End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 0.03,
+    "eval_loss": 155.7938690185547,
+    "eval_runtime": 55.6971,
+    "eval_samples": 301,
+    "eval_samples_per_second": 5.404,
+    "eval_steps_per_second": 0.682,
+    "eval_wer": 1.084206116464181,
+    "train_loss": 93.28157958984374,
+    "train_runtime": 23.9574,
+    "train_samples": 704,
+    "train_samples_per_second": 0.835,
+    "train_steps_per_second": 0.417
+}

checkpoint-5/config.json

@@ -1,96 +0,0 @@
-{
-  "_name_or_path": "hf-test/xls-r-dummy",
-  "activation_dropout": 0.0,
-  "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": 256,
-  "contrastive_logits_temperature": 0.1,
-  "conv_bias": false,
-  "conv_dim": [
-    32,
-    32,
-    32
-  ],
-  "conv_kernel": [
-    8,
-    8,
-    8
-  ],
-  "conv_stride": [
-    4,
-    4,
-    4
-  ],
-  "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_dropout_prob": 0.1,
-  "hidden_size": 16,
-  "initializer_range": 0.02,
-  "intermediate_size": 20,
-  "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
-  "mask_feature_length": 10,
-  "mask_feature_min_masks": 0,
-  "mask_feature_prob": 0.0,
-  "mask_time_length": 10,
-  "mask_time_min_masks": 2,
-  "mask_time_prob": 0.05,
-  "model_type": "wav2vec2",
-  "num_adapter_layers": 3,
-  "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,
-  "pad_token_id": 50,
-  "proj_codevector_dim": 256,
-  "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": 53,
-  "xvector_output_dim": 512
-}

checkpoint-5/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8e671769d8e7c6e50fda9751a0d3f50d1ad0a5867a3186328dbbea2c27bb8aaf
-size 128273

checkpoint-5/preprocessor_config.json

@@ -1,9 +0,0 @@
-{
-  "do_normalize": true,
-  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
-  "feature_size": 1,
-  "padding_side": "right",
-  "padding_value": 0.0,
-  "return_attention_mask": false,
-  "sampling_rate": 16000
-}

checkpoint-5/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fd01668f7ea1961fb498356d85e789d5b8ebe359ff437cea5845060c64f8eaa3
-size 142694

checkpoint-5/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:95b51a631a60af2739cb31adbae099700ec09270ddb7a7e50d2fca34dafca4ce
-size 13611

checkpoint-5/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:59216c25b5b10e66c1be135b3804bb7b79f89ad700aea4e78300a0b0e97a9507
-size 623

checkpoint-5/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0d984518be407c10d2f161021e8f4824522fcbc805d42098d3c9a603e88255e3
-size 2991

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.03,
+    "eval_loss": 155.7938690185547,
+    "eval_runtime": 55.6971,
+    "eval_samples": 301,
+    "eval_samples_per_second": 5.404,
+    "eval_steps_per_second": 0.682,
+    "eval_wer": 1.084206116464181
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.03,
+    "train_loss": 93.28157958984374,
+    "train_runtime": 23.9574,
+    "train_samples": 704,
+    "train_samples_per_second": 0.835,
+    "train_steps_per_second": 0.417
+}

checkpoint-5/trainer_state.json → trainer_state.json

@@ -1,15 +1,25 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014204545454545454,
-  "global_step": 5,
+  "epoch": 0.028409090909090908,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
-  "log_history": [],
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "step": 10,
+      "total_flos": 508182128640.0,
+      "train_loss": 93.28157958984374,
+      "train_runtime": 23.9574,
+      "train_samples_per_second": 0.835,
+      "train_steps_per_second": 0.417
+    }
+  ],
   "max_steps": 10,
   "num_train_epochs": 1,
-  "total_flos": 273921937920.0,
+  "total_flos": 508182128640.0,
   "trial_name": null,
   "trial_params": null
 }