Training in progress, step 100

config.json

@@ -1,13 +1,13 @@
 {
-  "_name_or_path": "waddledee/myBit-Llama2-jp-127M-4_hajime_0405",
+  "_name_or_path": "waddledee/myBit-Llama2-jp-127M-158b-hajime-0410",
   "architectures": [
     "LlamaForSequenceClassification"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "waddledee/myBit-Llama2-jp-127M-4_hajime_0405--modeling_bit_llama.BitLlamaConfig",
-    "AutoModelForCausalLM": "waddledee/myBit-Llama2-jp-127M-4_hajime_0405--modeling_bit_llama.BitLlamaForCausalLM"
+    "AutoConfig": "waddledee/myBit-Llama2-jp-127M-158b-hajime-0410--modeling_bit_llama.BitLlamaConfig",
+    "AutoModelForCausalLM": "waddledee/myBit-Llama2-jp-127M-158b-hajime-0410--modeling_bit_llama.BitLlamaForCausalLM"
   },
   "bitnet_type": "1.58b",
   "bits": 8,
@@ -52,7 +52,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float32",
   "transformers_version": "4.38.2",
   "use_cache": true,
   "vocab_size": 43176

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77a098de34b8ea0fa95547174074edf0a0f13c00bf4719e53593f49e37012f20
-size 189066320
+oid sha256:489fbc2d3b09883fb2c8f54d3d8a4930fc3861d9bc82feb0be0f971af6035359
+size 378120216

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecb7d5879dbffda21ddc48a1ce75b846c06156d60eaeb908d30fa438ec28948c
+oid sha256:be8982212a9666cd6091c66dd9ecdc7d07bb74b05da124bf61fededcb28b5de9
 size 4920