End of training

README.md

@@ -2,11 +2,18 @@
 license: other
 library_name: peft
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- nthakur/miracl-raft-sft-instruct-v0.1
+- nthakur/nomiracl-raft-sft-instruct-v0.1
+- nthakur/miracl-en-x-raft-sft-instruct-v0.1
+- nthakur/miracl-x-en-raft-sft-instruct-v0.1
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
 model-index:
 - name: Meta-Llama-3-8B-Instruct-miracl-mix-raft-sft-25th-apr-v1.0
@@ -18,7 +25,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Meta-Llama-3-8B-Instruct-miracl-mix-raft-sft-25th-apr-v1.0
 
-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 the generator 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-v0.1, the nthakur/nomiracl-raft-sft-instruct-v0.1, the nthakur/miracl-en-x-raft-sft-instruct-v0.1 and the nthakur/miracl-x-en-raft-sft-instruct-v0.1 datasets.
 It achieves the following results on the evaluation set:
 - Loss: 1.3064
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 1.3063520193099976,
+    "eval_runtime": 1755.0349,
+    "eval_samples": 12657,
+    "eval_samples_per_second": 2.16,
+    "eval_steps_per_second": 0.27,
     "train_loss": 1.4133363889659056,
     "train_runtime": 112943.9974,
     "train_samples": 239934,

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": "4.39.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.3063520193099976,
+    "eval_runtime": 1755.0349,
+    "eval_samples": 12657,
+    "eval_samples_per_second": 2.16,
+    "eval_steps_per_second": 0.27
+}