Training in progress, step 180

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "head_dim": 64,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": null,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 512,
+  "model_type": "gemma",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "vocab_size": 15000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.57.6"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afbf4b4e72f46ba67442fc3ebe54ab50555c7d784c37609e52b2700a66a685d9
+size 447249296

runs/Jan23_14-54-47_48f0a7cc1941/events.out.tfevents.1769180090.48f0a7cc1941.620.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:840daa2f84b88ad165d5fc268dec5e4a495d093d1c68cbee10f63fdf4644b41b
+size 5963

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0459bbb8045ea0aea5f8b2b930af4b4ee4465a247f20841cb3ed25a9da44864a
+size 5841