End of training

README.md

@@ -1,8 +1,14 @@
 ---
 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
+datasets:
+- barc0/induction_100k-gpt4-description-gpt4omini-code_generated_problems_messages_format_0.3
+- barc0/induction_100k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3
+- barc0/induction_gpt-4_description_20000_with_llama_codegen_messages_format_0.3
+- barc0/induction_gpt-4_description_20000_with_gpt-4o-mini_codegen_messages_format_0.3
 library_name: peft
 license: llama3.1
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # l3.1-8b-inst-lora64-induction-gpt4wmini100k-mini100k-gpt4wmini20k-gpt4wllama20k-lr2e-4-ep3
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the barc0/induction_100k-gpt4-description-gpt4omini-code_generated_problems_messages_format_0.3, the barc0/induction_100k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3, the barc0/induction_gpt-4_description_20000_with_llama_codegen_messages_format_0.3 and the barc0/induction_gpt-4_description_20000_with_gpt-4o-mini_codegen_messages_format_0.3 datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.2684
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 3.0,
+    "eval_loss": 0.26840582489967346,
+    "eval_runtime": 341.8072,
+    "eval_samples": 12017,
+    "eval_samples_per_second": 35.157,
+    "eval_steps_per_second": 1.1,
     "total_flos": 1.7156250092814991e+18,
     "train_loss": 0.28245328673299386,
     "train_runtime": 54133.2624,

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "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": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.26840582489967346,
+    "eval_runtime": 341.8072,
+    "eval_samples": 12017,
+    "eval_samples_per_second": 35.157,
+    "eval_steps_per_second": 1.1
+}

runs/Sep29_03-06-35_instance-20240925-140811/events.out.tfevents.1727633772.instance-20240925-140811.7624.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:908420f5075849baeee2bd1c47d2217a05e9d37e8a01c21e5394d9b272e0ce62
+size 359