End of training

README.md

@@ -1,13 +1,13 @@
 ---
-base_model: Qwen/Qwen2-0.5B-Instruct
-library_name: peft
+library_name: transformers
 license: apache-2.0
-metrics:
-- accuracy
+base_model: Qwen/Qwen2-0.5B-Instruct
 tags:
 - trl
 - reward-trainer
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: Qwen2-0.5B-Reward
   results: []
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 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
+- Loss: 0.5139
+- Accuracy: 0.723
 
 ## Model description
 
@@ -56,31 +56,30 @@ The following hyperparameters were used during training:
 
 | 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    |
+| 0.6426        | 0.0516 | 50   | 0.6197          | 0.664    |
+| 0.5877        | 0.1032 | 100  | 0.6080          | 0.662    |
+| 0.5902        | 0.1548 | 150  | 0.5787          | 0.697    |
+| 0.5582        | 0.2064 | 200  | 0.5555          | 0.694    |
+| 0.5664        | 0.2580 | 250  | 0.5441          | 0.699    |
+| 0.5638        | 0.3096 | 300  | 0.5290          | 0.716    |
+| 0.5375        | 0.3612 | 350  | 0.5315          | 0.729    |
+| 0.5233        | 0.4128 | 400  | 0.5380          | 0.718    |
+| 0.5375        | 0.4644 | 450  | 0.5482          | 0.71     |
+| 0.5223        | 0.5160 | 500  | 0.5352          | 0.72     |
+| 0.5229        | 0.5676 | 550  | 0.5251          | 0.724    |
+| 0.5173        | 0.6192 | 600  | 0.5181          | 0.717    |
+| 0.5227        | 0.6708 | 650  | 0.5178          | 0.724    |
+| 0.5103        | 0.7224 | 700  | 0.5153          | 0.728    |
+| 0.5178        | 0.7740 | 750  | 0.5198          | 0.725    |
+| 0.5072        | 0.8256 | 800  | 0.5195          | 0.722    |
+| 0.5137        | 0.8772 | 850  | 0.5168          | 0.725    |
+| 0.4995        | 0.9288 | 900  | 0.5146          | 0.724    |
+| 0.4988        | 0.9804 | 950  | 0.5135          | 0.723    |
 
 
 ### Framework versions
 
-- PEFT 0.12.0
 - Transformers 4.44.2
 - Pytorch 2.4.0+cu121
 - Datasets 2.21.0
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -1,8 +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_accuracy": 0.723,
+    "eval_loss": 0.5138623118400574,
+    "eval_runtime": 2.0077,
+    "eval_samples_per_second": 498.086,
+    "eval_steps_per_second": 7.969
 }

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
+}

eval_results.json

@@ -1,8 +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_accuracy": 0.723,
+    "eval_loss": 0.5138623118400574,
+    "eval_runtime": 2.0077,
+    "eval_samples_per_second": 498.086,
+    "eval_steps_per_second": 7.969
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df0861428ae56d0926aca933d0a8d4aa61d7eb92bb82d044f698df7907cf9f8c
+size 1976167144

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eacbd2f267eda550b52bb0f5fd652a7c08b660746d7c39a6941177db805dd92
+oid sha256:9b3fbf44a004ce45641fabec53e0923a0949fc045787bc754a16c82fbf95311f
 size 5240