Upload folder using huggingface_hub

README.md

@@ -21,12 +21,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7837
-- Accuracy: 0.8498
-- F1: 0.8473
-- Precision: 0.8494
-- Recall: 0.8498
-- Confusion Matrix: [[76, 11, 0, 0], [7, 35, 17, 0], [0, 5, 59, 0], [1, 0, 0, 62]]
+- Loss: 0.7942
+- Accuracy: 0.8242
+- F1: 0.8278
+- Precision: 0.8347
+- Recall: 0.8242
+- Confusion Matrix: [[51, 10, 0, 2], [5, 44, 9, 0], [1, 14, 67, 0], [7, 0, 0, 63]]
 
 ## Model description
 
@@ -46,24 +46,22 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0003
-- train_batch_size: 64
-- eval_batch_size: 64
+- train_batch_size: 128
+- eval_batch_size: 128
 - seed: 123
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 128
+- total_train_batch_size: 256
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine_with_restarts
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 30
-- mixed_precision_training: Native AMP
 - label_smoothing_factor: 0.1
 
 ### Training results
 
 | Training Loss | Epoch   | Step | Validation Loss | Accuracy | F1     | Precision | Recall | Confusion Matrix                                               |
 |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:--------------------------------------------------------------:|
-| 0.5938        | 11.1111 | 100  | 0.7100          | 0.8278   | 0.8206 | 0.8212    | 0.8278 | [[79, 7, 0, 1], [11, 29, 19, 0], [0, 8, 56, 0], [1, 0, 0, 62]] |
-| 0.3511        | 22.2222 | 200  | 0.7837          | 0.8498   | 0.8473 | 0.8494    | 0.8498 | [[76, 11, 0, 0], [7, 35, 17, 0], [0, 5, 59, 0], [1, 0, 0, 62]] |
+| 0.3691        | 22.2222 | 100  | 0.7942          | 0.8242   | 0.8278 | 0.8347    | 0.8242 | [[51, 10, 0, 2], [5, 44, 9, 0], [1, 14, 67, 0], [7, 0, 0, 63]] |
 
 
 ### Framework versions

checkpoint-100/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08e9cb732906b5f8e32e1a9e02636192812a954053f646a784f30a526c555580
+oid sha256:58cf140280d70389e1aece2ee9a69bdfb705db914d4944c5f4efd478daa1fd13
 size 94765560

checkpoint-100/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:661cb52b3461bb635323ecab97b907de2bea8cfd2a616b17ca0b9680a81f2086
+oid sha256:142e3924a56b6cd9c933c65339620f75678c6c9d9e8e06ea806f34bf4ae56a9c
 size 189556666

checkpoint-100/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa137f7efe9a3317de9d36d40c6ca56966dff64c2feada684ad95f64e143d9db
+oid sha256:17a31001969e690d6c1e7ecc15efb09ef0f6c296cc34685bfbe4d5ec7dbf4d37
 size 14308

checkpoint-100/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7d8b5ff37d2416ca0350cbb3fade2e2f68f962f7b1bdb89a67d154010119c7e
+oid sha256:233a3c28ff8d6558e54c4868ca9542c8aea9ce05af2702d9900bb59e7a606be3
 size 1064

