Model save

README.md

@@ -1,16 +1,8 @@
 ---
-license: apache-2.0
-base_model: alignment-handbook/zephyr-7b-sft-full
 tags:
-- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
-- trl
-- dpo
-- generated_from_trainer
-datasets:
-- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: zephyr-7b-dpo-full
   results: []
@@ -21,17 +13,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-full
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the HuggingFaceH4/ultrafeedback_binarized dataset.
+This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2141
-- Rewards/chosen: 4.2427
-- Rewards/rejected: -5.5362
-- Rewards/accuracies: 0.9141
-- Rewards/margins: 9.7789
-- Logps/rejected: -191.0266
-- Logps/chosen: -248.9478
-- Logits/rejected: -2.4882
-- Logits/chosen: -2.5045
+- Loss: 0.5418
+- Rewards/chosen: -3.1726
+- Rewards/rejected: -4.7390
+- Rewards/accuracies: 0.7539
+- Rewards/margins: 1.5664
+- Logps/rejected: -761.6608
+- Logps/chosen: -598.8974
+- Logits/rejected: 0.2389
+- Logits/chosen: -0.0634
 
 ## Model description
 
@@ -68,10 +60,19 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
 |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
-| 0.3315        | 0.21  | 100  | 0.2975          | 3.4373         | -3.8279          | 0.9023             | 7.2653          | -187.6101      | -250.5587    | -2.5158         | -2.5301       |
-| 0.2909        | 0.42  | 200  | 0.2754          | 4.8618         | -4.1200          | 0.9180             | 8.9818          | -188.1942      | -247.7097    | -2.5310         | -2.5459       |
-| 0.6445        | 0.63  | 300  | 0.2245          | 4.2165         | -5.3713          | 0.9102             | 9.5878          | -190.6968      | -249.0004    | -2.4915         | -2.5059       |
-| 0.2653        | 0.84  | 400  | 0.2103          | 4.5125         | -5.2808          | 0.9258             | 9.7933          | -190.5157      | -248.4084    | -2.4965         | -2.5123       |
+| 0.6142        | 0.07  | 100  | 0.6372          | -0.2112        | -0.4255          | 0.6992             | 0.2143          | -330.3116      | -302.7545    | -1.7521         | -1.7871       |
+| 0.4726        | 0.15  | 200  | 0.5516          | -1.3441        | -2.1046          | 0.75               | 0.7605          | -498.2208      | -416.0410    | -2.0018         | -2.0471       |
+| 0.4421        | 0.22  | 300  | 0.5335          | -1.1470        | -2.0463          | 0.7539             | 0.8992          | -492.3901      | -396.3379    | -1.7522         | -1.8325       |
+| 0.3828        | 0.3   | 400  | 0.5238          | -1.6652        | -2.7617          | 0.7695             | 1.0965          | -563.9280      | -448.1488    | -0.9530         | -1.1204       |
+| 0.3576        | 0.37  | 500  | 0.5184          | -1.6238        | -2.7277          | 0.7695             | 1.1039          | -560.5328      | -444.0173    | -0.8922         | -1.1202       |
+| 0.3328        | 0.45  | 600  | 0.5151          | -2.1202        | -3.4092          | 0.7656             | 1.2890          | -628.6859      | -493.6552    | 0.2423          | -0.0694       |
+| 0.3131        | 0.52  | 700  | 0.5153          | -1.7034        | -2.9038          | 0.7656             | 1.2004          | -578.1398      | -451.9696    | 0.1729          | -0.1656       |
+| 0.2547        | 0.59  | 800  | 0.5256          | -2.5366        | -3.8570          | 0.7617             | 1.3204          | -673.4565      | -535.2915    | 0.4476          | 0.1270        |
+| 0.2764        | 0.67  | 900  | 0.5221          | -2.5675        | -3.9457          | 0.7773             | 1.3782          | -682.3342      | -538.3813    | 0.0520          | -0.2431       |
+| 0.2261        | 0.74  | 1000 | 0.5298          | -2.7657        | -4.2499          | 0.7695             | 1.4842          | -712.7483      | -558.2006    | 0.2023          | -0.1104       |
+| 0.2219        | 0.82  | 1100 | 0.5380          | -3.0986        | -4.6646          | 0.7695             | 1.5660          | -754.2211      | -591.4904    | 0.3078          | -0.0067       |
+| 0.2165        | 0.89  | 1200 | 0.5336          | -2.9855        | -4.5026          | 0.7617             | 1.5170          | -738.0179      | -580.1855    | 0.2015          | -0.0980       |
+| 0.1728        | 0.97  | 1300 | 0.5418          | -3.1726        | -4.7390          | 0.7539             | 1.5664          | -761.6608      | -598.8974    | 0.2389          | -0.0634       |
 
