End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: apache-2.0
 base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- data/ui_logic
 model-index:
 - name: tinyllama-1.1b-chat-v1.0-ui-logic-dpo-2
   results: []
@@ -16,7 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-1.1b-chat-v1.0-ui-logic-dpo-2
 
-This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset.
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the data/ui_logic dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6931
+- Rewards/chosen: 0.0
+- Rewards/rejected: 0.0
+- Rewards/accuracies: 0.0
+- Rewards/margins: 0.0
+- Logps/rejected: -98.5013
+- Logps/chosen: -174.8483
+- Logits/rejected: -2.1785
+- Logits/chosen: -2.4442
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 2.0,
+    "eval_logits/chosen": -2.444159746170044,
+    "eval_logits/rejected": -2.178493022918701,
+    "eval_logps/chosen": -174.84832763671875,
+    "eval_logps/rejected": -98.5013198852539,
+    "eval_loss": 0.6931471228599548,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": 0.0,
+    "eval_rewards/margins": 0.0,
+    "eval_rewards/rejected": 0.0,
+    "eval_runtime": 0.4442,
+    "eval_samples": 50,
+    "eval_samples_per_second": 112.556,
+    "eval_steps_per_second": 2.251,
     "total_flos": 0.0,
     "train_loss": 0.1732867956161499,
     "train_runtime": 32.9673,

config.json

@@ -24,6 +24,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 2.0,
+    "eval_logits/chosen": -2.444159746170044,
+    "eval_logits/rejected": -2.178493022918701,
+    "eval_logps/chosen": -174.84832763671875,
+    "eval_logps/rejected": -98.5013198852539,
+    "eval_loss": 0.6931471228599548,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": 0.0,
+    "eval_rewards/margins": 0.0,
+    "eval_rewards/rejected": 0.0,
+    "eval_runtime": 0.4442,
+    "eval_samples": 50,
+    "eval_samples_per_second": 112.556,
+    "eval_steps_per_second": 2.251
+}