checkpoint-100/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.8205727670173567,
+  "best_metric": 0.8277802155149765,
   "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-100",
-  "epoch": 11.11111111111111,
+  "epoch": 22.22222222222222,
   "eval_steps": 100,
   "global_step": 100,
   "is_hyper_param_search": false,
@@ -9,60 +9,60 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 5.555555555555555,
-      "grad_norm": 3.0120761394500732,
-      "learning_rate": 0.0002954973225032615,
-      "loss": 0.9823,
+      "epoch": 11.11111111111111,
+      "grad_norm": 2.099414587020874,
+      "learning_rate": 0.00021731987703006933,
+      "loss": 0.7753,
       "step": 50
     },
     {
-      "epoch": 11.11111111111111,
-      "grad_norm": 1.183480143547058,
-      "learning_rate": 0.0002441718187008148,
-      "loss": 0.5938,
+      "epoch": 22.22222222222222,
+      "grad_norm": 0.09225956350564957,
+      "learning_rate": 2.4676828288059558e-05,
+      "loss": 0.3691,
       "step": 100
     },
     {
-      "epoch": 11.11111111111111,
-      "eval_accuracy": 0.8278388278388278,
+      "epoch": 22.22222222222222,
+      "eval_accuracy": 0.8241758241758241,
       "eval_confusion_matrix": [
         [
-          79,
-          7,
+          51,
+          10,
           0,
-          1
+          2
         ],
         [
-          11,
-          29,
-          19,
+          5,
+          44,
+          9,
           0
         ],
         [
-          0,
-          8,
-          56,
+          1,
+          14,
+          67,
           0
         ],
         [
-          1,
+          7,
           0,
           0,
-          62
+          63
         ]
       ],
-      "eval_f1": 0.8205727670173567,
-      "eval_loss": 0.7099524140357971,
-      "eval_precision": 0.8212472631153949,
-      "eval_recall": 0.8278388278388278,
-      "eval_runtime": 3.0504,
-      "eval_samples_per_second": 89.496,
-      "eval_steps_per_second": 1.639,
+      "eval_f1": 0.8277802155149765,
+      "eval_loss": 0.7942458391189575,
+      "eval_precision": 0.8346819204947628,
+      "eval_recall": 0.8241758241758241,
+      "eval_runtime": 3.7898,
+      "eval_samples_per_second": 72.036,
+      "eval_steps_per_second": 0.792,
       "step": 100
     }
   ],
   "logging_steps": 50,
-  "max_steps": 270,
+  "max_steps": 120,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
@@ -87,8 +87,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.755907745408e+16,
-  "train_batch_size": 64,
+  "total_flos": 5.511815490816e+16,
+  "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-100/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07df27942fd7faa53557a040600995f1eec08c68543b8c4ec8f3d5cdb0edfa8f
+oid sha256:04c36e688104e01b3bf86e2899b93cb9a0868d0f8f810b28125b46e47948bf14
 size 5240

checkpoint-120/config.json

@@ -0,0 +1,85 @@
+{
+  "_name_or_path": "ntu-spml/distilhubert",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": false,
+  "architectures": [
+    "HubertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "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,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": false,
+  "final_dropout": 0.0,
+  "finetuning_task": "audio-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "1s_normal",
+    "1": "1s_pain",
+    "2": "1s_hunger",
+    "3": "1s_asphyxia"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "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": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

checkpoint-120/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8db797f8abb6e63300b3c3787f2c734270d3192b7024f069b55ef27f94f271
+size 94765560

checkpoint-120/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a28cfe9149a4a414b2c23bd9f721401da187eb2ddd226a1ae973de2a767e72ba
+size 189556666

checkpoint-120/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:654b7b30eb2788cf161ef643bc0017567b05c040c7c8800275f7d819599bc31f
+size 14308

checkpoint-120/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:843e8fe068c808e64965cc91e30bb91768e712c534fccf13d58b96d94f1209bf
+size 1064

checkpoint-120/trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_metric": 0.8277802155149765,
+  "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-100",
+  "epoch": 26.666666666666668,
+  "eval_steps": 100,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 11.11111111111111,
+      "grad_norm": 2.099414587020874,
+      "learning_rate": 0.00021731987703006933,
+      "loss": 0.7753,
+      "step": 50
+    },
+    {
+      "epoch": 22.22222222222222,
+      "grad_norm": 0.09225956350564957,
+      "learning_rate": 2.4676828288059558e-05,
+      "loss": 0.3691,
+      "step": 100
+    },
+    {
+      "epoch": 22.22222222222222,
+      "eval_accuracy": 0.8241758241758241,
+      "eval_confusion_matrix": [
+        [
+          51,
+          10,
+          0,
+          2
+        ],
+        [
+          5,
+          44,
+          9,
+          0
+        ],
+        [
+          1,
+          14,
+          67,
+          0
+        ],
+        [
+          7,
+          0,
+          0,
+          63
+        ]
+      ],
+      "eval_f1": 0.8277802155149765,
+      "eval_loss": 0.7942458391189575,
+      "eval_precision": 0.8346819204947628,
+      "eval_recall": 0.8241758241758241,
+      "eval_runtime": 3.7898,
+      "eval_samples_per_second": 72.036,
+      "eval_steps_per_second": 0.792,
+      "step": 100
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 120,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.619818670848e+16,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-120/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04c36e688104e01b3bf86e2899b93cb9a0868d0f8f810b28125b46e47948bf14
+size 5240

