Model save

README.md

@@ -3,16 +3,10 @@ library_name: transformers
 license: llama3.2
 base_model: meta-llama/Llama-3.2-1B-Instruct
 tags:
-- alignment-handbook
-- trl
-- sft
-- generated_from_trainer
 - trl
 - sft
 - alignment-handbook
 - generated_from_trainer
-datasets:
-- preference-data
 model-index:
 - name: llama3.2_feedback_1b
   results: []
@@ -23,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3.2_feedback_1b
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the preference-data dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the None dataset.
 
 ## Model description
 

all_results.json

@@ -6,8 +6,8 @@
     "eval_steps_per_second": 2.241,
     "total_flos": 44008382398464.0,
     "train_loss": 0.0,
-    "train_runtime": 0.009,
+    "train_runtime": 0.0097,
     "train_samples": 98952,
-    "train_samples_per_second": 2937055.056,
-    "train_steps_per_second": 183614.45
+    "train_samples_per_second": 2738278.668,
+    "train_steps_per_second": 171187.643
 }

config.json

@@ -35,6 +35,6 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.1",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 128256
 }

runs/Sep30_22-11-00_COE-CS-sv003/events.out.tfevents.1727734271.COE-CS-sv003.1385721.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe4e1ac17388c5b2af2e837fa18dc3318a8f18c87d49e9b0e4bb7e34d8a432c
+size 6324

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "total_flos": 44008382398464.0,
     "train_loss": 0.0,
-    "train_runtime": 0.009,
+    "train_runtime": 0.0097,
     "train_samples": 98952,
-    "train_samples_per_second": 2937055.056,
-    "train_steps_per_second": 183614.45
+    "train_samples_per_second": 2738278.668,
+    "train_steps_per_second": 171187.643
 }

trainer_state.json

@@ -2344,9 +2344,9 @@
       "step": 1656,
       "total_flos": 44008382398464.0,
       "train_loss": 0.0,
-      "train_runtime": 0.009,
-      "train_samples_per_second": 2937055.056,
-      "train_steps_per_second": 183614.45
+      "train_runtime": 0.0097,
+      "train_samples_per_second": 2738278.668,
+      "train_steps_per_second": 171187.643
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc6ff02ea07019360ef1bfe0b453307c77a2f719e73135d435326789efd9b15
+oid sha256:b5bc2d6c482510bf6b354a53e1315f403620e02f71ff4e5ae0f9fa8faf852860
 size 7096