End of training

README.md

@@ -1,9 +1,15 @@
 ---
 base_model: HuggingFaceTB/cosmo2-1.7B-webinst-sc2
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- HuggingFaceTB/Helpsteer
 model-index:
 - name: cosmo2-1.7B-webinst-sc2-dpo-helpsteer-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/xzcjqvtn)
 # cosmo2-1.7B-webinst-sc2-dpo-helpsteer-ep1
 
-This model is a fine-tuned version of [HuggingFaceTB/cosmo2-1.7B-webinst-sc2](https://huggingface.co/HuggingFaceTB/cosmo2-1.7B-webinst-sc2) on an unknown dataset.
+This model is a fine-tuned version of [HuggingFaceTB/cosmo2-1.7B-webinst-sc2](https://huggingface.co/HuggingFaceTB/cosmo2-1.7B-webinst-sc2) on the HuggingFaceTB/Helpsteer dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6675
+- Rewards/chosen: -0.0462
+- Rewards/rejected: -0.0926
+- Rewards/accuracies: 0.5667
+- Rewards/margins: 0.0464
+- Logps/rejected: -149.4179
+- Logps/chosen: -121.9775
+- Logits/rejected: 0.8652
+- Logits/chosen: 0.9563
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9872958257713249,
+    "eval_logits/chosen": 0.9563044309616089,
+    "eval_logits/rejected": 0.865182638168335,
+    "eval_logps/chosen": -121.97750854492188,
+    "eval_logps/rejected": -149.4178924560547,
+    "eval_loss": 0.6674867272377014,
+    "eval_rewards/accuracies": 0.5666666626930237,
+    "eval_rewards/chosen": -0.04618287831544876,
+    "eval_rewards/margins": 0.046417996287345886,
+    "eval_rewards/rejected": -0.09260086715221405,
+    "eval_runtime": 4.5645,
+    "eval_samples": 464,
+    "eval_samples_per_second": 101.654,
+    "eval_steps_per_second": 3.286,
     "total_flos": 0.0,
     "train_loss": 0.6753217893488267,
     "train_runtime": 321.7901,

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": 0.9872958257713249,
+    "eval_logits/chosen": 0.9563044309616089,
+    "eval_logits/rejected": 0.865182638168335,
+    "eval_logps/chosen": -121.97750854492188,
+    "eval_logps/rejected": -149.4178924560547,
+    "eval_loss": 0.6674867272377014,
+    "eval_rewards/accuracies": 0.5666666626930237,
+    "eval_rewards/chosen": -0.04618287831544876,
+    "eval_rewards/margins": 0.046417996287345886,
+    "eval_rewards/rejected": -0.09260086715221405,
+    "eval_runtime": 4.5645,
+    "eval_samples": 464,
+    "eval_samples_per_second": 101.654,
+    "eval_steps_per_second": 3.286
+}

runs/Jul15_23-02-15_ip-26-0-175-34/events.out.tfevents.1721085077.ip-26-0-175-34.1294397.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:038d227d30387508a3dd8bb86a277ae6c97ddc940005a81c01cc74689ec17040
+size 815