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:657233a1d355cbeb81915e1e45af39e18c323629f94e2cf7bf66d64986ad4832
+oid sha256:58cf140280d70389e1aece2ee9a69bdfb705db914d4944c5f4efd478daa1fd13
 size 94765560

runs/Sep11_16-12-44_ubumarcos/events.out.tfevents.1726065155.ubumarcos

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3be92404dd47b537588e7830bd630958f0e701be7d5a3827a602f7db2ae77224
-size 40
+oid sha256:41acb25ea83d4d052ef60cbac634ffd331f6acab73a0e8686008829f0e7b31a9
+size 512

runs/Sep13_19-53-08_ubumarcos/events.out.tfevents.1726249989.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b7930a8e4459eb47b5328c1b5e30d89ff8346cb1f4271988173ec984bfa9e8e
+size 5940

runs/Sep14_16-07-17_ubumarcos/events.out.tfevents.1726322838.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d325f339559ba5e0776dae440f8a61994a1cdd3834c7a97959b6323dd31e5384
+size 5939

runs/Sep14_16-08-56_ubumarcos/events.out.tfevents.1726322937.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24cb9264741d43a908761050e52831ae3e684db680705cb18c12affe05311a6c
+size 5939

runs/Sep14_16-16-59_ubumarcos/events.out.tfevents.1726323420.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:422bf20c8baed359f9d53d14d6233b9787fe5f2d149f0d2cddad7178d20025b8
+size 6287

runs/Sep14_16-16-59_ubumarcos/events.out.tfevents.1726323549.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a0d269252898a00bafb94438b55d577574bd1bca3e70bd0e261310d2f058f74
+size 503

runs/Sep14_16-20-47_ubumarcos/events.out.tfevents.1726323648.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d893d8ff8727c98231a23f7d5e837886137d36b05ec61db4638d14adfcd881e7
+size 6287

runs/Sep14_16-20-47_ubumarcos/events.out.tfevents.1726323777.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:707ed4127dbf61a2650294365c8872721c86ea049c93edd03018bb76bcf23298
+size 503

runs/Sep14_16-29-21_ubumarcos/events.out.tfevents.1726324163.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b31c3d94122b47c9c3c886789a6e21fbe258ce29a30f2b9c912006d4a085218
+size 6287

runs/Sep14_16-29-21_ubumarcos/events.out.tfevents.1726324291.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96b77523bddefded39d845fc6666652e8514daaa8785251783f4abe22c576849
+size 503

runs/Sep14_16-32-20_ubumarcos/events.out.tfevents.1726324341.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e8753489d542af8cd4cbbb14ebb1c2c5d2f32901ce10646e5e2af9e59d317c5
+size 6287

runs/Sep14_16-32-20_ubumarcos/events.out.tfevents.1726324471.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:672e5af548e05cc57039d009eefa4f17daacd54f0af72c6d2443d9b1b26cf6b0
+size 503

runs/Sep14_16-34-43_ubumarcos/events.out.tfevents.1726324484.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d2d005f924c4dfb09b2ba7b3382cf3bf9e0ff9ac7517a3c329d5b57e901db7e
+size 6287

runs/Sep14_16-34-43_ubumarcos/events.out.tfevents.1726324615.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fd4bca5fe257ec01088bbd5fd271a5b0b4df0a00f0eb386f781315d03ba930d
+size 503

runs/Sep14_16-50-46_ubumarcos/events.out.tfevents.1726325447.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:226d764f96374d32745973f2a033a19d4d49f4f55ee30a748ca58b7175c80746
+size 6495

runs/Sep14_16-50-46_ubumarcos/events.out.tfevents.1726325703.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f3c03564384a0b7a95c1c5b0720f6187e99ff738cfaa214ba9eed4837d3dda
+size 503

runs/Sep14_16-55-25_ubumarcos/events.out.tfevents.1726325726.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fab9103bb09302f4a1c3f68effe3360ca543b35d8cb1ea70fbc27709a028d54
+size 5940

runs/Sep14_17-02-18_ubumarcos/events.out.tfevents.1726326139.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63dbf1c9f1ac79baefdd0f471938a0f748e5749c1ff2783a18e74f6591be6b37
+size 5940

runs/Sep14_17-03-33_ubumarcos/events.out.tfevents.1726326215.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9837dbddc3f665316e28bd2cb2fff8983951867a0a05467eb4199503ad969897
+size 5942

runs/Sep14_17-05-21_ubumarcos/events.out.tfevents.1726326322.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d481f74702f97625cdfc65dadcf5104c072691ee5d120c4b4a3ffef89ff3f223
+size 11844

runs/Sep14_17-06-50_ubumarcos/events.out.tfevents.1726326411.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4665947b0d19193d4067d8a629eb0dbf0702cbfc1837618455286fb6e0e1ff4a
+size 7167

runs/Sep14_17-06-50_ubumarcos/events.out.tfevents.1726327100.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d62f4c346935efa7b0e7b0b76b2c91431f8f67b53dc9c6fc95a650671d29a17e
+size 40

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07df27942fd7faa53557a040600995f1eec08c68543b8c4ec8f3d5cdb0edfa8f
+oid sha256:04c36e688104e01b3bf86e2899b93cb9a0868d0f8f810b28125b46e47948bf14
 size 5240