Training in progress, step 10000

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "HuggingFaceTB/SmolLM-135M",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 256000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e449c399e94ded828d27a1805e8d9f02e06775c379559ab8b0cd3d42e139031a
+size 1014668224

runs/Sep08_10-47-03_ae1f62290579/events.out.tfevents.1725792425.ae1f62290579.36.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09d5b25b6fa6babd4590fcf7ea6ad5f762dd6a74ffaa867d09f5f5b44ccb1827
+size 9195

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf73071f6500ddf783f04318c67a0a0b72444bb6e20fb7677bfa4452e26b7904
+size 5240