End of training

README.md

@@ -1,11 +1,13 @@
 ---
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - dpo
-- alignment-handbook
 - generated_from_trainer
 base_model: NbAiLab/nb-gpt-j-6B-v2
+datasets:
+- hugodk-sch/aftonposten_title_prefs
 model-index:
 - name: aftonposten-6b-align-scan
   results: []
@@ -16,17 +18,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # aftonposten-6b-align-scan
 
-This model is a fine-tuned version of [NbAiLab/nb-gpt-j-6B-v2](https://huggingface.co/NbAiLab/nb-gpt-j-6B-v2) on the None dataset.
+This model is a fine-tuned version of [data/ap-gpt-j-6b-sft-qlora-04-08](https://huggingface.co/data/ap-gpt-j-6b-sft-qlora-04-08) on the hugodk-sch/aftonposten_title_prefs dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6201
-- Rewards/chosen: 0.0327
-- Rewards/rejected: 0.0149
-- Rewards/accuracies: 0.5249
-- Rewards/margins: 0.0178
-- Logps/rejected: -37.4793
-- Logps/chosen: -33.9527
-- Logits/rejected: -2.2332
-- Logits/chosen: -2.2381
+- Loss: 1.6510
+- Rewards/chosen: 0.0280
+- Rewards/rejected: 0.0141
+- Rewards/accuracies: 0.5129
+- Rewards/margins: 0.0139
+- Logps/rejected: -37.4814
+- Logps/chosen: -33.9646
+- Logits/rejected: -2.2329
+- Logits/chosen: -2.2378
 
 ## Model description
 

all_results.json

@@ -1,18 +1,18 @@
 {
     "epoch": 4.0,
-    "eval_logits/chosen": -2.2312498092651367,
-    "eval_logits/rejected": -2.2264044284820557,
-    "eval_logps/chosen": -34.088890075683594,
-    "eval_logps/rejected": -37.596412658691406,
-    "eval_loss": 1.625149130821228,
-    "eval_rewards/accuracies": 0.5078904032707214,
-    "eval_rewards/chosen": -0.02173524722456932,
-    "eval_rewards/margins": 0.010181299410760403,
-    "eval_rewards/rejected": -0.0319165475666523,
-    "eval_runtime": 145.6511,
+    "eval_logits/chosen": -2.237769603729248,
+    "eval_logits/rejected": -2.232879638671875,
+    "eval_logps/chosen": -33.96460723876953,
+    "eval_logps/rejected": -37.48141860961914,
+    "eval_loss": 1.6509573459625244,
+    "eval_rewards/accuracies": 0.5128737688064575,
+    "eval_rewards/chosen": 0.02797684073448181,
+    "eval_rewards/margins": 0.013894001953303814,
+    "eval_rewards/rejected": 0.014082840643823147,
+    "eval_runtime": 145.2372,
     "eval_samples": 343,
-    "eval_samples_per_second": 2.355,
-    "eval_steps_per_second": 0.295,
+    "eval_samples_per_second": 2.362,
+    "eval_steps_per_second": 0.296,
     "train_loss": 0.36088944433571457,
     "train_runtime": 10769.3493,
     "train_samples": 3079,

config.json

@@ -18,6 +18,8 @@
   "n_layer": 28,
   "n_positions": 2048,
   "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,
@@ -45,7 +47,7 @@
   },
   "tie_word_embeddings": false,
   "tokenizer_class": "GPT2Tokenizer",
-  "transformers_version": "4.37.2",
+  "transformers_version": "4.39.0.dev0",
   "use_cache": true,
   "vocab_size": 50400
 }

eval_results.json

@@ -1,16 +1,16 @@
 {
-    "epoch": 1.0,
-    "eval_logits/chosen": -2.2312498092651367,
-    "eval_logits/rejected": -2.2264044284820557,
-    "eval_logps/chosen": -34.088890075683594,
-    "eval_logps/rejected": -37.596412658691406,
-    "eval_loss": 1.625149130821228,
-    "eval_rewards/accuracies": 0.5078904032707214,
-    "eval_rewards/chosen": -0.02173524722456932,
-    "eval_rewards/margins": 0.010181299410760403,
-    "eval_rewards/rejected": -0.0319165475666523,
-    "eval_runtime": 145.6511,
+    "epoch": 4.0,
+    "eval_logits/chosen": -2.237769603729248,
+    "eval_logits/rejected": -2.232879638671875,
+    "eval_logps/chosen": -33.96460723876953,
+    "eval_logps/rejected": -37.48141860961914,
+    "eval_loss": 1.6509573459625244,
+    "eval_rewards/accuracies": 0.5128737688064575,
+    "eval_rewards/chosen": 0.02797684073448181,
+    "eval_rewards/margins": 0.013894001953303814,
+    "eval_rewards/rejected": 0.014082840643823147,
+    "eval_runtime": 145.2372,
     "eval_samples": 343,
-    "eval_samples_per_second": 2.355,
-    "eval_steps_per_second": 0.295
+    "eval_samples_per_second": 2.362,
+    "eval_steps_per_second": 0.296
 }