Upload folder using huggingface_hub

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "total_flos": 200397839611200.0,
+    "train_loss": 2.0799516296386718,
+    "train_runtime": 679.6511,
+    "train_samples_per_second": 11.771,
+    "train_steps_per_second": 1.471
+}

config.json

@@ -0,0 +1,78 @@
+{
+  "architectures": [
+    "ClapModel"
+  ],
+  "audio_config": {
+    "aff_block_r": 4,
+    "attention_probs_dropout_prob": 0.0,
+    "depths": [
+      2,
+      2,
+      12,
+      2
+    ],
+    "drop_path_rate": 0.0,
+    "dtype": "float32",
+    "enable_fusion": false,
+    "enable_patch_layer_norm": true,
+    "flatten_patch_embeds": true,
+    "fusion_type": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 1024,
+    "initializer_factor": 1.0,
+    "layer_norm_eps": 1e-05,
+    "mlp_ratio": 4.0,
+    "model_type": "clap_audio_model",
+    "num_attention_heads": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "num_classes": 527,
+    "num_hidden_layers": 4,
+    "num_mel_bins": 64,
+    "patch_embed_input_channels": 1,
+    "patch_embeds_hidden_size": 128,
+    "patch_size": 4,
+    "patch_stride": [
+      4,
+      4
+    ],
+    "projection_dim": 512,
+    "projection_hidden_act": "relu",
+    "qkv_bias": true,
+    "spec_size": 256,
+    "window_size": 8
+  },
+  "dtype": "float32",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 14.285714285714285,
+  "model_type": "clap",
+  "num_hidden_layers": 16,
+  "projection_dim": 512,
+  "projection_hidden_act": "relu",
+  "text_config": {
+    "attention_probs_dropout_prob": 0.1,
+    "dtype": "float32",
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "initializer_factor": 1.0,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 514,
+    "model_type": "clap_text_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "position_embedding_type": "absolute",
+    "projection_dim": 512,
+    "projection_hidden_act": "relu",
+    "type_vocab_size": 1,
+    "use_cache": true,
+    "vocab_size": 50265
+  },
+  "transformers_version": "4.57.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4cd2dbfbf516a12298bf0719379520d034219915e03060471f574833e82740f
+size 776327440

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "chunk_length_s": 10,
+  "feature_extractor_type": "ClapFeatureExtractor",
+  "feature_size": 64,
+  "fft_window_size": 1024,
+  "frequency_max": 14000,
+  "frequency_min": 50,
+  "hop_length": 480,
+  "max_length_s": 10,
+  "n_fft": 1024,
+  "nb_frequency_bins": 513,
+  "nb_max_frames": 1000,
+  "nb_max_samples": 480000,
+  "padding": "repeatpad",
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "ClapProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 48000,
+  "top_db": null,
+  "truncation": "rand_trunc"
+}

runs/Nov19_17-34-53_e3c4d804683e/events.out.tfevents.1763573728.e3c4d804683e.546.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0abbde9a1126ade872de41e8b7fd188582ba4540b231ea770ad9c4dcadc733c0
+size 9948

runs/Nov19_18-14-29_e3c4d804683e/events.out.tfevents.1763576078.e3c4d804683e.546.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6624f4c8ccc875325f86b97afe27844eaac0b3067dc654b70e37b52012f89008
+size 6247

runs/Nov19_18-14-59_e3c4d804683e/events.out.tfevents.1763576110.e3c4d804683e.546.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55a1a914b1ebb57aa9c8b690759642aff4a5d449153b85f58f968c540a574478
+size 8639

runs/Nov19_18-21-39_e3c4d804683e/events.out.tfevents.1763576508.e3c4d804683e.546.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b69f5373c1530bbee3ba055433ff67219b8be07eb7b8499fed37f27fb84c552b
+size 9957

runs/Nov19_18-44-30_d2f0b4021fa1/events.out.tfevents.1763577933.d2f0b4021fa1.751.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fefe45d03fa100ef57a127914d98dee0f3041211e084235d25be10e8cd522b8
+size 9685

runs/Nov19_19-05-55_325006c1ffe4/events.out.tfevents.1763579188.325006c1ffe4.354.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48163902e53b28b29c91fc2056f9c426a3a2f5ce800fdc3520e42d4e0442bcc3
+size 9557

runs/Nov19_19-36-20_325006c1ffe4/events.out.tfevents.1763580988.325006c1ffe4.354.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:556856ca893929c21d2e48b3ebb2a42fbf14225edda075f0b9f08df2a00e5c53
+size 10039

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_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
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": null,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "ClapProcessor",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "total_flos": 200397839611200.0,
+    "train_loss": 2.0799516296386718,
+    "train_runtime": 679.6511,
+    "train_samples_per_second": 11.771,
+    "train_steps_per_second": 1.471
+}

trainer_state.json

@@ -0,0 +1,157 @@
+{
+  "best_global_step": 100,
+  "best_metric": 2.044290542602539,
+  "best_model_checkpoint": "/content/drive/MyDrive/AudioSet(sample)/clap_finetune_output(1)/checkpoint-100",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 350,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7630943059921265,
+      "learning_rate": 4.9e-05,
+      "loss": 2.0803,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.0514423847198486,
+      "eval_runtime": 10.2923,
+      "eval_samples_per_second": 9.716,
+      "eval_steps_per_second": 1.263,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.464395046234131,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 2.0797,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.044290542602539,
+      "eval_runtime": 10.4787,
+      "eval_samples_per_second": 9.543,
+      "eval_steps_per_second": 1.241,
+      "step": 100
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.13010422885417938,
+      "learning_rate": 9.455555555555556e-05,
+      "loss": 2.0819,
+      "step": 150
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.0508809089660645,
+      "eval_runtime": 10.1914,
+      "eval_samples_per_second": 9.812,
+      "eval_steps_per_second": 1.276,
+      "step": 150
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.009413039311766624,
+      "learning_rate": 8.900000000000001e-05,
+      "loss": 2.0794,
+      "step": 200
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.0517237186431885,
+      "eval_runtime": 10.5065,
+      "eval_samples_per_second": 9.518,
+      "eval_steps_per_second": 1.237,
+      "step": 200
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.004269932396709919,
+      "learning_rate": 8.344444444444445e-05,
+      "loss": 2.0795,
+      "step": 250
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.0517029762268066,
+      "eval_runtime": 10.497,
+      "eval_samples_per_second": 9.527,
+      "eval_steps_per_second": 1.238,
+      "step": 250
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.005160332657396793,
+      "learning_rate": 7.788888888888888e-05,
+      "loss": 2.0794,
+      "step": 300
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.051720380783081,
+      "eval_runtime": 10.5535,
+      "eval_samples_per_second": 9.476,
+      "eval_steps_per_second": 1.232,
+      "step": 300
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.006798981688916683,
+      "learning_rate": 7.233333333333335e-05,
+      "loss": 2.0795,
+      "step": 350
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.0517101287841797,
+      "eval_runtime": 10.4222,
+      "eval_samples_per_second": 9.595,
+      "eval_steps_per_second": 1.247,
+      "step": 350
+    },
+    {
+      "epoch": 7.0,
+      "step": 350,
+      "total_flos": 200397839611200.0,
+      "train_loss": 2.0799516296386718,
+      "train_runtime": 679.6511,
+      "train_samples_per_second": 11.771,
+      "train_steps_per_second": 1.471
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 5
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 200397839611200.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7de176f4ecb702123224fdcdb4cb123ca29d218f46caef620c1bc3f833e0cefa
+size 5905