Training in progress step 10000

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/checkpoint/dpf/models/cm-1.3B-hf",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "XGLMForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "attention_heads": 32,
+  "bos_token_id": 0,
+  "d_model": 1600,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "eos_token_id": 0,
+  "ffn_dim": 8192,
+  "init_std": 0.02,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 512,
+  "model_type": "xglm",
+  "num_layers": 12,
+  "pad_token_id": 0,
+  "scale_embedding": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "use_cache": true,
+  "vocab_size": 52003
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b8e9d16a39f42b0f4b7c5ef8c527a391b0b98a4a6ee2864533cac0432c1e07
+size 2083790139

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "bos_token": "<|endoftext|>",
   "model_max_length": 2048,
-  "name_or_path": "facebook/incoder-1B",
+  "name_or_path": "EddieChen372/incoder-1B-finetuned-jest",
   "special_tokens_map_file": "tokenizer/v2_trfs/special_tokens_map.json",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }