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_ref
+- data/ui_coding_ref
 model-index:
 - name: tinyllama-1.1b-chat-v1.0-ui-math-coding-group-dpo
   results: []
@@ -16,7 +23,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-1.1b-chat-v1.0-ui-math-coding-group-dpo
 
-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_ref and the data/ui_coding_ref datasets.
+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: -291.9316
+- Logps/chosen: -308.5898
+- Logits/rejected: -2.1579
+- Logits/chosen: -2.1562
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -2.156226873397827,
+    "eval_logits/rejected": -2.1579225063323975,
+    "eval_logps/chosen": -308.5898132324219,
+    "eval_logps/rejected": -291.931640625,
+    "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": 1.5116,
+    "eval_samples": 100,
+    "eval_samples_per_second": 66.156,
+    "eval_steps_per_second": 0.662,
     "total_flos": 0.0,
     "train_loss": 0.016206350177526474,
     "train_runtime": 33.2224,

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": 1.0,
+    "eval_logits/chosen": -2.156226873397827,
+    "eval_logits/rejected": -2.1579225063323975,
+    "eval_logps/chosen": -308.5898132324219,
+    "eval_logps/rejected": -291.931640625,
+    "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": 1.5116,
+    "eval_samples": 100,
+    "eval_samples_per_second": 66.156,
+    "eval_steps_per_second": 0.662
+}

runs/Sep03_02-47-58_ip-10-0-9-154.ec2.internal/events.out.tfevents.1725331823.ip-10-0-9-154.ec2.internal.12025.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7268d7be7a7507db9e6b188f07bf081697c8d7d5cf8db85edc453f02e183e59
+size 815