Model save

README.md

@@ -15,17 +15,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 18010.9043
-- Rewards/chosen: -1.5473
-- Rewards/rejected: -1.8909
-- Rewards/accuracies: 0.7429
-- Rewards/margins: 0.3436
-- Rewards/safe Rewards: -1.5421
-- Rewards/unsafe Rewards: -1.5499
-- Logps/rejected: -281.5577
-- Logps/chosen: -285.1670
-- Logits/rejected: 3.9983
-- Logits/chosen: 2.5248
+- Loss: 2897.3179
+- Rewards/chosen: -0.6441
+- Rewards/rejected: -0.5754
+- Rewards/accuracies: 0.4239
+- Rewards/margins: -0.0687
+- Rewards/safe Rewards: -0.6417
+- Rewards/unsafe Rewards: -0.6386
+- Logps/rejected: -150.0089
+- Logps/chosen: -194.8470
+- Logits/rejected: -1.5786
+- Logits/chosen: -1.8526
 
 ## Model description
 
@@ -62,9 +62,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Rewards/safe Rewards | Rewards/unsafe Rewards | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
 |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------------:|:----------------------:|:--------------:|:------------:|:---------------:|:-------------:|
-| 48290.35      | 0.27  | 500  | 18207.4277      | -0.8680        | -1.2092          | 0.7308             | 0.3412          | -0.8648              | -0.8682                | -213.3933      | -217.2423    | 0.5180          | -0.2676       |
-| 45912.9125    | 0.54  | 1000 | 18076.0898      | -1.4658        | -1.8259          | 0.7394             | 0.3601          | -1.4604              | -1.4691                | -275.0630      | -277.0186    | 3.7605          | 2.3434        |
-| 42808.3344    | 0.81  | 1500 | 18052.3926      | -1.6663        | -1.9853          | 0.7414             | 0.3191          | -1.6613              | -1.6696                | -291.0034      | -297.0653    | 4.3253          | 2.8214        |
+| 4952.3219     | 0.27  | 500  | 3031.1638       | -0.6585        | -0.5935          | 0.4215             | -0.0650         | -0.6552              | -0.6514                | -151.8219      | -196.2862    | -1.6812         | -1.9554       |
+| 4670.3188     | 0.54  | 1000 | 2931.8032       | -0.6547        | -0.5940          | 0.4353             | -0.0607         | -0.6514              | -0.6477                | -151.8720      | -195.9055    | -1.5084         | -1.7952       |
+| 4368.5492     | 0.81  | 1500 | 2899.6733       | -0.6504        | -0.5839          | 0.4268             | -0.0665         | -0.6481              | -0.6452                | -150.8582      | -195.4787    | -1.5552         | -1.8340       |
 
 
 ### Framework versions

all_results.json

@@ -1,23 +1,23 @@
 {
     "epoch": 1.0,
-    "eval_logits/chosen": 2.5248451232910156,
-    "eval_logits/rejected": 3.9983110427856445,
-    "eval_logps/chosen": -285.1670227050781,
-    "eval_logps/rejected": -281.55767822265625,
-    "eval_loss": 18010.904296875,
-    "eval_rewards/accuracies": 0.7428606152534485,
-    "eval_rewards/chosen": -1.5472811460494995,
-    "eval_rewards/margins": 0.3435833156108856,
-    "eval_rewards/rejected": -1.890864372253418,
-    "eval_rewards/safe_rewards": -1.5421195030212402,
-    "eval_rewards/unsafe_rewards": -1.5499401092529297,
-    "eval_runtime": 1041.5134,
+    "eval_logits/chosen": -1.8526086807250977,
+    "eval_logits/rejected": -1.5786068439483643,
+    "eval_logps/chosen": -194.84695434570312,
+    "eval_logps/rejected": -150.0089111328125,
+    "eval_loss": 2897.31787109375,
+    "eval_rewards/accuracies": 0.4238867461681366,
+    "eval_rewards/chosen": -0.644080638885498,
+    "eval_rewards/margins": -0.06870394200086594,
+    "eval_rewards/rejected": -0.5753766894340515,
+    "eval_rewards/safe_rewards": -0.6417209506034851,
+    "eval_rewards/unsafe_rewards": -0.6385891437530518,
+    "eval_runtime": 1137.2097,
     "eval_samples": 33044,
-    "eval_samples_per_second": 31.727,
-    "eval_steps_per_second": 0.992,
-    "train_loss": 47961.330580597416,
-    "train_runtime": 22084.0044,
+    "eval_samples_per_second": 29.057,
+    "eval_steps_per_second": 0.908,
+    "train_loss": 4921.10222895923,
+    "train_runtime": 23079.3417,
     "train_samples": 59478,
-    "train_samples_per_second": 2.693,
-    "train_steps_per_second": 0.084
+    "train_samples_per_second": 2.577,
+    "train_steps_per_second": 0.081
 }

