End of training

README.md

@@ -1,10 +1,11 @@
 ---
 base_model: meta-llama/Meta-Llama-3-8B
 datasets:
-- generator
+- llama-duo/synth_coding_dataset_dedup
 library_name: peft
 license: llama3
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-8b-coding-gpt4o-100k
 
-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 generator 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 llama-duo/synth_coding_dataset_dedup dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.5174
 

all_results.json

@@ -1,5 +1,10 @@
 {
  "epoch": 10.0,
+ "eval_loss": 1.517443060874939,
+ "eval_runtime": 1.3095,
+ "eval_samples": 16,
+ "eval_samples_per_second": 3.055,
+ "eval_steps_per_second": 0.764,
  "total_flos": 7.982333171800736e+18,
  "train_loss": 0.3983345487382677,
  "train_runtime": 11606.8402,

config.json

@@ -0,0 +1,45 @@
+{
+ "_name_or_path": "meta-llama/Meta-Llama-3-8B",
+ "architectures": [
+ "LlamaForCausalLM"
+ ],
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 128256,
+ "eos_token_id": 128257,
+ "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,
+ "pad_token_id": 128257,
+ "pretraining_tp": 1,
+ "quantization_config": {
+ "_load_in_4bit": true,
+ "_load_in_8bit": false,
+ "bnb_4bit_compute_dtype": "bfloat16",
+ "bnb_4bit_quant_storage": "uint8",
+ "bnb_4bit_quant_type": "nf4",
+ "bnb_4bit_use_double_quant": false,
+ "llm_int8_enable_fp32_cpu_offload": false,
+ "llm_int8_has_fp16_weight": false,
+ "llm_int8_skip_modules": null,
+ "llm_int8_threshold": 6.0,
+ "load_in_4bit": true,
+ "load_in_8bit": false,
+ "quant_method": "bitsandbytes"
+ },
+ "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": 128258
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+ "epoch": 10.0,
+ "eval_loss": 1.517443060874939,
+ "eval_runtime": 1.3095,
+ "eval_samples": 16,
+ "eval_samples_per_second": 3.055,
+ "eval_steps_per_second": 0.764
+}

runs/Aug10_01-50-35_e8f6cb577ded/events.out.tfevents.1723266512.e8f6cb577ded.87185.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ead9bd5cb45535e00bb38196cacf3c9ec695576853e9875c3481b76b349b9876
+size 359