Training in progress, step 800, checkpoint

checkpoint-800/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": 65,
+  "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": "4.52.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 68,
+  "xvector_output_dim": 512
+}

checkpoint-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba2f6f240e066a16d805bbb2c7d5adb04db45671bcf88e656c4aa599d7be7fb7
+size 3859080512

checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb8b39830e2e1f3a0a3aef0f579cce61843ffa68aa4440868a40597497b753a8
+size 18147578

checkpoint-800/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-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eea2ce622e6553ee1e1861b6df4ec5aec8baf9de39da107d4f95dfc9f4ec5511
+size 14308

checkpoint-800/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81659919e33cfb67b13f4af6e2f39fe752a4d8dfcee3a329eb6fbd1088778300
+size 988

checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f79853929a0d2464abae251e52d8d70efa27818f58dafeaf06a12349ec7aef
+size 1064

checkpoint-800/trainer_state.json

@@ -0,0 +1,162 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9476248477466505,
+  "eval_steps": 100,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.243605359317905,
+      "grad_norm": 33.11063766479492,
+      "learning_rate": 4.8844282238442824e-05,
+      "loss": 10.7343,
+      "step": 100
+    },
+    {
+      "epoch": 0.243605359317905,
+      "eval_loss": 4.385446548461914,
+      "eval_runtime": 206.0799,
+      "eval_samples_per_second": 7.992,
+      "eval_steps_per_second": 1.0,
+      "eval_wer": 1.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.48721071863581,
+      "grad_norm": 2.508547067642212,
+      "learning_rate": 4.762773722627738e-05,
+      "loss": 3.1325,
+      "step": 200
+    },
+    {
+      "epoch": 0.48721071863581,
+      "eval_loss": 2.1581695079803467,
+      "eval_runtime": 206.4525,
+      "eval_samples_per_second": 7.978,
+      "eval_steps_per_second": 0.998,
+      "eval_wer": 0.9690996270644646,
+      "step": 200
+    },
+    {
+      "epoch": 0.730816077953715,
+      "grad_norm": 1.2504737377166748,
+      "learning_rate": 4.641119221411192e-05,
+      "loss": 1.6166,
+      "step": 300
+    },
+    {
+      "epoch": 0.730816077953715,
+      "eval_loss": 1.1347323656082153,
+      "eval_runtime": 206.3117,
+      "eval_samples_per_second": 7.983,
+      "eval_steps_per_second": 0.998,
+      "eval_wer": 0.7188184455099745,
+      "step": 300
+    },
+    {
+      "epoch": 0.97442143727162,
+      "grad_norm": 1.3984403610229492,
+      "learning_rate": 4.520681265206813e-05,
+      "loss": 1.1808,
+      "step": 400
+    },
+    {
+      "epoch": 0.97442143727162,
+      "eval_loss": 0.9792075157165527,
+      "eval_runtime": 206.2345,
+      "eval_samples_per_second": 7.986,
+      "eval_steps_per_second": 0.999,
+      "eval_wer": 0.6746581424258569,
+      "step": 400
+    },
+    {
+      "epoch": 1.2168087697929355,
+      "grad_norm": 10.769020080566406,
+      "learning_rate": 4.3990267639902676e-05,
+      "loss": 1.0459,
+      "step": 500
+    },
+    {
+      "epoch": 1.2168087697929355,
+      "eval_loss": 0.9049620032310486,
+      "eval_runtime": 208.2322,
+      "eval_samples_per_second": 7.909,
+      "eval_steps_per_second": 0.989,
+      "eval_wer": 0.6494405966968567,
+      "step": 500
+    },
+    {
+      "epoch": 1.4604141291108403,
+      "grad_norm": 0.8941505551338196,
+      "learning_rate": 4.277372262773723e-05,
+      "loss": 1.0317,
+      "step": 600
+    },
+    {
+      "epoch": 1.4604141291108403,
+      "eval_loss": 0.8543379306793213,
+      "eval_runtime": 205.6459,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 1.002,
+      "eval_wer": 0.6338128218788848,
+      "step": 600
+    },
+    {
+      "epoch": 1.7040194884287454,
+      "grad_norm": 0.9768113493919373,
+      "learning_rate": 4.1569343065693435e-05,
+      "loss": 0.9836,
+      "step": 700
+    },
+    {
+      "epoch": 1.7040194884287454,
+      "eval_loss": 0.8191400766372681,
+      "eval_runtime": 207.1525,
+      "eval_samples_per_second": 7.951,
+      "eval_steps_per_second": 0.994,
+      "eval_wer": 0.6251701888356124,
+      "step": 700
+    },
+    {
+      "epoch": 1.9476248477466505,
+      "grad_norm": 0.9090480208396912,
+      "learning_rate": 4.035279805352798e-05,
+      "loss": 0.9567,
+      "step": 800
+    },
+    {
+      "epoch": 1.9476248477466505,
+      "eval_loss": 0.7955169081687927,
+      "eval_runtime": 206.8205,
+      "eval_samples_per_second": 7.963,
+      "eval_steps_per_second": 0.996,
+      "eval_wer": 0.6124430237376428,
+      "step": 800
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 4110,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.127804972102291e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41bd293a9b52d9fe0c62e74d444b5c5eb9f144a78a0b1288422dc9f7980a2243
+size 5240