End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9924812030075187,
+    "eval_loss": 2.0512757301330566,
+    "eval_runtime": 2.2723,
+    "eval_samples": 25,
+    "eval_samples_per_second": 11.002,
+    "eval_steps_per_second": 0.44,
     "total_flos": 1.3348374772438794e+18,
     "train_loss": 2.4112901976614287,
     "train_runtime": 910.693,

config.json

@@ -0,0 +1,32 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "meta-llama/Llama-2-13b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32000,
+  "eos_token_id": 32001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 32001,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 32002
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9924812030075187,
+    "eval_loss": 2.0512757301330566,
+    "eval_runtime": 2.2723,
+    "eval_samples": 25,
+    "eval_samples_per_second": 11.002,
+    "eval_steps_per_second": 0.44
+}

runs/Nov22_17-00-51_metallic-vm-falls-fin-02/events.out.tfevents.1732296173.metallic-vm-falls-fin-02.78441.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad52df79bbe955be369af04f80cfb67c457aeb0f33f73a533d040ef97bb2b5d1
+size 354