End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 2.2707738876342773,
+    "eval_runtime": 0.8188,
+    "eval_samples": 16,
+    "eval_samples_per_second": 4.885,
+    "eval_steps_per_second": 1.221,
     "total_flos": 3.60192752912171e+17,
     "train_loss": 2.376973159977647,
     "train_runtime": 294.1531,

config.json

@@ -0,0 +1,31 @@
+{
+  "_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,
+  "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": 1.0,
+    "eval_loss": 2.2707738876342773,
+    "eval_runtime": 0.8188,
+    "eval_samples": 16,
+    "eval_samples_per_second": 4.885,
+    "eval_steps_per_second": 1.221
+}

runs/Nov18_16-14-56_bold-food-flourishes-fin-02/events.out.tfevents.1731947975.bold-food-flourishes-fin-02.57612.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b95d1070f38ef1bd62130a9bdc1f49e40c4677bbc650a5fa844609ca710280f
+size 354