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: 0.7491
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.415         | 1.0   | 6    | 2.7963          |
+| 2.4074        | 2.0   | 12   | 1.9768          |
+| 1.8076        | 3.0   | 18   | 1.6975          |
+| 1.631         | 4.0   | 24   | 1.6085          |
+| 1.557         | 5.0   | 30   | 1.5766          |
+| 1.572         | 6.0   | 36   | 1.5571          |
+| 1.5449        | 7.0   | 42   | 1.5249          |
+| 1.4936        | 8.0   | 48   | 1.5404          |
+| 1.5192        | 9.0   | 54   | 1.4919          |
+| 1.4605        | 10.0  | 60   | 1.4851          |
+| 1.4553        | 11.0  | 66   | 1.4590          |
+| 1.4292        | 12.0  | 72   | 1.4652          |
+| 1.4121        | 13.0  | 78   | 1.4307          |
+| 1.3945        | 14.0  | 84   | 1.3903          |
+| 1.3656        | 15.0  | 90   | 1.3513          |
+| 1.323         | 16.0  | 96   | 1.3290          |
+| 1.2754        | 17.0  | 102  | 1.3396          |
+| 1.2643        | 18.0  | 108  | 1.2157          |
+| 1.1926        | 19.0  | 114  | 1.1660          |
+| 1.1646        | 20.0  | 120  | 1.0959          |
+| 1.1272        | 21.0  | 126  | 1.0731          |
+| 1.0866        | 22.0  | 132  | 1.0264          |
+| 1.0795        | 23.0  | 138  | 1.0202          |
+| 1.0375        | 24.0  | 144  | 1.0136          |
+| 1.0369        | 25.0  | 150  | 0.9635          |
+| 1.0076        | 26.0  | 156  | 0.9510          |
+| 0.9793        | 27.0  | 162  | 0.9585          |
+| 0.9608        | 28.0  | 168  | 0.8828          |
+| 0.9239        | 29.0  | 174  | 0.8845          |
+| 0.9138        | 30.0  | 180  | 0.8512          |
+| 0.9076        | 31.0  | 186  | 0.8600          |
+| 0.8815        | 32.0  | 192  | 0.8543          |
+| 0.8953        | 33.0  | 198  | 0.8376          |
+| 0.8682        | 34.0  | 204  | 0.7939          |
+| 0.8365        | 35.0  | 210  | 0.7926          |
+| 0.8287        | 36.0  | 216  | 0.7876          |
+| 0.8226        | 37.0  | 222  | 0.7683          |
+| 0.812         | 38.0  | 228  | 0.7613          |
+| 0.8063        | 39.0  | 234  | 0.7507          |
+| 0.7875        | 40.0  | 240  | 0.7491          |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- 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": 52
+  },
+  "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": 52
+  },
+  "eos_token_id": 0,
+  "is_encoder_decoder": true,
+  "model_type": "encoder-decoder",
+  "pad_token_id": 3,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "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": "4.38.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07bfa5d64d349bad265398f62db93bea4afe4bcba0d45808d55691470849b680
+size 31205552

runs/Mar04_13-51-18_7eccf1ba7969/events.out.tfevents.1709560279.7eccf1ba7969.331.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21b1d9b472cc2029a5ba88082b924aabca85b6c20d40bc7db590d3de3a5fe26b
+size 27997

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 +1,191 @@
+{
+  "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,
+      "10": 16,
+      "99": 17,
+      "98": 18,
+      "11": 19,
+      "97": 20,
+      "12": 21,
+      "96": 22,
+      "13": 23,
+      "14": 24,
+      "95": 25,
+      "15": 26,
+      "94": 27,
+      "16": 28,
+      "93": 29,
+      "17": 30,
+      "92": 31,
+      "91": 32,
+      "18": 33,
+      "19": 34,
+      "90": 35,
+      "89": 36,
+      "20": 37,
+      "88": 38,
+      "21": 39,
+      "87": 40,
+      "22": 41,
+      "23": 42,
+      "86": 43,
+      "24": 44,
+      "85": 45,
+      "25": 46,
+      "84": 47,
+      "83": 48,
+      "26": 49,
+      "27": 50,
+      "82": 51
+    },
+    "merges": [
+      "1 0",
+      "9 9",
+      "9 8",
+      "1 1",
+      "9 7",
+      "1 2",
+      "9 6",
+      "1 3",
+      "1 4",
+      "9 5",
+      "1 5",
+      "9 4",
+      "1 6",
+      "9 3",
+      "1 7",
+      "9 2",
+      "9 1",
+      "1 8",
+      "1 9",
+      "9 0",
+      "8 9",
+      "2 0",
+      "8 8",
+      "2 1",
+      "8 7",
+      "2 2",
+      "2 3",
+      "8 6",
+      "2 4",
+      "8 5",
+      "2 5",
+      "8 4",
+      "8 3",
+      "2 6",
+      "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:a8294176ab28a6fc070dce286a4286ee5fdd7e05248fed8ab759b6cd4cfe6c1d
+size 5112