Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen2.5-Math-7B-Instruct
+library_name: transformers
+model_name: Qwen2.5-Math-7B-limo-32b
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen2.5-Math-7B-limo-32b
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct).
+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="flyingbugs/Qwen2.5-Math-7B-limo-32b", 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/jjh233/huggingface/runs/krfigq0z) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.16.0.dev0
+- Transformers: 4.49.0
+- Pytorch: 2.5.1+cu121
+- Datasets: 3.3.2
+- Tokenizers: 0.21.0
+
+## Citations
+
+
+
+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}}
+}
+```

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 2.405963155911475e+16,
+    "train_loss": 1.1475475907325745,
+    "train_runtime": 2093.4116,
+    "train_samples": 817,
+    "train_samples_per_second": 0.279,
+    "train_steps_per_second": 0.017
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "4.49.0"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 2.405963155911475e+16,
+    "train_loss": 1.1475475907325745,
+    "train_runtime": 2093.4116,
+    "train_samples": 817,
+    "train_samples_per_second": 0.279,
+    "train_steps_per_second": 0.017
+}

trainer_state.json

@@ -0,0 +1,287 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.4,
+  "eval_steps": 500,
+  "global_step": 35,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 61.002196119963415,
+      "learning_rate": 1.25e-05,
+      "loss": 9.6521,
+      "step": 1
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 59.68197006424668,
+      "learning_rate": 2.5e-05,
+      "loss": 10.4754,
+      "step": 2
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 115.28866439806573,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 7.9276,
+      "step": 3
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 5.026604488593246,
+      "learning_rate": 5e-05,
+      "loss": 1.0091,
+      "step": 4
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 18.284557987546222,
+      "learning_rate": 4.8387096774193554e-05,
+      "loss": 0.821,
+      "step": 5
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.335241273848215,
+      "learning_rate": 4.67741935483871e-05,
+      "loss": 0.6936,
+      "step": 6
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 1.5610677709465839,
+      "learning_rate": 4.516129032258064e-05,
+      "loss": 0.641,
+      "step": 7
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.5610677709465839,
+      "learning_rate": 4.3548387096774194e-05,
+      "loss": 0.5921,
+      "step": 8
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 1.8146294678665253,
+      "learning_rate": 4.1935483870967746e-05,
+      "loss": 0.5122,
+      "step": 9
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.830943575869942,
+      "learning_rate": 4.032258064516129e-05,
+      "loss": 0.4664,
+      "step": 10
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.0646461102885592,
+      "learning_rate": 3.870967741935484e-05,
+      "loss": 0.4444,
+      "step": 11
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.7667627389601128,
+      "learning_rate": 3.7096774193548386e-05,
+      "loss": 0.4152,
+      "step": 12
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.6897014886908456,
+      "learning_rate": 3.548387096774194e-05,
+      "loss": 0.4101,
+      "step": 13
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.6554819229001853,
+      "learning_rate": 3.387096774193548e-05,
+      "loss": 0.4189,
+      "step": 14
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.6643280194216655,
+      "learning_rate": 3.2258064516129034e-05,
+      "loss": 0.3616,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8920680798592996,
+      "learning_rate": 3.0645161290322585e-05,
+      "loss": 0.3763,
+      "step": 16
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.43437514697907426,
+      "learning_rate": 2.9032258064516133e-05,
+      "loss": 0.3115,
+      "step": 17
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.5348299514481543,
+      "learning_rate": 2.7419354838709678e-05,
+      "loss": 0.3471,
+      "step": 18
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.39798671239558964,
+      "learning_rate": 2.5806451612903226e-05,
+      "loss": 0.3101,
+      "step": 19
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.3233409204244813,
+      "learning_rate": 2.4193548387096777e-05,
+      "loss": 0.3004,
+      "step": 20
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.3468443429436706,
+      "learning_rate": 2.258064516129032e-05,
+      "loss": 0.2864,
+      "step": 21
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.353852322346739,
+      "learning_rate": 2.0967741935483873e-05,
+      "loss": 0.3033,
+      "step": 22
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.34827318614267444,
+      "learning_rate": 1.935483870967742e-05,
+      "loss": 0.2909,
+      "step": 23
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.34827318614267444,
+      "learning_rate": 1.774193548387097e-05,
+      "loss": 0.2396,
+      "step": 24
+    },
+    {
+      "epoch": 3.1333333333333333,
+      "grad_norm": 0.5424513562301403,
+      "learning_rate": 1.6129032258064517e-05,
+      "loss": 0.2729,
+      "step": 25
+    },
+    {
+      "epoch": 3.2666666666666666,
+      "grad_norm": 0.22767648801657112,
+      "learning_rate": 1.4516129032258066e-05,
+      "loss": 0.2537,
+      "step": 26
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.2983041747382757,
+      "learning_rate": 1.2903225806451613e-05,
+      "loss": 0.2441,
+      "step": 27
+    },
+    {
+      "epoch": 3.533333333333333,
+      "grad_norm": 0.3182178332656054,
+      "learning_rate": 1.129032258064516e-05,
+      "loss": 0.247,
+      "step": 28
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.22393185039590235,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 0.2305,
+      "step": 29
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.2338202458675513,
+      "learning_rate": 8.064516129032258e-06,
+      "loss": 0.2154,
+      "step": 30
+    },
+    {
+      "epoch": 3.9333333333333336,
+      "grad_norm": 0.219474134538978,
+      "learning_rate": 6.451612903225806e-06,
+      "loss": 0.2298,
+      "step": 31
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.3171234500428613,
+      "learning_rate": 4.838709677419355e-06,
+      "loss": 0.2251,
+      "step": 32
+    },
+    {
+      "epoch": 4.133333333333334,
+      "grad_norm": 0.19082869700096614,
+      "learning_rate": 3.225806451612903e-06,
+      "loss": 0.2178,
+      "step": 33
+    },
+    {
+      "epoch": 4.266666666666667,
+      "grad_norm": 0.2368468460236031,
+      "learning_rate": 1.6129032258064516e-06,
+      "loss": 0.2157,
+      "step": 34
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 0.1873214549049323,
+      "learning_rate": 0.0,
+      "loss": 0.2057,
+      "step": 35
+    },
+    {
+      "epoch": 4.4,
+      "step": 35,
+      "total_flos": 2.405963155911475e+16,
+      "train_loss": 1.1475475907325745,
+      "train_runtime": 2093.4116,
+      "train_samples_per_second": 0.279,
+      "train_steps_per_second": 0.017
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 35,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.405963155911475e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}