End of training

README.md

@@ -2,10 +2,13 @@
 license: other
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
+datasets:
+- nthakur/miracl-raft-sft-instruct-v0.2
 model-index:
 - name: Meta-Llama-3-8B-Instruct-miracl-raft-sft-v2.0
   results: []
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Meta-Llama-3-8B-Instruct-miracl-raft-sft-v2.0
 
-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 an unknown 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/miracl-raft-sft-instruct-v0.2 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.4193
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9998354451209478,
+    "eval_loss": 1.4193336963653564,
+    "eval_runtime": 1872.9516,
+    "eval_samples": 4000,
+    "eval_samples_per_second": 2.136,
+    "eval_steps_per_second": 0.267,
     "total_flos": 2663384493981696.0,
     "train_loss": 1.5419490562605969,
     "train_runtime": 69992.3236,

config.json

@@ -0,0 +1,28 @@
+{
+  "_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": 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": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9998354451209478,
+    "eval_loss": 1.4193336963653564,
+    "eval_runtime": 1872.9516,
+    "eval_samples": 4000,
+    "eval_samples_per_second": 2.136,
+    "eval_steps_per_second": 0.267
+}