Model save

README.md

@@ -2,16 +2,9 @@
 license: mit
 base_model: HuggingFaceH4/mistral-7b-sft-beta
 tags:
-- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
-- trl
-- dpo
-- alignment-handbook
-- generated_from_trainer
-datasets:
-- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: DPO-Zephyr-7B
   results: []
@@ -22,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # DPO-Zephyr-7B
 
-This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the HuggingFaceH4/ultrafeedback_binarized dataset.
+This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on an unknown dataset.
 
 ## Model description
 
@@ -42,13 +35,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-07
-- train_batch_size: 3
-- eval_batch_size: 4
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 3
-- total_train_batch_size: 9
-- total_eval_batch_size: 12
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 96
+- total_eval_batch_size: 24
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
@@ -61,6 +55,6 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - Transformers 4.41.2
-- Pytorch 2.2.2+cu118
+- Pytorch 2.3.0+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

all_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 1.0,
+    "epoch": 0.9984301412872841,
     "total_flos": 0.0,
-    "train_loss": 0.03212777637888081,
-    "train_runtime": 304.206,
+    "train_loss": 0.6094696866641255,
+    "train_runtime": 4741.6763,
     "train_samples": 15283,
-    "train_samples_per_second": 50.239,
-    "train_steps_per_second": 5.585
+    "train_samples_per_second": 3.223,
+    "train_steps_per_second": 0.034
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed07fdcc303da844a15334663cac0f9eb94b882edfc382895331a4a77c6309f5
+oid sha256:f7a71fd86983200a0e9da467d2d7f8faa5ae8e9b0300040f8833bb139b00c1e2
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef8fdb879e2fe20e0c16e5caf7ab1cd0cb43e66ba719b7667622e7be48ce63b1
+oid sha256:3b32a56026769897ec6a84df6af5e995510cdf30f166051e86cf2731a21e2760
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f70f02056a1008a992e82d79bfc9f008db772ca1564a6c2773613fb9d0d7be03
+oid sha256:16c9c1d861d6afe007e669a5c048323be406c2e23f14ccde55c7157235e33b86
 size 4540516344

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 1.0,
+    "epoch": 0.9984301412872841,
     "total_flos": 0.0,
-    "train_loss": 0.03212777637888081,
-    "train_runtime": 304.206,
+    "train_loss": 0.6094696866641255,
+    "train_runtime": 4741.6763,
     "train_samples": 15283,
-    "train_samples_per_second": 50.239,
-    "train_steps_per_second": 5.585
+    "train_samples_per_second": 3.223,
+    "train_steps_per_second": 0.034
 }