {
+      "epoch": 0.43024494142705005,
+      "grad_norm": 0.3218703269958496,
+      "learning_rate": 0.00012902846772544624,
+      "loss": 0.5441,
+      "step": 101
+    },
+    {
+      "epoch": 0.43450479233226835,
+      "grad_norm": 0.26214686036109924,
+      "learning_rate": 0.00012768355114248494,
+      "loss": 0.5388,
+      "step": 102
+    },
+    {
+      "epoch": 0.4387646432374867,
+      "grad_norm": 0.421612411737442,
+      "learning_rate": 0.00012633318930243648,
+      "loss": 0.7557,
+      "step": 103
+    },
+    {
+      "epoch": 0.443024494142705,
+      "grad_norm": 0.5120344758033752,
+      "learning_rate": 0.0001249776478167227,
+      "loss": 0.7028,
+      "step": 104
+    },
+    {
+      "epoch": 0.4472843450479233,
+      "grad_norm": 0.27614736557006836,
+      "learning_rate": 0.00012361719331558345,
+      "loss": 0.3954,
+      "step": 105
+    },
+    {
+      "epoch": 0.45154419595314166,
+      "grad_norm": 0.269520103931427,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 0.4851,
+      "step": 106
+    },
+    {
+      "epoch": 0.45580404685835996,
+      "grad_norm": 0.2739225924015045,
+      "learning_rate": 0.000120882616567217,
+      "loss": 0.4907,
+      "step": 107
+    },
+    {
+      "epoch": 0.46006389776357826,
+      "grad_norm": 0.33920663595199585,
+      "learning_rate": 0.00011950903220161285,
+      "loss": 0.6288,
+      "step": 108
+    },
+    {
+      "epoch": 0.4643237486687966,
+      "grad_norm": 0.279832124710083,
+      "learning_rate": 0.00011813161047802985,
+      "loss": 0.447,
+      "step": 109
+    },
+    {
+      "epoch": 0.4685835995740149,
+      "grad_norm": 0.31790605187416077,
+      "learning_rate": 0.00011675062233047364,
+      "loss": 0.5933,
+      "step": 110
+    },
+    {
+      "epoch": 0.4728434504792332,
+      "grad_norm": 0.24926939606666565,
+      "learning_rate": 0.000115366339394453,
+      "loss": 0.4061,
+      "step": 111
+    },
+    {
+      "epoch": 0.47710330138445156,
+      "grad_norm": 0.3327280282974243,
+      "learning_rate": 0.00011397903395354996,
+      "loss": 0.484,
+      "step": 112
+    },
+    {
+      "epoch": 0.48136315228966986,
+      "grad_norm": 0.37822094559669495,
+      "learning_rate": 0.00011258897888586255,
+      "loss": 0.6416,
+      "step": 113
+    },
+    {
+      "epoch": 0.48562300319488816,
+      "grad_norm": 0.35605669021606445,
+      "learning_rate": 0.00011119644761033078,
+      "loss": 0.6136,
+      "step": 114
+    },
+    {
+      "epoch": 0.4898828541001065,
+      "grad_norm": 0.3513132929801941,
+      "learning_rate": 0.0001098017140329561,
+      "loss": 0.6299,
+      "step": 115
+    },
+    {
+      "epoch": 0.4941427050053248,
+      "grad_norm": 0.3040708899497986,
+      "learning_rate": 0.00010840505249292476,
+      "loss": 0.4658,
+      "step": 116
+    },
+    {
+      "epoch": 0.4984025559105431,
+      "grad_norm": 0.19006308913230896,
+      "learning_rate": 0.00010700673770864673,
+      "loss": 0.2694,
+      "step": 117
+    },
+    {
+      "epoch": 0.5026624068157615,
+      "grad_norm": 0.30643633008003235,
+      "learning_rate": 0.00010560704472371919,
+      "loss": 0.4492,
+      "step": 118
+    },
+    {
+      "epoch": 0.5026624068157615,
+      "eval_loss": 0.5326976180076599,
+      "eval_runtime": 17.5872,
+      "eval_samples_per_second": 22.46,
+      "eval_steps_per_second": 2.843,
+      "step": 118
+    },
+    {
+      "epoch": 0.5069222577209798,
+      "grad_norm": 0.3698013722896576,
+      "learning_rate": 0.00010420624885282653,
+      "loss": 0.6993,
+      "step": 119
+    },
+    {
+      "epoch": 0.5111821086261981,
