Model save

README.md

@@ -1,16 +1,11 @@
 ---
+library_name: transformers
 license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.2
 tags:
-- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
-- trl
-- sft
-- generated_from_trainer
-datasets:
-- preference-data
 model-index:
 - name: feedback_p0.1_seed42_level2_syntaxmixbatch16
   results: []
@@ -21,9 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # feedback_p0.1_seed42_level2_syntaxmixbatch16
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the preference-data dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.3189
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
 
 ## Model description
 
@@ -57,14 +50,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.3656        | 1.0   | 1950 | 0.3189          |
 
 
 ### Framework versions
 
-- Transformers 4.43.4
+- Transformers 4.44.2
 - Pytorch 2.3.1+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

all_results.json

@@ -1,14 +1,9 @@
 {
     "epoch": 1.0,
-    "eval_loss": 0.3188657760620117,
-    "eval_runtime": 1.3214,
-    "eval_samples": 10,
-    "eval_samples_per_second": 1.514,
-    "eval_steps_per_second": 0.757,
-    "total_flos": 204145164288000.0,
-    "train_loss": 0.5252774189068721,
-    "train_runtime": 19779.9981,
+    "total_flos": 194513700126720.0,
+    "train_loss": 0.5105859521772428,
+    "train_runtime": 16588.6757,
     "train_samples": 98927,
-    "train_samples_per_second": 1.577,
-    "train_steps_per_second": 0.099
+    "train_samples_per_second": 1.791,
+    "train_steps_per_second": 0.112
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.43.4"
+  "transformers_version": "4.44.2"
 }

runs/Sep17_05-11-37_COE-CS-sv003/events.out.tfevents.1726550202.COE-CS-sv003.3171136.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cac4eb2784bd876a490ecb1652aa9b14fd9f654392d148486954dc85f24cb0e7
-size 83877
+oid sha256:923f4e74a2f0b0a29dc3f113f1b7d70086baee738a395f03cb68c9c9b088092c
+size 84231

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
-    "total_flos": 204145164288000.0,
-    "train_loss": 0.5252774189068721,
-    "train_runtime": 19779.9981,
+    "total_flos": 194513700126720.0,
+    "train_loss": 0.5105859521772428,
+    "train_runtime": 16588.6757,
     "train_samples": 98927,
-    "train_samples_per_second": 1.577,
-    "train_steps_per_second": 0.099
+    "train_samples_per_second": 1.791,
+    "train_steps_per_second": 0.112
 }