End of training

README.md

@@ -3,9 +3,17 @@ 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
+- generated_from_trainer
+datasets:
+- barc0/transduction_angmented_100k-gpt4-description-gpt4omini-code_generated_problems
+- barc0/transduction_angmented_100k_gpt4o-mini_generated_problems
+- barc0/transduction_rearc_dataset_400k
 model-index:
 - name: llama3.2-1b-instruct-fft-transduction-engineer_lr1e-5_epoch4
   results: []
@@ -16,7 +24,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3.2-1b-instruct-fft-transduction-engineer_lr1e-5_epoch4
 
-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.
+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 barc0/transduction_angmented_100k-gpt4-description-gpt4omini-code_generated_problems, the barc0/transduction_angmented_100k_gpt4o-mini_generated_problems and the barc0/transduction_rearc_dataset_400k datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.0409
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 4.0,
+    "eval_loss": 0.04085389897227287,
+    "eval_runtime": 77.96,
+    "eval_samples": 15166,
+    "eval_samples_per_second": 194.536,
+    "eval_steps_per_second": 3.04,
     "total_flos": 1010769106173952.0,
     "train_loss": 0.055861650320550765,
     "train_runtime": 18499.8374,

config.json

@@ -35,6 +35,6 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.9991117033089054,
-    "eval_loss": 0.03634560480713844,
-    "eval_runtime": 402.1706,
+    "epoch": 4.0,
+    "eval_loss": 0.04085389897227287,
+    "eval_runtime": 77.96,
     "eval_samples": 15166,
-    "eval_samples_per_second": 37.71,
-    "eval_steps_per_second": 1.179
+    "eval_samples_per_second": 194.536,
+    "eval_steps_per_second": 3.04
 }

runs/Oct10_19-42-40_dadbe548fd7a/events.out.tfevents.1728608966.dadbe548fd7a.2251.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e20d9e0eebbe4268e8315539d2dc59446e705e7e71fb6771a0567825c5edcc4
+size 359