Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,67 @@
+---
+base_model: Qwen/Qwen2-1.5B-Instruct
+datasets: RyanFan/PMData-readiness-raw-update
+library_name: transformers
+tags:
+- generated_from_trainer
+- rl-verify
+licence: license
+---
+
+# Model Card for None
+
+This model is a fine-tuned version of [Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct) on the [RyanFan/PMData-readiness-raw-update](https://huggingface.co/datasets/RyanFan/PMData-readiness-raw-update) dataset.
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ryanzhang123-the-university-of-auckland/RLCR/runs/i44bgsik) 
+
+
+This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+
+### Framework versions
+
+- TRL: 0.16.0.dev0
+- Transformers: 4.57.6
+- Pytorch: 2.5.1
+- Datasets: 4.0.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+Cite GRPO as:
+
+```bibtex
+@article{zhihong2024deepseekmath,
+    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year         = 2024,
+    eprint       = {arXiv:2402.03300},
+}
+
+```
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.6"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:867039882f8213186957057f6806c1eb05fbc2099b9cee1b7a5ce30efb7749ba
+size 2097152

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c852534ad33d333aa478034d64cd37cb14da033a24674c4b2518300f488efa
+size 11418433

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,225 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9855072463768116,
+  "eval_steps": 50,
+  "global_step": 34,
+  "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": 0.009375,
+      "completions/max_length": 1421.6,
+      "completions/max_terminated_length": 1060.8,
+      "completions/mean_length": 251.61875,
+      "completions/mean_terminated_length": 239.34337158203124,
+      "completions/min_length": 79.4,
+      "completions/min_terminated_length": 79.4,
+      "epoch": 0.14492753623188406,
+      "grad_norm": 0.42041119933128357,
+      "learning_rate": 1e-06,
+      "loss": 0.0214,
+      "num_tokens": 708324.0,
+      "reward": 0.6069940328598022,
+      "reward_std": 0.2593126893043518,
+      "rewards/accuracy_reward": 0.0390625,
+      "rewards/brier_reward": 0.31242387294769286,
+      "rewards/confidence_one_or_zero": 0.1171875,
+      "rewards/format_reward": 0.8625,
+      "rewards/mean_confidence_reward": 0.721567976474762,
+      "step": 5
+    },
+    {
+      "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": 0.0171875,
+      "completions/max_length": 1386.4,
+      "completions/max_terminated_length": 1058.6,
+      "completions/mean_length": 247.63125,
+      "completions/mean_terminated_length": 225.28215637207032,
+      "completions/min_length": 71.0,
+      "completions/min_terminated_length": 71.0,
+      "epoch": 0.2898550724637681,
+      "grad_norm": 0.36987483501434326,
+      "learning_rate": 1e-06,
+      "loss": 0.0255,
+      "num_tokens": 1434540.0,
+      "reward": 0.6972500443458557,
+      "reward_std": 0.2571786344051361,
+      "rewards/accuracy_reward": 0.0875,
+      "rewards/brier_reward": 0.383560973405838,
+      "rewards/confidence_one_or_zero": 0.0953125,
+      "rewards/format_reward": 0.9234375,
+      "rewards/mean_confidence_reward": 0.7222430467605591,
+      "step": 10
+    },
+    {
+      "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": 0.009375,
+      "completions/max_length": 1118.2,
+      "completions/max_terminated_length": 599.6,
+      "completions/mean_length": 194.978125,
+      "completions/mean_terminated_length": 182.34744262695312,
+      "completions/min_length": 67.0,
+      "completions/min_terminated_length": 67.0,
+      "epoch": 0.43478260869565216,
+      "grad_norm": 0.4234364330768585,
+      "learning_rate": 1e-06,
+      "loss": 0.0102,
+      "num_tokens": 2107210.0,
+      "reward": 0.7554357528686524,
+      "reward_std": 0.21138001680374147,
+      "rewards/accuracy_reward": 0.0828125,
+      "rewards/brier_reward": 0.4499324679374695,
