Upload 7 files

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "m-polignano-uniba/bert_uncased_L-12_H-768_A-12_italian_alb3rt0",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "opos",
+    "1": "oneg",
+    "2": "neutral"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "neutral": 2,
+    "oneg": 1,
+    "opos": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 128000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6d879f0b6908423a11beb32d2047d0d082583118245ccd87e83de309a47bb2e
+size 1474949370

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2143fe3b7e1951f0c04f804f467f28c71e22475e8fd01f64a1030ac34719d696
+size 737459438

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c3682429541cdfcd0fb02189c7dfaf1302c413c5cea42ffd84b55726ff4fcc9
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:294a2cbc9f8d1f1da5a37e31d9fe1a8765e61888c57d0937b3de64f71d5bbbc2
+size 1064

trainer_state.json

@@ -0,0 +1,96 @@
+{
+  "best_metric": 0.28317779302597046,
+  "best_model_checkpoint": "./model_sentiment/checkpoint-1300",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1950,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.652286529541016,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 0.4381,
+      "step": 650
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7561327561327561,
+      "eval_f1": 0.8001123753336142,
+      "eval_f1_macro": 0.7961336354425609,
+      "eval_loss": 0.3537029027938843,
+      "eval_runtime": 6.6113,
+      "eval_samples_per_second": 524.102,
+      "eval_steps_per_second": 32.823,
+      "step": 650
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 13.353829383850098,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 0.2336,
+      "step": 1300
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8207792207792208,
+      "eval_f1": 0.8560773480662983,
+      "eval_f1_macro": 0.853074547088536,
+      "eval_loss": 0.28317779302597046,
+      "eval_runtime": 6.6046,
+      "eval_samples_per_second": 524.635,
+      "eval_steps_per_second": 32.856,
+      "step": 1300
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 29.17078971862793,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.1322,
+      "step": 1950
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8421356421356422,
+      "eval_f1": 0.8724869182043515,
+      "eval_f1_macro": 0.8692950229330473,
+      "eval_loss": 0.2874596118927002,
+      "eval_runtime": 6.5966,
+      "eval_samples_per_second": 525.269,
+      "eval_steps_per_second": 32.896,
+      "step": 1950
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "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": 2050903312835328.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:285ea59fa8936381ad7ee4ca536a1b6ce932342f81985c2503d0b2279c0b6443
+size 5048