End of training

README.md

@@ -1,9 +1,15 @@
 ---
 base_model: HuggingFaceTB/cosmo2-350M-webinst-sc2
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- argilla/dpo-mix-7k
 model-index:
 - name: cosmo2-350M-webinst-sc2-dpo-argilla-ep1
   results: []
@@ -15,7 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/loubnabnl/huggingface/runs/z5gb262b)
 # cosmo2-350M-webinst-sc2-dpo-argilla-ep1
 
-This model is a fine-tuned version of [HuggingFaceTB/cosmo2-350M-webinst-sc2](https://huggingface.co/HuggingFaceTB/cosmo2-350M-webinst-sc2) on an unknown dataset.
+This model is a fine-tuned version of [HuggingFaceTB/cosmo2-350M-webinst-sc2](https://huggingface.co/HuggingFaceTB/cosmo2-350M-webinst-sc2) on the argilla/dpo-mix-7k dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6834
+- Rewards/chosen: -0.0086
+- Rewards/rejected: -0.0304
+- Rewards/accuracies: 0.5938
+- Rewards/margins: 0.0218
+- Logps/rejected: -418.5675
+- Logps/chosen: -442.4709
+- Logits/rejected: -0.7106
+- Logits/chosen: -0.5211
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.985781990521327,
+    "eval_logits/chosen": -0.5211005210876465,
+    "eval_logits/rejected": -0.7105662226676941,
+    "eval_logps/chosen": -442.4708557128906,
+    "eval_logps/rejected": -418.5675354003906,
+    "eval_loss": 0.6833909749984741,
+    "eval_rewards/accuracies": 0.59375,
+    "eval_rewards/chosen": -0.008601006120443344,
+    "eval_rewards/margins": 0.021825773641467094,
+    "eval_rewards/rejected": -0.03042677976191044,
+    "eval_runtime": 8.5409,
+    "eval_samples": 750,
+    "eval_samples_per_second": 87.812,
+    "eval_steps_per_second": 2.81,
     "total_flos": 0.0,
     "train_loss": 0.6860739244864538,
     "train_runtime": 316.322,

config.json

@@ -25,6 +25,6 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.42.3",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 49152
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.985781990521327,
+    "eval_logits/chosen": -0.5211005210876465,
+    "eval_logits/rejected": -0.7105662226676941,
+    "eval_logps/chosen": -442.4708557128906,
+    "eval_logps/rejected": -418.5675354003906,
+    "eval_loss": 0.6833909749984741,
+    "eval_rewards/accuracies": 0.59375,
+    "eval_rewards/chosen": -0.008601006120443344,
+    "eval_rewards/margins": 0.021825773641467094,
+    "eval_rewards/rejected": -0.03042677976191044,
+    "eval_runtime": 8.5409,
+    "eval_samples": 750,
+    "eval_samples_per_second": 87.812,
+    "eval_steps_per_second": 2.81
+}

runs/Jul15_21-49-55_ip-26-0-167-245/events.out.tfevents.1721080634.ip-26-0-167-245.4053728.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:958e3bee85da7cc72b429819cff501ffb58ca95731aaf61bdefa71b132d36753
+size 815