Upload folder using huggingface_hub

checkpoint-970/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "SZTAKI-HLT/hubert-base-cc",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32001
+}

checkpoint-970/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c61a803010eeca4849c6dcf5b385eb26fd9bcbe571bbbfbb736a5a883a0ed30
+size 442502136

checkpoint-970/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05cd126d61bae7fcdcd105a55a79643322f7228cd74252ee8be03050b67e35d6
+size 885125370

checkpoint-970/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d49e5cf15ef76fa8005b09eccfb9fdf8a22db9e5f8350589ae6a14c261f28614
+size 14244

checkpoint-970/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f8ffbf622f2f7aa7de9ba6c500ea833c4fbee6ae412fb9a806526d93924b66d
+size 1064

checkpoint-970/trainer_state.json

@@ -0,0 +1,80 @@
+{
+  "best_metric": 0.5480151772499084,
+  "best_model_checkpoint": "/content/drive/MyDrive/Bert-base_large/bert-base/checkpoint-970",
+  "epoch": 2.0,
+  "eval_steps": 100,
+  "global_step": 970,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 14.9495210647583,
+      "learning_rate": 4.5e-06,
+      "loss": 0.6114,
+      "step": 485
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7244582043343654,
+      "eval_f1": 0.7233586178139445,
+      "eval_loss": 0.5499718189239502,
+      "eval_precision": 0.7260032681064872,
+      "eval_recall": 0.7244582043343654,
+      "eval_runtime": 16.152,
+      "eval_samples_per_second": 59.993,
+      "eval_steps_per_second": 3.777,
+      "step": 485
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 9.681391716003418,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.5015,
+      "step": 970
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.717234262125903,
+      "eval_f1": 0.7172764249732223,
+      "eval_loss": 0.5480151772499084,
+      "eval_precision": 0.717929796191282,
+      "eval_recall": 0.717234262125903,
+      "eval_runtime": 15.759,
+      "eval_samples_per_second": 61.489,
+      "eval_steps_per_second": 3.871,
+      "step": 970
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 4850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4081378690744320.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-970/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4809421de76a57aaf019ec88bffb1b17ea5cf9555fa7c70e19960d4f5b0edd94
+size 5112

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "SZTAKI-HLT/hubert-base-cc",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32001
+}

events.out.tfevents.1719763761.e2fc7d27e7b4.712.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f208238274d51fb51b3698f64c808182a4ab966389e5f549accaeab5b114e6d2
+size 7983

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c61a803010eeca4849c6dcf5b385eb26fd9bcbe571bbbfbb736a5a883a0ed30
+size 442502136

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4809421de76a57aaf019ec88bffb1b17ea5cf9555fa7c70e19960d4f5b0edd94
+size 5112