+      "rewards/confidence_one_or_zero": 0.0921875,
+      "rewards/format_reward": 0.978125,
+      "rewards/mean_confidence_reward": 0.6967766165733338,
+      "step": 15
+    },
+    {
+      "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": 0.003125,
+      "completions/max_length": 1042.4,
+      "completions/max_terminated_length": 569.6,
+      "completions/mean_length": 167.0515625,
+      "completions/mean_terminated_length": 162.76224060058593,
+      "completions/min_length": 63.8,
+      "completions/min_terminated_length": 63.8,
+      "epoch": 0.5797101449275363,
+      "grad_norm": 0.46815362572669983,
+      "learning_rate": 1e-06,
+      "loss": 0.0123,
+      "num_tokens": 2777563.0,
+      "reward": 0.8507023096084595,
+      "reward_std": 0.22829608023166656,
+      "rewards/accuracy_reward": 0.1375,
+      "rewards/brier_reward": 0.5732782363891602,
+      "rewards/confidence_one_or_zero": 0.078125,
+      "rewards/format_reward": 0.990625,
+      "rewards/mean_confidence_reward": 0.616986072063446,
+      "step": 20
+    },
+    {
+      "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": 0.00625,
+      "completions/max_length": 1114.8,
+      "completions/max_terminated_length": 488.8,
+      "completions/mean_length": 158.7921875,
+      "completions/mean_terminated_length": 150.14754943847657,
+      "completions/min_length": 58.2,
+      "completions/min_terminated_length": 58.2,
+      "epoch": 0.7246376811594203,
+      "grad_norm": 0.33041155338287354,
+      "learning_rate": 1e-06,
+      "loss": 0.0136,
+      "num_tokens": 3419758.0,
+      "reward": 0.8955987334251404,
+      "reward_std": 0.19381383955478668,
+      "rewards/accuracy_reward": 0.128125,
+      "rewards/brier_reward": 0.6771338224411011,
+      "rewards/confidence_one_or_zero": 0.0953125,
+      "rewards/format_reward": 0.9859375,
+      "rewards/mean_confidence_reward": 0.4792247414588928,
+      "step": 25
+    },
+    {
+      "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": 318.2,
+      "completions/max_terminated_length": 318.2,
+      "completions/mean_length": 124.6,
+      "completions/mean_terminated_length": 124.6,
+      "completions/min_length": 51.4,
+      "completions/min_terminated_length": 51.4,
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.22344355285167694,
+      "learning_rate": 1e-06,
+      "loss": 0.0017,
+      "num_tokens": 4041286.0,
+      "reward": 0.9700731754302978,
+      "reward_std": 0.11841013431549072,
+      "rewards/accuracy_reward": 0.128125,
+      "rewards/brier_reward": 0.8135828733444214,
+      "rewards/confidence_one_or_zero": 0.209375,
+      "rewards/format_reward": 0.9984375,
+      "rewards/mean_confidence_reward": 0.2868975430727005,
+      "step": 30
+    },
+    {
+      "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": 342.25,
+      "completions/max_terminated_length": 342.25,
+      "completions/mean_length": 104.64101600646973,
+      "completions/mean_terminated_length": 104.64101600646973,
+      "completions/min_length": 47.0,
+      "completions/min_terminated_length": 47.0,
+      "epoch": 0.9855072463768116,
+      "num_tokens": 4536704.0,
+      "reward": 0.9970973432064056,
+      "reward_std": 0.06293923873454332,
+      "rewards/accuracy_reward": 0.12109375,
+      "rewards/brier_reward": 0.8730999976396561,
+      "rewards/confidence_one_or_zero": 0.306640625,
+      "rewards/format_reward": 1.0,
+      "rewards/mean_confidence_reward": 0.1555468812584877,
+      "step": 34,
+      "total_flos": 0.0,
+      "train_loss": 0.012820063487571828,
+      "train_runtime": 632.9133,
+      "train_samples_per_second": 1.744,
+      "train_steps_per_second": 0.055
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 35,
+  "num_input_tokens_seen": 4536704,
+  "num_train_epochs": 1,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc056d1bec36d62fee133165b27a4db6078148570bde87c754335bb403236e82
+size 8184