 
 ### Framework versions

all_results.json

@@ -1,21 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_logits/chosen": -2.5045135021209717,
-    "eval_logits/rejected": -2.4882149696350098,
-    "eval_logps/chosen": -248.94781494140625,
-    "eval_logps/rejected": -191.02655029296875,
-    "eval_loss": 0.21413667500019073,
-    "eval_rewards/accuracies": 0.9140625,
-    "eval_rewards/chosen": 4.242725372314453,
-    "eval_rewards/margins": 9.778908729553223,
-    "eval_rewards/rejected": -5.536184310913086,
-    "eval_runtime": 97.1606,
-    "eval_samples": 2000,
-    "eval_samples_per_second": 20.584,
-    "eval_steps_per_second": 0.329,
-    "train_loss": 0.4018711235732713,
-    "train_runtime": 7633.33,
-    "train_samples": 61135,
-    "train_samples_per_second": 8.009,
-    "train_steps_per_second": 0.063
+    "train_loss": 0.3438705863959722,
+    "train_runtime": 21850.8794,
+    "train_samples": 172268,
+    "train_samples_per_second": 7.884,
+    "train_steps_per_second": 0.062
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 2,
+  "eos_token_id": 32000,
   "transformers_version": "4.38.2"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfb8492185343c9d55349b5a527c87db359b2d402335a698c56b9e370a925913
-size 4943162336
+oid sha256:dd6ded02da6ed2a67b1ccb05b3e25c1a08de70168c93e24452883b16a331d860
+size 4943178720

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba393e9a2d11b34d07ac9d99ef5e04d768742661ce3b2481b1f60cc95ca2f01b
+oid sha256:89ce8ea846a3d7c9e49af7bf0cabce9bf61d2357db44c6a45bf678e5f26f2442
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d94e5203e43f9e579be385f67b02371d9511906fc38a8db6ea9093ff97e8bee
-size 4540516344
+oid sha256:6fd7ad7a8a30cf5d12237b54b2b2736d530ebb352c2b25a8a564e6dd23102581
+size 4540532728

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 14483464192
+    "total_size": 14483496960
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",

runs/May17_14-55-11_n136-082-130/events.out.tfevents.1715929074.n136-082-130.1748187.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ef82381c9b0a828f96f07183c4249857826bab4bfe541f3c52cccdf44d5cfaf
-size 104425
+oid sha256:14c040c01cefed894d5e32c42475eb45f945221e65a089933344299efdbd8272
+size 107531

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 0.4018711235732713,
-    "train_runtime": 7633.33,
-    "train_samples": 61135,
-    "train_samples_per_second": 8.009,
-    "train_steps_per_second": 0.063
+    "train_loss": 0.3438705863959722,
+    "train_runtime": 21850.8794,
+    "train_samples": 172268,
+    "train_samples_per_second": 7.884,
+    "train_steps_per_second": 0.062
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e502af158ed3a6fabdbc5ad5001d9718cbe7ad4aeeca45d421c1857817025938
-size 6264
+oid sha256:c0caf9fbe23969e1c8a215e53c1fd063c17f339e7fb0eda9b65ed88e2360b089
+size 6200