End of training

README.md

@@ -1,7 +1,12 @@
 ---
 base_model: slm-research-vn/Qwen2-7B-Instruct-SPPO-Function-call-v2.5
+datasets:
+- slm-research-vn/dpo-format-function-calling-v4
+- slm-research-vn/dpo-format-glaive-code-assistant-v3-with-mistral-large-slm-iter4
+- argilla/dpo-mix-7k
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
@@ -15,17 +20,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Qwen2-7B-Instruct-SPPO-Function-call-v2.6
 
-This model is a fine-tuned version of [slm-research-vn/Qwen2-7B-Instruct-SPPO-Function-call-v2.5](https://huggingface.co/slm-research-vn/Qwen2-7B-Instruct-SPPO-Function-call-v2.5) on the None dataset.
+This model is a fine-tuned version of [slm-research-vn/Qwen2-7B-Instruct-SPPO-Function-call-v2.5](https://huggingface.co/slm-research-vn/Qwen2-7B-Instruct-SPPO-Function-call-v2.5) on the slm-research-vn/dpo-format-function-calling-v4, the slm-research-vn/dpo-format-glaive-code-assistant-v3-with-mistral-large-slm-iter4 and the argilla/dpo-mix-7k datasets.
 It achieves the following results on the evaluation set:
-- Loss: 0.2999
-- Rewards/chosen: 1.6798
-- Rewards/rejected: -0.4929
-- Rewards/accuracies: 0.8844
-- Rewards/margins: 2.1726
-- Logps/rejected: -276.8312
-- Logps/chosen: -200.8157
-- Logits/rejected: -0.6690
-- Logits/chosen: -0.6635
+- Loss: 0.3005
+- Rewards/chosen: 1.6737
+- Rewards/rejected: -0.4932
+- Rewards/accuracies: 0.8699
+- Rewards/margins: 2.1670
+- Logps/rejected: -276.8380
+- Logps/chosen: -200.9362
+- Logits/rejected: -0.6568
+- Logits/chosen: -0.6408
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9995419147961521,
+    "eval_logits/chosen": -0.6407761573791504,
+    "eval_logits/rejected": -0.6567662358283997,
+    "eval_logps/chosen": -200.93621826171875,
+    "eval_logps/rejected": -276.8379821777344,
+    "eval_loss": 0.30047258734703064,
+    "eval_rewards/accuracies": 0.8699421882629395,
+    "eval_rewards/chosen": 1.6737332344055176,
+    "eval_rewards/margins": 2.166951894760132,
+    "eval_rewards/rejected": -0.4932188391685486,
+    "eval_runtime": 252.7931,
+    "eval_samples": 2763,
+    "eval_samples_per_second": 10.93,
+    "eval_steps_per_second": 1.369,
     "total_flos": 0.0,
     "train_loss": 0.37405444834616947,
     "train_runtime": 8738.9435,

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "slm-research-vn/Qwen2-7B-Instruct-SPPO-Function-call-v2.5",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9995419147961521,
+    "eval_logits/chosen": -0.6407761573791504,
+    "eval_logits/rejected": -0.6567662358283997,
+    "eval_logps/chosen": -200.93621826171875,
+    "eval_logps/rejected": -276.8379821777344,
+    "eval_loss": 0.30047258734703064,
+    "eval_rewards/accuracies": 0.8699421882629395,
+    "eval_rewards/chosen": 1.6737332344055176,
+    "eval_rewards/margins": 2.166951894760132,
+    "eval_rewards/rejected": -0.4932188391685486,
+    "eval_runtime": 252.7931,
+    "eval_samples": 2763,
+    "eval_samples_per_second": 10.93,
+    "eval_steps_per_second": 1.369
+}