FLAN-T5

README.md

@@ -12,4 +12,5 @@
 ## Modyfikacje
 1. Zamrożenie pierwszych 20 warstw
 
-# Transformer w trybie few-shot/zero-shot learning - ?????
+# Transformer w trybie few-shot/zero-shot learning - FLAN-T5
+## Brak modyfikacji

models/flan-t5/README.md

@@ -0,0 +1,62 @@
+---
+language:
+- text
+- label
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+- accuracy
+model-index:
+- name: flan_t5
+  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. -->
+
+# flan_t5
+
+This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4009
+- Bleu: 0.0
+- Accuracy: 1.0
+- Gen Len: 2.0
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.26.1
+- Pytorch 1.13.1+cu116
+- Datasets 2.9.0
+- Tokenizers 0.13.2

models/flan-t5/all_results.json

@@ -0,0 +1,24 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 1.0,
+    "eval_bleu": 0.0,
+    "eval_gen_len": 2.0,
+    "eval_loss": 0.4009273052215576,
+    "eval_runtime": 265.8814,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 7.522,
+    "eval_steps_per_second": 0.94,
+    "predict_accuracy": 1.0,
+    "predict_bleu": 0.0,
+    "predict_gen_len": 2.0,
+    "predict_loss": 0.3817981481552124,
+    "predict_runtime": 289.0109,
+    "predict_samples": 2000,
+    "predict_samples_per_second": 6.92,
+    "predict_steps_per_second": 0.865,
+    "train_loss": 0.6111455688476563,
+    "train_runtime": 3912.895,
+    "train_samples": 16000,
+    "train_samples_per_second": 4.089,
+    "train_steps_per_second": 0.511
+}

models/flan-t5/config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "google/flan-t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "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: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 32100
+}

models/flan-t5/eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 1.0,
+    "eval_bleu": 0.0,
+    "eval_gen_len": 2.0,
+    "eval_loss": 0.4009273052215576,
+    "eval_runtime": 265.8814,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 7.522,
+    "eval_steps_per_second": 0.94
+}

models/flan-t5/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": "4.26.1"
+}

models/flan-t5/predict_results.json

@@ -0,0 +1,10 @@
+{
+    "predict_accuracy": 1.0,
+    "predict_bleu": 0.0,
+    "predict_gen_len": 2.0,
+    "predict_loss": 0.3817981481552124,
+    "predict_runtime": 289.0109,
+    "predict_samples": 2000,
+    "predict_samples_per_second": 6.92,
+    "predict_steps_per_second": 0.865
+}

models/flan-t5/special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

models/flan-t5/tokenizer_config.json

@@ -0,0 +1,113 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "name_or_path": "google/flan-t5-small",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-small/snapshots/fb7e6cba609f7bab11c614294bc04f82f613c7b1/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

models/flan-t5/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.6111455688476563,
+    "train_runtime": 3912.895,
+    "train_samples": 16000,
+    "train_samples_per_second": 4.089,
+    "train_steps_per_second": 0.511
+}

models/flan-t5/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.8478,
+      "step": 500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.5e-05,
+      "loss": 0.5567,
+      "step": 1000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.25e-05,
+      "loss": 0.5195,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.5205,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "step": 2000,
+      "total_flos": 289235175800832.0,
+      "train_loss": 0.6111455688476563,
+      "train_runtime": 3912.895,
+      "train_samples_per_second": 4.089,
+      "train_steps_per_second": 0.511
+    }
+  ],
+  "max_steps": 2000,
+  "num_train_epochs": 1,
+  "total_flos": 289235175800832.0,
+  "trial_name": null,
+  "trial_params": null
+}