End of training

README.md

@@ -1,8 +1,12 @@
 ---
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
+datasets:
+- nthakur/mirage-gpt-4o-sft-instruct-llama-3
+- nthakur/mirage-meta-llama-3-mistral-sft-instruct-meta-llama-tokenizer
 library_name: peft
 license: llama3
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Meta-Llama-3-8B-Instruct-mirage-all-teacher-instruct-llama-3-sft
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the nthakur/mirage-gpt-4o-sft-instruct-llama-3 and the nthakur/mirage-meta-llama-3-mistral-sft-instruct-meta-llama-tokenizer datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.2593
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.999896960329727,
+    "eval_loss": 0.25926071405410767,
+    "eval_runtime": 2934.4316,
+    "eval_samples": 8000,
+    "eval_samples_per_second": 2.726,
+    "eval_steps_per_second": 0.341,
     "total_flos": 2.4144679757152256e+16,
     "train_loss": 0.3040192322367887,
     "train_runtime": 137718.1009,

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "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": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.999896960329727,
+    "eval_loss": 0.25926071405410767,
+    "eval_runtime": 2934.4316,
+    "eval_samples": 8000,
+    "eval_samples_per_second": 2.726,
+    "eval_steps_per_second": 0.341
+}