Upload iter_0049

.gitattributes

@@ -42,3 +42,4 @@ iter_0029/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 iter_0034/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 iter_0039/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 iter_0044/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+iter_0049/tokenizer.json filter=lfs diff=lfs merge=lfs -text

iter_0049/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-7B-Instruct
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

iter_0049/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

iter_0049/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e5dad26a96eecad3b9b701a3ea8312465e5c8bfc42e4179cb291bfbae0ed084
+size 161533192

iter_0049/chat_template.jinja

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

iter_0049/dual_variables.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a10d030ca3802f0c69ea2880ab492b1d32530e8468991825da245a85d53dbc
+size 1020

iter_0049/log.json

@@ -0,0 +1,902 @@
+[
+  {
+    "iteration": 0,
+    "elapsed_s": 391.3745548725128,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6811992694805196,
+    "avg_questions": 0.75,
+    "avg_turns": 1.71875,
+    "ppo_loss": 0.004306373502393919,
+    "value_loss": 1.0939653792551585,
+    "approx_kl": 0.007651447518063443,
+    "clip_frac": 0.13775510394147464,
+    "entropy": 0.2519512538399015,
+    "kl_penalty": 0.023890904017857144,
+    "kl_per_seq": 0.023890904017857144,
+    "kl_seq_max": 0.17354910714285715
+  },
+  {
+    "iteration": 1,
+    "elapsed_s": 396.91996574401855,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7128395909645909,
+    "avg_questions": 1.0,
+    "avg_turns": 2.0,
+    "ppo_loss": -6.200931966304779e-05,
+    "value_loss": 1.34129982534796,
+    "approx_kl": 0.007126425625756383,
+    "clip_frac": 0.10546875,
+    "entropy": 0.23710179142653942,
+    "kl_penalty": 0.006378173828125,
+    "kl_per_seq": 0.006378173828125,
+    "kl_seq_max": 0.139892578125
+  },
+  {
+    "iteration": 2,
+    "elapsed_s": 401.90613555908203,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6647683046120546,
+    "avg_questions": 0.84375,
+    "avg_turns": 1.84375,
+    "ppo_loss": -0.0019026017398573458,
+    "value_loss": 0.41530144587159157,
+    "approx_kl": 0.00716985405961168,
+    "clip_frac": 0.10546875,
+    "entropy": 0.22521109459921718,
+    "kl_penalty": 0.021810531616210938,
+    "kl_per_seq": 0.021810531616210938,
+    "kl_seq_max": 0.16015625
+  },
+  {
+    "iteration": 3,
+    "elapsed_s": 353.3246395587921,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7448705808080808,
+    "avg_questions": 0.71875,
+    "avg_turns": 1.71875,
+    "ppo_loss": -0.014360849878617696,
+    "value_loss": 0.3274324876921518,
+    "approx_kl": 0.007058224391325244,
+    "clip_frac": 0.13839285873941012,
+    "entropy": 0.25282684128199306,
+    "kl_penalty": 0.013009207589285714,
+    "kl_per_seq": 0.013009207589285714,
+    "kl_seq_max": 0.19224330357142858
+  },
+  {
+    "iteration": 4,
+    "elapsed_s": 373.22468972206116,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.696688988095238,
+    "avg_questions": 0.8125,
+    "avg_turns": 1.8125,
+    "ppo_loss": -0.006632264354266226,
+    "value_loss": 0.2759131940547377,
+    "approx_kl": 0.007126917596906424,
