End of training

README.md

@@ -3,9 +3,17 @@ library_name: transformers
 license: llama3.2
 base_model: meta-llama/Llama-3.2-1B
 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](https://huggingface.co/meta-llama/Llama-3.2-1B) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) 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: 0.0363
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 3.9991117033089054,
+    "eval_loss": 0.03634560480713844,
+    "eval_runtime": 402.1706,
+    "eval_samples": 15166,
+    "eval_samples_per_second": 37.71,
+    "eval_steps_per_second": 1.179,
     "total_flos": 1010387024977920.0,
     "train_loss": 0.05092642861352228,
     "train_runtime": 98184.5209,

config.json

@@ -31,6 +31,6 @@
   "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

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.9991117033089054,
+    "eval_loss": 0.03634560480713844,
+    "eval_runtime": 402.1706,
+    "eval_samples": 15166,
+    "eval_samples_per_second": 37.71,
+    "eval_steps_per_second": 1.179
+}

runs/Oct09_05-10-25_376e664caf09/events.out.tfevents.1728549278.376e664caf09.7652.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0cfae1af2f8340a7927e78a86775ea8c2696d1f2c975ec4f962c6222d4b5085
+size 359