Upload task output 1

README.md

@@ -0,0 +1,209 @@
+---
+base_model: None
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/cache/models/Qwen--Qwen2.5-3B-Instruct
+- grpo
+- lora
+- transformers
+- trl
+---
+
+# 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

adapter_config.json

@@ -9,35 +9,35 @@
   "ensure_weight_tying": false,
   "eva_config": null,
   "exclude_modules": null,
-  "fan_in_fan_out": null,
-  "inference_mode": false,
+  "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_alpha": 256,
   "lora_bias": false,
-  "lora_dropout": 0.0,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
-  "r": 64,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "v_proj",
-    "q_proj",
-    "gate_proj",
+    "up_proj",
     "k_proj",
+    "gate_proj",
     "o_proj",
+    "q_proj",
     "down_proj"
   ],
-  "target_parameters": [],
+  "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8770f625ea3546b7a1ccec5ee214f397ae1e299ec3812d8981bb4a76c17c241d
+size 957942768

chat_template.jinja

@@ -1,5 +1,54 @@
-{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
-
-'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
-
-' }}{% endif %}
+{%- 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 %}

loss.txt

@@ -0,0 +1 @@
+8,-0.56

special_tokens_map.json

@@ -14,13 +14,6 @@
     "<|image_pad|>",
     "<|video_pad|>"
   ],
-  "bos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "eos_token": {
     "content": "<|im_end|>",
     "lstrip": false,

tokenizer_config.json

@@ -194,7 +194,7 @@
     "<|image_pad|>",
     "<|video_pad|>"
   ],
-  "bos_token": "<|im_end|>",
+  "bos_token": null,
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",