+    "clip_frac": 0.09765625,
+    "entropy": 0.27006574370898306,
+    "kl_penalty": 0.01776123046875,
+    "kl_per_seq": 0.01776123046875,
+    "kl_seq_max": 0.1474609375
+  },
+  {
+    "iteration": 5,
+    "elapsed_s": 331.5490596294403,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7473958333333334,
+    "avg_questions": 0.6875,
+    "avg_turns": 1.65625,
+    "ppo_loss": 0.014228555839508772,
+    "value_loss": 0.4080925668988909,
+    "approx_kl": 0.007350156366425965,
+    "clip_frac": 0.12589285735573089,
+    "entropy": 0.23711106394018447,
+    "kl_penalty": 0.014600481305803572,
+    "kl_per_seq": 0.014600481305803572,
+    "kl_seq_max": 0.14801897321428573
+  },
+  {
+    "iteration": 6,
+    "elapsed_s": 341.383020401001,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7013764880952381,
+    "avg_questions": 0.78125,
+    "avg_turns": 1.75,
+    "ppo_loss": -0.018149102372782572,
+    "value_loss": 0.29358129096882685,
+    "approx_kl": 0.005304289449538503,
+    "clip_frac": 0.08928571428571429,
+    "entropy": 0.22091922430055483,
+    "kl_penalty": 0.009870256696428572,
+    "kl_per_seq": 0.009870256696428572,
+    "kl_seq_max": 0.16964285714285715
+  },
+  {
+    "iteration": 7,
+    "elapsed_s": 376.68281722068787,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6373480685980686,
+    "avg_questions": 0.71875,
+    "avg_turns": 1.71875,
+    "ppo_loss": 0.004498574583392058,
+    "value_loss": 0.37072710426790373,
+    "approx_kl": 0.009875988438060241,
+    "clip_frac": 0.14795918390154839,
+    "entropy": 0.21651536146444933,
+    "kl_penalty": 0.021937779017857144,
+    "kl_per_seq": 0.021937779017857144,
+    "kl_seq_max": 0.19810267857142858
+  },
+  {
+    "iteration": 8,
+    "elapsed_s": 357.74306988716125,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.714941829004329,
+    "avg_questions": 0.84375,
+    "avg_turns": 1.8125,
+    "ppo_loss": -0.0019490616396069527,
+    "value_loss": 0.23783158784499392,
+    "approx_kl": 0.007750324672088027,
+    "clip_frac": 0.125,
+    "entropy": 0.23043718142434955,
+    "kl_penalty": 0.0068511962890625,
+    "kl_per_seq": 0.0068511962890625,
+    "kl_seq_max": 0.153564453125
+  },
+  {
+    "iteration": 9,
+    "elapsed_s": 349.43006443977356,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6326783459595958,
+    "avg_questions": 0.78125,
+    "avg_turns": 1.75,
+    "ppo_loss": -0.011805641597935132,
+    "value_loss": 0.41574244254401754,
+    "approx_kl": 0.006929813751152584,
+    "clip_frac": 0.09375,
+    "entropy": 0.2451656689601285,
+    "kl_penalty": 0.0011160714285714285,
+    "kl_per_seq": 0.0011160714285714285,
+    "kl_seq_max": 0.13169642857142858
+  },
+  {
+    "iteration": 10,
+    "elapsed_s": 342.33648896217346,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.5290933892496392,
+    "avg_questions": 0.65625,
+    "avg_turns": 1.65625,
+    "ppo_loss": -0.04690079101003773,
+    "value_loss": 0.389953757503203,
+    "approx_kl": 0.008378872460785456,
+    "clip_frac": 0.11785714328289032,
+    "entropy": 0.23241628972547396,
+    "kl_penalty": 0.007162911551339286,
+    "kl_per_seq": 0.007162911551339286,
+    "kl_seq_max": 0.16908482142857142
+  },
+  {
+    "iteration": 11,
+    "elapsed_s": 345.7173488140106,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.5870106456043955,