+      "grad_norm": 0.2801634967327118,
+      "learning_rate": 0.0001028046256275869,
+      "loss": 0.4059,
+      "step": 120
+    },
+    {
+      "epoch": 0.5154419595314164,
+      "grad_norm": 0.2864643931388855,
+      "learning_rate": 0.00010140245074235624,
+      "loss": 0.5024,
+      "step": 121
+    },
+    {
+      "epoch": 0.5197018104366348,
+      "grad_norm": 0.30105265974998474,
+      "learning_rate": 0.0001,
+      "loss": 0.6774,
+      "step": 122
+    },
+    {
+      "epoch": 0.5239616613418531,
+      "grad_norm": 0.39152050018310547,
+      "learning_rate": 9.859754925764378e-05,
+      "loss": 0.625,
+      "step": 123
+    },
+    {
+      "epoch": 0.5282215122470714,
+      "grad_norm": 0.3618883192539215,
+      "learning_rate": 9.719537437241312e-05,
+      "loss": 0.6978,
+      "step": 124
+    },
+    {
+      "epoch": 0.5324813631522897,
+      "grad_norm": 0.23670899868011475,
+      "learning_rate": 9.579375114717351e-05,
+      "loss": 0.3379,
+      "step": 125
+    },
+    {
+      "epoch": 0.536741214057508,
+      "grad_norm": 0.3124864101409912,
+      "learning_rate": 9.439295527628081e-05,
+      "loss": 0.525,
+      "step": 126
+    },
+    {
+      "epoch": 0.5410010649627263,
+      "grad_norm": 0.3667398989200592,
+      "learning_rate": 9.299326229135326e-05,
+      "loss": 0.6164,
+      "step": 127
+    },
+    {
+      "epoch": 0.5452609158679447,
+      "grad_norm": 0.2894105613231659,
+      "learning_rate": 9.159494750707526e-05,
+      "loss": 0.4335,
+      "step": 128
+    },
+    {
+      "epoch": 0.549520766773163,
+      "grad_norm": 0.30680200457572937,
+      "learning_rate": 9.019828596704394e-05,
+      "loss": 0.4507,
+      "step": 129
+    },
+    {
+      "epoch": 0.5537806176783813,
+      "grad_norm": 0.3676758110523224,
+      "learning_rate": 8.880355238966923e-05,
+      "loss": 0.5955,
+      "step": 130
+    },
+    {
+      "epoch": 0.5580404685835996,
+      "grad_norm": 0.3194178342819214,
+      "learning_rate": 8.741102111413748e-05,
+      "loss": 0.5675,
+      "step": 131
+    },
+    {
+      "epoch": 0.5623003194888179,
+      "grad_norm": 0.29750558733940125,
+      "learning_rate": 8.602096604645009e-05,
+      "loss": 0.5785,
+      "step": 132
+    },
+    {
+      "epoch": 0.5665601703940362,
+      "grad_norm": 0.37204545736312866,
+      "learning_rate": 8.463366060554698e-05,
+      "loss": 0.612,
+      "step": 133
+    },
+    {
+      "epoch": 0.5708200212992546,
+      "grad_norm": 0.36891940236091614,
+      "learning_rate": 8.324937766952638e-05,
+      "loss": 0.5463,
+      "step": 134
+    },
+    {
+      "epoch": 0.5750798722044729,
+      "grad_norm": 0.2863575518131256,
+      "learning_rate": 8.186838952197018e-05,
+      "loss": 0.4884,
+      "step": 135
+    },
+    {
+      "epoch": 0.5793397231096912,
+      "grad_norm": 0.354523241519928,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.7727,
+      "step": 136
+    },
+    {
+      "epoch": 0.5835995740149095,
+      "grad_norm": 0.30339759588241577,
+      "learning_rate": 7.911738343278304e-05,
+      "loss": 0.5543,
+      "step": 137
+    },
+    {
+      "epoch": 0.5878594249201278,
+      "grad_norm": 0.27778202295303345,
+      "learning_rate": 7.774790660436858e-05,
+      "loss": 0.4716,
+      "step": 138
+    },
+    {
+      "epoch": 0.5921192758253461,
+      "grad_norm": 0.38618960976600647,
+      "learning_rate": 7.63828066844166e-05,
+      "loss": 0.6519,
+      "step": 139
+    },
+    {
+      "epoch": 0.5963791267305645,
+      "grad_norm": 0.3573627769947052,
+      "learning_rate": 7.502235218327731e-05,
+      "loss": 0.5128,
