Training in progress, step 100

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "waddledee/myBit-Llama2-jp-127M-4_hajime_0405",
+  "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"
+  },
+  "bitnet_type": "1.58b",
+  "bits": 8,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "topic-news",
+    "1": "dokujo-tsushin",
+    "2": "livedoor-homme",
+    "3": "it-life-hack",
+    "4": "kaden-channel",
+    "5": "smax",
+    "6": "sports-watch",
+    "7": "peachy",
+    "8": "movie-enter"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "dokujo-tsushin": 1,
+    "it-life-hack": 3,
+    "kaden-channel": 4,
+    "livedoor-homme": 2,
+    "movie-enter": 8,
+    "peachy": 7,
+    "smax": 5,
+    "sports-watch": 6,
+    "topic-news": 0
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "llama",
+  "n_ctx": 128,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 4,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "problem_type": "single_label_classification",
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 43176
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a098de34b8ea0fa95547174074edf0a0f13c00bf4719e53593f49e37012f20
+size 189066320

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c877c5ca885bad5c19d1b1706a2703f8b30de90f03c1f834f8bdb9faf79821e8
+size 914000

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb7d5879dbffda21ddc48a1ce75b846c06156d60eaeb908d30fa438ec28948c
+size 4920