trainer_state.json

@@ -0,0 +1,354 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 8,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 3.0,
+      "completions/max_terminated_length": 3.0,
+      "completions/mean_length": 2.407738208770752,
+      "completions/mean_terminated_length": 2.407738208770752,
+      "completions/min_length": 2.0,
+      "completions/min_terminated_length": 2.0,
+      "entropy": 0.7712807655334473,
+      "epoch": 0.25,
+      "frac_reward_zero_std": 0.5297619104385376,
+      "grad_norm": 4.7248921394348145,
+      "learning_rate": 0.0,
+      "loss": 0.0255,
+      "num_tokens": 117737.0,
+      "reward": 0.4955357313156128,
+      "reward_std": 0.4984852075576782,
+      "rewards/env_game_reward/mean": 0.4955357015132904,
+      "rewards/env_game_reward/std": 0.4984852075576782,
+      "sampling/importance_sampling_ratio/max": 2.444530487060547,
+      "sampling/importance_sampling_ratio/mean": 0.9743361473083496,
+      "sampling/importance_sampling_ratio/min": 0.3661190867424011,
+      "sampling/sampling_logp_difference/max": 0.8435878753662109,
+      "sampling/sampling_logp_difference/mean": 0.10781625658273697,
+      "step": 1,
+      "step_time": 86.73120934999952
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 41.0,
+      "completions/max_terminated_length": 41.0,
+      "completions/mean_length": 2.5892858505249023,
+      "completions/mean_terminated_length": 2.5892858505249023,
+      "completions/min_length": 2.0,
+      "completions/min_terminated_length": 2.0,
+      "entropy": 0.6681132614612579,
+      "epoch": 0.5,
+      "frac_reward_zero_std": 0.3988095223903656,
+      "grad_norm": 2.0864083766937256,
+      "learning_rate": 2.84304e-07,
+      "loss": 0.0384,
+      "num_tokens": 222599.0,
+      "reward": 0.5297619104385376,
+      "reward_std": 0.4908183515071869,
+      "rewards/env_game_reward/mean": 0.5297619104385376,
+      "rewards/env_game_reward/std": 0.4908183515071869,
+      "sampling/importance_sampling_ratio/max": 2.3313705921173096,
+      "sampling/importance_sampling_ratio/mean": 0.9879763126373291,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 1.0128240585327148,
+      "sampling/sampling_logp_difference/mean": 0.09322669357061386,
+      "step": 2,
+      "step_time": 49.185698066999976
+    },
+    {
+      "clip_ratio/high_max": 0.010094599798321724,
+      "clip_ratio/high_mean": 0.005047299899160862,
+      "clip_ratio/low_mean": 0.01141490787267685,
+      "clip_ratio/low_min": 0.0053089887369424105,
+      "clip_ratio/region_mean": 0.016462208004668355,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 9.0,
+      "completions/max_terminated_length": 9.0,
+      "completions/mean_length": 2.267857074737549,
+      "completions/mean_terminated_length": 2.267857074737549,
+      "completions/min_length": 2.0,
+      "completions/min_terminated_length": 2.0,
+      "entropy": 0.6272067576646805,
+      "epoch": 0.75,
+      "frac_reward_zero_std": 0.4583333432674408,
+      "grad_norm": 3.2909624576568604,
+      "learning_rate": 5.68608e-07,
+      "loss": 0.0251,
+      "num_tokens": 334913.0,
+      "reward": 0.5223214626312256,
+      "reward_std": 0.49499765038490295,
+      "rewards/env_game_reward/mean": 0.5223214030265808,
+      "rewards/env_game_reward/std": 0.49499762058258057,
+      "sampling/importance_sampling_ratio/max": 1.6051479578018188,
+      "sampling/importance_sampling_ratio/mean": 0.9814748764038086,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 1.094405174255371,
+      "sampling/sampling_logp_difference/mean": 0.07474357634782791,
+      "step": 3,
+      "step_time": 74.23962842500077
+    },
+    {
+      "clip_ratio/high_max": 0.034161615651100874,
+      "clip_ratio/high_mean": 0.023498072754591703,
+      "clip_ratio/low_mean": 0.008893569000065327,
+      "clip_ratio/low_min": 0.005104166688397527,
+      "clip_ratio/region_mean": 0.03239164222031832,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 3.0,
+      "completions/max_terminated_length": 3.0,
+      "completions/mean_length": 2.3035714626312256,
+      "completions/mean_terminated_length": 2.3035714626312256,
+      "completions/min_length": 2.0,
+      "completions/min_terminated_length": 2.0,
+      "entropy": 0.5872454345226288,
+      "epoch": 1.0,
+      "frac_reward_zero_std": 0.386904776096344,
+      "grad_norm": 1.5831847190856934,
+      "learning_rate": 8.529119999999999e-07,
+      "loss": 0.0144,
+      "num_tokens": 439679.0,
+      "reward": 0.5372024178504944,
+      "reward_std": 0.4834112823009491,
