End of training

README.md

@@ -0,0 +1,85 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Qwen/Qwen2-0.5B-Instruct
+tags:
+- trl
+- reward-trainer
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: Qwen2-0.5B-Reward
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Qwen2-0.5B-Reward
+
+This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5182
+- Accuracy: 0.728
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.6444        | 0.0516 | 50   | 0.6037          | 0.672    |
+| 0.5825        | 0.1032 | 100  | 0.5859          | 0.682    |
+| 0.5732        | 0.1548 | 150  | 0.5751          | 0.704    |
+| 0.5494        | 0.2064 | 200  | 0.5514          | 0.701    |
+| 0.5654        | 0.2580 | 250  | 0.5427          | 0.709    |
+| 0.5514        | 0.3096 | 300  | 0.5309          | 0.723    |
+| 0.537         | 0.3612 | 350  | 0.5259          | 0.735    |
+| 0.5236        | 0.4128 | 400  | 0.5368          | 0.714    |
+| 0.536         | 0.4644 | 450  | 0.5451          | 0.726    |
+| 0.5236        | 0.5160 | 500  | 0.5371          | 0.727    |
+| 0.526         | 0.5676 | 550  | 0.5293          | 0.729    |
+| 0.5197        | 0.6192 | 600  | 0.5239          | 0.727    |
+| 0.525         | 0.6708 | 650  | 0.5227          | 0.732    |
+| 0.5123        | 0.7224 | 700  | 0.5206          | 0.723    |
+| 0.5171        | 0.7740 | 750  | 0.5237          | 0.718    |
+| 0.5156        | 0.8256 | 800  | 0.5245          | 0.722    |
+| 0.5115        | 0.8772 | 850  | 0.5234          | 0.723    |
+| 0.5007        | 0.9288 | 900  | 0.5207          | 0.729    |
+| 0.5018        | 0.9804 | 950  | 0.5182          | 0.728    |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

added_tokens.json

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

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "architectures": [
+    "Qwen2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc663e240eb3b5a1f4b8ae4e24ff03fa11cd39d397d93b73f62bef3f5645f4e
+size 1976167144

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_config.json

@@ -0,0 +1,43 @@
+{
+  "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",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56f657b0820015fb3d9eeffd7193b370e0029b9f4fb1a9ce77bb75e184f10ec
+size 5240