+      "step": 140
+    },
+    {
+      "epoch": 0.6006389776357828,
+      "grad_norm": 0.30529165267944336,
+      "learning_rate": 7.366681069756352e-05,
+      "loss": 0.5184,
+      "step": 141
+    },
+    {
+      "epoch": 0.6048988285410011,
+      "grad_norm": 0.2819828987121582,
+      "learning_rate": 7.231644885751507e-05,
+      "loss": 0.4259,
+      "step": 142
+    },
+    {
+      "epoch": 0.6091586794462194,
+      "grad_norm": 0.32307252287864685,
+      "learning_rate": 7.097153227455379e-05,
+      "loss": 0.6048,
+      "step": 143
+    },
+    {
+      "epoch": 0.6134185303514377,
+      "grad_norm": 0.31262722611427307,
+      "learning_rate": 6.963232548903853e-05,
+      "loss": 0.4834,
+      "step": 144
+    },
+    {
+      "epoch": 0.617678381256656,
+      "grad_norm": 0.318851500749588,
+      "learning_rate": 6.829909191823121e-05,
+      "loss": 0.5011,
+      "step": 145
+    },
+    {
+      "epoch": 0.6219382321618744,
+      "grad_norm": 0.44246405363082886,
+      "learning_rate": 6.697209380448333e-05,
+      "loss": 0.4384,
+      "step": 146
+    },
+    {
+      "epoch": 0.6261980830670927,
+      "grad_norm": 0.3459945023059845,
+      "learning_rate": 6.565159216365389e-05,
+      "loss": 0.5657,
+      "step": 147
+    },
+    {
+      "epoch": 0.630457933972311,
+      "grad_norm": 0.33843329548835754,
+      "learning_rate": 6.43378467337687e-05,
+      "loss": 0.5711,
+      "step": 148
+    },
+    {
+      "epoch": 0.6347177848775293,
+      "grad_norm": 0.3812694549560547,
+      "learning_rate": 6.30311159239305e-05,
+      "loss": 0.6142,
+      "step": 149
+    },
+    {
+      "epoch": 0.6389776357827476,
+      "grad_norm": 0.29333916306495667,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.585,
+      "step": 150
+    },
+    {
+      "epoch": 0.6432374866879659,
+      "grad_norm": 0.2884041666984558,
+      "learning_rate": 6.043972485149414e-05,
+      "loss": 0.4866,
+      "step": 151
+    },
+    {
+      "epoch": 0.6474973375931843,
+      "grad_norm": 0.33954814076423645,
+      "learning_rate": 5.9155574306400395e-05,
+      "loss": 0.571,
+      "step": 152
+    },
+    {
+      "epoch": 0.6517571884984026,
+      "grad_norm": 0.33935782313346863,
+      "learning_rate": 5.787945771610296e-05,
+      "loss": 0.5037,
+      "step": 153
+    },
+    {
+      "epoch": 0.6560170394036209,
+      "grad_norm": 0.27371054887771606,
+      "learning_rate": 5.6611626088244194e-05,
+      "loss": 0.3322,
+      "step": 154
+    },
+    {
+      "epoch": 0.6602768903088392,
+      "grad_norm": 0.30788496136665344,
+      "learning_rate": 5.5352328800843724e-05,
+      "loss": 0.4454,
+      "step": 155
+    },
+    {
+      "epoch": 0.6645367412140575,
+      "grad_norm": 0.34366151690483093,
+      "learning_rate": 5.410181355324622e-05,
+      "loss": 0.5788,
+      "step": 156
+    },
+    {
+      "epoch": 0.6687965921192758,
+      "grad_norm": 0.33698371052742004,
+      "learning_rate": 5.286032631740023e-05,
+      "loss": 0.4378,
+      "step": 157
+    },
+    {
+      "epoch": 0.6730564430244942,
+      "grad_norm": 0.4181162416934967,
+      "learning_rate": 5.162811128947602e-05,
+      "loss": 0.5367,
+      "step": 158
+    },
+    {
+      "epoch": 0.6773162939297125,
+      "grad_norm": 0.4480881690979004,
+      "learning_rate": 5.0405410841833253e-05,
+      "loss": 0.6633,
+      "step": 159
+    },
+    {
+      "epoch": 0.6815761448349308,
+      "grad_norm": 0.37488028407096863,
+      "learning_rate": 4.919246547534708e-05,
+      "loss": 0.5402,
+      "step": 160
+    },
+    {
+      "epoch": 0.6858359957401491,
+      "grad_norm": 0.2964366376399994,
