End of training

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+base_model: vikhyatk/moondream2
+tags:
+- generated_from_trainer
+model-index:
+- name: training_the_moon
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# training_the_moon
+
+This model is a fine-tuned version of [vikhyatk/moondream2](https://huggingface.co/vikhyatk/moondream2) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

configuration_moondream.py

@@ -0,0 +1,98 @@
+from transformers import PretrainedConfig
+
+
+class PhiConfig(PretrainedConfig):
+    model_type = "phi"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=51200,
+        hidden_size=2048,
+        intermediate_size=8192,
+        num_hidden_layers=24,
+        num_attention_heads=32,
+        num_key_value_heads=None,
+        resid_pdrop=0.0,
+        embd_pdrop=0.0,
+        attention_dropout=0.0,
+        hidden_act="gelu_new",
+        max_position_embeddings=2048,
+        initializer_range=0.02,
+        layer_norm_eps=1e-5,
+        use_cache=True,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        partial_rotary_factor=0.5,
+        qk_layernorm=False,
+        bos_token_id=1,
+        eos_token_id=2,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.resid_pdrop = resid_pdrop
+        self.embd_pdrop = embd_pdrop
+        self.attention_dropout = attention_dropout
+        self.hidden_act = hidden_act
+        self.max_position_embeddings = max_position_embeddings
+        self.initializer_range = initializer_range
+        self.layer_norm_eps = layer_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.partial_rotary_factor = partial_rotary_factor
+        self.qk_layernorm = qk_layernorm
+        self._rope_scaling_validation()
+
+        super().__init__(
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+
+    # Copied from transformers.models.llama.configuration_llama.LlamaConfig._rope_scaling_validation
+    def _rope_scaling_validation(self):
+        """
+        Validate the `rope_scaling` configuration.
+        """
+        if self.rope_scaling is None:
+            return
+
+        if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2:
+            raise ValueError(
+                "`rope_scaling` must be a dictionary with with two fields, `type` and `factor`, "
+                f"got {self.rope_scaling}"
+            )
+        rope_scaling_type = self.rope_scaling.get("type", None)
+        rope_scaling_factor = self.rope_scaling.get("factor", None)
+        if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic"]:
+            raise ValueError(
+                f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}"
+            )
+        if (
+            rope_scaling_factor is None
+            or not isinstance(rope_scaling_factor, float)
+            or rope_scaling_factor <= 1.0
+        ):
+            raise ValueError(
+                f"`rope_scaling`'s factor field must be a float > 1, got {rope_scaling_factor}"
+            )
+
+
+class MoondreamConfig(PretrainedConfig):
+    model_type = "moondream1"
+
+    def __init__(self, **kwargs):
+        self.text_config = PhiConfig(**kwargs.pop("text_config", {}))
+        super().__init__(**kwargs)

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.41.2"
+}

runs/Jun05_22-09-36_158-101-18-255/events.out.tfevents.1717625377.158-101-18-255.10761.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9755c4de141be3e9cab5712cc2a5c1e79d43ecd7be4e34314917b5ce7923e638
-size 4973
+oid sha256:1124aedbbc8934ef4ac30dfe9c40a136995f956f634bb5a84845238574bba2f1
+size 5528