+    "avg_questions": 0.78125,
+    "avg_turns": 1.75,
+    "ppo_loss": -0.03757930214383772,
+    "value_loss": 0.4524953413222517,
+    "approx_kl": 0.01115357130765915,
+    "clip_frac": 0.16964285714285715,
+    "entropy": 0.26108588597604204,
+    "kl_penalty": 0.024867466517857144,
+    "kl_per_seq": 0.024867466517857144,
+    "kl_seq_max": 0.240234375
+  },
+  {
+    "iteration": 12,
+    "elapsed_s": 306.3272204399109,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7858630952380952,
+    "avg_questions": 0.6875,
+    "avg_turns": 1.6875,
+    "ppo_loss": -0.019100983094956194,
+    "value_loss": 0.3620611775134291,
+    "approx_kl": 0.011536365250192051,
+    "clip_frac": 0.1845238097012043,
+    "entropy": 0.23151074828846113,
+    "kl_penalty": 0.003513881138392857,
+    "kl_per_seq": 0.003513881138392857,
+    "kl_seq_max": 0.23744419642857142
+  },
+  {
+    "iteration": 13,
+    "elapsed_s": 355.70493721961975,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7175832847707848,
+    "avg_questions": 0.65625,
+    "avg_turns": 1.65625,
+    "ppo_loss": -0.0652177867445129,
+    "value_loss": 0.3424999515215556,
+    "approx_kl": 0.013465716365586829,
+    "clip_frac": 0.20000000022075795,
+    "entropy": 0.23204838788067852,
+    "kl_penalty": 0.01655183015046296,
+    "kl_per_seq": 0.01655183015046296,
+    "kl_seq_max": 0.39699074074074076
+  },
+  {
+    "iteration": 14,
+    "elapsed_s": 365.0925495624542,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7429315476190476,
+    "avg_questions": 0.875,
+    "avg_turns": 1.78125,
+    "ppo_loss": -0.001045653218170628,
+    "value_loss": 0.3470733960857615,
+    "approx_kl": 0.012083928100764751,
+    "clip_frac": 0.19140625,
+    "entropy": 0.23629889893345535,
+    "kl_penalty": 0.01666259765625,
+    "kl_per_seq": 0.01666259765625,
+    "kl_seq_max": 0.29931640625
+  },
+  {
+    "iteration": 15,
+    "elapsed_s": 328.12679862976074,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7816208964646464,
+    "avg_questions": 0.84375,
+    "avg_turns": 1.71875,
+    "ppo_loss": -0.0340351372724399,
+    "value_loss": 0.49711630772799253,
+    "approx_kl": 0.011802275160637995,
+    "clip_frac": 0.1569940478851398,
+    "entropy": 0.22923278994858265,
+    "kl_penalty": 0.047520955403645836,
+    "kl_per_seq": 0.047520955403645836,
+    "kl_seq_max": 0.4407552083333333
+  },
+  {
+    "iteration": 16,
+    "elapsed_s": 369.71018528938293,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.653125,
+    "avg_questions": 0.90625,
+    "avg_turns": 1.84375,
+    "ppo_loss": -0.05429610134712581,
+    "value_loss": 0.3952947693138287,
+    "approx_kl": 0.014259007245559117,
+    "clip_frac": 0.19971264436327177,
+    "entropy": 0.24027319355257626,
+    "kl_penalty": 0.018824084051724137,
+    "kl_per_seq": 0.018824084051724137,
+    "kl_seq_max": 0.31950431034482757
+  },
+  {
+    "iteration": 17,
+    "elapsed_s": 337.72703647613525,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6515252976190476,
+    "avg_questions": 0.71875,
+    "avg_turns": 1.71875,
+    "ppo_loss": -0.06590800095970432,
+    "value_loss": 0.35246419596175355,
+    "approx_kl": 0.015718272576729458,
+    "clip_frac": 0.24404762126505375,
+    "entropy": 0.24462667045493922,
