ILC-CNR/gs-aristoBERTo

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+base_model: Jacobo/aristoBERTo
+tags:
+- generated_from_trainer
+model-index:
+- name: model-checkpoints
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# model-checkpoints
+
+This model is a fine-tuned version of [Jacobo/aristoBERTo](https://huggingface.co/Jacobo/aristoBERTo) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9964
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 2.9782        | 1.0   | 5617  | 2.5919          |
+| 2.5711        | 2.0   | 11234 | 2.4118          |
+| 2.4112        | 3.0   | 16851 | 2.3027          |
+| 2.2997        | 4.0   | 22468 | 2.2044          |
+| 2.2077        | 5.0   | 28085 | 2.1578          |
+| 2.1414        | 6.0   | 33702 | 2.1075          |
+| 2.0819        | 7.0   | 39319 | 2.0618          |
+| 2.0388        | 8.0   | 44936 | 2.0305          |
+| 2.0048        | 9.0   | 50553 | 2.0053          |
+| 1.9773        | 10.0  | 56170 | 2.0138          |
+
+
+### Framework versions
+
+- Transformers 4.50.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+base_model: Jacobo/aristoBERTo
+tags:
+- generated_from_trainer
+model-index:
+- name: model-checkpoints
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# model-checkpoints
+
+This model is a fine-tuned version of [Jacobo/aristoBERTo](https://huggingface.co/Jacobo/aristoBERTo) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9793
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 2.9726        | 1.0   | 5652  | 2.5978          |
+| 2.5639        | 2.0   | 11304 | 2.3816          |
+| 2.4014        | 3.0   | 16956 | 2.2645          |
+| 2.2988        | 4.0   | 22608 | 2.2166          |
+| 2.2089        | 5.0   | 28260 | 2.1206          |
+| 2.1371        | 6.0   | 33912 | 2.0921          |
+| 2.0808        | 7.0   | 39564 | 2.0355          |
+| 2.0361        | 8.0   | 45216 | 2.0193          |
+| 2.001         | 9.0   | 50868 | 1.9988          |
+| 1.977         | 10.0  | 56520 | 1.9922          |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.7.0+cu126
+- Datasets 3.5.0
+- Tokenizers 0.21.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 1.9793492555618286,
+    "eval_runtime": 19.7795,
+    "eval_samples_per_second": 491.923,
+    "eval_steps_per_second": 30.789,
+    "step": 56520,
+    "total_flos": 2.975422706417664e+16,
+    "train_loss": 2.2677627250309627,
+    "train_runtime": 6971.4542,
+    "train_samples_per_second": 129.738,
+    "train_steps_per_second": 8.107
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 35000
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 1.9793492555618286,
+    "eval_runtime": 19.7795,
+    "eval_samples_per_second": 491.923,
+    "eval_steps_per_second": 30.789
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac48d52adb26e2fddddb2ca2062b638e638322e6dcaa395cb7f33fd5e6f5338
+size 451855232

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "step": 56520,
+    "total_flos": 2.975422706417664e+16,
+    "train_loss": 2.2677627250309627,
+    "train_runtime": 6971.4542,
+    "train_samples_per_second": 129.738,
+    "train_steps_per_second": 8.107
+}

trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 56520,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 12.995927810668945,
+      "learning_rate": 4.50070771408351e-05,
+      "loss": 2.9726,
+      "step": 5652
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.5977725982666016,
+      "eval_runtime": 19.8579,
+      "eval_samples_per_second": 489.981,
+      "eval_steps_per_second": 30.668,
+      "step": 5652
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 10.8749361038208,
+      "learning_rate": 4.000796178343949e-05,
+      "loss": 2.5639,
+      "step": 11304
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.381584405899048,
+      "eval_runtime": 19.7379,
+      "eval_samples_per_second": 492.959,
+      "eval_steps_per_second": 30.854,
+      "step": 11304
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 11.009535789489746,
+      "learning_rate": 3.500973106864827e-05,
+      "loss": 2.4014,
+      "step": 16956
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.2645437717437744,
+      "eval_runtime": 19.6521,
+      "eval_samples_per_second": 495.112,
+      "eval_steps_per_second": 30.989,
+      "step": 16956
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 11.495499610900879,
+      "learning_rate": 3.0011500353857042e-05,
+      "loss": 2.2988,
+      "step": 22608
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.2165863513946533,
+      "eval_runtime": 19.8532,
+      "eval_samples_per_second": 490.097,
+      "eval_steps_per_second": 30.675,
+      "step": 22608
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 11.591689109802246,
+      "learning_rate": 2.501238499646143e-05,
+      "loss": 2.2089,
+      "step": 28260
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.120560884475708,
+      "eval_runtime": 19.806,
+      "eval_samples_per_second": 491.265,
+      "eval_steps_per_second": 30.748,
+      "step": 28260
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 10.091324806213379,
+      "learning_rate": 2.0015923566878984e-05,
+      "loss": 2.1371,
+      "step": 33912
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.0921123027801514,
+      "eval_runtime": 19.6342,
+      "eval_samples_per_second": 495.564,
+      "eval_steps_per_second": 31.017,
+      "step": 33912
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 9.590017318725586,
+      "learning_rate": 1.5016808209483369e-05,
+      "loss": 2.0808,
+      "step": 39564
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.035478115081787,
+      "eval_runtime": 19.7938,
+      "eval_samples_per_second": 491.568,
+      "eval_steps_per_second": 30.767,
+      "step": 39564
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 11.4172945022583,
+      "learning_rate": 1.0017692852087757e-05,
+      "loss": 2.0361,
+      "step": 45216
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.019296169281006,
+      "eval_runtime": 19.7587,
+      "eval_samples_per_second": 492.442,
+      "eval_steps_per_second": 30.822,
+      "step": 45216
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 13.36776351928711,
+      "learning_rate": 5.019462137296532e-06,
+      "loss": 2.001,
+      "step": 50868
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.9987555742263794,
+      "eval_runtime": 19.4188,
+      "eval_samples_per_second": 501.06,
+      "eval_steps_per_second": 31.361,
+      "step": 50868
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 11.329434394836426,
+      "learning_rate": 2.1231422505307857e-08,
+      "loss": 1.977,
+      "step": 56520
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.992159366607666,
+      "eval_runtime": 19.7519,
+      "eval_samples_per_second": 492.612,
+      "eval_steps_per_second": 30.833,
+      "step": 56520
+    },
+    {
+      "epoch": 10.0,
+      "step": 56520,
+      "total_flos": 2.975422706417664e+16,
+      "train_loss": 2.2677627250309627,
+      "train_runtime": 6971.4542,
+      "train_samples_per_second": 129.738,
+      "train_steps_per_second": 8.107
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.9793492555618286,
+      "eval_runtime": 19.7795,
+      "eval_samples_per_second": 491.923,
+      "eval_steps_per_second": 30.789,
+      "step": 56520
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 56520,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.975422706417664e+16,
+  "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 sha256:3b67c2a3013a187a18e50cba2537a82dc555169447cfcc62169c9520a9e77c19
+size 5713