End of training

README.md

@@ -0,0 +1,94 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: calculator_model_test
+  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. -->
+
+# calculator_model_test
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1663
+
+## 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: 0.001
+- train_batch_size: 512
+- eval_batch_size: 512
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 40
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.0776        | 1.0   | 5    | 2.3467          |
+| 2.1508        | 2.0   | 10   | 1.8830          |
+| 1.7317        | 3.0   | 15   | 1.5145          |
+| 1.3813        | 4.0   | 20   | 1.1827          |
+| 1.1212        | 5.0   | 25   | 0.9861          |
+| 0.946         | 6.0   | 30   | 0.8613          |
+| 0.8189        | 7.0   | 35   | 0.7596          |
+| 0.7274        | 8.0   | 40   | 0.6659          |
+| 0.6581        | 9.0   | 45   | 0.6032          |
+| 0.6222        | 10.0  | 50   | 0.5788          |
+| 0.5988        | 11.0  | 55   | 0.5530          |
+| 0.5561        | 12.0  | 60   | 0.5159          |
+| 0.5173        | 13.0  | 65   | 0.4937          |
+| 0.4961        | 14.0  | 70   | 0.4725          |
+| 0.4748        | 15.0  | 75   | 0.4424          |
+| 0.4517        | 16.0  | 80   | 0.4525          |
+| 0.4394        | 17.0  | 85   | 0.4096          |
+| 0.4145        | 18.0  | 90   | 0.3804          |
+| 0.3882        | 19.0  | 95   | 0.3678          |
+| 0.3736        | 20.0  | 100  | 0.3467          |
+| 0.3562        | 21.0  | 105  | 0.3246          |
+| 0.3406        | 22.0  | 110  | 0.3180          |
+| 0.3231        | 23.0  | 115  | 0.2966          |
+| 0.3111        | 24.0  | 120  | 0.2839          |
+| 0.2992        | 25.0  | 125  | 0.2701          |
+| 0.2815        | 26.0  | 130  | 0.2644          |
+| 0.2753        | 27.0  | 135  | 0.2459          |
+| 0.2651        | 28.0  | 140  | 0.2375          |
+| 0.2532        | 29.0  | 145  | 0.2226          |
+| 0.2407        | 30.0  | 150  | 0.2142          |
+| 0.2339        | 31.0  | 155  | 0.2031          |
+| 0.2218        | 32.0  | 160  | 0.1959          |
+| 0.2142        | 33.0  | 165  | 0.1880          |
+| 0.2107        | 34.0  | 170  | 0.1871          |
+| 0.2062        | 35.0  | 175  | 0.1816          |
+| 0.1997        | 36.0  | 180  | 0.1789          |
+| 0.1961        | 37.0  | 185  | 0.1740          |
+| 0.1929        | 38.0  | 190  | 0.1707          |
+| 0.1907        | 39.0  | 195  | 0.1681          |
+| 0.1885        | 40.0  | 200  | 0.1663          |
+
+
+### Framework versions
+
+- Transformers 4.39.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,169 @@
+{
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "",
+    "add_cross_attention": true,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 256,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 1024,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 4,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 53
+  },
+  "decoder_start_token_id": 2,
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 256,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 1024,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 4,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 53
+  },
+  "eos_token_id": 0,
+  "is_encoder_decoder": true,
+  "model_type": "encoder-decoder",
+  "pad_token_id": 3,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.1",
+  "unk_token_id": null
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 0,
+  "pad_token_id": 3,
+  "transformers_version": "4.39.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7133da0abe87ddcc3978209157c141eac99f55ff0a2825c543cebcb7cbb204b6
+size 31207604

runs/Mar24_19-54-28_kordian/events.out.tfevents.1711306469.kordian.22620.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7446c398525006cc1a241a9883ad317b58c4bea6e682656c3b5e017bc7a89ca1
+size 8594

runs/Mar24_19-55-51_kordian/events.out.tfevents.1711306552.kordian.22620.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71cade5f9331d64ff3d05cdf04009c3d9d627c822fbf358acf5f97c0a8591a3e
+size 8280

runs/Mar24_19-58-44_kordian/events.out.tfevents.1711306724.kordian.28736.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c926125f8dc9f062b4f0c7de988b4540125400fe9f3d3b9d52473301e7acb5c1
+size 8595

runs/Mar24_20-41-05_kordian/events.out.tfevents.1711309265.kordian.28736.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3302b19a878b457bdffaf64a2fc7bb3b3a604b1656f6df35dd20f61d2bf7883
+size 8280

runs/Mar24_20-41-13_kordian/events.out.tfevents.1711309273.kordian.28736.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5015c87809d7dd63eb0b670a8d2b6128ba5950101985c31a3dd64597da6b3d21
+size 8280

runs/Mar24_20-41-31_kordian/events.out.tfevents.1711309292.kordian.32482.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3604eca45498d48e3b1935484f949600e38baf50b0fef5e1162fe6f0ea805679
+size 28004

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[EOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,192 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "[EOS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "[UNK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "[CLS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Whitespace"
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[EOS]",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "[EOS]": {
+        "id": "[EOS]",
+        "ids": [
+          0
+        ],
+        "tokens": [
+          "[EOS]"
+        ]
+      }
+    }
+  },
+  "decoder": null,
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": "[UNK]",
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "vocab": {
+      "[EOS]": 0,
+      "[UNK]": 1,
+      "[CLS]": 2,
+      "[PAD]": 3,
+      "+": 4,
+      "-": 5,
+      "0": 6,
+      "1": 7,
+      "2": 8,
+      "3": 9,
+      "4": 10,
+      "5": 11,
+      "6": 12,
+      "7": 13,
+      "8": 14,
+      "9": 15,
+      "=": 16,
+      "10": 17,
+      "99": 18,
+      "11": 19,
+      "98": 20,
+      "97": 21,
+      "12": 22,
+      "96": 23,
+      "13": 24,
+      "95": 25,
+      "14": 26,
+      "94": 27,
+      "15": 28,
+      "16": 29,
+      "93": 30,
+      "17": 31,
+      "92": 32,
+      "18": 33,
+      "91": 34,
+      "90": 35,
+      "19": 36,
+      "20": 37,
+      "89": 38,
+      "21": 39,
+      "88": 40,
+      "22": 41,
+      "87": 42,
+      "86": 43,
+      "23": 44,
+      "24": 45,
+      "85": 46,
+      "84": 47,
+      "25": 48,
+      "26": 49,
+      "83": 50,
+      "27": 51,
+      "82": 52
+    },
+    "merges": [
+      "1 0",
+      "9 9",
+      "1 1",
+      "9 8",
+      "9 7",
+      "1 2",
+      "9 6",
+      "1 3",
+      "9 5",
+      "1 4",
+      "9 4",
+      "1 5",
+      "1 6",
+      "9 3",
+      "1 7",
+      "9 2",
+      "1 8",
+      "9 1",
+      "9 0",
+      "1 9",
+      "2 0",
+      "8 9",
+      "2 1",
+      "8 8",
+      "2 2",
+      "8 7",
+      "8 6",
+      "2 3",
+      "2 4",
+      "8 5",
+      "8 4",
+      "2 5",
+      "2 6",
+      "8 3",
+      "2 7",
+      "8 2"
+    ]
+  }
+}

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "eos_token": "[EOS]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6687e1e7175ca42c8aefe4135139564a15855b1f8c179cd70328e5a737d8570b
+size 5112