End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1228
+- Loss: 0.1714
 
 ## Model description
 
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
 - 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: 400
-- training_steps: 4000
+- training_steps: 12000
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -61,6 +61,8 @@ The following hyperparameters were used during training:
 | 0.1148        | 0.4228 | 3000 | 0.1313          |
 | 0.1128        | 0.4933 | 3500 | 0.1264          |
 | 0.1277        | 0.5638 | 4000 | 0.1228          |
+| 0.1851        | 0.6342 | 4500 | 0.1940          |
+| 0.1678        | 0.7047 | 5000 | 0.1714          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da935c3bc56db2ab39bcff7186d07ffe9b0cb96fe5fa752bb4e14046fd96ada9
+oid sha256:06040f0a65c33d2a3f082f5bfa1f8a8328ec6bf7f83978e0aabf2a928168fffb
 size 63056714

adapter_model/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "WhisperForConditionalGeneration",
+    "parent_library": "transformers.models.whisper.modeling_whisper"
+  },
+  "base_model_name_or_path": "openai/whisper-large-v2",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06040f0a65c33d2a3f082f5bfa1f8a8328ec6bf7f83978e0aabf2a928168fffb
+size 63056714

runs/Dec22_11-22-57_DESKTOP-1TFDHRE/events.out.tfevents.1734862979.DESKTOP-1TFDHRE.10356.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b01296d2f7aec22ac6de34c87cab17f9bc48272b27e064c35999010f2bcc070b
-size 15483
+oid sha256:8502137ffc8015232dc0a619ec686140de4c38f12540154344b787f283702f18
+size 15837