End of training

README.md

@@ -3,9 +3,16 @@ 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_100k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3
+- barc0/transduction_rearc
 model-index:
 - name: 100k_transduction-gpt4omini_lr1e-5_epoch3_engineering
   results: []
@@ -16,7 +23,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # 100k_transduction-gpt4omini_lr1e-5_epoch3_engineering
 
-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_100k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3 and the barc0/transduction_rearc datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.0372
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.9985775248933146,
+    "eval_loss": 0.03720796853303909,
+    "eval_runtime": 199.8889,
+    "eval_samples": 7103,
+    "eval_samples_per_second": 35.535,
+    "eval_steps_per_second": 1.111,
     "total_flos": 1.1417019656175288e+18,
     "train_loss": 0.048461434403982234,
     "train_runtime": 39585.3646,

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": 2.9985775248933146,
+    "eval_loss": 0.03720796853303909,
+    "eval_runtime": 199.8889,
+    "eval_samples": 7103,
+    "eval_samples_per_second": 35.535,
+    "eval_steps_per_second": 1.111
+}

runs/Sep26_17-18-16_instance-20240926-032616/events.out.tfevents.1727412065.instance-20240926-032616.102699.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0198d3f0efe1d58cf9ddd0231115447df7a8e6bbf0785411a6b4b1c5b59a33e2
+size 359