+      "rewards/env_game_reward/mean": 0.5372023582458496,
+      "rewards/env_game_reward/std": 0.4834113121032715,
+      "sampling/importance_sampling_ratio/max": 2.0064399242401123,
+      "sampling/importance_sampling_ratio/mean": 1.0050137042999268,
+      "sampling/importance_sampling_ratio/min": 0.48575615882873535,
+      "sampling/sampling_logp_difference/max": 0.7220797538757324,
+      "sampling/sampling_logp_difference/mean": 0.09695391356945038,
+      "step": 4,
+      "step_time": 48.50994999100112
+    },
+    {
+      "epoch": 1.0,
+      "eval_clip_ratio/high_max": 0.0,
+      "eval_clip_ratio/high_mean": 0.0,
+      "eval_clip_ratio/low_mean": 0.0,
+      "eval_clip_ratio/low_min": 0.0,
+      "eval_clip_ratio/region_mean": 0.0,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 2.9,
+      "eval_completions/max_terminated_length": 2.9,
+      "eval_completions/mean_length": 2.27,
+      "eval_completions/mean_terminated_length": 2.27,
+      "eval_completions/min_length": 2.0,
+      "eval_completions/min_terminated_length": 2.0,
+      "eval_entropy": 0.6556259167194366,
+      "eval_frac_reward_zero_std": 0.49,
+      "eval_loss": -0.002539175096899271,
+      "eval_num_tokens": 439679.0,
+      "eval_reward": 0.5225,
+      "eval_reward_std": 0.4914883863925934,
+      "eval_rewards/env_game_reward/mean": 0.5225,
+      "eval_rewards/env_game_reward/std": 0.4914884132146835,
+      "eval_runtime": 72.4746,
+      "eval_samples_per_second": 2.76,
+      "eval_sampling/importance_sampling_ratio/max": 1.344225935935974,
+      "eval_sampling/importance_sampling_ratio/mean": 0.9896444308757782,
+      "eval_sampling/importance_sampling_ratio/min": 0.7344249868392945,
+      "eval_sampling/sampling_logp_difference/max": 0.3614662927389145,
+      "eval_sampling/sampling_logp_difference/mean": 0.08291504085063935,
+      "eval_steps_per_second": 0.345,
+      "step": 4
+    },
+    {
+      "clip_ratio/high_max": 0.015843799337744713,
+      "clip_ratio/high_mean": 0.011610739515163004,
+      "clip_ratio/low_mean": 0.01242961548268795,
+      "clip_ratio/low_min": 0.0023809524718672037,
+      "clip_ratio/region_mean": 0.024040354881435633,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 7.0,
+      "completions/max_terminated_length": 7.0,
+      "completions/mean_length": 2.372023820877075,
+      "completions/mean_terminated_length": 2.372023820877075,
+      "completions/min_length": 2.0,
+      "completions/min_terminated_length": 2.0,
+      "entropy": 0.7024529576301575,
+      "epoch": 1.25,
+      "frac_reward_zero_std": 0.4345238208770752,
+      "grad_norm": 2.5793297290802,
+      "learning_rate": 1.137216e-06,
+      "loss": 0.0003,
+      "num_tokens": 560092.0,
+      "reward": 0.5684524178504944,
+      "reward_std": 0.48845046758651733,
+      "rewards/env_game_reward/mean": 0.5684523582458496,
+      "rewards/env_game_reward/std": 0.4884504973888397,
+      "sampling/importance_sampling_ratio/max": 2.402831554412842,
+      "sampling/importance_sampling_ratio/mean": 0.9943535923957825,
+      "sampling/importance_sampling_ratio/min": 0.5057061910629272,
+      "sampling/sampling_logp_difference/max": 0.8499932289123535,
+      "sampling/sampling_logp_difference/mean": 0.0851290300488472,
+      "step": 5,
+      "step_time": 79.1233635949975
+    },
+    {
+      "clip_ratio/high_max": 0.02467681560665369,
+      "clip_ratio/high_mean": 0.015116185648366809,
+      "clip_ratio/low_mean": 0.008386317640542984,
+      "clip_ratio/low_min": 0.005376344081014395,
+      "clip_ratio/region_mean": 0.02350250235758722,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 5.0,
+      "completions/mean_length": 2.136904716491699,
+      "completions/mean_terminated_length": 2.136904716491699,
+      "completions/min_length": 2.0,
+      "completions/min_terminated_length": 2.0,
+      "entropy": 0.5466470569372177,
+      "epoch": 1.5,
+      "frac_reward_zero_std": 0.380952388048172,
+      "grad_norm": 1.9452687501907349,
+      "learning_rate": 1.4215199999999998e-06,
+      "loss": 0.0011,
+      "num_tokens": 664298.0,
+      "reward": 0.4940476417541504,
+      "reward_std": 0.49621880054473877,
+      "rewards/env_game_reward/mean": 0.494047611951828,
+      "rewards/env_game_reward/std": 0.49621880054473877,
+      "sampling/importance_sampling_ratio/max": 1.6991724967956543,
+      "sampling/importance_sampling_ratio/mean": 0.9933019876480103,
+      "sampling/importance_sampling_ratio/min": 0.4511236548423767,
+      "sampling/sampling_logp_difference/max": 0.7959003448486328,
