End of training

README.md

@@ -0,0 +1,52 @@
+---
+library_name: transformers
+license: mit
+base_model: microsoft/git-base
+tags:
+- generated_from_trainer
+model-index:
+- name: git-base-pokemon
+  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-pokemon
+
+This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 50
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- 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": "4.44.2",
+  "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": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a48eef7e5f77cd148653f406cd52b958e99bbe7668d3aaca0447eba66fd662c3
+size 706516040

runs/Sep30_17-50-16_91f8d9b032e7/events.out.tfevents.1727719451.91f8d9b032e7.25585.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426d998110def142985bcc9133bc7c02306ebeaf79889debda14958a30cb6252
+size 10164

runs/Sep30_18-30-52_91f8d9b032e7/events.out.tfevents.1727721154.91f8d9b032e7.25585.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29edda63377f9e5928386ef076d586cefd0b77f6def2906c38da5cce8d3ebf09
+size 5126

runs/Sep30_18-30-52_91f8d9b032e7/events.out.tfevents.1727721533.91f8d9b032e7.25585.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa1f702428ea6a788d9f15c5cb415ca23426748438d2f1a6e2daf86ad8531ef7
+size 4184

runs/Sep30_18-30-52_91f8d9b032e7/events.out.tfevents.1727721570.91f8d9b032e7.25585.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c77e782308e8912854cdba36b0f59b369b5da6e555478c07e40ba8884c735a9c
+size 4184

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:681c86e4fedd8a52c360f39ab011402a1fe158cdeec12549dd5b91a840bc5513
+size 5176