+    "kl_penalty": 0.04541015625,
+    "kl_per_seq": 0.04541015625,
+    "kl_seq_max": 0.4153645833333333
+  },
+  {
+    "iteration": 18,
+    "elapsed_s": 332.5594162940979,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6804981476856476,
+    "avg_questions": 0.96875,
+    "avg_turns": 1.90625,
+    "ppo_loss": -0.04017568537249015,
+    "value_loss": 0.44942460467035955,
+    "approx_kl": 0.02055981710481529,
+    "clip_frac": 0.2740384621115831,
+    "entropy": 0.2769430299791006,
+    "kl_penalty": 0.035719651442307696,
+    "kl_per_seq": 0.035719651442307696,
+    "kl_seq_max": 0.48677884615384615
+  },
+  {
+    "iteration": 19,
+    "elapsed_s": 318.5729606151581,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6635416666666667,
+    "avg_questions": 0.75,
+    "avg_turns": 1.6875,
+    "ppo_loss": -0.052246415100636934,
+    "value_loss": 0.5782804233687264,
+    "approx_kl": 0.01484049868858641,
+    "clip_frac": 0.2103174612635658,
+    "entropy": 0.23401837263788497,
+    "kl_penalty": 0.061802455357142856,
+    "kl_per_seq": 0.061802455357142856,
+    "kl_seq_max": 0.5197172619047619
+  },
+  {
+    "iteration": 20,
+    "elapsed_s": 285.7307300567627,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7629768668831168,
+    "avg_questions": 0.71875,
+    "avg_turns": 1.6875,
+    "ppo_loss": -0.05846322079499563,
+    "value_loss": 0.4565003253519535,
+    "approx_kl": 0.021936011500656605,
+    "clip_frac": 0.29166666728754836,
+    "entropy": 0.2204122617840767,
+    "kl_penalty": 0.0718994140625,
+    "kl_per_seq": 0.0718994140625,
+    "kl_seq_max": 0.6236979166666666
+  },
+  {
+    "iteration": 21,
+    "elapsed_s": 296.0143573284149,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7436383928571428,
+    "avg_questions": 0.96875,
+    "avg_turns": 1.84375,
+    "ppo_loss": -0.039464282989501956,
+    "value_loss": 0.5258069838086764,
+    "approx_kl": 0.01652249412921568,
+    "clip_frac": 0.225,
+    "entropy": 0.253475824991862,
+    "kl_penalty": 0.18424479166666666,
+    "kl_per_seq": 0.18424479166666666,
+    "kl_seq_max": 0.9989583333333333
+  },
+  {
+    "iteration": 22,
+    "elapsed_s": 244.58502197265625,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.8692508012820512,
+    "avg_questions": 0.8125,
+    "avg_turns": 1.71875,
+    "ppo_loss": -0.03790540310243765,
+    "value_loss": 0.3813536564509074,
+    "approx_kl": 0.018072095544387896,
+    "clip_frac": 0.2098214291036129,
+    "entropy": 0.25934165467818576,
+    "kl_penalty": 0.12317403157552083,
+    "kl_per_seq": 0.12317403157552083,
+    "kl_seq_max": 0.8372395833333334
+  },
+  {
+    "iteration": 23,
+    "elapsed_s": 251.4962739944458,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7587606837606837,
+    "avg_questions": 0.84375,
+    "avg_turns": 1.8125,
+    "ppo_loss": 0.012825549495491114,
+    "value_loss": 0.2953187877481634,
+    "approx_kl": 0.012077649885957891,
+    "clip_frac": 0.125,
+    "entropy": 0.26409894092516467,
+    "kl_penalty": 0.047407670454545456,
+    "kl_per_seq": 0.047407670454545456,
+    "kl_seq_max": 0.5653409090909091
+  },
+  {
+    "iteration": 24,
+    "elapsed_s": 309.9806978702545,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7514423076923075,
+    "avg_questions": 0.75,
