End of training

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 3.0,
+    "epoch": 1.0,
     "eval_loss": Infinity,
-    "eval_runtime": 10.6149,
+    "eval_runtime": 10.6101,
     "eval_samples": 301,
-    "eval_samples_per_second": 28.356,
-    "eval_steps_per_second": 3.58,
+    "eval_samples_per_second": 28.369,
+    "eval_steps_per_second": 3.582,
     "eval_wer": 1.0,
-    "train_loss": 3.7429571440725615,
-    "train_runtime": 101.8953,
+    "train_loss": 4.538612365722656,
+    "train_runtime": 31.4322,
     "train_samples": 704,
-    "train_samples_per_second": 20.727,
-    "train_steps_per_second": 2.591
+    "train_samples_per_second": 22.397,
+    "train_steps_per_second": 2.8
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 3.0,
+    "epoch": 1.0,
     "eval_loss": Infinity,
-    "eval_runtime": 10.6149,
+    "eval_runtime": 10.6101,
     "eval_samples": 301,
-    "eval_samples_per_second": 28.356,
-    "eval_steps_per_second": 3.58,
+    "eval_samples_per_second": 28.369,
+    "eval_steps_per_second": 3.582,
     "eval_wer": 1.0
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:941203e6a17701b67c1cafc3d6cb41d4cf74fc16cad3faa57ca84153d5da0cd2
+oid sha256:612dd692031680aae02deafa36c7fa8dadce27d4b31ce9acb75461c1e48b9ddb
 size 1247823

run.sh

@@ -4,7 +4,7 @@ python run_speech_recognition_ctc.py \
 	--dataset_config_name="ab" \
 	--output_dir="./" \
 	--overwrite_output_dir \
-	--num_train_epochs="3" \
+	--num_train_epochs="1" \
 	--save_steps="100" \
 	--eval_steps="500" \
 	--per_device_train_batch_size="8" \
@@ -21,3 +21,4 @@ python run_speech_recognition_ctc.py \
 	--push_to_hub \
 	--use_auth_token \
 	--do_train --do_eval
+

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

test_load_cv_en.py

@@ -0,0 +1,6 @@
+
+from transformers import AutoModelForCTC, AutoProcessor
+from datasets import load_dataset
+train_ds = load_dataset('mozilla-foundation/common_voice_7_0', 'en', split='train[10:20]')
+
+print(len(train_ds))

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 3.7429571440725615,
-    "train_runtime": 101.8953,
+    "epoch": 1.0,
+    "train_loss": 4.538612365722656,
+    "train_runtime": 31.4322,
     "train_samples": 704,
-    "train_samples_per_second": 20.727,
-    "train_steps_per_second": 2.591
+    "train_samples_per_second": 22.397,
+    "train_steps_per_second": 2.8
 }

trainer_state.json

@@ -1,25 +1,25 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
-  "global_step": 264,
+  "epoch": 1.0,
+  "global_step": 88,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 264,
-      "total_flos": 391664972335104.0,
-      "train_loss": 3.7429571440725615,
-      "train_runtime": 101.8953,
-      "train_samples_per_second": 20.727,
-      "train_steps_per_second": 2.591
+      "epoch": 1.0,
+      "step": 88,
+      "total_flos": 130613499224064.0,
+      "train_loss": 4.538612365722656,
+      "train_runtime": 31.4322,
+      "train_samples_per_second": 22.397,
+      "train_steps_per_second": 2.8
     }
   ],
-  "max_steps": 264,
-  "num_train_epochs": 3,
-  "total_flos": 391664972335104.0,
+  "max_steps": 88,
+  "num_train_epochs": 1,
+  "total_flos": 130613499224064.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59923f372893625f0de9829d44a4b74c369997fe40d4b7f08759e5a30b318f24
+oid sha256:d118e42535c934c70d07a3714d6d1920cb49fd8cfe6d64fc5e126f0905ace316
 size 2991