Training in progress, step 300, checkpoint

checkpoint-300/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-300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e8fa0b1edb1264cc7f405b92e3f14e2ac27efd21f280dd137f5c3977e5a928
+size 3859080512

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ef0416b7603904a8d5c0b81dd312c297a777823e112a59d357fe0a5ededfab
+size 18147578

checkpoint-300/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-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9c223a43096becbb35c15b6a1f56c48201b7e12f94c4950ef06b3ae32a0a44
+size 14244

checkpoint-300/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d364c61d0e979a026535749a892b3c65596f0b32426c62108258606ed5546d
+size 988

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4f4fbb6c6d1ffab263f467a330dbbc4ccb5d03d25f7e314fa49d00f2117ac88
+size 1064

checkpoint-300/trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.730816077953715,
+  "eval_steps": 100,
+  "global_step": 300,
+  "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
+    }
+  ],
+  "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": 4.1934420666648576e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

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