+    "avg_turns": 1.75,
+    "ppo_loss": -0.01857047031323115,
+    "value_loss": 0.26617255012194313,
+    "approx_kl": 0.015973625580469768,
+    "clip_frac": 0.25,
+    "entropy": 0.2604304631551107,
+    "kl_penalty": 0.1037109375,
+    "kl_per_seq": 0.1037109375,
+    "kl_seq_max": 0.9010416666666666
+  },
+  {
+    "iteration": 25,
+    "elapsed_s": 320.49351263046265,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7063911782661781,
+    "avg_questions": 0.9375,
+    "avg_turns": 1.8125,
+    "ppo_loss": -0.018078277317377236,
+    "value_loss": 0.3845859192884885,
+    "approx_kl": 0.015237291271869954,
+    "clip_frac": 0.18269230769230768,
+    "entropy": 0.23346925297608742,
+    "kl_penalty": 0.15362079326923078,
+    "kl_per_seq": 0.15362079326923078,
+    "kl_seq_max": 0.9837740384615384
+  },
+  {
+    "iteration": 26,
+    "elapsed_s": 323.8589389324188,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.8306948260073259,
+    "avg_questions": 0.78125,
+    "avg_turns": 1.75,
+    "ppo_loss": -0.043510055059895796,
+    "value_loss": 0.534914461128852,
+    "approx_kl": 0.019320455105865702,
+    "clip_frac": 0.2426470588235294,
+    "entropy": 0.24094978325507221,
+    "kl_penalty": 0.0927734375,
+    "kl_per_seq": 0.0927734375,
+    "kl_seq_max": 1.0303308823529411
+  },
+  {
+    "iteration": 27,
+    "elapsed_s": 324.9500458240509,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.5760957792207793,
+    "avg_questions": 0.96875,
+    "avg_turns": 1.875,
+    "ppo_loss": -0.026346603079753762,
+    "value_loss": 0.45603471643784466,
+    "approx_kl": 0.01608422179432476,
+    "clip_frac": 0.22058823529411764,
+    "entropy": 0.27300574586671944,
+    "kl_penalty": 0.20151654411764705,
+    "kl_per_seq": 0.20151654411764705,
+    "kl_seq_max": 1.130514705882353
+  },
+  {
+    "iteration": 28,
+    "elapsed_s": 303.5472674369812,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.8513192536630036,
+    "avg_questions": 0.8125,
+    "avg_turns": 1.71875,
+    "ppo_loss": -0.02768323285614743,
+    "value_loss": 0.3881389936980079,
+    "approx_kl": 0.01575610044357531,
+    "clip_frac": 0.23739495873451233,
+    "entropy": 0.24715220226961024,
+    "kl_penalty": 0.04279641544117647,
+    "kl_per_seq": 0.04279641544117647,
+    "kl_seq_max": 0.8924632352941176
+  },
+  {
+    "iteration": 29,
+    "elapsed_s": 270.20724177360535,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7441840277777778,
+    "avg_questions": 0.71875,
+    "avg_turns": 1.6875,
+    "ppo_loss": -0.010159298498183488,
+    "value_loss": 0.37185330092906954,
+    "approx_kl": 0.01564621306024492,
+    "clip_frac": 0.16666666716337203,
+    "entropy": 0.25186163634061814,
+    "kl_penalty": 0.138134765625,
+    "kl_per_seq": 0.138134765625,
+    "kl_seq_max": 1.165625
+  },
+  {
+    "iteration": 30,
+    "elapsed_s": 289.7729663848877,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7611979166666666,
+    "avg_questions": 0.8125,
+    "avg_turns": 1.78125,
+    "ppo_loss": -0.06356357607771368,
+    "value_loss": 0.29646791298599806,
+    "approx_kl": 0.015403931193491992,
+    "clip_frac": 0.16176470588235295,
+    "entropy": 0.2366870492696762,
+    "kl_penalty": 0.10173483455882353,
+    "kl_per_seq": 0.10173483455882353,
+    "kl_seq_max": 1.0441176470588236