+      "sampling/sampling_logp_difference/mean": 0.048079028725624084,
+      "step": 6,
+      "step_time": 37.11783460799961
+    },
+    {
+      "clip_ratio/high_max": 0.019634235184639692,
+      "clip_ratio/high_mean": 0.014030600897967815,
+      "clip_ratio/low_mean": 0.005204149056226015,
+      "clip_ratio/low_min": 0.002577319508418441,
+      "clip_ratio/region_mean": 0.019234750187024474,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 10.0,
+      "completions/max_terminated_length": 10.0,
+      "completions/mean_length": 2.282738208770752,
+      "completions/mean_terminated_length": 2.282738208770752,
+      "completions/min_length": 2.0,
+      "completions/min_terminated_length": 2.0,
+      "entropy": 0.6793178021907806,
+      "epoch": 1.75,
+      "frac_reward_zero_std": 0.5059524178504944,
+      "grad_norm": 2.815258741378784,
+      "learning_rate": 1.7058239999999999e-06,
+      "loss": 0.0239,
+      "num_tokens": 773929.0,
+      "reward": 0.4851190447807312,
+      "reward_std": 0.4990306794643402,
+      "rewards/env_game_reward/mean": 0.4851190447807312,
+      "rewards/env_game_reward/std": 0.4990306794643402,
+      "sampling/importance_sampling_ratio/max": 1.8610674142837524,
+      "sampling/importance_sampling_ratio/mean": 1.0055298805236816,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 0.8122937679290771,
+      "sampling/sampling_logp_difference/mean": 0.07463809102773666,
+      "step": 7,
+      "step_time": 63.86528683999859
+    },
+    {
+      "clip_ratio/high_max": 0.01532895234413445,
+      "clip_ratio/high_mean": 0.008953135926276445,
+      "clip_ratio/low_mean": 0.009014535578899086,
+      "clip_ratio/low_min": 0.0024038462433964014,
+      "clip_ratio/region_mean": 0.017967671272344887,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 3.0,
+      "completions/max_terminated_length": 3.0,
+      "completions/mean_length": 2.2708334922790527,
+      "completions/mean_terminated_length": 2.2708334922790527,
+      "completions/min_length": 2.0,
+      "completions/min_terminated_length": 2.0,
+      "entropy": 0.6921011656522751,
+      "epoch": 2.0,
+      "frac_reward_zero_std": 0.4523809552192688,
+      "grad_norm": 2.390941619873047,
+      "learning_rate": 1.9901279999999997e-06,
+      "loss": 0.0071,
+      "num_tokens": 883556.0,
+      "reward": 0.5595238208770752,
+      "reward_std": 0.48962223529815674,
+      "rewards/env_game_reward/mean": 0.5595238208770752,
+      "rewards/env_game_reward/std": 0.48962223529815674,
+      "sampling/importance_sampling_ratio/max": 1.963092565536499,
+      "sampling/importance_sampling_ratio/mean": 0.9806411266326904,
+      "sampling/importance_sampling_ratio/min": 0.33748432993888855,
+      "sampling/sampling_logp_difference/max": 1.0179762840270996,
+      "sampling/sampling_logp_difference/mean": 0.07029423117637634,
+      "step": 8,
+      "step_time": 61.923666292001144
+    },
+    {
+      "epoch": 2.0,
+      "eval_clip_ratio/high_max": 0.0,
+      "eval_clip_ratio/high_mean": 0.0,
+      "eval_clip_ratio/low_mean": 0.0,
+      "eval_clip_ratio/low_min": 0.0,
+      "eval_clip_ratio/region_mean": 0.0,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 2.96,
+      "eval_completions/max_terminated_length": 2.96,
+      "eval_completions/mean_length": 2.25,
+      "eval_completions/mean_terminated_length": 2.25,
+      "eval_completions/min_length": 2.0,
+      "eval_completions/min_terminated_length": 2.0,
+      "eval_entropy": 0.663043782711029,
+      "eval_frac_reward_zero_std": 0.585,
+      "eval_loss": 0.014494094997644424,
+      "eval_num_tokens": 883556.0,
+      "eval_reward": 0.56,
+      "eval_reward_std": 0.458708074092865,
+      "eval_rewards/env_game_reward/mean": 0.56,
+      "eval_rewards/env_game_reward/std": 0.4587080860137939,
+      "eval_runtime": 84.5816,
+      "eval_samples_per_second": 2.365,
+      "eval_sampling/importance_sampling_ratio/max": 1.2596182644367218,
+      "eval_sampling/importance_sampling_ratio/mean": 0.9817599618434906,
+      "eval_sampling/importance_sampling_ratio/min": 0.7732881844043732,
+      "eval_sampling/sampling_logp_difference/max": 0.30535031914710997,
+      "eval_sampling/sampling_logp_difference/mean": 0.06819972261786461,
+      "eval_steps_per_second": 0.296,
+      "step": 8
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 40,
+  "num_input_tokens_seen": 883556,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 42,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c032b79691ec0f0ef3021b1a710ed25323ffa7544442b5a3dae4d76703d8ce5d
+size 7889