Training in progress, step 1200

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3014043560ae95ee794fee02adc8424db97112b18de521b2e3279d9e17aad1ad
+oid sha256:63f94a6a9cd4c89cdfd4646195bf773b619e0875fab562370f4a07cee69255c1
 size 1261934580

run-2/checkpoint-1200/added_tokens.json

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

run-2/checkpoint-1200/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-2/checkpoint-1200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63f94a6a9cd4c89cdfd4646195bf773b619e0875fab562370f4a07cee69255c1
+size 1261934580

run-2/checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:419496a8c4f6bafa21bbe0f481355ae42d554c88de72cd1d27d5cf6c0f6940cb
+size 2524118858

run-2/checkpoint-1200/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-2/checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63069002d8e4253cd12064a35023278a570ebc0393b03bfbc472a716f6f342a3
+size 14244

run-2/checkpoint-1200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a120c023e9366a3346cdde1e5274cf16a00cc281e8702329cfa47ea4bee6961d
+size 1064

run-2/checkpoint-1200/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-2/checkpoint-1200/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-2/checkpoint-1200/trainer_state.json

@@ -0,0 +1,168 @@
+{
+  "best_metric": 0.32650595903396606,
+  "best_model_checkpoint": "/scratch/skscla001/speech/results/xls-r-300m-nyagen-combined-hp-tuning-test-model/run-2/checkpoint-900",
+  "epoch": 26.676056338028168,
+  "eval_steps": 100,
+  "global_step": 1200,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.2253521126760565,
+      "eval_loss": 4.691487789154053,
+      "eval_runtime": 27.3219,
+      "eval_samples_per_second": 12.225,
+      "eval_steps_per_second": 3.074,
+      "eval_wer": 1.0,
+      "step": 100
+    },
+    {
+      "epoch": 4.450704225352113,
+      "eval_loss": 3.126436710357666,
+      "eval_runtime": 27.3988,
+      "eval_samples_per_second": 12.19,
+      "eval_steps_per_second": 3.066,
+      "eval_wer": 1.0,
+      "step": 200
+    },
+    {
+      "epoch": 6.676056338028169,
+      "eval_loss": 2.8149311542510986,
+      "eval_runtime": 27.5698,
+      "eval_samples_per_second": 12.115,
+      "eval_steps_per_second": 3.047,
+      "eval_wer": 0.9955227221849116,
+      "step": 300
+    },
+    {
+      "epoch": 8.901408450704226,
+      "eval_loss": 1.4846134185791016,
+      "eval_runtime": 27.6337,
+      "eval_samples_per_second": 12.087,
+      "eval_steps_per_second": 3.04,
+      "eval_wer": 0.9697783747481531,
+      "step": 400
+    },
+    {
+      "epoch": 11.112676056338028,
+      "grad_norm": 13.883740425109863,
+      "learning_rate": 9.031515049879765e-05,
+      "loss": 64.2699,
+      "step": 500
+    },
+    {
+      "epoch": 11.112676056338028,
+      "eval_loss": 0.9131842255592346,
+      "eval_runtime": 27.7548,
+      "eval_samples_per_second": 12.034,
+      "eval_steps_per_second": 3.027,
+      "eval_wer": 0.8806805462278935,
+      "step": 500
+    },
+    {
+      "epoch": 13.338028169014084,
+      "eval_loss": 0.39768707752227783,
+      "eval_runtime": 27.8156,
+      "eval_samples_per_second": 12.008,
+      "eval_steps_per_second": 3.02,
+      "eval_wer": 0.5108573987015894,
+      "step": 600
+    },
+    {
+      "epoch": 15.56338028169014,
+      "eval_loss": 0.4330301880836487,
+      "eval_runtime": 28.0379,
+      "eval_samples_per_second": 11.912,
+      "eval_steps_per_second": 2.996,
+      "eval_wer": 0.513319901499888,
+      "step": 700
+    },
+    {
+      "epoch": 17.788732394366196,
+      "eval_loss": 0.3541100323200226,
+      "eval_runtime": 27.8352,
+      "eval_samples_per_second": 11.999,
+      "eval_steps_per_second": 3.018,
+      "eval_wer": 0.4853369151555854,
+      "step": 800
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 0.32650595903396606,
+      "eval_runtime": 27.8087,
+      "eval_samples_per_second": 12.011,
+      "eval_steps_per_second": 3.021,
+      "eval_wer": 0.44414595925677186,
+      "step": 900
+    },
+    {
+      "epoch": 22.225352112676056,
+      "grad_norm": 10.343697547912598,
+      "learning_rate": 3.652730200008266e-05,
+      "loss": 3.6476,
+      "step": 1000
+    },
+    {
+      "epoch": 22.225352112676056,
+      "eval_loss": 0.35389816761016846,
+      "eval_runtime": 27.8299,
+      "eval_samples_per_second": 12.001,
+      "eval_steps_per_second": 3.018,
+      "eval_wer": 0.46272666218938885,
+      "step": 1000
+    },
+    {
+      "epoch": 24.450704225352112,
+      "eval_loss": 0.3330628275871277,
+      "eval_runtime": 27.9733,
+      "eval_samples_per_second": 11.94,
+      "eval_steps_per_second": 3.003,
+      "eval_wer": 0.44056413700470115,
+      "step": 1100
+    },
+    {
+      "epoch": 26.676056338028168,
+      "eval_loss": 0.34280532598495483,
+      "eval_runtime": 27.9351,
+      "eval_samples_per_second": 11.956,
+      "eval_steps_per_second": 3.007,
+      "eval_wer": 0.4369823147526304,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1320,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 4,
+        "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.957731258551549e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.159751571886171e-05,
+    "per_device_eval_batch_size": 4,
+    "per_device_train_batch_size": 4
+  }
+}

run-2/checkpoint-1200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96987aa27b524b7b0ab19f82c8aaec5df71b2d9205adf81adf3cf4331530a72e
+size 5496

run-2/checkpoint-1200/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/Jan26_00-13-00_srvrocgpu011.uct.ac.za/events.out.tfevents.1737860607.srvrocgpu011.uct.ac.za

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63158188c920ac8b145fcf62a7901fabcdfc36dba5ba4d4e78b1294bddbb9cce
-size 9388
+oid sha256:e538157936530373044ce6098ed7311f0f3f7b55c1470a8b2c29fc758945662f
+size 10871