Model natrénován s nejlepší metrikou -0.0609 v epoše 0

config.json

@@ -0,0 +1,80 @@
+{
+  "_name_or_path": "./output_test_freeze_dense_only/best_model",
+  "activation_function": "gelu",
+  "add_pooling_layer": false,
+  "architectures": [
+    "NomicBertModel"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_hf_nomic_bert.NomicBertConfig",
+    "AutoModel": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertModel",
+    "AutoModelForMaskedLM": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForPreTraining",
+    "AutoModelForMultipleChoice": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForMultipleChoice",
+    "AutoModelForQuestionAnswering": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForQuestionAnswering",
+    "AutoModelForSequenceClassification": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForSequenceClassification",
+    "AutoModelForTokenClassification": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForTokenClassification"
+  },
+  "base_model_name": "./output_test_freeze_dense_only/best_model",
+  "bos_token_id": null,
+  "causal": false,
+  "dense_seq_output": true,
+  "embd_pdrop": 0.1,
+  "embedding_dim": 2048,
+  "eos_token_id": null,
+  "expert_choice_router": false,
+  "ffn_div": 1,
+  "freeze_embeddings": false,
+  "freeze_strategy": "selective",
+  "fused_bias_fc": true,
+  "fused_dropout_add_ln": true,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_trained_positions": 2048,
+  "mlp_fc1_bias": true,
+  "mlp_fc2_bias": true,
+  "model_type": "nomic_bert",
+  "moe_every_n_layers": 2,
+  "moe_impl": "megablocks",
+  "moe_normalize_expert_weights": false,
+  "moe_resid_pdrop": 0.0,
+  "moe_top_k": 2,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 2048,
+  "num_experts": 8,
+  "num_shared_experts": 0,
+  "num_unfrozen_layers": 6,
+  "pad_token_id": 1,
+  "pad_vocab_size_multiple": 64,
+  "parallel_block": false,
+  "parallel_block_tied_norm": false,
+  "prenorm": false,
+  "qkv_proj_bias": true,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "rotary_emb_base": 10000,
+  "rotary_emb_fraction": 1.0,
+  "rotary_emb_interleaved": false,
+  "rotary_emb_scale_base": null,
+  "rotary_scaling_factor": null,
+  "router_aux_loss_coef": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 1,
+  "unfreeze_experts": false,
+  "use_cache": true,
+  "use_flash_attn": true,
+  "use_rms_norm": null,
+  "use_xentropy": true,
+  "vocab_size": 250048
+}

configuration_hf_nomic_bert.py

@@ -0,0 +1,56 @@
+from transformers import GPT2Config
+
+
+class NomicBertConfig(GPT2Config):
+    model_type = "nomic_bert"
+
+    def __init__(
+        self,
+        prenorm=False,
+        parallel_block=False,
+        parallel_block_tied_norm=False,
+        rotary_emb_fraction=0.0,
+        fused_dropout_add_ln=False,
+        fused_bias_fc=False,
+        use_flash_attn=False,
+        use_xentropy=False,
+        qkv_proj_bias=True,
+        rotary_emb_base=10_000,
+        rotary_emb_scale_base=None,
+        rotary_emb_interleaved=False,
+        mlp_fc1_bias=True,
+        mlp_fc2_bias=True,
+        use_rms_norm=False,
+        causal=False,
+        type_vocab_size=2,
+        dense_seq_output=True,
+        pad_vocab_size_multiple=1,
+        tie_word_embeddings=True,
+        rotary_scaling_factor=None,
+        max_trained_positions=2048,
+        **kwargs,
+    ):
+        self.prenorm = prenorm
+        self.parallel_block = parallel_block
+        self.parallel_block_tied_norm = parallel_block_tied_norm
+        self.rotary_emb_fraction = rotary_emb_fraction
+        self.tie_word_embeddings = tie_word_embeddings
+        self.fused_dropout_add_ln = fused_dropout_add_ln
+        self.fused_bias_fc = fused_bias_fc
+        self.use_flash_attn = use_flash_attn
+        self.use_xentropy = use_xentropy
+        self.qkv_proj_bias = qkv_proj_bias
+        self.rotary_emb_base = rotary_emb_base
+        self.rotary_emb_scale_base = rotary_emb_scale_base
+        self.rotary_emb_interleaved = rotary_emb_interleaved
+        self.mlp_fc1_bias = mlp_fc1_bias
+        self.mlp_fc2_bias = mlp_fc2_bias
+        self.use_rms_norm = use_rms_norm
+        self.causal = causal
+        self.type_vocab_size = type_vocab_size
+        self.dense_seq_output = dense_seq_output
+        self.pad_vocab_size_multiple = pad_vocab_size_multiple
+        self.rotary_scaling_factor = rotary_scaling_factor
+        self.max_trained_positions = max_trained_positions
+
+        super().__init__(**kwargs)

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc09ba7e0974054dfd397f3ec4028ec1793e3ed396e2e9131b31b0f2896cec31
+size 1901187232

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01eb629a1c6c6166faadae1cbbd6f98224d172feab00fae51867d5efd1a57ce6
+size 6318080