Upload iter_0034

.gitattributes

@@ -45,3 +45,4 @@ iter_0014/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 iter_0019/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 iter_0024/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 iter_0029/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+iter_0034/tokenizer.json filter=lfs diff=lfs merge=lfs -text

iter_0034/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_0034/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": [
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

iter_0034/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1f2c082924768c03f2f98d999956f6724ffd5e33b388582e8bbf26d46d90e0b
+size 161533192

iter_0034/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_0034/dual_variables.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883e4267252d955cde80c36e5b51e2ff16804576b6b517e8121d6d1b185c50c6
+size 1020

iter_0034/log.json

@@ -0,0 +1,632 @@
+[
+  {
+    "iteration": 0,
+    "elapsed_s": 283.72707653045654,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6677320075757578,
+    "avg_questions": 0.71875,
+    "avg_turns": 1.6875,
+    "ppo_loss": -0.0012642779620364308,
+    "value_loss": 0.9520214434180941,
+    "approx_kl": 0.009626129126575376,
+    "clip_frac": 0.18303571481789863,
+    "entropy": 0.25815688552600996,
+    "kl_penalty": 0.011675153459821428,
+    "kl_per_seq": 0.011675153459821428,
+    "kl_seq_max": 0.18973214285714285
+  },
+  {
+    "iteration": 1,
+    "elapsed_s": 265.6153476238251,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6511522331834831,
+    "avg_questions": 0.75,
+    "avg_turns": 1.71875,
+    "ppo_loss": -0.02305267165814127,
+    "value_loss": 0.3821369180721896,
+    "approx_kl": 0.006722210083223347,
+    "clip_frac": 0.09438775533011981,
+    "entropy": 0.22343750271414006,
+    "kl_penalty": 0.010663713727678572,
+    "kl_per_seq": 0.010663713727678572,
+    "kl_seq_max": 0.14174107142857142
+  },
+  {
+    "iteration": 2,
+    "elapsed_s": 283.4707496166229,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6145833333333333,
+    "avg_questions": 0.71875,
+    "avg_turns": 1.6875,
+    "ppo_loss": 0.0003246570039274437,
+    "value_loss": 0.5281469119446618,
+    "approx_kl": 0.005086135942422386,
+    "clip_frac": 0.0595238097012043,
+    "entropy": 0.20671099424362183,
+    "kl_penalty": 0.022153581891741072,
+    "kl_per_seq": 0.022153581891741072,
+    "kl_seq_max": 0.15959821428571427
+  },
+  {
+    "iteration": 3,
+    "elapsed_s": 277.0273263454437,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.8185267857142857,
+    "avg_questions": 0.875,
+    "avg_turns": 1.84375,
+    "ppo_loss": 0.017307979986071587,
+    "value_loss": 0.2391173227224499,
+    "approx_kl": 0.006241402057639789,
+    "clip_frac": 0.0859375,
+    "entropy": 0.24670861288905144,
+    "kl_penalty": 0.0052337646484375,
+    "kl_per_seq": 0.0052337646484375,
+    "kl_seq_max": 0.130126953125
+  },
+  {
+    "iteration": 4,
+    "elapsed_s": 286.0855031013489,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6283482142857142,
+    "avg_questions": 0.875,
+    "avg_turns": 1.875,
+    "ppo_loss": -0.023693807190284133,
+    "value_loss": 0.23578157555311918,
+    "approx_kl": 0.006290083052590489,
+    "clip_frac": 0.08984375,
+    "entropy": 0.2442768611945212,
+    "kl_penalty": 0.013458251953125,
+    "kl_per_seq": 0.013458251953125,
+    "kl_seq_max": 0.13818359375
+  },
+  {
+    "iteration": 5,
+    "elapsed_s": 242.1764998435974,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7465401785714285,
+    "avg_questions": 0.78125,
+    "avg_turns": 1.78125,
+    "ppo_loss": -0.0412354568640391,
+    "value_loss": 0.36194167503466207,
+    "approx_kl": 0.02360554877668619,
+    "clip_frac": 0.21354166666666666,
