Training in progress, step 500

.ipynb_checkpoints/all_results-checkpoint.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 50.0,
+    "eval_loss": 0.31790396571159363,
+    "eval_runtime": 136.0793,
+    "eval_samples": 4620,
+    "eval_samples_per_second": 33.951,
+    "eval_steps_per_second": 4.248,
+    "eval_wer": 0.2734810010402007,
+    "train_loss": 1.4555730460410894,
+    "train_runtime": 29339.4334,
+    "train_samples": 11030,
+    "train_samples_per_second": 18.797,
+    "train_steps_per_second": 0.586
+}

.ipynb_checkpoints/run-checkpoint.sh

@@ -1,6 +1,6 @@
 python run_speech_recognition_ctc.py \
 	--dataset_name="mozilla-foundation/common_voice_7_0" \
-	--model_name_or_path="facebook/wav2vec2-xls-r-300m" \
+	--model_name_or_path="marinone94/xls-r-300m-sv-robust" \
 	--dataset_config_name="sv-SE" \
 	--output_dir="./" \
 	--overwrite_output_dir \

checkpoint-500/config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "marinone94/xls-r-300m-sv-robust",
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "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_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 64,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.25,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.75,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 34,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 37,
+  "xvector_output_dim": 512
+}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d7b3b64b03807fa1443a1bbb6c48b3760f1488bdb1c3d2a04da0de2ef280a6
+size 2490362385

checkpoint-500/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

checkpoint-500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:849f22348838353270f3fea71da7123aea0c4d81f944d73fe8359395ee3e8678
+size 1262075377

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32b82ac75b07e68dc3bc90e76f55a339f64dce724d87a9ae3c69ee46df441867
+size 14503

checkpoint-500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c42d0f35980b579693b6d665e1977f1cb989811c56ccb359dcaf6fac0e92a29d
+size 559

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ea5e90d46886b0a7f8061d0a93792e2f7c6219a21813faad05be67fa21d1a40
+size 623

checkpoint-500/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4525018129079044,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.29,
+      "learning_rate": 3.675e-06,
+      "loss": 1.0197,
+      "step": 100
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.425e-06,
+      "loss": 1.0171,
+      "step": 200
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.1137499999999998e-05,
+      "loss": 1.026,
+      "step": 300
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.48875e-05,
+      "loss": 1.0383,
+      "step": 400
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.86375e-05,
+      "loss": 1.0296,
+      "step": 500
+    },
+    {
+      "epoch": 1.45,
+      "eval_loss": 0.3191435635089874,
+      "eval_runtime": 138.7872,
+      "eval_samples_per_second": 33.288,
+      "eval_steps_per_second": 4.165,
+      "eval_wer": 0.27421526035611576,
+      "step": 500
+    }
+  ],
+  "max_steps": 17200,
+  "num_train_epochs": 50,
+  "total_flos": 1.4827194756605722e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0efc7aad7fd151e94de194f50e712cd8d3c82a2cf2ccee51d253c9130af43c3a
+size 2991

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "_name_or_path": "marinone94/xls-r-300m-sv-robust",
   "activation_dropout": 0.1,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e501ae3712d27da72be4224776458113a2e4b0d236983057ecd2414a0d777c3e
+oid sha256:849f22348838353270f3fea71da7123aea0c4d81f944d73fe8359395ee3e8678
 size 1262075377

run.sh

@@ -1,6 +1,6 @@
 python run_speech_recognition_ctc.py \
 	--dataset_name="mozilla-foundation/common_voice_7_0" \
-	--model_name_or_path="facebook/wav2vec2-xls-r-300m" \
+	--model_name_or_path="marinone94/xls-r-300m-sv-robust" \
 	--dataset_config_name="sv-SE" \
 	--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}, {"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}]}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a168f126d02648193e16ba893c3e1ef9f2c2de91803928caf5e25532aff1325
+oid sha256:0efc7aad7fd151e94de194f50e712cd8d3c82a2cf2ccee51d253c9130af43c3a
 size 2991