End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 9.936275482177734,
+    "eval_runtime": 1.4558,
+    "eval_samples": 518,
+    "eval_samples_per_second": 122.269,
+    "eval_steps_per_second": 2.061,
     "total_flos": 4.268850850782249e+17,
     "train_loss": 14.163321549551828,
     "train_runtime": 384.2161,

config.json

@@ -0,0 +1,29 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "google/gemma-7b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 256000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 9.936275482177734,
+    "eval_runtime": 1.4558,
+    "eval_samples": 518,
+    "eval_samples_per_second": 122.269,
+    "eval_steps_per_second": 2.061
+}

runs/Nov18_16-49-44_bold-food-flourishes-fin-02/events.out.tfevents.1731950447.bold-food-flourishes-fin-02.72110.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aa6a88e5ad1a2df217bd8331478acec2ca97b73bddae9471762e1a7ebbc18e1
+size 359