+  },
+  {
+    "iteration": 31,
+    "elapsed_s": 294.3575747013092,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7660361340048841,
+    "avg_questions": 0.75,
+    "avg_turns": 1.71875,
+    "ppo_loss": -0.030728849582374096,
+    "value_loss": 0.33501161262393,
+    "approx_kl": 0.014336224063299596,
+    "clip_frac": 0.13392857182770967,
+    "entropy": 0.2197267608717084,
+    "kl_penalty": 0.38299560546875,
+    "kl_per_seq": 0.38299560546875,
+    "kl_seq_max": 1.33203125
+  },
+  {
+    "iteration": 32,
+    "elapsed_s": 299.1265091896057,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.8308035714285714,
+    "avg_questions": 0.65625,
+    "avg_turns": 1.65625,
+    "ppo_loss": -0.014888413871328035,
+    "value_loss": 0.32986761008699733,
+    "approx_kl": 0.013485311220089594,
+    "clip_frac": 0.16875000049670538,
+    "entropy": 0.2205644448598226,
+    "kl_penalty": 0.2767740885416667,
+    "kl_per_seq": 0.2767740885416667,
+    "kl_seq_max": 1.0611979166666667
+  },
+  {
+    "iteration": 33,
+    "elapsed_s": 320.4849829673767,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7507440476190477,
+    "avg_questions": 0.90625,
+    "avg_turns": 1.84375,
+    "ppo_loss": -0.025071768806530878,
+    "value_loss": 0.36624723558242506,
+    "approx_kl": 0.016349044270240344,
+    "clip_frac": 0.2564102571744185,
+    "entropy": 0.23642447246954992,
+    "kl_penalty": 0.2841045673076923,
+    "kl_per_seq": 0.2841045673076923,
+    "kl_seq_max": 1.6057692307692308
+  },
+  {
+    "iteration": 34,
+    "elapsed_s": 335.4435408115387,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.8330490689865689,
+    "avg_questions": 0.90625,
+    "avg_turns": 1.84375,
+    "ppo_loss": -0.04892163421027362,
+    "value_loss": 0.26098416664171964,
+    "approx_kl": 0.018442555650835857,
+    "clip_frac": 0.20833333395421505,
+    "entropy": 0.2286389684304595,
+    "kl_penalty": 0.43194580078125,
+    "kl_per_seq": 0.43194580078125,
+    "kl_seq_max": 1.59375
+  },
+  {
+    "iteration": 35,
+    "elapsed_s": 282.9512393474579,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.8354910714285713,
+    "avg_questions": 0.75,
+    "avg_turns": 1.75,
+    "ppo_loss": -0.0367674125591293,
+    "value_loss": 0.30591199081391096,
+    "approx_kl": 0.016904023941606283,
+    "clip_frac": 0.21875,
+    "entropy": 0.20543238706886768,
+    "kl_penalty": 0.213134765625,
+    "kl_per_seq": 0.213134765625,
+    "kl_seq_max": 1.28125
+  },
+  {
+    "iteration": 36,
+    "elapsed_s": 292.89799666404724,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7528407356532356,
+    "avg_questions": 0.75,
+    "avg_turns": 1.6875,
+    "ppo_loss": -0.03817850281484425,
+    "value_loss": 0.41386527102440596,
+    "approx_kl": 0.01689695258392021,
+    "clip_frac": 0.2473958358168602,
+    "entropy": 0.24886011239141226,
+    "kl_penalty": 0.08984375,
+    "kl_per_seq": 0.08984375,
+    "kl_seq_max": 0.95703125
+  },
+  {
+    "iteration": 37,
+    "elapsed_s": 313.5319194793701,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6774102633477633,
+    "avg_questions": 0.71875,
+    "avg_turns": 1.6875,
+    "ppo_loss": -0.043462164948383966,
+    "value_loss": 0.4542760963241259,
+    "approx_kl": 0.01639264728873968,
+    "clip_frac": 0.2583333343267441,
