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/rlced_conifer
 model-index:
 - name: tinyllama-1.1b-chat-v1.0-rlced-conifer-3-1-dpo
   results: []
@@ -16,7 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-1.1b-chat-v1.0-rlced-conifer-3-1-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 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/rlced_conifer 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: -434.8671
+- Logps/chosen: -505.9707
+- Logits/rejected: -2.4495
+- Logits/chosen: -2.6012
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 2.0,
+    "eval_logits/chosen": -2.6012232303619385,
+    "eval_logits/rejected": -2.4494504928588867,
+    "eval_logps/chosen": -505.9706726074219,
+    "eval_logps/rejected": -434.8670959472656,
+    "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": 0.7315,
+    "eval_samples": 50,
+    "eval_samples_per_second": 68.352,
+    "eval_steps_per_second": 1.367,
     "total_flos": 0.0,
     "train_loss": 0.1732867956161499,
     "train_runtime": 30.5921,

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": -2.6012232303619385,
+    "eval_logits/rejected": -2.4494504928588867,
+    "eval_logps/chosen": -505.9706726074219,
+    "eval_logps/rejected": -434.8670959472656,
+    "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": 0.7315,
+    "eval_samples": 50,
+    "eval_samples_per_second": 68.352,
+    "eval_steps_per_second": 1.367
+}

runs/Sep04_01-23-03_ip-10-0-5-67.ec2.internal/events.out.tfevents.1725413112.ip-10-0-5-67.ec2.internal.13066.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:affc39ad386c0265621c0d893f3ca38e0599c9caefdcc20585f744af02565c7e
+size 815