Training in progress, step 360

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": 38566
+}

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:ee20f7e473fa2b69b1a33079a8320f86e420f3e3edec02e83a9d4a3a1a5edba0
+size 519644080

runs/Jan25_09-57-50_ff1d9a4addb6/events.out.tfevents.1769335074.ff1d9a4addb6.433.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9b9344abd1ad6db28b00e883ce3d77796405693bc645cf3109614e47a510bfa
+size 6801

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9230a3ad49af30e748d3923af3536bfe51713235a6bd07b2ec066a063ec957e7
+size 5841