End of training

README.md

@@ -1,8 +1,13 @@
 ---
 base_model: barc0/Llama-3.1-ARC-Potpourri-Transduction-8B
+datasets:
+- barc0/transduction_formatted_test_time_finetune_for_evaluation
+- barc0/transduction_formatted_rearc_dataset_100k
+- barc0/transduction_heavy_100k_jsonl
 library_name: peft
 license: llama3.1
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -16,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # engineer1-heavy-barc-llama3.1-8b-instruct-lora64-testtime-finetuning
 
-This model is a fine-tuned version of [barc0/Llama-3.1-ARC-Potpourri-Transduction-8B](https://huggingface.co/barc0/Llama-3.1-ARC-Potpourri-Transduction-8B) on the None dataset.
+This model is a fine-tuned version of [barc0/Llama-3.1-ARC-Potpourri-Transduction-8B](https://huggingface.co/barc0/Llama-3.1-ARC-Potpourri-Transduction-8B) on the barc0/transduction_formatted_test_time_finetune_for_evaluation, the barc0/transduction_formatted_rearc_dataset_100k and the barc0/transduction_heavy_100k_jsonl datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.0337
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 3.0,
+    "eval_loss": 0.03369831293821335,
+    "eval_runtime": 481.4711,
+    "eval_samples": 10376,
+    "eval_samples_per_second": 21.551,
+    "eval_steps_per_second": 1.348,
     "total_flos": 2.2064687673350554e+17,
     "train_loss": 0.016641332297180983,
     "train_runtime": 13115.3958,

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "barc0/Llama-3.1-ARC-Potpourri-Transduction-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.03369831293821335,
+    "eval_runtime": 481.4711,
+    "eval_samples": 10376,
+    "eval_samples_per_second": 21.551,
+    "eval_steps_per_second": 1.348
+}

runs/Nov05_15-43-06_ampere6.stanford.edu/events.out.tfevents.1730863850.ampere6.stanford.edu.1582579.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c159ef8f5124ff9efb6e528b01cf70933906ad0953e1bbcba5c291e7126a963
+size 359