Training in progress, step 500

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "head_dim": 2,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_size": 12,
+  "initializer_range": 0.02,
+  "intermediate_size": 24,
+  "max_position_embeddings": 430,
+  "model_type": "gemma",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "use_bidirectional_attention": null,
+  "use_cache": false,
+  "vocab_size": 9500
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.0.0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac0619afa9c01168683eaca311fb4997f57d05eae3b62a10bcb4431bd888844
+size 492328

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db62a57b9d259483eb24965269b300d1953890cd2474f199211b036a51ada51b
+size 5201