End of training

README.md

@@ -1,17 +1,20 @@
 ---
 base_model: mistralai/Mistral-7B-v0.1
+datasets: HuggingFaceH4/ultrafeedback_binarized
 library_name: transformers
-model_name: SKYWORKmistral16_4_1
+model_name: mistralai/Mistral-7B-v0.1
 tags:
 - generated_from_trainer
+- alignment-handbook
+- HuggingFaceH4/ultrafeedback_binarized
 - trl
 - dpo
 licence: license
 ---
 
-# Model Card for SKYWORKmistral16_4_1
+# Model Card for mistralai/Mistral-7B-v0.1
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1).
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the [HuggingFaceH4/ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": NaN,
+    "eval_logits/rejected": NaN,
+    "eval_logps/chosen": -294.74468994140625,
+    "eval_logps/rejected": -309.10638427734375,
+    "eval_loss": 0.4653571844100952,
+    "eval_rewards/accuracies": 0.5249335169792175,
+    "eval_rewards/chosen": 0.0826416015625,
+    "eval_rewards/margins": 0.7734790444374084,
+    "eval_rewards/rejected": -0.6906270980834961,
+    "eval_runtime": 291.0951,
+    "eval_samples": 1445,
+    "eval_samples_per_second": 15.418,
+    "eval_steps_per_second": 0.244,
     "total_flos": 0.0,
     "train_loss": 0.540496826171875,
     "train_runtime": 4914.1422,

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": NaN,
+    "eval_logits/rejected": NaN,
+    "eval_logps/chosen": -294.74468994140625,
+    "eval_logps/rejected": -309.10638427734375,
+    "eval_loss": 0.4653571844100952,
+    "eval_rewards/accuracies": 0.5249335169792175,
+    "eval_rewards/chosen": 0.0826416015625,
+    "eval_rewards/margins": 0.7734790444374084,
+    "eval_rewards/rejected": -0.6906270980834961,
+    "eval_runtime": 291.0951,
+    "eval_samples": 1445,
+    "eval_samples_per_second": 15.418,
+    "eval_steps_per_second": 0.244
+}

runs/Jun06_11-10-50_cn-g028.server.mila.quebec/events.out.tfevents.1749228223.cn-g028.server.mila.quebec.4119622.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03c636edf1b94f325ff28733c9dae6f26562ae04bfcfdbb7b031e9d51bed6685
+size 815

training_DATA/multi_aot_data.npy

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:113b44a8171ebeac16077f5ac6d3529b5313e597b8ca399ea9d2d52b50da31e2
-size 22461
+oid sha256:c712c14b00d3761d88aaa3c691725eeb155f61188bcac9d1ea37b8cfe210d200
+size 23395