End of training

README.md

@@ -0,0 +1,86 @@
+---
+base_model: Qwen/Qwen2-0.5B-Instruct
+library_name: peft
+license: apache-2.0
+metrics:
+- accuracy
+tags:
+- trl
+- reward-trainer
+- generated_from_trainer
+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: 0.6423
+- Accuracy: 0.628
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.9852        | 0.0516 | 50   | 0.9181          | 0.478    |
+| 0.811         | 0.1032 | 100  | 0.8217          | 0.52     |
+| 0.7701        | 0.1548 | 150  | 0.7529          | 0.56     |
+| 0.7239        | 0.2064 | 200  | 0.7145          | 0.59     |
+| 0.723         | 0.2580 | 250  | 0.6917          | 0.597    |
+| 0.6912        | 0.3096 | 300  | 0.6812          | 0.615    |
+| 0.6577        | 0.3612 | 350  | 0.6702          | 0.626    |
+| 0.645         | 0.4128 | 400  | 0.6632          | 0.616    |
+| 0.6749        | 0.4644 | 450  | 0.6584          | 0.623    |
+| 0.6497        | 0.5160 | 500  | 0.6541          | 0.625    |
+| 0.659         | 0.5676 | 550  | 0.6526          | 0.626    |
+| 0.634         | 0.6192 | 600  | 0.6495          | 0.626    |
+| 0.6393        | 0.6708 | 650  | 0.6463          | 0.624    |
+| 0.6263        | 0.7224 | 700  | 0.6456          | 0.629    |
+| 0.6428        | 0.7740 | 750  | 0.6440          | 0.625    |
+| 0.6335        | 0.8256 | 800  | 0.6431          | 0.634    |
+| 0.6313        | 0.8772 | 850  | 0.6425          | 0.638    |
+| 0.6323        | 0.9288 | 900  | 0.6419          | 0.636    |
+| 0.6313        | 0.9804 | 950  | 0.6424          | 0.645    |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c86910d512447103802a83bb6ab96f48b13ed11262421c7a92b1f7c1eada139c
+size 8667080

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.628,
+    "eval_loss": 0.6423238515853882,
+    "eval_runtime": 2.1549,
+    "eval_samples_per_second": 464.065,
+    "eval_steps_per_second": 7.425
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.628,
+    "eval_loss": 0.6423238515853882,
+    "eval_runtime": 2.1549,
+    "eval_samples_per_second": 464.065,
+    "eval_steps_per_second": 7.425
+}

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 sha256:1eacbd2f267eda550b52bb0f5fd652a7c08b660746d7c39a6941177db805dd92
+size 5240