End of training

README.md

@@ -1,10 +1,11 @@
 ---
 base_model: meta-llama/Meta-Llama-3-8B
 datasets:
-- generator
+- llama-duo/synth_closed_qa_dataset_dedup
 library_name: peft
 license: llama3
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3.1-8b-closedqa-gpt4o-100k
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the llama-duo/synth_closed_qa_dataset_dedup dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.1008
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 10.0,
+    "eval_loss": 2.1007895469665527,
+    "eval_runtime": 0.5646,
+    "eval_samples": 15,
+    "eval_samples_per_second": 10.627,
+    "eval_steps_per_second": 1.771,
     "total_flos": 7.568434414263206e+18,
     "train_loss": 0.7105431989766657,
     "train_runtime": 14792.6859,

config.json

@@ -1,22 +1,23 @@
 {
-  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "bos_token_id": 128256,
+  "eos_token_id": 128257,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 131072,
+  "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "pad_token_id": 128257,
   "pretraining_tp": 1,
   "quantization_config": {
     "_load_in_4bit": true,
@@ -34,17 +35,11 @@
     "quant_method": "bitsandbytes"
   },
   "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_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.0",
   "use_cache": true,
-  "vocab_size": 128256
+  "vocab_size": 128258
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 9.991416309012875,
-    "eval_loss": 3.8423588275909424,
-    "eval_runtime": 0.4239,
+    "epoch": 10.0,
+    "eval_loss": 2.1007895469665527,
+    "eval_runtime": 0.5646,
     "eval_samples": 15,
-    "eval_samples_per_second": 14.156,
-    "eval_steps_per_second": 2.359
+    "eval_samples_per_second": 10.627,
+    "eval_steps_per_second": 1.771
 }

runs/Aug09_18-43-20_main-witty-otter-1-0-0/events.out.tfevents.1723258613.main-witty-otter-1-0-0.542.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624c433c04411e3d83a74fdea2a70105cb250b598565c7a59b0f92e47f24e57b
+size 359