Training in progress, step 800

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:641c60417b0b894a121ac6cf5bc115ff4fc234524b349ab6e55493301a240799
+oid sha256:9c265f8b58a68a3359f37133f13e82c0ffb2aed7827129c2125e6eec4a173aa9
 size 1261934580

run-1/checkpoint-800/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 30,
+  "<s>": 29
+}

run-1/checkpoint-800/config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "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": true,
+  "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": 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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 28,
+  "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": "4.47.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 31,
+  "xvector_output_dim": 512
+}

run-1/checkpoint-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c265f8b58a68a3359f37133f13e82c0ffb2aed7827129c2125e6eec4a173aa9
+size 1261934580

run-1/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:130d8fe50ac5a3b5c45c3ced4c2aa94a0b1d14a7eaf60a71abd716bc2d5190bf
+size 2524118858

run-1/checkpoint-800/preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

run-1/checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5ec0c6b696d00b32a0a38dd99a72e12e7d99d8da66ea9e06bcef298bf65b4b2
+size 14308

run-1/checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6fc3adad63926c9a4e2d6a940c40dd26e30e93eb2eb0d50167e1f8f576c4be4
+size 1064

run-1/checkpoint-800/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

run-1/checkpoint-800/tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "27": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

run-1/checkpoint-800/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": 0.313192218542099,
+  "best_model_checkpoint": "/scratch/skscla001/speech/results/xls-r-300m-bemgen-combined-hp-tuning-test-model/run-1/checkpoint-700",
+  "epoch": 11.271186440677965,
+  "eval_steps": 100,
+  "global_step": 800,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.4139161462979484,
+      "eval_loss": 3.211536407470703,
+      "eval_runtime": 39.06,
+      "eval_samples_per_second": 13.85,
+      "eval_steps_per_second": 3.482,
+      "eval_wer": 1.0,
+      "step": 100
+    },
+    {
+      "epoch": 2.8278322925958967,
+      "eval_loss": 2.594022512435913,
+      "eval_runtime": 38.831,
+      "eval_samples_per_second": 13.932,
+      "eval_steps_per_second": 3.502,
+      "eval_wer": 1.0,
+      "step": 200
+    },
+    {
+      "epoch": 4.2283675289919715,
+      "eval_loss": 0.4984978139400482,
+      "eval_runtime": 39.2533,
+      "eval_samples_per_second": 13.782,
+      "eval_steps_per_second": 3.465,
+      "eval_wer": 0.6931009440813363,
+      "step": 300
+    },
+    {
+      "epoch": 5.64228367528992,
+      "eval_loss": 0.3650150001049042,
+      "eval_runtime": 39.1414,
+      "eval_samples_per_second": 13.822,
+      "eval_steps_per_second": 3.475,
+      "eval_wer": 0.5648511256354394,
+      "step": 400
+    },
+    {
+      "epoch": 7.042818911685995,
+      "grad_norm": 7.630068778991699,
+      "learning_rate": 0.0003214523712229859,
+      "loss": 39.5064,
+      "step": 500
+    },
+    {
+      "epoch": 7.042818911685995,
+      "eval_loss": 0.3255084156990051,
+      "eval_runtime": 39.4755,
+      "eval_samples_per_second": 13.705,
+      "eval_steps_per_second": 3.445,
+      "eval_wer": 0.5060275962236747,
+      "step": 500
+    },
+    {
+      "epoch": 8.456735057983943,
+      "eval_loss": 0.3325551450252533,
+      "eval_runtime": 39.3569,
+      "eval_samples_per_second": 13.746,
+      "eval_steps_per_second": 3.456,
+      "eval_wer": 0.49862018881626724,
+      "step": 600
+    },
+    {
+      "epoch": 9.870651204281891,
+      "eval_loss": 0.313192218542099,
+      "eval_runtime": 39.0977,
+      "eval_samples_per_second": 13.837,
+      "eval_steps_per_second": 3.478,
+      "eval_wer": 0.46579520697167753,
+      "step": 700
+    },
+    {
+      "epoch": 11.271186440677965,
+      "eval_loss": 0.3283321261405945,
+      "eval_runtime": 39.044,
+      "eval_samples_per_second": 13.856,
+      "eval_steps_per_second": 3.483,
+      "eval_wer": 0.4652142338416848,
+      "step": 800
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.014903861568819e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 0.0003253566510354108,
+    "per_device_eval_batch_size": 4,
+    "per_device_train_batch_size": 4
+  }
+}

run-1/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d2ba7a008d618790da91075bf31efea5d83a5d45fd5e59848c7b981105c081d
+size 5496

run-1/checkpoint-800/vocab.json

@@ -0,0 +1,31 @@
+{
+  "[PAD]": 28,
+  "[UNK]": 27,
+  "a": 1,
+  "b": 2,
+  "c": 3,
+  "d": 4,
+  "e": 5,
+  "f": 6,
+  "g": 7,
+  "h": 8,
+  "i": 9,
+  "j": 10,
+  "k": 11,
+  "l": 12,
+  "m": 13,
+  "n": 14,
+  "o": 15,
+  "p": 16,
+  "q": 17,
+  "r": 18,
+  "s": 19,
+  "t": 20,
+  "u": 21,
+  "v": 22,
+  "w": 23,
+  "x": 24,
+  "y": 25,
+  "z": 26,
+  "|": 0
+}

runs/Dec24_19-41-58_srvrocgpu011.uct.ac.za/events.out.tfevents.1735074270.srvrocgpu011.uct.ac.za

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c465600f1ef219e0517d9f87988cf67a2e64460cc204cbd75723bc6a04746f69
-size 7587
+oid sha256:8aca1cf8150de6e704966f1d36d9eeec05cf114a7271ca87c446bb6736a6f41c
+size 9388