+    "entropy": 0.23586804270744324,
+    "kl_penalty": 0.12975260416666667,
+    "kl_per_seq": 0.12975260416666667,
+    "kl_seq_max": 1.2072916666666667
+  },
+  {
+    "iteration": 38,
+    "elapsed_s": 349.16768193244934,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.8287257881007881,
+    "avg_questions": 0.90625,
+    "avg_turns": 1.84375,
+    "ppo_loss": -0.03279211334884167,
+    "value_loss": 0.3306866534054279,
+    "approx_kl": 0.010876875882968307,
+    "clip_frac": 0.1375,
+    "entropy": 0.22659268453717232,
+    "kl_penalty": 0.11552734375,
+    "kl_per_seq": 0.11552734375,
+    "kl_seq_max": 0.834375
+  },
+  {
+    "iteration": 39,
+    "elapsed_s": 272.25116062164307,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7600804143772895,
+    "avg_questions": 0.75,
+    "avg_turns": 1.6875,
+    "ppo_loss": -0.03180356610279817,
+    "value_loss": 0.4273397899591006,
+    "approx_kl": 0.020467953469890814,
+    "clip_frac": 0.2371794879436493,
+    "entropy": 0.2425022514966818,
+    "kl_penalty": 0.2255859375,
+    "kl_per_seq": 0.2255859375,
+    "kl_seq_max": 1.6490384615384615
+  },
+  {
+    "iteration": 40,
+    "elapsed_s": 269.50211477279663,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7029626623376625,
+    "avg_questions": 0.8125,
+    "avg_turns": 1.71875,
+    "ppo_loss": -0.0321302478286353,
+    "value_loss": 0.577810294248841,
+    "approx_kl": 0.01944747863506729,
+    "clip_frac": 0.18344155902212317,
+    "entropy": 0.242206794294444,
+    "kl_penalty": 0.08931107954545454,
+    "kl_per_seq": 0.08931107954545454,
+    "kl_seq_max": 1.625
+  },
+  {
+    "iteration": 41,
+    "elapsed_s": 371.24641847610474,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7627604166666667,
+    "avg_questions": 0.8125,
+    "avg_turns": 1.8125,
+    "ppo_loss": 0.030330276116728783,
+    "value_loss": 0.26581343294431764,
+    "approx_kl": 0.02612483004728953,
+    "clip_frac": 0.2916666666666667,
+    "entropy": 0.23142454897363982,
+    "kl_penalty": 0.183349609375,
+    "kl_per_seq": 0.183349609375,
+    "kl_seq_max": 1.3502604166666667
+  },
+  {
+    "iteration": 42,
+    "elapsed_s": 350.80748987197876,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6765050054112554,
+    "avg_questions": 0.875,
+    "avg_turns": 1.8125,
+    "ppo_loss": -0.04271211375792821,
+    "value_loss": 0.4131243268648783,
+    "approx_kl": 0.02223969946304957,
+    "clip_frac": 0.275,
+    "entropy": 0.19973871211210886,
+    "kl_penalty": 0.5397135416666666,
+    "kl_per_seq": 0.5397135416666666,
+    "kl_seq_max": 2.316666666666667
+  },
+  {
+    "iteration": 43,
+    "elapsed_s": 287.90204405784607,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6825036075036075,
+    "avg_questions": 0.6875,
+    "avg_turns": 1.6875,
+    "ppo_loss": -0.04165783175267279,
+    "value_loss": 0.3417245242744684,
+    "approx_kl": 0.01348413826781325,
+    "clip_frac": 0.17447916697710752,
+    "entropy": 0.20020899455994368,
+    "kl_penalty": 0.45849609375,
+    "kl_per_seq": 0.45849609375,
+    "kl_seq_max": 2.16796875
+  },
+  {
+    "iteration": 44,
+    "elapsed_s": 256.77041816711426,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7132553210678211,
+    "avg_questions": 0.75,
+    "avg_turns": 1.71875,
