End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9961389961389961,
+    "eval_loss": 2.3773248195648193,
+    "eval_runtime": 0.8404,
+    "eval_samples": 15,
+    "eval_samples_per_second": 14.279,
+    "eval_steps_per_second": 1.19,
     "total_flos": 7.617195409366057e+17,
     "train_loss": 1.8217888118684753,
     "train_runtime": 663.1517,

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": 0.9961389961389961,
+    "eval_loss": 2.3773248195648193,
+    "eval_runtime": 0.8404,
+    "eval_samples": 15,
+    "eval_samples_per_second": 14.279,
+    "eval_steps_per_second": 1.19
+}

runs/Nov19_04-04-56_kind-face-sings-fin-02/events.out.tfevents.1731991144.kind-face-sings-fin-02.3943.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c889b82517ce795d7fd1230bf53fb1218d44714ae84381f743b8a8c49a3b8da
+size 359