+      "learning_rate": 4.7989513772102537e-05,
+      "loss": 0.4109,
+      "step": 161
+    },
+    {
+      "epoch": 0.6900958466453674,
+      "grad_norm": 0.35376259684562683,
+      "learning_rate": 4.6796792348466356e-05,
+      "loss": 0.636,
+      "step": 162
+    },
+    {
+      "epoch": 0.6943556975505857,
+      "grad_norm": 0.3158915638923645,
+      "learning_rate": 4.561453580854516e-05,
+      "loss": 0.4893,
+      "step": 163
+    },
+    {
+      "epoch": 0.6986155484558041,
+      "grad_norm": 0.420785516500473,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.7147,
+      "step": 164
+    },
+    {
+      "epoch": 0.7028753993610224,
+      "grad_norm": 0.3272782564163208,
+      "learning_rate": 4.328234545850442e-05,
+      "loss": 0.3444,
+      "step": 165
+    },
+    {
+      "epoch": 0.7071352502662407,
+      "grad_norm": 0.30052492022514343,
+      "learning_rate": 4.213287038201943e-05,
+      "loss": 0.5209,
+      "step": 166
+    },
+    {
+      "epoch": 0.711395101171459,
+      "grad_norm": 0.37648481130599976,
+      "learning_rate": 4.0994777566287204e-05,
+      "loss": 0.684,
+      "step": 167
+    },
+    {
+      "epoch": 0.7156549520766773,
+      "grad_norm": 0.3135606646537781,
+      "learning_rate": 3.9868290870159405e-05,
+      "loss": 0.4871,
+      "step": 168
+    },
+    {
+      "epoch": 0.7199148029818956,
+      "grad_norm": 0.33847576379776,
+      "learning_rate": 3.875363186960499e-05,
+      "loss": 0.5294,
+      "step": 169
+    },
+    {
+      "epoch": 0.724174653887114,
+      "grad_norm": 0.3337070047855377,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 0.4425,
+      "step": 170
+    },
+    {
+      "epoch": 0.7284345047923323,
+      "grad_norm": 0.4173165261745453,
+      "learning_rate": 3.6560671583635467e-05,
+      "loss": 0.637,
+      "step": 171
+    },
+    {
+      "epoch": 0.7326943556975506,
+      "grad_norm": 0.41098451614379883,
+      "learning_rate": 3.548280164579126e-05,
+      "loss": 0.52,
+      "step": 172
+    },
+    {
+      "epoch": 0.7369542066027689,
+      "grad_norm": 0.3789665699005127,
+      "learning_rate": 3.4417622013817595e-05,
+      "loss": 0.5995,
+      "step": 173
+    },
+    {
+      "epoch": 0.7412140575079872,
+      "grad_norm": 0.3996846675872803,
+      "learning_rate": 3.336534220479961e-05,
+      "loss": 0.6237,
+      "step": 174
+    },
+    {
+      "epoch": 0.7454739084132055,
+      "grad_norm": 0.3990687131881714,
+      "learning_rate": 3.2326169198472556e-05,
+      "loss": 0.555,
+      "step": 175
+    },
+    {
+      "epoch": 0.7497337593184239,
+      "grad_norm": 0.32280924916267395,
+      "learning_rate": 3.130030739650983e-05,
+      "loss": 0.4742,
+      "step": 176
+    },
+    {
+      "epoch": 0.7539936102236422,
+      "grad_norm": 0.4192362129688263,
+      "learning_rate": 3.0287958582317676e-05,
+      "loss": 0.6569,
+      "step": 177
+    },
+    {
+      "epoch": 0.7539936102236422,
+      "eval_loss": 0.5110090970993042,
+      "eval_runtime": 20.8066,
+      "eval_samples_per_second": 18.984,
+      "eval_steps_per_second": 2.403,
+      "step": 177
+    },
+    {
+      "epoch": 0.7582534611288605,
+      "grad_norm": 0.35410746932029724,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.4828,
+      "step": 178
+    },
+    {
+      "epoch": 0.7625133120340788,
+      "grad_norm": 0.4463326036930084,
+      "learning_rate": 2.8304593721917285e-05,
+      "loss": 0.6976,
+      "step": 179
+    },
+    {
+      "epoch": 0.7667731629392971,
+      "grad_norm": 0.29797378182411194,
+      "learning_rate": 2.7333967796597315e-05,
+      "loss": 0.564,