+    "entropy": 0.28217028516034287,
+    "kl_penalty": 0.044108072916666664,
+    "kl_per_seq": 0.044108072916666664,
+    "kl_seq_max": 0.22916666666666666
+  },
+  {
+    "iteration": 6,
+    "elapsed_s": 297.9436032772064,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6431051587301587,
+    "avg_questions": 0.84375,
+    "avg_turns": 1.84375,
+    "ppo_loss": -0.01692520675715059,
+    "value_loss": 0.28041012212634087,
+    "approx_kl": 0.006847011674835812,
+    "clip_frac": 0.11197916697710752,
+    "entropy": 0.25802480173297226,
+    "kl_penalty": 0.01638031005859375,
+    "kl_per_seq": 0.01638031005859375,
+    "kl_seq_max": 0.14501953125
+  },
+  {
+    "iteration": 7,
+    "elapsed_s": 330.66188168525696,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6246899801587302,
+    "avg_questions": 0.8125,
+    "avg_turns": 1.78125,
+    "ppo_loss": 0.004835611267480999,
+    "value_loss": 0.42471681741881184,
+    "approx_kl": 0.006292660720646381,
+    "clip_frac": 0.078125,
+    "entropy": 0.22681239678058773,
+    "kl_penalty": 0.0085601806640625,
+    "kl_per_seq": 0.0085601806640625,
+    "kl_seq_max": 0.14404296875
+  },
+  {
+    "iteration": 8,
+    "elapsed_s": 300.30717039108276,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6534733495670996,
+    "avg_questions": 0.78125,
+    "avg_turns": 1.75,
+    "ppo_loss": -0.017197133707148687,
+    "value_loss": 0.3457076509616205,
+    "approx_kl": 0.006416547777397292,
+    "clip_frac": 0.07589285714285714,
+    "entropy": 0.22316500225237437,
+    "kl_penalty": 0.004743303571428571,
+    "kl_per_seq": 0.004743303571428571,
+    "kl_seq_max": 0.197265625
+  },
+  {
+    "iteration": 9,
+    "elapsed_s": 286.7236270904541,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7079376352813853,
+    "avg_questions": 0.78125,
+    "avg_turns": 1.75,
+    "ppo_loss": -0.011897004608597075,
+    "value_loss": 0.411878263843911,
+    "approx_kl": 0.007929061938609396,
+    "clip_frac": 0.11607142857142858,
+    "entropy": 0.2569970648203577,
+    "kl_penalty": 0.00020926339285714285,
+    "kl_per_seq": 0.00020926339285714285,
+    "kl_seq_max": 0.16936383928571427
+  },
+  {
+    "iteration": 10,
+    "elapsed_s": 276.631822347641,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.8028939810189811,
+    "avg_questions": 0.84375,
+    "avg_turns": 1.78125,
+    "ppo_loss": -0.033312247483991086,
+    "value_loss": 0.2869396444875747,
+    "approx_kl": 0.008976982207968831,
+    "clip_frac": 0.12109375,
+    "entropy": 0.25112444773549214,
+    "kl_penalty": 0.01202392578125,
+    "kl_per_seq": 0.01202392578125,
+    "kl_seq_max": 0.203857421875
+  },
+  {
+    "iteration": 11,
+    "elapsed_s": 255.2351098060608,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.5704326923076923,
+    "avg_questions": 0.78125,
+    "avg_turns": 1.75,
+    "ppo_loss": -0.005331723640362422,
+    "value_loss": 0.42935604602098465,
+    "approx_kl": 0.016193445358011458,
+    "clip_frac": 0.2222222222222222,
+    "entropy": 0.23103458185990652,
+    "kl_penalty": 0.0,
+    "kl_per_seq": 0.0,
+    "kl_seq_max": 0.2294921875
+  },
+  {
+    "iteration": 12,
+    "elapsed_s": 254.100581407547,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.5869724025974025,
+    "avg_questions": 0.71875,
+    "avg_turns": 1.6875,
+    "ppo_loss": -0.03959607765344637,
+    "value_loss": 0.34272722474166323,
+    "approx_kl": 0.012407979046526765,
+    "clip_frac": 0.20684523933700152,
+    "entropy": 0.24096926195280893,
+    "kl_penalty": 0.007428850446428571,
+    "kl_per_seq": 0.007428850446428571,
+    "kl_seq_max": 0.2572544642857143
+  },
+  {
+    "iteration": 13,
+    "elapsed_s": 335.7170238494873,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6823145604395605,
