Model save

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: mistralai/Mistral-7B-v0.1
+base_model: alignment-handbook/zephyr-7b-sft-full
 tags:
 - generated_from_trainer
 model-index:
@@ -13,17 +13,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-lora
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5266
-- Rewards/chosen: -0.1470
-- Rewards/rejected: -0.8985
-- Rewards/accuracies: 0.7460
-- Rewards/margins: 0.7516
-- Logps/rejected: -228.2694
-- Logps/chosen: -266.1304
-- Logits/rejected: -1.9412
-- Logits/chosen: -2.0659
+- Loss: 0.6931
+- Rewards/chosen: 0.0
+- Rewards/rejected: 0.0
+- Rewards/accuracies: 0.0
+- Rewards/margins: 0.0
+- Logps/rejected: -179.8250
+- Logps/chosen: -194.3670
+- Logits/rejected: -3.0430
+- Logits/chosen: -3.0079
 
 ## Model description
 
@@ -42,27 +42,25 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-07
-- train_batch_size: 2
+- learning_rate: 0.05
+- train_batch_size: 8
 - eval_batch_size: 4
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 4
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 64
-- total_eval_batch_size: 16
+- num_devices: 2
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
 |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
-| 0.5501        | 1.0   | 968  | 0.5560          | -0.1093        | -0.6400          | 0.7200             | 0.5307          | -225.6847      | -265.7538    | -1.9901         | -2.1115       |
-| 0.5412        | 2.0   | 1936 | 0.5318          | -0.1497        | -0.8640          | 0.7420             | 0.7143          | -227.9245      | -266.1583    | -1.9509         | -2.0748       |
-| 0.5454        | 3.0   | 2904 | 0.5266          | -0.1470        | -0.8985          | 0.7460             | 0.7516          | -228.2694      | -266.1304    | -1.9412         | -2.0659       |
+| 0.3466        | 1.0   | 1    | 0.6931          | 0.0            | 0.0              | 0.0                | 0.0             | -179.8250      | -194.3670    | -3.0430         | -3.0079       |
 
 
 ### Framework versions

all_results.json

@@ -1,8 +1,21 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -3.0078587532043457,
+    "eval_logits/rejected": -3.042999744415283,
+    "eval_logps/chosen": -194.36697387695312,
+    "eval_logps/rejected": -179.82501220703125,
+    "eval_loss": 0.6931471824645996,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": 0.0,
+    "eval_rewards/margins": 0.0,
+    "eval_rewards/rejected": 0.0,
+    "eval_runtime": 5.0964,
+    "eval_samples": 10,
+    "eval_samples_per_second": 1.962,
+    "eval_steps_per_second": 0.392,
     "train_loss": 0.3465735912322998,
-    "train_runtime": 16.8246,
+    "train_runtime": 16.8017,
     "train_samples": 61966,
-    "train_samples_per_second": 0.594,
-    "train_steps_per_second": 0.059
+    "train_samples_per_second": 0.595,
+    "train_steps_per_second": 0.06
 }

eval_results.json

@@ -1,16 +1,16 @@
 {
-    "epoch": 3.0,
-    "eval_logits/chosen": -2.0658671855926514,
-    "eval_logits/rejected": -1.9411793947219849,
-    "eval_logps/chosen": -266.13037109375,
-    "eval_logps/rejected": -228.2694091796875,
-    "eval_loss": 0.5265706777572632,
-    "eval_rewards/accuracies": 0.7459999918937683,
-    "eval_rewards/chosen": -0.1469534933567047,
-    "eval_rewards/margins": 0.7515553832054138,
-    "eval_rewards/rejected": -0.8985088467597961,
-    "eval_runtime": 453.4186,
-    "eval_samples": 2000,
-    "eval_samples_per_second": 4.411,
-    "eval_steps_per_second": 0.276
+    "epoch": 1.0,
+    "eval_logits/chosen": -3.0078587532043457,
+    "eval_logits/rejected": -3.042999744415283,
+    "eval_logps/chosen": -194.36697387695312,
+    "eval_logps/rejected": -179.82501220703125,
+    "eval_loss": 0.6931471824645996,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": 0.0,
+    "eval_rewards/margins": 0.0,
+    "eval_rewards/rejected": 0.0,
+    "eval_runtime": 5.0964,
+    "eval_samples": 10,
+    "eval_samples_per_second": 1.962,
+    "eval_steps_per_second": 0.392
 }

runs/Dec10_16-14-13_uclaml03.cs.ucla.edu/events.out.tfevents.1702253798.uclaml03.cs.ucla.edu.2937386.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec0bae8e866d712f5d5194f8e2e2b98c738d9915557d7f009470f8b0773de15
+size 815

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.3465735912322998,
-    "train_runtime": 16.8246,
+    "train_runtime": 16.8017,
     "train_samples": 61966,
-    "train_samples_per_second": 0.594,
-    "train_steps_per_second": 0.059
+    "train_samples_per_second": 0.595,
+    "train_steps_per_second": 0.06
 }

trainer_state.json

@@ -33,9 +33,9 @@
       "eval_rewards/chosen": 0.0,
       "eval_rewards/margins": 0.0,
       "eval_rewards/rejected": 0.0,
-      "eval_runtime": 5.132,
-      "eval_samples_per_second": 1.949,
-      "eval_steps_per_second": 0.39,
+      "eval_runtime": 5.1666,
+      "eval_samples_per_second": 1.936,
+      "eval_steps_per_second": 0.387,
       "step": 1
     },
     {
@@ -43,9 +43,9 @@
       "step": 1,
       "total_flos": 0.0,
       "train_loss": 0.3465735912322998,
-      "train_runtime": 16.8246,
-      "train_samples_per_second": 0.594,
-      "train_steps_per_second": 0.059
+      "train_runtime": 16.8017,
+      "train_samples_per_second": 0.595,
+      "train_steps_per_second": 0.06
     }
   ],
   "logging_steps": 10,