+      "step": 180
+    },
+    {
+      "epoch": 0.7710330138445154,
+      "grad_norm": 0.31337812542915344,
+      "learning_rate": 2.6377635024089087e-05,
+      "loss": 0.5607,
+      "step": 181
+    },
+    {
+      "epoch": 0.7752928647497338,
+      "grad_norm": 0.40470513701438904,
+      "learning_rate": 2.5435783511683443e-05,
+      "loss": 0.6428,
+      "step": 182
+    },
+    {
+      "epoch": 0.7795527156549521,
+      "grad_norm": 0.413817822933197,
+      "learning_rate": 2.450859851825842e-05,
+      "loss": 0.7303,
+      "step": 183
+    },
+    {
+      "epoch": 0.7838125665601704,
+      "grad_norm": 0.2931414842605591,
+      "learning_rate": 2.3596262417839255e-05,
+      "loss": 0.4051,
+      "step": 184
+    },
+    {
+      "epoch": 0.7880724174653887,
+      "grad_norm": 0.34086865186691284,
+      "learning_rate": 2.26989546637263e-05,
+      "loss": 0.4329,
+      "step": 185
+    },
+    {
+      "epoch": 0.792332268370607,
+      "grad_norm": 0.40336307883262634,
+      "learning_rate": 2.181685175319702e-05,
+      "loss": 0.5791,
+      "step": 186
+    },
+    {
+      "epoch": 0.7965921192758253,
+      "grad_norm": 0.30092838406562805,
+      "learning_rate": 2.095012719278966e-05,
+      "loss": 0.4491,
+      "step": 187
+    },
+    {
+      "epoch": 0.8008519701810437,
+      "grad_norm": 0.31043168902397156,
+      "learning_rate": 2.009895146417512e-05,
+      "loss": 0.4681,
+      "step": 188
+    },
+    {
+      "epoch": 0.805111821086262,
+      "grad_norm": 0.3712119162082672,
+      "learning_rate": 1.926349199062376e-05,
+      "loss": 0.549,
+      "step": 189
+    },
+    {
+      "epoch": 0.8093716719914803,
+      "grad_norm": 0.3679051995277405,
+      "learning_rate": 1.8443913104073983e-05,
+      "loss": 0.4971,
+      "step": 190
+    },
+    {
+      "epoch": 0.8136315228966986,
+      "grad_norm": 0.3244669735431671,
+      "learning_rate": 1.7640376012808536e-05,
+      "loss": 0.4732,
+      "step": 191
+    },
+    {
+      "epoch": 0.8178913738019169,
+      "grad_norm": 0.28653696179389954,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.3469,
+      "step": 192
+    },
+    {
+      "epoch": 0.8221512247071352,
+      "grad_norm": 0.3144218325614929,
+      "learning_rate": 1.6082056241349786e-05,
+      "loss": 0.5127,
+      "step": 193
+    },
+    {
+      "epoch": 0.8264110756123536,
+      "grad_norm": 0.3801470994949341,
+      "learning_rate": 1.5327580077171587e-05,
+      "loss": 0.5178,
+      "step": 194
+    },
+    {
+      "epoch": 0.8306709265175719,
+      "grad_norm": 0.37223386764526367,
+      "learning_rate": 1.4589758680017263e-05,
+      "loss": 0.5114,
+      "step": 195
+    },
+    {
+      "epoch": 0.8349307774227902,
+      "grad_norm": 0.4167802333831787,
+      "learning_rate": 1.3868737176759106e-05,
+      "loss": 0.6949,
+      "step": 196
+    },
+    {
+      "epoch": 0.8391906283280085,
+      "grad_norm": 0.620794951915741,
+      "learning_rate": 1.3164657389789458e-05,
+      "loss": 0.7015,
+      "step": 197
+    },
+    {
+      "epoch": 0.8434504792332268,
+      "grad_norm": 0.32053133845329285,
+      "learning_rate": 1.2477657809124631e-05,
+      "loss": 0.5328,
+      "step": 198
+    },
+    {
+      "epoch": 0.8477103301384451,
+      "grad_norm": 0.41892528533935547,
+      "learning_rate": 1.1807873565164506e-05,
+      "loss": 0.5929,
+      "step": 199
+    },
+    {
+      "epoch": 0.8519701810436635,
+      "grad_norm": 0.2980664372444153,
+      "learning_rate": 1.1155436402112785e-05,
+      "loss": 0.4209,
+      "step": 200
+    },
+    {
+      "epoch": 0.8562300319488818,
+      "grad_norm": 0.3290930986404419,