+    "avg_questions": 0.84375,
+    "avg_turns": 1.84375,
+    "ppo_loss": -0.03688290709008773,
+    "value_loss": 0.21781166903674604,
+    "approx_kl": 0.013189310727951428,
+    "clip_frac": 0.19583333432674407,
+    "entropy": 0.2323363353808721,
+    "kl_penalty": 0.024055989583333333,
+    "kl_per_seq": 0.024055989583333333,
+    "kl_seq_max": 0.3768229166666667
+  },
+  {
+    "iteration": 14,
+    "elapsed_s": 264.29171442985535,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7472098214285713,
+    "avg_questions": 0.875,
+    "avg_turns": 1.875,
+    "ppo_loss": -0.027799080746869247,
+    "value_loss": 0.4135706809659799,
+    "approx_kl": 0.012586234758297602,
+    "clip_frac": 0.15625,
+    "entropy": 0.2517068100472291,
+    "kl_penalty": 0.0135498046875,
+    "kl_per_seq": 0.0135498046875,
+    "kl_seq_max": 0.3229166666666667
+  },
+  {
+    "iteration": 15,
+    "elapsed_s": 241.14811420440674,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6659226190476191,
+    "avg_questions": 0.65625,
+    "avg_turns": 1.65625,
+    "ppo_loss": -0.03369090032009851,
+    "value_loss": 0.34638335804144543,
+    "approx_kl": 0.013905501381183663,
+    "clip_frac": 0.19047619189534867,
+    "entropy": 0.22407633740277516,
+    "kl_penalty": 0.036342075892857144,
+    "kl_per_seq": 0.036342075892857144,
+    "kl_seq_max": 0.45982142857142855
+  },
+  {
+    "iteration": 16,
+    "elapsed_s": 238.80150389671326,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6585475288600288,
+    "avg_questions": 0.90625,
+    "avg_turns": 1.84375,
+    "ppo_loss": -0.056268499715736615,
+    "value_loss": 0.3362144205581259,
+    "approx_kl": 0.019216162325055512,
+    "clip_frac": 0.3024691376421187,
+    "entropy": 0.2751925124062432,
+    "kl_penalty": 0.022162543402777776,
+    "kl_per_seq": 0.022162543402777776,
+    "kl_seq_max": 0.5263310185185185
+  },
+  {
+    "iteration": 17,
+    "elapsed_s": 232.22505855560303,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7668154761904762,
+    "avg_questions": 0.90625,
+    "avg_turns": 1.875,
+    "ppo_loss": -0.0331775728199217,
+    "value_loss": 0.3092526584449742,
+    "approx_kl": 0.01231207988328404,
+    "clip_frac": 0.20833333333333334,
+    "entropy": 0.25865906063053345,
+    "kl_penalty": 0.07600911458333333,
+    "kl_per_seq": 0.07600911458333333,
+    "kl_seq_max": 0.65625
+  },
+  {
+    "iteration": 18,
+    "elapsed_s": 311.01340675354004,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6972830988455989,
+    "avg_questions": 0.8125,
+    "avg_turns": 1.78125,
+    "ppo_loss": 0.009420987218618393,
+    "value_loss": 0.4465955500304699,
+    "approx_kl": 0.015329486131668091,
+    "clip_frac": 0.26,
+    "entropy": 0.21777834206819535,
+    "kl_penalty": 0.04673828125,
+    "kl_per_seq": 0.04673828125,
+    "kl_seq_max": 0.56625
+  },
+  {
+    "iteration": 19,
+    "elapsed_s": 249.58963227272034,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7551739926739928,
+    "avg_questions": 0.6875,
+    "avg_turns": 1.6875,
+    "ppo_loss": -0.037938538430766625,
+    "value_loss": 0.36645138856362214,
+    "approx_kl": 0.018135146047411996,
+    "clip_frac": 0.2746212130243128,
+    "entropy": 0.24184788357127796,
+    "kl_penalty": 0.002840909090909091,
+    "kl_per_seq": 0.002840909090909091,
+    "kl_seq_max": 0.6051136363636364
+  },
+  {
+    "iteration": 20,
+    "elapsed_s": 292.7258870601654,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7158272283272281,
+    "avg_questions": 0.8125,
+    "avg_turns": 1.75,
+    "ppo_loss": -0.04037410455445448,
+    "value_loss": 0.35967613384127617,
+    "approx_kl": 0.016659200191497803,
+    "clip_frac": 0.23958333333333334,
+    "entropy": 0.24879397824406624,
+    "kl_penalty": 0.111328125,
