Model save

README.md

@@ -0,0 +1,51 @@
+---
+license: mit
+base_model: microsoft/git-base
+tags:
+- generated_from_trainer
+model-index:
+- name: git-base-cartoon
+  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. -->
+
+# git-base-cartoon
+
+This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the None 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "microsoft/git-base",
+  "architectures": [
+    "GitForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 101,
+  "classifier_dropout": null,
+  "eos_token_id": 102,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 1024,
+  "model_type": "git",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "num_image_with_embedding": null,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vision_config": {
+    "dropout": 0.0,
+    "initializer_factor": 1.0,
+    "model_type": "git_vision_model",
+    "projection_dim": 512
+  },
+  "vocab_size": 30522
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 101,
+  "eos_token_id": 102,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:346fa81bf8da44b06783b6709717b09de9ddf0f3f6b8270f1dd6ae105574f30c
+size 706516040

runs/Aug02_04-38-04_c3297f3b0c1b/events.out.tfevents.1722573496.c3297f3b0c1b.486.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4364f7f3dd8064f87c01913d9bf7f204409c499e419c576b02d91d2ab678eb54
+size 5059

runs/Aug02_04-41-26_c3297f3b0c1b/events.out.tfevents.1722573695.c3297f3b0c1b.486.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d89de035e4c788a1cc56561ee8740163b23dfe079ef1f2bd6dbe1e5d1ca9788b
+size 5057

runs/Aug02_04-42-06_c3297f3b0c1b/events.out.tfevents.1722573734.c3297f3b0c1b.486.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c63b7b2091ef88d7a3673e21271085342febad1af96497e991d93f45d834a3a9
+size 10438

runs/Aug02_04-51-55_c3297f3b0c1b/events.out.tfevents.1722574327.c3297f3b0c1b.486.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bf0d0760df27f359288a9ca6fb7f6e4872db3c85acea424790f87568706e857
+size 4184

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7762cd7c40d5a39a4b17cad6152f473b10cd569eb0ad47c0ae546d843268ae63
+size 5112