End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9961389961389961,
+    "eval_loss": 2.2848541736602783,
+    "eval_runtime": 1.1208,
+    "eval_samples": 15,
+    "eval_samples_per_second": 10.707,
+    "eval_steps_per_second": 0.892,
     "total_flos": 7.61719099628716e+17,
     "train_loss": 1.5859730927519096,
     "train_runtime": 2226.6138,

config.json

@@ -0,0 +1,46 @@
+{
+  "_attn_implementation_autoset": true,
+  "_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,
+  "head_dim": 128,
+  "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": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "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": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 128258
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9961389961389961,
+    "eval_loss": 2.2848541736602783,
+    "eval_runtime": 1.1208,
+    "eval_samples": 15,
+    "eval_samples_per_second": 10.707,
+    "eval_steps_per_second": 0.892
+}

runs/Nov17_19-51-48_main-lora-llama3-8b-closedqa-0-0/events.out.tfevents.1731894242.main-lora-llama3-8b-closedqa-0-0.458.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37238d99c8a7879a542e8c038911cc07b5efa111ba28292d89fcf31b4ba82d99
+size 359