End of training

README.md

@@ -0,0 +1,50 @@
+---
+license: mit
+base_model: microsoft/git-base
+tags:
+- generated_from_trainer
+model-index:
+- name: working_dir
+  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. -->
+
+# working_dir
+
+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
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.15.2

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": "4.38.2",
+  "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": "4.38.2"
+}

model.safetensors

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

runs/Apr21_15-37-09_bae5d767b986/events.out.tfevents.1713715784.bae5d767b986.9349.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e443f243c3ca1922db63649647534c025e26c3d4484c0dd505e60d4304f96baf
+size 4184

runs/Apr21_16-15-16_bae5d767b986/events.out.tfevents.1713716116.bae5d767b986.17908.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f4f39ac912ff9756506c4e50e989ecce5905fbf17b49e33f1c5022d04d468d
+size 4184

runs/Apr21_16-22-21_bae5d767b986/events.out.tfevents.1713716543.bae5d767b986.19442.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e115734119ae8ee819f6696b17fc93d3f3e193300dc050ccf1dba994830b4ae0
+size 4184

runs/Apr21_16-35-56_bae5d767b986/events.out.tfevents.1713717360.bae5d767b986.21273.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9674d30668ac921e3bb2ec50b5fb226ea16f2f26a165999b069dc19167a68efd
+size 4184

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfab546c674a8e821c4720e851b5fcc256a7ad0652b55434659ca6b437e93b1e
+size 4856