End of training

README.md

@@ -1,7 +1,11 @@
 ---
+language:
+- ta
 license: apache-2.0
 base_model: facebook/wav2vec2-large-xlsr-53
 tags:
+- automatic-speech-recognition
+- mozilla-foundation/common_voice_6_1
 - generated_from_trainer
 datasets:
 - common_voice_6_1
@@ -14,15 +18,15 @@ model-index:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: common_voice_6_1
+      name: MOZILLA-FOUNDATION/COMMON_VOICE_6_1 - TA
       type: common_voice_6_1
       config: ta
       split: test
-      args: ta
+      args: 'Config: ta, Training split: train+validation, Eval split: test'
     metrics:
     - name: Wer
       type: wer
-      value: 0.7094281298299846
+      value: 0.7095686384712659
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +34,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-common_voice-ta
 
-This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_6_1 dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the MOZILLA-FOUNDATION/COMMON_VOICE_6_1 - TA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6599
-- Wer: 0.7094
+- Loss: 0.6563
+- Wer: 0.7096
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 14.94,
+    "eval_loss": 0.656301736831665,
+    "eval_runtime": 121.3421,
+    "eval_samples": 1781,
+    "eval_samples_per_second": 14.678,
+    "eval_steps_per_second": 1.838,
+    "eval_wer": 0.7095686384712659,
+    "train_loss": 1.3876537419981876,
+    "train_runtime": 7307.918,
+    "train_samples": 3788,
+    "train_samples_per_second": 7.775,
+    "train_steps_per_second": 0.242
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 14.94,
+    "eval_loss": 0.656301736831665,
+    "eval_runtime": 121.3421,
+    "eval_samples": 1781,
+    "eval_samples_per_second": 14.678,
+    "eval_steps_per_second": 1.838,
+    "eval_wer": 0.7095686384712659
+}

runs/Feb09_15-12-11_96d880c2e067/events.out.tfevents.1707499153.96d880c2e067.6291.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b94465293a77c750fcf9d623b8c32f534ec288d22707af7470d905e26c5a3235
+size 406

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 14.94,
+    "train_loss": 1.3876537419981876,
+    "train_runtime": 7307.918,
+    "train_samples": 3788,
+    "train_samples_per_second": 7.775,
+    "train_steps_per_second": 0.242
+}

trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 14.936708860759493,
+  "eval_steps": 100,
+  "global_step": 1770,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.84,
+      "eval_loss": 4.394069194793701,
+      "eval_runtime": 118.8089,
+      "eval_samples_per_second": 14.99,
+      "eval_steps_per_second": 1.877,
+      "eval_wer": 1.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.69,
+      "eval_loss": 3.200528383255005,
+      "eval_runtime": 116.974,
+      "eval_samples_per_second": 15.226,
+      "eval_steps_per_second": 1.906,
+      "eval_wer": 1.0,
+      "step": 200
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 2.7843868732452393,
+      "eval_runtime": 118.9835,
+      "eval_samples_per_second": 14.968,
+      "eval_steps_per_second": 1.874,
+      "eval_wer": 1.0144723900519883,
+      "step": 300
+    },
+    {
+      "epoch": 3.38,
+      "eval_loss": 0.8691409230232239,
+      "eval_runtime": 118.7268,
+      "eval_samples_per_second": 15.001,
+      "eval_steps_per_second": 1.878,
+      "eval_wer": 1.000281017282563,
+      "step": 400
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 0.0002988,
+      "loss": 4.317,
+      "step": 500
+    },
+    {
+      "epoch": 4.22,
+      "eval_loss": 0.684583306312561,
+      "eval_runtime": 119.9053,
+      "eval_samples_per_second": 14.853,
+      "eval_steps_per_second": 1.86,
+      "eval_wer": 0.8393986230153154,
+      "step": 500
+    },
+    {
+      "epoch": 5.06,
+      "eval_loss": 0.6270079612731934,
+      "eval_runtime": 120.1998,
+      "eval_samples_per_second": 14.817,
+      "eval_steps_per_second": 1.855,
+      "eval_wer": 0.7789799072642968,
+      "step": 600
+    },
+    {
+      "epoch": 5.91,
+      "eval_loss": 0.593498945236206,
+      "eval_runtime": 120.001,
+      "eval_samples_per_second": 14.842,
+      "eval_steps_per_second": 1.858,
+      "eval_wer": 0.7802444850358297,
+      "step": 700
+    },
+    {
+      "epoch": 6.75,
+      "eval_loss": 0.570054829120636,
+      "eval_runtime": 120.3712,
+      "eval_samples_per_second": 14.796,
+      "eval_steps_per_second": 1.853,
+      "eval_wer": 0.7812280455247997,
+      "step": 800
+    },
+    {
+      "epoch": 7.59,
+      "eval_loss": 0.564914345741272,
+      "eval_runtime": 122.0077,
+      "eval_samples_per_second": 14.597,
+      "eval_steps_per_second": 1.828,
+      "eval_wer": 0.7890965294365604,
+      "step": 900
+    },
+    {
+      "epoch": 8.44,
+      "learning_rate": 0.00018236220472440942,
+      "loss": 0.3656,
+      "step": 1000
+    },
+    {
+      "epoch": 8.44,
+      "eval_loss": 0.6092184782028198,
+      "eval_runtime": 120.3224,
+      "eval_samples_per_second": 14.802,
+      "eval_steps_per_second": 1.853,
+      "eval_wer": 0.8177602922579739,
+      "step": 1000
+    },
+    {
+      "epoch": 9.28,
+      "eval_loss": 0.6092739701271057,
+      "eval_runtime": 120.225,
+      "eval_samples_per_second": 14.814,
+      "eval_steps_per_second": 1.855,
+      "eval_wer": 0.7720949838415062,
+      "step": 1100
+    },
+    {
+      "epoch": 10.13,
+      "eval_loss": 0.6154232621192932,
+      "eval_runtime": 120.1186,
+      "eval_samples_per_second": 14.827,
+      "eval_steps_per_second": 1.856,
+      "eval_wer": 0.7286778136855416,
+      "step": 1200
+    },
+    {
+      "epoch": 10.97,
+      "eval_loss": 0.6283690333366394,
+      "eval_runtime": 122.0867,
+      "eval_samples_per_second": 14.588,
+      "eval_steps_per_second": 1.827,
+      "eval_wer": 0.7407615568357454,
+      "step": 1300
+    },
+    {
+      "epoch": 11.81,
+      "eval_loss": 0.6343453526496887,
+      "eval_runtime": 120.4977,
+      "eval_samples_per_second": 14.78,
+      "eval_steps_per_second": 1.851,
+      "eval_wer": 0.7143459322748349,
+      "step": 1400
+    },
+    {
+      "epoch": 12.66,
+      "learning_rate": 6.425196850393701e-05,
+      "loss": 0.1681,
+      "step": 1500
+    },
+    {
+      "epoch": 12.66,
+      "eval_loss": 0.6523498296737671,
+      "eval_runtime": 119.5948,
+      "eval_samples_per_second": 14.892,
+      "eval_steps_per_second": 1.865,
+      "eval_wer": 0.7362652803147394,
+      "step": 1500
+    },
+    {
+      "epoch": 13.5,
+      "eval_loss": 0.6542894244194031,
+      "eval_runtime": 120.5721,
+      "eval_samples_per_second": 14.771,
+      "eval_steps_per_second": 1.85,
+      "eval_wer": 0.7139244063509906,
+      "step": 1600
+    },
+    {
+      "epoch": 14.35,
+      "eval_loss": 0.6598775386810303,
+      "eval_runtime": 124.634,
+      "eval_samples_per_second": 14.29,
+      "eval_steps_per_second": 1.789,
+      "eval_wer": 0.7094281298299846,
+      "step": 1700
+    },
+    {
+      "epoch": 14.94,
+      "step": 1770,
+      "total_flos": 7.546311277696558e+18,
+      "train_loss": 1.3876537419981876,
+      "train_runtime": 7307.918,
+      "train_samples_per_second": 7.775,
+      "train_steps_per_second": 0.242
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1770,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 400,
+  "total_flos": 7.546311277696558e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}