+      "learning_rate": 1.0520474652063394e-05,
+      "loss": 0.4423,
+      "step": 201
+    },
+    {
+      "epoch": 0.8604898828541001,
+      "grad_norm": 0.3246372640132904,
+      "learning_rate": 9.903113209758096e-06,
+      "loss": 0.4631,
+      "step": 202
+    },
+    {
+      "epoch": 0.8647497337593184,
+      "grad_norm": 0.3644905388355255,
+      "learning_rate": 9.303473508019944e-06,
+      "loss": 0.552,
+      "step": 203
+    },
+    {
+      "epoch": 0.8690095846645367,
+      "grad_norm": 0.49974295496940613,
+      "learning_rate": 8.72167349386811e-06,
+      "loss": 0.7516,
+      "step": 204
+    },
+    {
+      "epoch": 0.873269435569755,
+      "grad_norm": 0.3242340087890625,
+      "learning_rate": 8.157827605317892e-06,
+      "loss": 0.412,
+      "step": 205
+    },
+    {
+      "epoch": 0.8775292864749734,
+      "grad_norm": 0.33690881729125977,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.4841,
+      "step": 206
+    },
+    {
+      "epoch": 0.8817891373801917,
+      "grad_norm": 0.3246766924858093,
+      "learning_rate": 7.084438277702188e-06,
+      "loss": 0.4341,
+      "step": 207
+    },
+    {
+      "epoch": 0.88604898828541,
+      "grad_norm": 0.4262131452560425,
+      "learning_rate": 6.5751059705400295e-06,
+      "loss": 0.6306,
+      "step": 208
+    },
+    {
+      "epoch": 0.8903088391906283,
+      "grad_norm": 0.32158687710762024,
+      "learning_rate": 6.084150011257239e-06,
+      "loss": 0.4687,
+      "step": 209
+    },
+    {
+      "epoch": 0.8945686900958466,
+      "grad_norm": 0.377208948135376,
+      "learning_rate": 5.611666969163243e-06,
+      "loss": 0.5849,
+      "step": 210
+    },
+    {
+      "epoch": 0.898828541001065,
+      "grad_norm": 0.30956804752349854,
+      "learning_rate": 5.157749780009735e-06,
+      "loss": 0.4355,
+      "step": 211
+    },
+    {
+      "epoch": 0.9030883919062833,
+      "grad_norm": 0.4885202944278717,
+      "learning_rate": 4.722487727710368e-06,
+      "loss": 0.6129,
+      "step": 212
+    },
+    {
+      "epoch": 0.9073482428115016,
+      "grad_norm": 0.3384571075439453,
+      "learning_rate": 4.305966426779118e-06,
+      "loss": 0.4345,
+      "step": 213
+    },
+    {
+      "epoch": 0.9116080937167199,
+      "grad_norm": 0.4629303514957428,
+      "learning_rate": 3.908267805490051e-06,
+      "loss": 0.6158,
+      "step": 214
+    },
+    {
+      "epoch": 0.9158679446219382,
+      "grad_norm": 0.3206894099712372,
+      "learning_rate": 3.529470089762421e-06,
+      "loss": 0.4689,
+      "step": 215
+    },
+    {
+      "epoch": 0.9201277955271565,
+      "grad_norm": 0.41424816846847534,
+      "learning_rate": 3.169647787773866e-06,
+      "loss": 0.5235,
+      "step": 216
+    },
+    {
+      "epoch": 0.9243876464323749,
+      "grad_norm": 0.3189912736415863,
+      "learning_rate": 2.8288716753049005e-06,
+      "loss": 0.4262,
+      "step": 217
+    },
+    {
+      "epoch": 0.9286474973375932,
+      "grad_norm": 0.3202993869781494,
+      "learning_rate": 2.5072087818176382e-06,
+      "loss": 0.493,
+      "step": 218
+    },
+    {
+      "epoch": 0.9329073482428115,
+      "grad_norm": 0.32974228262901306,
+      "learning_rate": 2.20472237727124e-06,
+      "loss": 0.5512,
+      "step": 219
+    },
+    {
+      "epoch": 0.9371671991480298,
+      "grad_norm": 0.27346375584602356,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.4154,
+      "step": 220
+    },
+    {
+      "epoch": 0.9414270500532481,
+      "grad_norm": 0.29039615392684937,
+      "learning_rate": 1.657513243395159e-06,
+      "loss": 0.4367,
+      "step": 221
+    },
