End of training

README.md

@@ -3,9 +3,16 @@ 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_math
+- data/ui_coding
 model-index:
 - name: tinyllama-1.1b-chat-v1.0-ui-math-coding-dpo-2
   results: []
@@ -16,17 +23,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-1.1b-chat-v1.0-ui-math-coding-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 the None 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_math and the data/ui_coding datasets.
 It achieves the following results on the evaluation set:
-- Loss: 0.3224
-- Rewards/chosen: -3.3080
-- Rewards/rejected: -7.0491
-- Rewards/accuracies: 0.9062
-- Rewards/margins: 3.7411
-- Logps/rejected: -1048.2871
-- Logps/chosen: -689.9403
-- Logits/rejected: -1.4398
-- Logits/chosen: -1.4575
+- Loss: 0.3362
+- Rewards/chosen: -3.2340
+- Rewards/rejected: -7.1489
+- Rewards/accuracies: 0.875
+- Rewards/margins: 3.9149
+- Logps/rejected: -1058.2659
+- Logps/chosen: -682.5323
+- Logits/rejected: -1.3117
+- Logits/chosen: -1.3352
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 2.0,
+    "eval_logits/chosen": -1.3352028131484985,
+    "eval_logits/rejected": -1.3116942644119263,
+    "eval_logps/chosen": -682.5323486328125,
+    "eval_logps/rejected": -1058.265869140625,
+    "eval_loss": 0.3361551761627197,
+    "eval_rewards/accuracies": 0.875,
+    "eval_rewards/chosen": -3.233959674835205,
+    "eval_rewards/margins": 3.914942741394043,
+    "eval_rewards/rejected": -7.148902893066406,
+    "eval_runtime": 2.9627,
+    "eval_samples": 200,
+    "eval_samples_per_second": 67.507,
+    "eval_steps_per_second": 1.35,
     "total_flos": 0.0,
     "train_loss": 0.2817063624168927,
     "train_runtime": 11455.6006,

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": -1.3352028131484985,
+    "eval_logits/rejected": -1.3116942644119263,
+    "eval_logps/chosen": -682.5323486328125,
+    "eval_logps/rejected": -1058.265869140625,
+    "eval_loss": 0.3361551761627197,
+    "eval_rewards/accuracies": 0.875,
+    "eval_rewards/chosen": -3.233959674835205,
+    "eval_rewards/margins": 3.914942741394043,
+    "eval_rewards/rejected": -7.148902893066406,
+    "eval_runtime": 2.9627,
+    "eval_samples": 200,
+    "eval_samples_per_second": 67.507,
+    "eval_steps_per_second": 1.35
+}