End of training

README.md

@@ -3,9 +3,18 @@ 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/induction_heavy_100k_jsonl
+- barc0/induction_heavy_suggestfunction_100k_jsonl
+- barc0/induction_100k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3
+- barc0/induction_100k-gpt4-description-gpt4omini-code_generated_problems_messages_format_0.3
 model-index:
 - name: engineer-heavy-500k-barc-llama3.1-8b-ins-fft-induction_lr1e-5_epoch3-1122
   results: []
@@ -16,7 +25,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # engineer-heavy-500k-barc-llama3.1-8b-ins-fft-induction_lr1e-5_epoch3-1122
 
-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/induction_heavy_100k_jsonl, the barc0/induction_heavy_suggestfunction_100k_jsonl, the barc0/induction_100k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3 and the barc0/induction_100k-gpt4-description-gpt4omini-code_generated_problems_messages_format_0.3 datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.2710
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.0,
+    "eval_loss": 0.2709648013114929,
+    "eval_runtime": 405.2177,
+    "eval_samples": 20178,
+    "eval_samples_per_second": 49.795,
+    "eval_steps_per_second": 0.39,
     "total_flos": 2071185792860160.0,
     "train_loss": 0.28316346206181436,
     "train_runtime": 60100.1098,

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": 2.0,
+    "eval_loss": 0.2709648013114929,
+    "eval_runtime": 405.2177,
+    "eval_samples": 20178,
+    "eval_samples_per_second": 49.795,
+    "eval_steps_per_second": 0.39
+}

runs/Nov22_05-44-44_msccl-dev-000001/events.out.tfevents.1732314905.msccl-dev-000001.2395521.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d444f9aa293bcffca1a78d8a40cfc26f80c9712f8e7e1bf3659f533517cdbacc
+size 359