Training in progress, epoch 1

config.json

@@ -58,11 +58,13 @@
   "id2label": {
     "0": "human",
     "1": "machine",
-    "2": "not_sure"
+    "2": "not_sure",
+    "3": "bot"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
+    "bot": "3",
     "human": "0",
     "machine": "1",
     "not_sure": "2"

last-checkpoint/config.json

@@ -0,0 +1,129 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "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": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "human",
+    "1": "machine",
+    "2": "not_sure",
+    "3": "bot"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "bot": "3",
+    "human": "0",
+    "machine": "1",
+    "not_sure": "2"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "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_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "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": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "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": "4.28.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f1bdfd9e0aac203965c782dea354353b7d2d42e6e1d4b269832af24259f02b
+size 756676997

last-checkpoint/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": false,
+  "sampling_rate": 16000
+}

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec49de05b6d0fc9760a0e4b8496ff8fbf4ceb9ee023b5d568ac0a6f84b39efd8
+size 378349481

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59301807699134cc6087afb3fa6b30a719118ddf7c2b9a165a4e3f81e46e979
+size 13681

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f444185c3e228ee6138ca7334fba6706bbb1da32fc13357fe5c32dffd6ee429b
+size 627

last-checkpoint/trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_metric": 0.9507272727272728,
+  "best_model_checkpoint": "wav2vec2-base-finetuned-amd/checkpoint-290",
+  "epoch": 1.0,
+  "global_step": 290,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.913793103448276e-05,
+      "loss": 1.2481,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.827586206896552e-05,
+      "loss": 0.8865,
+      "step": 20
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.741379310344828e-05,
+      "loss": 0.6388,
+      "step": 30
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.655172413793104e-05,
+      "loss": 0.5496,
+      "step": 40
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.5689655172413794e-05,
+      "loss": 0.4895,
+      "step": 50
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.482758620689655e-05,
+      "loss": 0.3954,
+      "step": 60
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.396551724137931e-05,
+      "loss": 0.4283,
+      "step": 70
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.3103448275862066e-05,
+      "loss": 0.3545,
+      "step": 80
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.224137931034483e-05,
+      "loss": 0.2903,
+      "step": 90
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.1379310344827587e-05,
+      "loss": 0.371,
+      "step": 100
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.0517241379310344e-05,
+      "loss": 0.3175,
+      "step": 110
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.965517241379311e-05,
+      "loss": 0.351,
+      "step": 120
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.8793103448275865e-05,
+      "loss": 0.2955,
+      "step": 130
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 3.793103448275862e-05,
+      "loss": 0.294,
+      "step": 140
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 3.7068965517241385e-05,
+      "loss": 0.2744,
+      "step": 150
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 3.620689655172414e-05,
+      "loss": 0.2634,
+      "step": 160
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 3.53448275862069e-05,
+      "loss": 0.2813,
+      "step": 170
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.4482758620689657e-05,
+      "loss": 0.2948,
+      "step": 180
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.3620689655172414e-05,
+      "loss": 0.28,
+      "step": 190
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.275862068965517e-05,
+      "loss": 0.2003,
+      "step": 200
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.1896551724137935e-05,
+      "loss": 0.2322,
+      "step": 210
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.103448275862069e-05,
+      "loss": 0.3084,
+      "step": 220
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.017241379310345e-05,
+      "loss": 0.3097,
+      "step": 230
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.9310344827586206e-05,
+      "loss": 0.2311,
+      "step": 240
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.844827586206897e-05,
+      "loss": 0.28,
+      "step": 250
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.7586206896551727e-05,
+      "loss": 0.2528,
+      "step": 260
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.672413793103448e-05,
+      "loss": 0.3334,
+      "step": 270
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.5862068965517244e-05,
+      "loss": 0.2705,
+      "step": 280
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2501,
+      "step": 290
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9507272727272728,
+      "eval_loss": 0.19648206233978271,
+      "eval_runtime": 2253.6221,
+      "eval_samples_per_second": 2.441,
+      "eval_steps_per_second": 0.076,
+      "step": 290
+    }
+  ],
+  "max_steps": 580,
+  "num_train_epochs": 2,
+  "total_flos": 5.04847347766272e+17,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb51e6346c045a349a2c9c36ae9e5384e658b64fbf1dc3fd694f45f501a4d344
+size 3643

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a298a391f6a64a85950144b7d764c9be875cdbf3e07197ec8e9cc8cde0fda74
-size 378348457
+oid sha256:ec49de05b6d0fc9760a0e4b8496ff8fbf4ceb9ee023b5d568ac0a6f84b39efd8
+size 378349481

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6ce9497385c488a22ae92cb2249699d4cb97b3e82921cf19befde92665fa9b5
+oid sha256:bb51e6346c045a349a2c9c36ae9e5384e658b64fbf1dc3fd694f45f501a4d344
 size 3643