Training in progress, step 800

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c68a760e1bcbc0033b9658463632c9d011fd3e4a3760f2145be785f9d720e19a
+oid sha256:f3a3952ffc5cd5fa21efa33bc65ef6b5ed950c3a461342d692dd2c78eb8c720f
 size 1261934580

run-5/checkpoint-800/added_tokens.json

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

run-5/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-5/checkpoint-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a3952ffc5cd5fa21efa33bc65ef6b5ed950c3a461342d692dd2c78eb8c720f
+size 1261934580

run-5/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b2e65597c6b51e7464ba84011640b54bfb2e84f48d2724a4b42933b7ca108c
+size 2524118858

run-5/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-5/checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2668e34a1548883ee68b14f5a5f61321c78383f143225f4b1805911886f475f3
+size 14244

run-5/checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7fc2c344a356067724bc68c8e9cfa34bcfd91ea5461eba1db29b6457dad8c7c
+size 1064

run-5/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-5/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-5/checkpoint-800/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": 0.3216058313846588,
+  "best_model_checkpoint": "/scratch/skscla001/speech/results/xls-r-300m-bemgen-combined-hp-tuning-test-model/run-5/checkpoint-500",
+  "epoch": 22.228163992869874,
+  "eval_steps": 100,
+  "global_step": 800,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.7985739750445635,
+      "eval_loss": 2.948845148086548,
+      "eval_runtime": 39.616,
+      "eval_samples_per_second": 13.656,
+      "eval_steps_per_second": 3.433,
+      "eval_wer": 1.0,
+      "step": 100
+    },
+    {
+      "epoch": 5.570409982174688,
+      "eval_loss": 1.9485849142074585,
+      "eval_runtime": 39.7926,
+      "eval_samples_per_second": 13.595,
+      "eval_steps_per_second": 3.418,
+      "eval_wer": 0.9997095134350036,
+      "step": 200
+    },
+    {
+      "epoch": 8.342245989304812,
+      "eval_loss": 0.3670712411403656,
+      "eval_runtime": 39.9938,
+      "eval_samples_per_second": 13.527,
+      "eval_steps_per_second": 3.401,
+      "eval_wer": 0.5453885257806826,
+      "step": 300
+    },
+    {
+      "epoch": 11.114081996434937,
+      "eval_loss": 0.3357694745063782,
+      "eval_runtime": 39.9278,
+      "eval_samples_per_second": 13.549,
+      "eval_steps_per_second": 3.406,
+      "eval_wer": 0.49092229484386346,
+      "step": 400
+    },
+    {
+      "epoch": 13.9126559714795,
+      "grad_norm": 6.9620232582092285,
+      "learning_rate": 0.0005749490472389087,
+      "loss": 33.0097,
+      "step": 500
+    },
+    {
+      "epoch": 13.9126559714795,
+      "eval_loss": 0.3216058313846588,
+      "eval_runtime": 39.9746,
+      "eval_samples_per_second": 13.534,
+      "eval_steps_per_second": 3.402,
+      "eval_wer": 0.484241103848947,
+      "step": 500
+    },
+    {
+      "epoch": 16.684491978609625,
+      "eval_loss": 0.34371960163116455,
+      "eval_runtime": 39.4179,
+      "eval_samples_per_second": 13.725,
+      "eval_steps_per_second": 3.45,
+      "eval_wer": 0.45824255628177196,
+      "step": 600
+    },
+    {
+      "epoch": 19.45632798573975,
+      "eval_loss": 0.37039127945899963,
+      "eval_runtime": 39.4287,
+      "eval_samples_per_second": 13.721,
+      "eval_steps_per_second": 3.449,
+      "eval_wer": 0.440958605664488,
+      "step": 700
+    },
+    {
+      "epoch": 22.228163992869874,
+      "eval_loss": 0.3815551698207855,
+      "eval_runtime": 39.462,
+      "eval_samples_per_second": 13.709,
+      "eval_steps_per_second": 3.446,
+      "eval_wer": 0.407116920842411,
+      "step": 800
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1050,
+  "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": 3
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5849350285457297e+19,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 0.0005819322340474784,
+    "per_device_eval_batch_size": 4,
+    "per_device_train_batch_size": 8
+  }
+}

run-5/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3c127d4f65d04a4839c35ed1699c7e65956c5e1c243be38fe509d1f09960378
+size 5496

run-5/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.1735111336.srvrocgpu011.uct.ac.za

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ddb1336457cfb702b1553775b90ace6835dbc3ed6d865be9a147847fe82ce8b
-size 7905
+oid sha256:b7ba13b8f001e3c2425ada809cb35ddca9b1f3a324f47079cff01af1cb6f75d8
+size 9742