eval_results.json

@@ -1,18 +1,18 @@
 {
     "epoch": 1.0,
-    "eval_logits/chosen": 2.5248451232910156,
-    "eval_logits/rejected": 3.9983110427856445,
-    "eval_logps/chosen": -285.1670227050781,
-    "eval_logps/rejected": -281.55767822265625,
-    "eval_loss": 18010.904296875,
-    "eval_rewards/accuracies": 0.7428606152534485,
-    "eval_rewards/chosen": -1.5472811460494995,
-    "eval_rewards/margins": 0.3435833156108856,
-    "eval_rewards/rejected": -1.890864372253418,
-    "eval_rewards/safe_rewards": -1.5421195030212402,
-    "eval_rewards/unsafe_rewards": -1.5499401092529297,
-    "eval_runtime": 1041.5134,
+    "eval_logits/chosen": -1.8526086807250977,
+    "eval_logits/rejected": -1.5786068439483643,
+    "eval_logps/chosen": -194.84695434570312,
+    "eval_logps/rejected": -150.0089111328125,
+    "eval_loss": 2897.31787109375,
+    "eval_rewards/accuracies": 0.4238867461681366,
+    "eval_rewards/chosen": -0.644080638885498,
+    "eval_rewards/margins": -0.06870394200086594,
+    "eval_rewards/rejected": -0.5753766894340515,
+    "eval_rewards/safe_rewards": -0.6417209506034851,
+    "eval_rewards/unsafe_rewards": -0.6385891437530518,
+    "eval_runtime": 1137.2097,
     "eval_samples": 33044,
-    "eval_samples_per_second": 31.727,
-    "eval_steps_per_second": 0.992
+    "eval_samples_per_second": 29.057,
+    "eval_steps_per_second": 0.908
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d76fa56459649e710be1932fc16796e50b99b310e4f94a79b7f8fe19fd93f9a7
+oid sha256:20432f8815518e6c964d71ac826f847ac8e950fb5b92850b8341440459907ce2
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36159876d802d663a963bc90952b05bc4b2c4d843d3fac77a7c730ffbeca5dd3
+oid sha256:3938ebe0667ca2758ffb46354beca6da6b14fead06b688f37e085ca48171e2de
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:224d0158e3757ae675efb8874cec676a2bb44d3f113d4c9985a1c83d73edc560
+oid sha256:fb3c6d62e5e682e54493eac6f2ecc97e4f409e240a1ef8ae126617c8927def02
 size 4540516344

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 47961.330580597416,
-    "train_runtime": 22084.0044,
+    "train_loss": 4921.10222895923,
+    "train_runtime": 23079.3417,
     "train_samples": 59478,
-    "train_samples_per_second": 2.693,
-    "train_steps_per_second": 0.084
+    "train_samples_per_second": 2.577,
+    "train_steps_per_second": 0.081
 }