Training in progress, step 647

config.json

@@ -0,0 +1,67 @@
+{
+  "A_initializer_range": [
+    1,
+    16
+  ],
+  "_name_or_path": "OuteAI/Lite-Oute-2-Mamba2Attn-Base",
+  "architectures": [
+    "CustomModelForSequenceClassification"
+  ],
+  "attention_conv_kernel": 4,
+  "attention_head_dim": 128,
+  "attention_layers_idx": [
+    6,
+    12,
+    18,
+    24
+  ],
+  "auto_map": {
+    "AutoConfig": "OuteAI/Lite-Oute-2-Mamba2Attn-Base--configuration_mamba2attn.Mamba2Config",
+    "AutoModelForCausalLM": "OuteAI/Lite-Oute-2-Mamba2Attn-Base--modeling_mamba2attn.Mamba2ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "chunk_size": 256,
+  "classifier_dropout": 0.1,
+  "conv_initializer_range": null,
+  "emb_initializer_range": 0.02,
+  "eos_token_id": 2,
+  "expand": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "intermediate_size": 2048,
+  "layer_norm_epsilon": 1e-05,
+  "mamba2_conv_kernel": 4,
+  "mamba2_head_dim": 64,
+  "mamba2_num_heads": 32,
+  "max_position_embeddings": 8192,
+  "mlp_intermediate_size": 0,
+  "mlp_padding_size": 128,
+  "model_type": "mamba2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "rescale_prenorm_residual": false,
+  "residual_in_fp32": true,
+  "rope_emb_dim": 64,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "state_size": 128,
+  "tie_embedding_weights": true,
+  "time_step_floor": 0.0001,
+  "time_step_limit": [
+    0.0,
+    Infinity
+  ],
+  "time_step_max": 0.1,
+  "time_step_min": 0.001,
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.0.dev0",
+  "use_attention_out_bias": false,
+  "use_attention_qkv_bias": false,
+  "use_cache": true,
+  "use_conv_bias": true,
+  "use_mamba2_bias": false,
+  "use_mlp_bias": false,
+  "vocab_size": 32768
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e8d9ebfb3e206d14696f25673d424fda3a9d157c67a185b08567f67b62ad749
+size 1008305552

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "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 sha256:26662296c9eb6d1862a26ae7ad25658589c82d73a60a09e7a1b7a7048fcbfbf9
+size 5112