Training in progress, step 5

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.03,
+    "train_loss": 94.465576171875,
+    "train_runtime": 12.1749,
+    "train_samples": 704,
+    "train_samples_per_second": 1.643,
+    "train_steps_per_second": 0.821
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "hf-test/xls-r-dummy",
+  "_name_or_path": "patrickvonplaten/wav2vec2_tiny_random_robust",
   "activation_dropout": 0.0,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -15,19 +15,16 @@
   "contrastive_logits_temperature": 0.1,
   "conv_bias": false,
   "conv_dim": [
-    32,
-    32,
-    32
+    64,
+    64
   ],
   "conv_kernel": [
-    8,
-    8,
-    8
+    40,
+    40
   ],
   "conv_stride": [
-    4,
-    4,
-    4
+    30,
+    30
   ],
   "ctc_loss_reduction": "mean",
   "ctc_zero_infinity": false,
@@ -35,17 +32,15 @@
   "do_stable_layer_norm": true,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
-  "feat_extract_dropout": 0.0,
   "feat_extract_norm": "layer",
   "feat_proj_dropout": 0.0,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
   "hidden_act": "gelu",
   "hidden_dropout": 0.0,
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 16,
+  "hidden_size": 64,
   "initializer_range": 0.02,
-  "intermediate_size": 20,
+  "intermediate_size": 128,
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.0,
   "mask_feature_length": 10,
@@ -59,12 +54,12 @@
   "num_attention_heads": 2,
   "num_codevector_groups": 2,
   "num_codevectors_per_group": 320,
-  "num_conv_pos_embedding_groups": 2,
-  "num_conv_pos_embeddings": 16,
-  "num_feat_extract_layers": 3,
-  "num_hidden_layers": 4,
-  "num_negatives": 10,
-  "output_hidden_size": 16,
+  "num_conv_pos_embedding_groups": 4,
+  "num_conv_pos_embeddings": 64,
+  "num_feat_extract_layers": 2,
+  "num_hidden_layers": 2,
+  "num_negatives": 100,
+  "output_hidden_size": 64,
   "pad_token_id": 50,
   "proj_codevector_dim": 256,
   "tdnn_dilation": [

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18108facdfef7d095a72c1de2b3b686991bb59f7128014a6326150cdc04d91b1
-size 143910
+oid sha256:f7a2903d916d51d415eeac7b97c1af82cb6941d2ec5390d1f34259b064120421
+size 1247823

run.sh

@@ -1,6 +1,6 @@
 python run_speech_recognition_ctc.py \
 	--dataset_name="mozilla-foundation/common_voice_7_0" \
-	--model_name_or_path="hf-test/xls-r-dummy" \
+	--model_name_or_path="patrickvonplaten/wav2vec2_tiny_random_robust" \
 	--dataset_config_name="ab" \
 	--output_dir="./" \
 	--overwrite_output_dir \

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}]}
+{"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}]}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.03,
+    "train_loss": 94.465576171875,
+    "train_runtime": 12.1749,
+    "train_samples": 704,
+    "train_samples_per_second": 1.643,
+    "train_steps_per_second": 0.821
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.028409090909090908,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "step": 10,
+      "total_flos": 508182128640.0,
+      "train_loss": 94.465576171875,
+      "train_runtime": 12.1749,
+      "train_samples_per_second": 1.643,
+      "train_steps_per_second": 0.821
+    }
+  ],
+  "max_steps": 10,
+  "num_train_epochs": 1,
+  "total_flos": 508182128640.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbdf2d3958633fdb29fe0d2d7d5677f2ba26d588d895af42a9d045f43bd17f85
+oid sha256:98c0ec628eb5b67c35784454f7e2b25d6572700b45737cf330ddf9ce21d18f23
 size 2991