Model save

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: openai/whisper-large
+model-index:
+- name: output_0324
+  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. -->
+
+# output_0324
+
+This model is a fine-tuned version of [openai/whisper-large](https://huggingface.co/openai/whisper-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4165
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 5
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 11   | 1.4216          |
+| No log        | 2.0   | 22   | 1.4178          |
+| 1.3809        | 3.0   | 33   | 1.4165          |
+
+
+### Framework versions
+
+- PEFT 0.10.1.dev0
+- Transformers 4.40.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "WhisperForConditionalGeneration",
+    "parent_library": "transformers.models.whisper.modeling_whisper"
+  },
+  "base_model_name_or_path": "openai/whisper-large",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.decoder.layers.31.self_attn.out_proj",
+    "model.decoder.layers.31.encoder_attn.q_proj",
+    "model.decoder.layers.31.self_attn.k_proj",
+    "model.decoder.layers.31.self_attn.v_proj",
+    "model.decoder.layers.31.encoder_attn.v_proj",
+    "model.decoder.layers.31.encoder_attn.out_proj",
+    "model.decoder.layers.31.self_attn.q_proj",
+    "model.decoder.layers.31.encoder_attn.k_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:896f5ff9e10f988222810f711d6394eec3657d62ec90d2f43f4244ac47e6164a
+size 2623752

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

runs/Mar24_20-42-18_03bc7e99d747/events.out.tfevents.1711312944.03bc7e99d747.1287.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdd793c5781e760df30d1ab66ae826a5109ccbba113aab3bbe8572f26a0dd0b9
+size 7367

runs/Mar24_21-14-34_03bc7e99d747/events.out.tfevents.1711314877.03bc7e99d747.1287.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0d5ea5343b2b670461294e05d6c4a854b3701d41ba601c69cade746e5b5720e
+size 7367

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c7a7cf54359618c222c3fa6eabcd879d3c14e6002bd7ee990d06aae9e7801b6
+size 5048