Training in progress, step 100

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "StockLlamaForForecasting"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 5000,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "stockllama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "term_number": 4,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 10000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e96e2d9f0dd3b431271ddd7b8047f3d518ccfbcf4fa2bf2364d4923e8976956c
+size 707739976

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac7591d12511e1e80b7c21b70a2f1362cffe0bd3c68962c9d298e468af9f0b2d
+size 5112