End of training

README.md

@@ -1,9 +1,15 @@
 ---
 base_model: HuggingFaceTB/cosmo2-135M-webinst-sc2
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- HuggingFaceTB/Helpsteer
 model-index:
 - name: cosmo2-135M-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/bh5ijwbx)
 # cosmo2-135M-webinst-sc2-dpo-helpsteer-ep1
 
-This model is a fine-tuned version of [HuggingFaceTB/cosmo2-135M-webinst-sc2](https://huggingface.co/HuggingFaceTB/cosmo2-135M-webinst-sc2) on an unknown dataset.
+This model is a fine-tuned version of [HuggingFaceTB/cosmo2-135M-webinst-sc2](https://huggingface.co/HuggingFaceTB/cosmo2-135M-webinst-sc2) on the HuggingFaceTB/Helpsteer dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6824
+- Rewards/chosen: -0.0115
+- Rewards/rejected: -0.0340
+- Rewards/accuracies: 0.5833
+- Rewards/margins: 0.0225
+- Logps/rejected: -190.0087
+- Logps/chosen: -147.2760
+- Logits/rejected: 0.1785
+- Logits/chosen: -0.0247
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9872958257713249,
+    "eval_logits/chosen": -0.02468078024685383,
+    "eval_logits/rejected": 0.17850716412067413,
+    "eval_logps/chosen": -147.27601623535156,
+    "eval_logps/rejected": -190.00872802734375,
+    "eval_loss": 0.6824025511741638,
+    "eval_rewards/accuracies": 0.5833333134651184,
+    "eval_rewards/chosen": -0.011536384001374245,
+    "eval_rewards/margins": 0.022468576207756996,
+    "eval_rewards/rejected": -0.03400496393442154,
+    "eval_runtime": 5.069,
+    "eval_samples": 464,
+    "eval_samples_per_second": 91.536,
+    "eval_steps_per_second": 2.959,
     "total_flos": 0.0,
     "train_loss": 0.6879464878755457,
     "train_runtime": 373.787,

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": -0.02468078024685383,
+    "eval_logits/rejected": 0.17850716412067413,
+    "eval_logps/chosen": -147.27601623535156,
+    "eval_logps/rejected": -190.00872802734375,
+    "eval_loss": 0.6824025511741638,
+    "eval_rewards/accuracies": 0.5833333134651184,
+    "eval_rewards/chosen": -0.011536384001374245,
+    "eval_rewards/margins": 0.022468576207756996,
+    "eval_rewards/rejected": -0.03400496393442154,
+    "eval_runtime": 5.069,
+    "eval_samples": 464,
+    "eval_samples_per_second": 91.536,
+    "eval_steps_per_second": 2.959
+}

runs/Jul15_23-01-23_ip-26-0-167-245/events.out.tfevents.1721085009.ip-26-0-167-245.4063478.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83bb55b2a1d8dcebdea334b1730745674464d573603f20649d7cd9cb2f329bb9
+size 815