Training in progress, epoch 5, checkpoint

checkpoint-37740/config.json

@@ -0,0 +1,107 @@
+{
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "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": 1024,
+  "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": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "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": 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": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 62,
+  "proj_codevector_dim": 1024,
+  "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": "4.55.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 65,
+  "xvector_output_dim": 512
+}

checkpoint-37740/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eafbae736cd405dc7ae32e0b7ceb328b4e037fc449972862247bf4f93cc52367
+size 3859065140

checkpoint-37740/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6754ead81932c3361fa9e4fe4baaaf8d4d5c2819420069038a4fbec0bca6b9a1
+size 18116858

checkpoint-37740/preprocessor_config.json

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

checkpoint-37740/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e10db95f0d2b59708dc74974d4a1745da6a257f41b42f9a3d1ad62ab1b62e4b
+size 14308

checkpoint-37740/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed065afbde0882a9b931decb012c49822fae8b44e41665a4d746ffab100fc702
+size 988

checkpoint-37740/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc7efc65cb259b27e887410245c98e1236cef4dbcb5deb4f869de57abd794a6d
+size 1064

checkpoint-37740/trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_global_step": 37740,
+  "best_metric": 0.3747682913531785,
+  "best_model_checkpoint": "fb-mms-1b-cleaned-jssaluja_rajinder_singh-epochs-12-test-datasets-10-20250812_232950/checkpoint-37740",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 37740,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.42587602138519287,
+      "learning_rate": 0.0009188058776666371,
+      "loss": 0.387,
+      "step": 7548
+    },
+    {
+      "epoch": 1.0,
+      "eval_cer": 0.12580931434965467,
+      "eval_loss": 0.4400504529476166,
+      "eval_mer": 0.4452148370790355,
+      "eval_runtime": 175.5013,
+      "eval_samples_per_second": 8.94,
+      "eval_steps_per_second": 1.122,
+      "eval_wer": 0.4737760331479664,
+      "eval_wil": 0.6682418758522689,
+      "step": 7548
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.229217290878296,
+      "learning_rate": 0.0008353213242453749,
+      "loss": 0.2054,
+      "step": 15096
+    },
+    {
+      "epoch": 2.0,
+      "eval_cer": 0.10598448894547981,
+      "eval_loss": 0.3444209694862366,
+      "eval_mer": 0.3981059527200228,
+      "eval_runtime": 176.4752,
+      "eval_samples_per_second": 8.891,
+      "eval_steps_per_second": 1.116,
+      "eval_wer": 0.4064260531385163,
+      "eval_wil": 0.6145206422660318,
+      "step": 15096
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.2057112455368042,
+      "learning_rate": 0.0007501545663310369,
+      "loss": 0.1811,
+      "step": 22644
+    },
+    {
+      "epoch": 3.0,
+      "eval_cer": 0.11019793957633986,
+      "eval_loss": 0.3718140423297882,
+      "eval_mer": 0.4041122692184554,
+      "eval_runtime": 117.258,
+      "eval_samples_per_second": 13.381,
+      "eval_steps_per_second": 1.68,
+      "eval_wer": 0.4128957220223167,
+      "eval_wil": 0.6234012866542855,
+      "step": 22644
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.06720034778118134,
+      "learning_rate": 0.0006668433139021374,
+      "loss": 0.1666,
+      "step": 30192
+    },
+    {
+      "epoch": 4.0,
+      "eval_cer": 0.10207971601651426,
+      "eval_loss": 0.33335745334625244,
+      "eval_mer": 0.39927228186468766,
+      "eval_runtime": 116.5053,
+      "eval_samples_per_second": 13.467,
+      "eval_steps_per_second": 1.691,
+      "eval_wer": 0.40282775415258243,
+      "eval_wil": 0.6107857931270173,
+      "step": 30192
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.2346702814102173,
+      "learning_rate": 0.0005835431019254549,
+      "loss": 0.1548,
+      "step": 37740
+    },
+    {
+      "epoch": 5.0,
+      "eval_cer": 0.09676274260138133,
+      "eval_loss": 0.32630863785743713,
+      "eval_mer": 0.36752806986276954,
+      "eval_runtime": 118.542,
+      "eval_samples_per_second": 13.236,
+      "eval_steps_per_second": 1.662,
+      "eval_wer": 0.3747682913531785,
+      "eval_wil": 0.5768814499686782,
+      "step": 37740
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 90576,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3829557019609866e+20,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-37740/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69e65a25bdaa9fcab13cdcd94b922f6df8111f5368fadc209379e61dda3af48
+size 5624