+    {
+      "epoch": 0.9456869009584664,
+      "grad_norm": 0.3864074647426605,
+      "learning_rate": 1.4128981481764115e-06,
+      "loss": 0.5531,
+      "step": 222
+    },
+    {
+      "epoch": 0.9499467518636848,
+      "grad_norm": 0.4020756185054779,
+      "learning_rate": 1.1876747889491223e-06,
+      "loss": 0.6631,
+      "step": 223
+    },
+    {
+      "epoch": 0.9542066027689031,
+      "grad_norm": 0.37475478649139404,
+      "learning_rate": 9.818874663554357e-07,
+      "loss": 0.4979,
+      "step": 224
+    },
+    {
+      "epoch": 0.9584664536741214,
+      "grad_norm": 0.3484041690826416,
+      "learning_rate": 7.955766580375335e-07,
+      "loss": 0.5207,
+      "step": 225
+    },
+    {
+      "epoch": 0.9627263045793397,
+      "grad_norm": 0.3385999798774719,
+      "learning_rate": 6.287790106757396e-07,
+      "loss": 0.4832,
+      "step": 226
+    },
+    {
+      "epoch": 0.966986155484558,
+      "grad_norm": 0.27909693121910095,
+      "learning_rate": 4.815273327803182e-07,
+      "loss": 0.3506,
+      "step": 227
+    },
+    {
+      "epoch": 0.9712460063897763,
+      "grad_norm": 0.34196606278419495,
+      "learning_rate": 3.5385058823809156e-07,
+      "loss": 0.5283,
+      "step": 228
+    },
+    {
+      "epoch": 0.9755058572949947,
+      "grad_norm": 0.39571547508239746,
+      "learning_rate": 2.457738906153972e-07,
+      "loss": 0.5099,
+      "step": 229
+    },
+    {
+      "epoch": 0.979765708200213,
+      "grad_norm": 0.4107287526130676,
+      "learning_rate": 1.5731849821833954e-07,
+      "loss": 0.5042,
+      "step": 230
+    },
+    {
+      "epoch": 0.9840255591054313,
+      "grad_norm": 0.3254135251045227,
+      "learning_rate": 8.850180991131219e-08,
+      "loss": 0.4929,
+      "step": 231
+    },
+    {
+      "epoch": 0.9882854100106496,
+      "grad_norm": 0.2778495252132416,
+      "learning_rate": 3.933736169471347e-08,
+      "loss": 0.3571,
+      "step": 232
+    },
+    {
+      "epoch": 0.9925452609158679,
+      "grad_norm": 0.4703886806964874,
+      "learning_rate": 9.834824042498358e-09,
+      "loss": 0.7013,
+      "step": 233
+    },
+    {
+      "epoch": 0.9968051118210862,
+      "grad_norm": 0.3349379599094391,
+      "learning_rate": 0.0,
+      "loss": 0.4725,
+      "step": 234
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 234,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1191352754700288e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-234/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c6dff82c92ff421662262ee123f0b7f4459c1dd00632eac81d0179c6c4eac67
+size 6200

merged/added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
+  "<|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
+}

merged/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "unsloth/Qwen2.5-Coder-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151665,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "unsloth_fixed": true,
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

merged/generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 32768,
+  "pad_token_id": 151665,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.42.3"
+}

merged/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af18e658ab422d0a1dfdcd34a449739681f0b6eb4be0d3a4b33d07ca5a61d9e
+size 3087537682

merged/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": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

merged/tokenizer_config.json

@@ -0,0 +1,216 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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",
+  "model_max_length": 131072,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}