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-gpt4-description-gpt4omini-code_generated_problems_messages_format_0.3
+- barc0/induction_100k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3
 model-index:
 - name: l3.1-8b-inst-fft-induction-barc-heavy-200k-old-200k-lr1e-5-ep3
   results: []
@@ -16,7 +25,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # l3.1-8b-inst-fft-induction-barc-heavy-200k-old-200k-lr1e-5-ep3
 
-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-gpt4-description-gpt4omini-code_generated_problems_messages_format_0.3 and the barc0/induction_100k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3 datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.3711
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 3.0,
+    "eval_loss": 0.37112197279930115,
+    "eval_runtime": 822.0002,
+    "eval_samples": 20178,
+    "eval_samples_per_second": 24.547,
+    "eval_steps_per_second": 0.768,
     "total_flos": 3.068536882104107e+18,
     "train_loss": 0.5731845734878321,
     "train_runtime": 174288.5534,

config.json

@@ -35,6 +35,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.37112197279930115,
+    "eval_runtime": 822.0002,
+    "eval_samples": 20178,
+    "eval_samples_per_second": 24.547,
+    "eval_steps_per_second": 0.768
+}