Model save

README.md

@@ -1,16 +1,12 @@
 ---
+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
+- alignment-handbook
 - generated_from_trainer
-datasets:
-- preference-data
 model-index:
 - name: preference_p0.2_seed42_level2_raremixbatch16
   results: []
@@ -21,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # preference_p0.2_seed42_level2_raremixbatch16
 
-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.
+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.
 It achieves the following results on the evaluation set:
 - Loss: 0.2978
 
@@ -64,7 +60,7 @@ The following hyperparameters were used during training:
 
 ### 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

@@ -6,9 +6,9 @@
     "eval_samples_per_second": 2.288,
     "eval_steps_per_second": 0.763,
     "total_flos": 252616554577920.0,
-    "train_loss": 0.5160677275912573,
-    "train_runtime": 24380.0574,
+    "train_loss": 0.0,
+    "train_runtime": 0.0114,
     "train_samples": 98881,
-    "train_samples_per_second": 1.584,
-    "train_steps_per_second": 0.099
+    "train_samples_per_second": 3374709.271,
+    "train_steps_per_second": 210930.256
 }

config.json

@@ -21,7 +21,7 @@
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.43.4",
-  "use_cache": true,
+  "transformers_version": "4.44.2",
+  "use_cache": false,
   "vocab_size": 32000
 }

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/Sep15_08-35-03_COE-CS-sv004/events.out.tfevents.1726390105.COE-CS-sv004.1922595.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cef41a7d5b1daf720d87c02366cb076f0cb04d90a0763a8449ce32b9e6a4060
+size 5620

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 252616554577920.0,
-    "train_loss": 0.5160677275912573,
-    "train_runtime": 24380.0574,
+    "train_loss": 0.0,
+    "train_runtime": 0.0114,
     "train_samples": 98881,
-    "train_samples_per_second": 1.584,
-    "train_steps_per_second": 0.099
+    "train_samples_per_second": 3374709.271,
+    "train_steps_per_second": 210930.256
 }

trainer_state.json

@@ -3401,10 +3401,10 @@
       "epoch": 1.0,
       "step": 2413,
       "total_flos": 252616554577920.0,
-      "train_loss": 0.5160677275912573,
-      "train_runtime": 24380.0574,
-      "train_samples_per_second": 1.584,
-      "train_steps_per_second": 0.099
+      "train_loss": 0.0,
+      "train_runtime": 0.0114,
+      "train_samples_per_second": 3374709.271,
+      "train_steps_per_second": 210930.256
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66620393a949675652bad6af04ba7c628396c77736dbdc2d00735479ef4e3f41
-size 6584
+oid sha256:2f601c7b20f78cffbc8d6ff050826de00392857a78353c245cf7f34118053e52
+size 7032