+    "kl_per_seq": 0.111328125,
+    "kl_seq_max": 1.0013020833333333
+  },
+  {
+    "iteration": 21,
+    "elapsed_s": 184.79159307479858,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.743264678030303,
+    "avg_questions": 0.75,
+    "avg_turns": 1.6875,
+    "ppo_loss": -0.019979689947583458,
+    "value_loss": 0.42602486231110315,
+    "approx_kl": 0.009891370269046589,
+    "clip_frac": 0.11363636363636363,
+    "entropy": 0.2355451394211162,
+    "kl_penalty": 0.09295099431818182,
+    "kl_per_seq": 0.09295099431818182,
+    "kl_seq_max": 0.8309659090909091
+  },
+  {
+    "iteration": 22,
+    "elapsed_s": 269.67527770996094,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.731497061965812,
+    "avg_questions": 0.6875,
+    "avg_turns": 1.6875,
+    "ppo_loss": -0.06142320060594515,
+    "value_loss": 0.32878022911873733,
+    "approx_kl": 0.01706851857968352,
+    "clip_frac": 0.28598484938794916,
+    "entropy": 0.22095515849915418,
+    "kl_penalty": 0.03235973011363636,
+    "kl_per_seq": 0.03235973011363636,
+    "kl_seq_max": 0.8068181818181818
+  },
+  {
+    "iteration": 23,
+    "elapsed_s": 287.49955129623413,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7941430097680098,
+    "avg_questions": 0.90625,
+    "avg_turns": 1.90625,
+    "ppo_loss": -0.02508886717259884,
+    "value_loss": 0.23930740232268968,
+    "approx_kl": 0.01800820985550268,
+    "clip_frac": 0.20972222255335915,
+    "entropy": 0.26301920496755177,
+    "kl_penalty": 0.2238498263888889,
+    "kl_per_seq": 0.2238498263888889,
+    "kl_seq_max": 1.0772569444444444
+  },
+  {
+    "iteration": 24,
+    "elapsed_s": 234.66244316101074,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7230979957542457,
+    "avg_questions": 0.75,
+    "avg_turns": 1.71875,
+    "ppo_loss": -0.007767030461267991,
+    "value_loss": 0.5475986464457079,
+    "approx_kl": 0.014794111082499678,
+    "clip_frac": 0.27435064993121405,
+    "entropy": 0.24171581187031485,
+    "kl_penalty": 0.06498579545454546,
+    "kl_per_seq": 0.06498579545454546,
+    "kl_seq_max": 0.9232954545454546
+  },
+  {
+    "iteration": 25,
+    "elapsed_s": 319.03157591819763,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6251251352813854,
+    "avg_questions": 0.75,
+    "avg_turns": 1.6875,
+    "ppo_loss": -0.04657436514066325,
+    "value_loss": 0.41042184829711914,
+    "approx_kl": 0.023139544607450564,
+    "clip_frac": 0.2708333333333333,
+    "entropy": 0.24344126342071426,
+    "kl_penalty": 0.04966905381944445,
+    "kl_per_seq": 0.04966905381944445,
+    "kl_seq_max": 0.7352430555555556
+  },
+  {
+    "iteration": 26,
+    "elapsed_s": 278.54370284080505,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7391369047619047,
+    "avg_questions": 0.90625,
+    "avg_turns": 1.84375,
+    "ppo_loss": -0.011602610815316439,
+    "value_loss": 0.37313461070880294,
+    "approx_kl": 0.0172485489747487,
+    "clip_frac": 0.25781250186264515,
+    "entropy": 0.2445761663839221,
+    "kl_penalty": 0.2266845703125,
+    "kl_per_seq": 0.2266845703125,
+    "kl_seq_max": 1.1806640625
+  },
+  {
+    "iteration": 27,
+    "elapsed_s": 246.0258011817932,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.654265873015873,
+    "avg_questions": 0.84375,
+    "avg_turns": 1.78125,
+    "ppo_loss": -0.00885420270702418,
+    "value_loss": 0.40379785308066535,
+    "approx_kl": 0.017032040392651278,
+    "clip_frac": 0.20588235294117646,
+    "entropy": 0.22635302780305638,
+    "kl_penalty": 0.062270220588235295,
+    "kl_per_seq": 0.062270220588235295,
+    "kl_seq_max": 0.6709558823529411
+  },
+  {
+    "iteration": 28,
+    "elapsed_s": 328.36840200424194,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.715736607142857,
+    "avg_questions": 0.90625,
