Test con T5 iniziale

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: t5-small
+tags:
+- generated_from_trainer
+model-index:
+- name: T5_MLM
+  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. -->
+
+# T5_MLM
+
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0781
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.1184        | 0.0667 | 500  | 0.0904          |
+| 0.1136        | 0.1333 | 1000 | 0.0839          |
+| 0.1101        | 0.2    | 1500 | 0.0846          |
+| 0.1029        | 0.2667 | 2000 | 0.0819          |
+| 0.1041        | 0.3333 | 2500 | 0.0816          |
+| 0.1009        | 0.4    | 3000 | 0.0805          |
+| 0.1018        | 0.4667 | 3500 | 0.0798          |
+| 0.0964        | 0.5333 | 4000 | 0.0790          |
+| 0.0957        | 0.6    | 4500 | 0.0793          |
+| 0.0984        | 0.6667 | 5000 | 0.0763          |
+| 0.0976        | 0.7333 | 5500 | 0.0768          |
+| 0.0953        | 0.8    | 6000 | 0.0780          |
+| 0.096         | 0.8667 | 6500 | 0.0786          |
+| 0.0951        | 0.9333 | 7000 | 0.0782          |
+| 0.096         | 1.0    | 7500 | 0.0781          |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ec34bf560b7eb29c91f0f58703982da5e772f8c674e03e2c98dbbf326e5450
+size 242041896

runs/Jul27_09-02-54_dfa311b303a1/events.out.tfevents.1722070978.dfa311b303a1.583.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83ad4cb20d80792b94800ef226e6025ccd78a6a051517fbce736d7ee90a33d90
+size 5702

runs/Jul27_09-11-03_dfa311b303a1/events.out.tfevents.1722071467.dfa311b303a1.583.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:109e94d41ba30047b6cec751d4995caebeb9e8e16763677552e9600d76ae8768
+size 5702

runs/Jul27_09-13-34_dfa311b303a1/events.out.tfevents.1722071618.dfa311b303a1.583.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d4a68ccee56ba02d05c10bcd977c55555da6567bf54a0d415a687477336c79b
+size 5700

runs/Jul27_09-16-26_dfa311b303a1/events.out.tfevents.1722071794.dfa311b303a1.583.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8c1b2b4802eae10b1afd1dada5cf12cfde8ed0f5ac24fb5e74cb2a18bcacadf
+size 13284

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd9e3fb50f20eef5fb0687c3c5c8fb70077afa1ec46359461c0a5ab16d823386
+size 5112