mrSoul7766/git-base-instagram-cap

README.md

@@ -0,0 +1,73 @@
+---
+license: mit
+base_model: microsoft/git-base
+tags:
+- generated_from_trainer
+model-index:
+- name: git-base-instagram-cap
+  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-instagram-cap
+
+This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1859
+- Wer Score: 1.0566
+
+## 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
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer Score |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|
+| 7.3647        | 3.85  | 50   | 4.5576          | 1.0161    |
+| 2.4064        | 7.69  | 100  | 0.5626          | 0.9656    |
+| 0.2425        | 11.54 | 150  | 0.1644          | 0.8256    |
+| 0.0894        | 15.38 | 200  | 0.1631          | 0.8623    |
+| 0.0636        | 19.23 | 250  | 0.1660          | 0.8730    |
+| 0.0472        | 23.08 | 300  | 0.1701          | 0.8783    |
+| 0.0384        | 26.92 | 350  | 0.1743          | 0.8692    |
+| 0.0327        | 30.77 | 400  | 0.1778          | 0.8814    |
+| 0.0286        | 34.62 | 450  | 0.1791          | 0.8891    |
+| 0.0242        | 38.46 | 500  | 0.1818          | 0.8982    |
+| 0.0187        | 42.31 | 550  | 0.1831          | 0.9120    |
+| 0.0141        | 46.15 | 600  | 0.1856          | 1.0092    |
+| 0.012         | 50.0  | 650  | 0.1859          | 1.0566    |
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -1,5 +1,5 @@
 {
-  "_commit_hash": null,
+  "_name_or_path": "microsoft/git-base",
   "architectures": [
     "GitForCausalLM"
   ],
@@ -22,85 +22,13 @@
   "position_embedding_type": "absolute",
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": null,
+  "transformers_version": "4.37.0.dev0",
   "use_cache": true,
   "vision_config": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
     "dropout": 0.0,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "quick_gelu",
-    "hidden_size": 768,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "image_size": 224,
     "initializer_factor": 1.0,
-    "initializer_range": 0.02,
-    "intermediate_size": 3072,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-05,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
     "model_type": "git_vision_model",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 12,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_channels": 3,
-    "num_hidden_layers": 12,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "patch_size": 16,
-    "prefix": null,
-    "problem_type": null,
-    "projection_dim": 512,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "transformers_version": "4.26.0.dev0",
-    "typical_p": 1.0,
-    "use_bfloat16": false
+    "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": "4.37.0.dev0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21ce39d9e50e5fc303f6c58903bfa8a90acf14f004551a1b92aee0c0dcbb2182
+oid sha256:aceb1e9825e815ed1713c24e84c47aeeea0bccaf7bbf9abd96a7aa0308cfad19
 size 706516040