End of training

README.md

@@ -1,8 +1,11 @@
 ---
 base_model: meta-llama/Meta-Llama-3-8B
+datasets:
+- yihanwang617/WizardLM_70k_processed_indicator_4k
 library_name: peft
 license: llama3
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -16,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama-3-qlora-wizard-processed-indicator-0.6
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown 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 yihanwang617/WizardLM_70k_processed_indicator_4k dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6736
+- Loss: 0.6735
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.6735442876815796,
+    "eval_runtime": 47.4166,
+    "eval_samples": 500,
+    "eval_samples_per_second": 10.545,
+    "eval_steps_per_second": 0.675,
     "total_flos": 4801486812086272.0,
     "train_loss": 0.7253576234998405,
     "train_runtime": 22925.9932,

config.json

@@ -0,0 +1,28 @@
+{
+  "_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,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "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": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 128258
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.6735442876815796,
+    "eval_runtime": 47.4166,
+    "eval_samples": 500,
+    "eval_samples_per_second": 10.545,
+    "eval_steps_per_second": 0.675
+}

runs/Sep06_16-22-59_nova.cs.ucla.edu/events.out.tfevents.1725688243.nova.cs.ucla.edu.2404961.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c10f44ca36a7b926a7ea3651de17b1b504a0e47273ece59ec5b00ae9c2ac75f7
+size 359

runs/Sep06_22-01-38_nova.cs.ucla.edu/events.out.tfevents.1725685482.nova.cs.ucla.edu.2653377.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9489445a0dcffaa6507d796c0bf4e9cc05b28bb98c668c470850fb348e7fde6
-size 10494
+oid sha256:be375c358ad0cfce7a2cd45d3aad683730989c261eeed120c876869ee117c717
+size 10705