End of training

README.md

@@ -1,11 +1,13 @@
 ---
-license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
 base_model: norallm/normistral-7b-warm
+datasets:
+- hugodk-sch/aftonposten_title_prefs
 model-index:
 - name: ap-normistral-7b-align-scan
   results: []
@@ -16,17 +18,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ap-normistral-7b-align-scan
 
-This model is a fine-tuned version of [norallm/normistral-7b-warm](https://huggingface.co/norallm/normistral-7b-warm) on the None dataset.
+This model is a fine-tuned version of [data/ap-normistral-7b-sft-qlora](https://huggingface.co/data/ap-normistral-7b-sft-qlora) on the hugodk-sch/aftonposten_title_prefs dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7249
-- Rewards/chosen: -0.1096
-- Rewards/rejected: -0.2129
-- Rewards/accuracies: 0.5282
-- Rewards/margins: 0.1033
-- Logps/rejected: -36.3214
-- Logps/chosen: -32.6259
-- Logits/rejected: 98.6240
-- Logits/chosen: 98.6482
+- Loss: 0.7295
+- Rewards/chosen: -0.1029
+- Rewards/rejected: -0.1921
+- Rewards/accuracies: 0.5507
+- Rewards/margins: 0.0893
+- Logps/rejected: -36.2867
+- Logps/chosen: -32.6146
+- Logits/rejected: 98.5914
+- Logits/chosen: 98.6142
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": 98.61418151855469,
+    "eval_logits/rejected": 98.59135437011719,
+    "eval_logps/chosen": -32.61461639404297,
+    "eval_logps/rejected": -36.286746978759766,
+    "eval_loss": 0.7295444011688232,
+    "eval_rewards/accuracies": 0.550664484500885,
+    "eval_rewards/chosen": -0.10286416858434677,
+    "eval_rewards/margins": 0.08926620334386826,
+    "eval_rewards/rejected": -0.19213035702705383,
+    "eval_runtime": 103.7555,
+    "eval_samples": 343,
+    "eval_samples_per_second": 3.306,
+    "eval_steps_per_second": 0.414,
     "train_loss": 0.5886486524111265,
     "train_runtime": 2556.9439,
     "train_samples": 3079,

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "norallm/normistral-7b-warm",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 2048,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 2048,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32768
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": 98.61418151855469,
+    "eval_logits/rejected": 98.59135437011719,
+    "eval_logps/chosen": -32.61461639404297,
+    "eval_logps/rejected": -36.286746978759766,
+    "eval_loss": 0.7295444011688232,
+    "eval_rewards/accuracies": 0.550664484500885,
+    "eval_rewards/chosen": -0.10286416858434677,
+    "eval_rewards/margins": 0.08926620334386826,
+    "eval_rewards/rejected": -0.19213035702705383,
+    "eval_runtime": 103.7555,
+    "eval_samples": 343,
+    "eval_samples_per_second": 3.306,
+    "eval_steps_per_second": 0.414
+}