Training in progress, step 1000

config.json

@@ -4,21 +4,21 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "bos_token_id": 0,
+  "eos_token_id": 3,
   "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 576,
   "initializer_range": 0.041666666666666664,
   "intermediate_size": 1536,
   "is_llama_config": true,
-  "max_position_embeddings": 2048,
+  "max_position_embeddings": 4096,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 9,
   "num_hidden_layers": 30,
   "num_key_value_heads": 3,
-  "pad_token_id": 128001,
+  "pad_token_id": 1,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_interleaved": false,
@@ -28,5 +28,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.52.4",
   "use_cache": true,
-  "vocab_size": 128256
+  "vocab_size": 32000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:699426dfe341552585255b67a25938d9ad1c936c7a033c9e895939165f705140
-size 720346024
+oid sha256:13894f58a44deafe22e9e403e7aa510a54f7fbe72b8d436a319899d17c2be6bc
+size 498572168

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a6c212cb2bdfb63b9ba29a3878d4e915d4c6e833b0521f156691c2be787136d
+size 5713