Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "_name_or_path": "facebook/wav2vec2-xls-r-1b",
   "activation_dropout": 0.1,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -11,7 +11,7 @@
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "codevector_dim": 768,
+  "codevector_dim": 1024,
   "contrastive_logits_temperature": 0.1,
   "conv_bias": true,
   "conv_dim": [
@@ -54,9 +54,9 @@
   "final_dropout": 0.0,
   "hidden_act": "gelu",
   "hidden_dropout": 0.0,
-  "hidden_size": 1024,
+  "hidden_size": 1280,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 5120,
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.0,
   "mask_feature_length": 64,
@@ -73,11 +73,11 @@
   "num_conv_pos_embedding_groups": 16,
   "num_conv_pos_embeddings": 128,
   "num_feat_extract_layers": 7,
-  "num_hidden_layers": 24,
+  "num_hidden_layers": 48,
   "num_negatives": 100,
-  "output_hidden_size": 1024,
+  "output_hidden_size": 1280,
   "pad_token_id": 32,
-  "proj_codevector_dim": 768,
+  "proj_codevector_dim": 1024,
   "tdnn_dilation": [
     1,
     2,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c61887e8de90f59def760685397a0bad5cec2197e2628a26877131b05b148ab
-size 1262067185
+oid sha256:98ca6cb6a4403735d0aed9aef6e54a5f44e23f21a39828c037ee1f6302dcb1f7
+size 3850492081

run.sh

@@ -1,6 +1,6 @@
 python run_speech_recognition_ctc.py \
         --dataset_name="NbAiLab/NPSC" \
-        --model_name_or_path="facebook/wav2vec2-xls-r-300m" \
+        --model_name_or_path="facebook/wav2vec2-xls-r-1b" \
         --hub_model_id="NbAiLab/wav2vec2-xlsr-300M-NPSC-OH" \
 	--dataset_config_name="16K_mp3" \
         --output_dir="./" \
@@ -9,7 +9,7 @@ python run_speech_recognition_ctc.py \
         --per_device_train_batch_size="16" \
         --per_device_eval_batch_size="16" \
         --gradient_accumulation_steps="4" \
-        --learning_rate="7.5e-5" \
+        --learning_rate="2e-5" \
         --warmup_steps="2000" \
         --length_column_name="input_length" \
         --evaluation_strategy="steps" \

runs/Jan30_09-16-39_job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba/events.out.tfevents.1643534309.job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba.1157150.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29602394e4b0e86ba670fc9db67937d579945ea3d95553e9105356b711241ea0
-size 19052
+oid sha256:d48d414a24b21fb2e6fa09fac343c45b4beb5e5158ad81f35a40e3359c7e6306
+size 19209

runs/Jan30_20-13-05_job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba/1643573666.538277/events.out.tfevents.1643573666.job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba.1415010.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:116ea9d42498f0e6a6985fd76d607d3ce2576c1176f900eedec3dede561bc6e6
+size 4783

runs/Jan30_20-13-05_job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba/events.out.tfevents.1643573666.job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba.1415010.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7538e84ca98d42e24476a056d5e772af1050e741ab4f5f9db86e9d6d16b379e
+size 4714

runs/Jan30_20-19-55_job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba/1643574132.9513216/events.out.tfevents.1643574132.job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba.1417756.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fa90f9eb84049d5b110aa5e3cd70f53f0281d1970a02e1911f38cedc51063b5
+size 4783

runs/Jan30_20-19-55_job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba/events.out.tfevents.1643574132.job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba.1417756.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:377ae36279644f1876b82bbe88e84c8da31c1cb87c5b0ce920133b1599af8c6f
+size 5814

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}]}
+{"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}]}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:309a21a0f8e2c363dbaf6d485f64374b32e42e88ac8e48be120784a07d38d1ca
+oid sha256:7d898881ca41ce3ef5f2e21a5181124abe9e36c9986de843bfecd137a49be81b
 size 3055