Training in progress, step 800

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d9a74af030b2d665a05160d8ac6f5c376407580bab3ba28db134d68ebd6d074
+oid sha256:84fb8ac2202c1164cc2bf147842b8689af9e070b5269faa6da4d6072f858e1e1
 size 1261934580

run-3/checkpoint-800/added_tokens.json

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

run-3/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-3/checkpoint-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84fb8ac2202c1164cc2bf147842b8689af9e070b5269faa6da4d6072f858e1e1
+size 1261934580

run-3/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac0fc0179bbf3023ab387824c4cea81c9bf5815cd763aefc522673fbc1fac48f
+size 2524118858

run-3/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-3/checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:876969f490997e04e1bba579c7783b172d06df6f120dc8af05c9b5a511c32b0f
+size 14308

run-3/checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac6924e637616b7a34c20c5cc77b2bf5b5c0de0b912b454d7a203e1f7ca8ac79
+size 1064

run-3/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-3/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-3/checkpoint-800/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": 0.3297356367111206,
+  "best_model_checkpoint": "/scratch/skscla001/speech/results/xls-r-300m-bemgen-combined-hp-tuning-test-model/run-3/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": 2.8470966815948486,
+      "eval_runtime": 38.892,
+      "eval_samples_per_second": 13.91,
+      "eval_steps_per_second": 1.748,
+      "eval_wer": 1.0,
+      "step": 100
+    },
+    {
+      "epoch": 2.8278322925958967,
+      "eval_loss": 0.6609583497047424,
+      "eval_runtime": 39.2401,
+      "eval_samples_per_second": 13.787,
+      "eval_steps_per_second": 1.733,
+      "eval_wer": 0.8823529411764706,
+      "step": 200
+    },
+    {
+      "epoch": 4.2283675289919715,
+      "eval_loss": 0.4018990099430084,
+      "eval_runtime": 39.1145,
+      "eval_samples_per_second": 13.831,
+      "eval_steps_per_second": 1.738,
+      "eval_wer": 0.6053740014524328,
+      "step": 300
+    },
+    {
+      "epoch": 5.64228367528992,
+      "eval_loss": 0.3591904938220978,
+      "eval_runtime": 39.197,
+      "eval_samples_per_second": 13.802,
+      "eval_steps_per_second": 1.735,
+      "eval_wer": 0.575599128540305,
+      "step": 400
+    },
+    {
+      "epoch": 7.042818911685995,
+      "grad_norm": 6.002938270568848,
+      "learning_rate": 0.0009311398489906478,
+      "loss": 30.1235,
+      "step": 500
+    },
+    {
+      "epoch": 7.042818911685995,
+      "eval_loss": 0.33262646198272705,
+      "eval_runtime": 39.0746,
+      "eval_samples_per_second": 13.845,
+      "eval_steps_per_second": 1.74,
+      "eval_wer": 0.5138707334785766,
+      "step": 500
+    },
+    {
+      "epoch": 8.456735057983943,
+      "eval_loss": 0.33609554171562195,
+      "eval_runtime": 39.0678,
+      "eval_samples_per_second": 13.848,
+      "eval_steps_per_second": 1.741,
+      "eval_wer": 0.5115468409586057,
+      "step": 600
+    },
+    {
+      "epoch": 9.870651204281891,
+      "eval_loss": 0.3297356367111206,
+      "eval_runtime": 39.1201,
+      "eval_samples_per_second": 13.829,
+      "eval_steps_per_second": 1.738,
+      "eval_wer": 0.48729121278140886,
+      "step": 700
+    },
+    {
+      "epoch": 11.271186440677965,
+      "eval_loss": 0.3309989273548126,
+      "eval_runtime": 39.1347,
+      "eval_samples_per_second": 13.824,
+      "eval_steps_per_second": 1.738,
+      "eval_wer": 0.4797385620915033,
+      "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": 8.01593354590756e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 0.0009424492398690768,
+    "per_device_eval_batch_size": 8,
+    "per_device_train_batch_size": 4
+  }
+}

run-3/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef5efef89d4210598f182240ddb74552ecf684021891c1b3d332ad394626691
+size 5496

run-3/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.1735092435.srvrocgpu011.uct.ac.za

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c53c91d60f1d13c7c4caed13bdea61407f46adb7c1ed2e12b6a3e55fab41573f
-size 7905
+oid sha256:af8f31d882872bbd7a1b17745e814e2edd366f6b7f363b52d69b288aa28e2fe0
+size 9388