End of training

README.md

@@ -3,9 +3,19 @@ library_name: transformers
 license: llama3.1
 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- barc0/transduction_heavy_100k_jsonl
+- barc0/transduction_heavy_suggestfunction_100k_jsonl
+- barc0/transduction_rearc_dataset_400k
+- barc0/transduction_angmented_100k-gpt4-description-gpt4omini-code_generated_problems
+- barc0/transduction_angmented_100k_gpt4o-mini_generated_problems
 model-index:
 - name: engineer1-heavy-barc-llama3.1-8b-ins-fft-transduction_lr1e-5_epoch3
   results: []
@@ -16,7 +26,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # engineer1-heavy-barc-llama3.1-8b-ins-fft-transduction_lr1e-5_epoch3
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the barc0/transduction_heavy_100k_jsonl, the barc0/transduction_heavy_suggestfunction_100k_jsonl, the barc0/transduction_rearc_dataset_400k, the barc0/transduction_angmented_100k-gpt4-description-gpt4omini-code_generated_problems and the barc0/transduction_angmented_100k_gpt4o-mini_generated_problems datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.0219
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 3.0,
+    "eval_loss": 0.02185099571943283,
+    "eval_runtime": 292.4151,
+    "eval_samples": 25121,
+    "eval_samples_per_second": 85.909,
+    "eval_steps_per_second": 1.344,
     "total_flos": 4.3304182632184545e+18,
     "train_loss": 0.030125039980372262,
     "train_runtime": 67465.0545,

config.json

@@ -35,6 +35,6 @@
   "tie_word_embeddings": false,
   "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": 3.0,
+    "eval_loss": 0.02185099571943283,
+    "eval_runtime": 292.4151,
+    "eval_samples": 25121,
+    "eval_samples_per_second": 85.909,
+    "eval_steps_per_second": 1.344
+}

runs/Oct26_18-07-58_7bcc0bab7cf9/events.out.tfevents.1730035682.7bcc0bab7cf9.660.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5d7c7188fbf1a847c859f39e709de9736dc1cd888fe237d2301993c46125f64
+size 359