+    "avg_turns": 1.78125,
+    "ppo_loss": -0.03573833931894863,
+    "value_loss": 0.44778402368812,
+    "approx_kl": 0.016466796398162842,
+    "clip_frac": 0.25735294117647056,
+    "entropy": 0.27092264066724214,
+    "kl_penalty": 0.3297334558823529,
+    "kl_per_seq": 0.3297334558823529,
+    "kl_seq_max": 1.3786764705882353
+  },
+  {
+    "iteration": 29,
+    "elapsed_s": 263.61545872688293,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7022214764402265,
+    "avg_questions": 0.875,
+    "avg_turns": 1.75,
+    "ppo_loss": -0.042088701079289116,
+    "value_loss": 0.374366395175457,
+    "approx_kl": 0.0180306788533926,
+    "clip_frac": 0.15625,
+    "entropy": 0.2805991160372893,
+    "kl_penalty": 0.06697591145833333,
+    "kl_per_seq": 0.06697591145833333,
+    "kl_seq_max": 1.2955729166666667
+  },
+  {
+    "iteration": 30,
+    "elapsed_s": 303.52203917503357,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.6189224837662338,
+    "avg_questions": 0.78125,
+    "avg_turns": 1.625,
+    "ppo_loss": -0.009862170120080312,
+    "value_loss": 0.588172604640325,
+    "approx_kl": 0.018847733736038208,
+    "clip_frac": 0.21666666666666667,
+    "entropy": 0.2482275903224945,
+    "kl_penalty": 0.0869140625,
+    "kl_per_seq": 0.0869140625,
+    "kl_seq_max": 0.8333333333333334
+  },
+  {
+    "iteration": 31,
+    "elapsed_s": 249.05430436134338,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7663931988150738,
+    "avg_questions": 0.6875,
+    "avg_turns": 1.625,
+    "ppo_loss": -0.055953570586793566,
+    "value_loss": 0.4904465508811614,
+    "approx_kl": 0.018582439159645754,
+    "clip_frac": 0.2867647058823529,
+    "entropy": 0.21470373255365036,
+    "kl_penalty": 0.09777113970588236,
+    "kl_per_seq": 0.09777113970588236,
+    "kl_seq_max": 1.2426470588235294
+  },
+  {
+    "iteration": 32,
+    "elapsed_s": 212.35868120193481,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.75,
+    "avg_questions": 0.65625,
+    "avg_turns": 1.625,
+    "ppo_loss": -0.03906370233744383,
+    "value_loss": 0.45569973066449165,
+    "approx_kl": 0.01507616974413395,
+    "clip_frac": 0.234375,
+    "entropy": 0.21894092485308647,
+    "kl_penalty": 0.0474853515625,
+    "kl_per_seq": 0.0474853515625,
+    "kl_seq_max": 0.763671875
+  },
+  {
+    "iteration": 33,
+    "elapsed_s": 326.989426612854,
+    "lambda1": 0.0,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.5256744123931625,
+    "avg_questions": 0.90625,
+    "avg_turns": 1.8125,
+    "ppo_loss": -0.03463981207460165,
+    "value_loss": 0.4421174842864275,
+    "approx_kl": 0.02097482793033123,
+    "clip_frac": 0.328125,
+    "entropy": 0.24500909820199013,
+    "kl_penalty": 0.127197265625,
+    "kl_per_seq": 0.127197265625,
+    "kl_seq_max": 1.5625
+  },
+  {
+    "iteration": 34,
+    "elapsed_s": 274.3689548969269,
+    "lambda1": 0.009375000000000001,
+    "lambda2": 0.0,
+    "n_episodes": 32,
+    "avg_reward": 0.7299278846153846,
+    "avg_questions": 1.09375,
+    "avg_turns": 1.9375,
+    "ppo_loss": -0.03937706899117021,
+    "value_loss": 1.6494529334937824,
+    "approx_kl": 0.01805254674571402,
+    "clip_frac": 0.29411764793536244,
+    "entropy": 0.22951026655295315,
+    "kl_penalty": 0.19114774816176472,
+    "kl_per_seq": 0.19114774816176472,
+    "kl_seq_max": 1.5441176470588236
+  }
+]

iter_0034/tokenizer.json

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

iter_0034/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_0034/train_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e562edc9af12505e29d46b8b2d833fd5e48705f50cc3e979b18ee143e7f75a2
+size 104946180

iter_0034/value_heads.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a11214ad0e7d6c74945e138325e6dc6ed34f735c0920317209f059ff60f798dd
+size 44096056