Training in progress, step 198

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": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 512,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 16,
+  "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": 13588
+}

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:ba8dc551503b5cfc928160820f32952d8f777108382bbdff6366b12ab44b6fd1
+size 401205064

runs/Jan25_17-00-18_0b06f93a2b3d/events.out.tfevents.1769360423.0b06f93a2b3d.266.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d6834c37ab347c7e2fcc5eedd05f3f93c67fae906c813359d9c492abf2553a7
+size 5952

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db60f14b446b24da17a59df5efb11dad0711127efa4480e41655bf21f65ed0fa
+size 5841