+    "ppo_loss": -0.02102078828546736,
+    "value_loss": 0.341541384657224,
+    "approx_kl": 0.014034368615183566,
+    "clip_frac": 0.140873016582595,
+    "entropy": 0.21113828155729505,
+    "kl_penalty": 0.2854275173611111,
+    "kl_per_seq": 0.2854275173611111,
+    "kl_seq_max": 1.4357638888888888
+  },
+  {
+    "iteration": 45,
+    "elapsed_s": 271.3997755050659,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7859441773504274,
+    "avg_questions": 0.75,
+    "avg_turns": 1.71875,
+    "ppo_loss": -0.006101595517247915,
+    "value_loss": 0.2919745832681656,
+    "approx_kl": 0.013501223083585501,
+    "clip_frac": 0.15,
+    "entropy": 0.23480196595191954,
+    "kl_penalty": 0.6962890625,
+    "kl_per_seq": 0.6962890625,
+    "kl_seq_max": 2.746875
+  },
+  {
+    "iteration": 46,
+    "elapsed_s": 311.24193572998047,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.701680957930958,
+    "avg_questions": 0.90625,
+    "avg_turns": 1.78125,
+    "ppo_loss": -0.005692539840108818,
+    "value_loss": 0.8236626475118101,
+    "approx_kl": 0.012441118558247885,
+    "clip_frac": 0.18055555555555555,
+    "entropy": 0.22401968306965298,
+    "kl_penalty": 0.5151909722222222,
+    "kl_per_seq": 0.5151909722222222,
+    "kl_seq_max": 1.8715277777777777
+  },
+  {
+    "iteration": 47,
+    "elapsed_s": 288.4601163864136,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.817701655982906,
+    "avg_questions": 0.6875,
+    "avg_turns": 1.6875,
+    "ppo_loss": -0.042878850524385385,
+    "value_loss": 0.25026855130608266,
+    "approx_kl": 0.019887132928348504,
+    "clip_frac": 0.18589743627951696,
+    "entropy": 0.1946051109295625,
+    "kl_penalty": 0.42964993990384615,
+    "kl_per_seq": 0.42964993990384615,
+    "kl_seq_max": 1.9290865384615385
+  },
+  {
+    "iteration": 48,
+    "elapsed_s": 284.8813784122467,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7755022321428571,
+    "avg_questions": 0.8125,
+    "avg_turns": 1.78125,
+    "ppo_loss": -0.028697991371154787,
+    "value_loss": 0.3553868573158979,
+    "approx_kl": 0.014469949901103974,
+    "clip_frac": 0.1375,
+    "entropy": 0.2283128436654806,
+    "kl_penalty": 0.4259765625,
+    "kl_per_seq": 0.4259765625,
+    "kl_seq_max": 2.24140625
+  },
+  {
+    "iteration": 49,
+    "elapsed_s": 303.35283875465393,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7369190705128206,
+    "avg_questions": 0.5625,
+    "avg_turns": 1.5625,
+    "ppo_loss": -0.02507639303803444,
+    "value_loss": 0.32029884060223895,
+    "approx_kl": 0.017448070148626964,
+    "clip_frac": 0.19791666666666666,
+    "entropy": 0.23259289811054865,
+    "kl_penalty": 0.5426432291666666,
+    "kl_per_seq": 0.5426432291666666,
+    "kl_seq_max": 2.8619791666666665
+  }
+]

iter_0049/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb9ccc29b4517e9dccf26d1b9f1bb48113a6eb969a61c50ba9c8a2b0089d586
+size 11421990

iter_0049/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "left",
+  "unk_token": null
+}

iter_0049/train_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15158f2d9ca2c862a220783abcc67bef883b543444c3cf7c5d84aa2214a869f7
+size 104946244

iter_0049/value_heads.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:927fc9b6c56cf2896aa3bd64df587f11606eefb6a3eea2cee9befa82af625b7f
+size 44096056