End of training

.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 +1,71 @@
+---
+base_model: Qwen/Qwen1.5-0.5B-Chat
+library_name: transformers
+model_name: Qwen1.5-0.5B-Chat-Gensyn-Swarm-barky_sedate_albatross
+tags:
+- generated_from_trainer
+- rl-swarm
+- grpo
+- gensyn
+- I am barky sedate albatross
+- trl
+licence: license
+---
+
+# Model Card for Qwen1.5-0.5B-Chat-Gensyn-Swarm-barky_sedate_albatross
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat).
+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="jimmychin/Qwen1.5-0.5B-Chat-Gensyn-Swarm-barky_sedate_albatross", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+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: 0.15.2
+- Transformers: 4.51.3
+- Pytorch: 2.6.0
+- Datasets: 3.5.0
+- Tokenizers: 0.21.1
+
+## 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
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 3.0766487361688634e-05,
+    "train_runtime": 15532.1172,
+    "train_samples": 31,
+    "train_samples_per_second": 0.021,
+    "train_steps_per_second": 0.001
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "top_p": 0.8,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c0c764ca0d933b93819ff7bc0585a7efbb24e10508fb899d9467e6278c0cec
+size 1855983640

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,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 3.0766487361688634e-05,
+    "train_runtime": 15532.1172,
+    "train_samples": 31,
+    "train_samples_per_second": 0.021,
+    "train_steps_per_second": 0.001
+}

trainer_state.json

@@ -0,0 +1,233 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 20.375,
+      "epoch": 0.5161290322580645,
+      "grad_norm": 11.062353134155273,
+      "kl": 0.0,
+      "learning_rate": 5e-07,
+      "loss": 0.0,
+      "reward": 0.04815642529865727,
+      "reward_std": 0.008239762046287069,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.04815642529865727,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.0,
+      "step": 2
+    },
+    {
+      "completion_length": 47.96666666666667,
+      "epoch": 1.0,
+      "grad_norm": 33.4072151184082,
+      "kl": 0.0021562006848398598,
+      "learning_rate": 4.864543104251586e-07,
+      "loss": 0.0,
+      "reward": 0.13018689304590225,
+      "reward_std": 0.057520271216829615,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.13018689304590225,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.0,
+      "step": 4
+    },
+    {
+      "completion_length": 45.09375,
+      "epoch": 1.5161290322580645,
+      "grad_norm": 8.136409759521484,
+      "kl": 0.012652793423512776,
+      "learning_rate": 4.472851273490984e-07,
+      "loss": 0.0,
+      "reward": 0.11348086304496974,
+      "reward_std": 0.03734262226498686,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.11482461250852793,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.0013437500456348062,
+      "step": 6
+    },
+    {
+      "completion_length": 42.266666666666666,
+      "epoch": 2.0,
+      "grad_norm": 34.756309509277344,
+      "kl": 0.022623057938956966,
+      "learning_rate": 3.8673703953060673e-07,
+      "loss": 0.0,
+      "reward": 0.06224373144408067,
+      "reward_std": 0.02971583668064947,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.06224373144408067,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.0,
+      "step": 8
+    },
+    {
+      "completion_length": 46.21875,
+      "epoch": 2.5161290322580645,
+      "grad_norm": 7.123109340667725,
+      "kl": 0.03502856167324353,
+      "learning_rate": 3.1137137178519977e-07,
+      "loss": 0.0,
+      "reward": 0.0759008351014927,
+      "reward_std": 0.02389856088848319,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.0759008351014927,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.0,
+      "step": 10
+    },
+    {
+      "completion_length": 44.36666666666667,
+      "epoch": 3.0,
+      "grad_norm": 7.818780422210693,
+      "kl": 0.022568917196864883,
+      "learning_rate": 2.2935516363191693e-07,
+      "loss": 0.0,
+      "reward": 0.08929347985734543,
+      "reward_std": 0.017616315085130434,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.08929347985734543,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.0,
+      "step": 12
+    },
+    {
+      "completion_length": 73.15625,
+      "epoch": 3.5161290322580645,
+      "grad_norm": 16.331836700439453,
+      "kl": 0.044795535439334344,
+      "learning_rate": 1.4957614383675767e-07,
+      "loss": 0.0,
+      "reward": 0.10291314494679682,
+      "reward_std": 0.03227931309083942,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.10291314494679682,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.0,
+      "step": 14
+    },
+    {
+      "completion_length": 55.333333333333336,
+      "epoch": 4.0,
+      "grad_norm": 6.074650287628174,
+      "kl": 0.014543108890453975,
+      "learning_rate": 8.067960709356475e-08,
+      "loss": 0.0,
+      "reward": 0.0832365710909168,
+      "reward_std": 0.030701078412433466,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.0832365710909168,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.0,
+      "step": 16
+    },
+    {
+      "completion_length": 51.125,
+      "epoch": 4.516129032258064,
+      "grad_norm": 10.109783172607422,
+      "kl": 0.024721574096474797,
+      "learning_rate": 3.013156219837776e-08,
+      "loss": 0.0,
+      "reward": 0.0759926013997756,
+      "reward_std": 0.026536535182458465,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.0759926013997756,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.0,
+      "step": 18
+    },
+    {
+      "completion_length": 100.86666666666666,
+      "epoch": 5.0,
+      "grad_norm": 14.475935935974121,
+      "kl": 0.141564985178411,
+      "learning_rate": 3.4096741493194193e-09,
+      "loss": 0.0001,
+      "reward": 0.13194180838763714,
+      "reward_std": 0.04699777302642663,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
+      "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.13194180838763714,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "step": 20,
+      "total_flos": 0.0,
+      "train_loss": 3.0766487361688634e-05,
+      "train_runtime": 15532.1172,
+      "train_samples_per_second": 0.021,
+      "train_steps_per_second": 0.001
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60af420daa27dea7801dca555dbe68a13e85fa702d2aa8601127d14949d55ee9
+size 5944