Model save

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: hierarchical-music-t5
+  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. -->
+
+# hierarchical-music-t5
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4033
+
+## 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: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.8955        | 0.2319 | 500  | 2.7612          |
+| 2.3273        | 0.4637 | 1000 | 2.1916          |
+| 2.0087        | 0.6956 | 1500 | 1.9170          |
+| 1.8677        | 0.9274 | 2000 | 1.7573          |
+| 1.7551        | 1.1591 | 2500 | 1.6827          |
+| 1.6952        | 1.3909 | 3000 | 1.5931          |
+| 1.6407        | 1.6228 | 3500 | 1.5399          |
+| 1.5992        | 1.8546 | 4000 | 1.4942          |
+| 1.5402        | 2.0863 | 4500 | 1.4600          |
+| 1.5282        | 2.3181 | 5000 | 1.4403          |
+| 1.5036        | 2.5500 | 5500 | 1.4165          |
+| 1.4906        | 2.7818 | 6000 | 1.4033          |
+
+
+### Framework versions
+
+- Transformers 4.54.0
+- Pytorch 2.6.0+cu124
+- Datasets 4.0.0
+- Tokenizers 0.21.2

final_model/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 3,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 4,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 8,
+  "num_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.54.0",
+  "use_cache": false,
+  "vocab_size": 4796
+}

final_model/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 3,
+  "eos_token_id": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.54.0",
+  "use_cache": false
+}

final_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5324439a7ae397ca800913e58eb0ef2d9f26e6d1f9470810acdd07fcb02710e1
+size 362303176

final_model/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "bos_token": {
+    "content": "[START]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[END]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

final_model/tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[START]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[END]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[START]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[END]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

final_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1fcfc25c74fae6af9e60450b4b2cb088a33b150a996b99652aaf2b1868923a
+size 5560

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 3,
+  "eos_token_id": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.54.0",
+  "use_cache": false
+}