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: 0.6102
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.4688        | 1.0   | 5    | 2.8659          |
+| 2.5395        | 2.0   | 10   | 2.1007          |
+| 1.9592        | 3.0   | 15   | 1.7491          |
+| 1.6895        | 4.0   | 20   | 1.5873          |
+| 1.5985        | 5.0   | 25   | 1.5268          |
+| 1.5444        | 6.0   | 30   | 1.5378          |
+| 1.5074        | 7.0   | 35   | 1.4607          |
+| 1.4651        | 8.0   | 40   | 1.4537          |
+| 1.4525        | 9.0   | 45   | 1.4718          |
+| 1.4429        | 10.0  | 50   | 1.3729          |
+| 1.3852        | 11.0  | 55   | 1.3508          |
+| 1.3357        | 12.0  | 60   | 1.2872          |
+| 1.2972        | 13.0  | 65   | 1.2634          |
+| 1.2483        | 14.0  | 70   | 1.1977          |
+| 1.1983        | 15.0  | 75   | 1.1583          |
+| 1.1462        | 16.0  | 80   | 1.0801          |
+| 1.0846        | 17.0  | 85   | 1.0128          |
+| 1.055         | 18.0  | 90   | 1.0017          |
+| 1.0239        | 19.0  | 95   | 0.9550          |
+| 0.9661        | 20.0  | 100  | 0.9190          |
+| 0.9551        | 21.0  | 105  | 0.8978          |
+| 0.9148        | 22.0  | 110  | 0.8516          |
+| 0.887         | 23.0  | 115  | 0.8381          |
+| 0.8872        | 24.0  | 120  | 0.8330          |
+| 0.8642        | 25.0  | 125  | 0.8257          |
+| 0.8441        | 26.0  | 130  | 0.7729          |
+| 0.8151        | 27.0  | 135  | 0.7500          |
+| 0.7906        | 28.0  | 140  | 0.7392          |
+| 0.7797        | 29.0  | 145  | 0.7292          |
+| 0.7707        | 30.0  | 150  | 0.7043          |
+| 0.7475        | 31.0  | 155  | 0.6987          |
+| 0.74          | 32.0  | 160  | 0.6696          |
+| 0.7274        | 33.0  | 165  | 0.6536          |
+| 0.7121        | 34.0  | 170  | 0.6459          |
+| 0.7113        | 35.0  | 175  | 0.6505          |
+| 0.7016        | 36.0  | 180  | 0.6299          |
+| 0.6946        | 37.0  | 185  | 0.6234          |
+| 0.6886        | 38.0  | 190  | 0.6157          |
+| 0.6821        | 39.0  | 195  | 0.6146          |
+| 0.6768        | 40.0  | 200  | 0.6102          |
+
+
+### 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 sha256:1c32d48b712da09b0c5a3723cf4402b1d061e6c2f0779a9a6acd07679ed5edbf
+size 31205552

runs/Mar04_14-09-53_298a5956960a/events.out.tfevents.1709561393.298a5956960a.2619.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37bae1573add1354dcb31a04e545a0d68430d9f157456d722c366b58ef251531
+size 27961

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,
+      "99": 16,
+      "10": 17,
+      "11": 18,
+      "98": 19,
+      "97": 20,
+      "12": 21,
+      "96": 22,
+      "13": 23,
+      "14": 24,
+      "95": 25,
+      "15": 26,
+      "94": 27,
+      "16": 28,
+      "93": 29,
+      "92": 30,
+      "17": 31,
+      "18": 32,
+      "91": 33,
+      "19": 34,
+      "90": 35,
+      "89": 36,
+      "20": 37,
+      "21": 38,
+      "88": 39,
+      "22": 40,
+      "87": 41,
+      "86": 42,
+      "23": 43,
+      "24": 44,
+      "85": 45,
+      "25": 46,
+      "84": 47,
+      "26": 48,
+      "83": 49,
+      "27": 50,
+      "82": 51
+    },
+    "merges": [
+      "9 9",
+      "1 0",
+      "1 1",
+      "9 8",
+      "9 7",
+      "1 2",
+      "9 6",
+      "1 3",
+      "1 4",
+      "9 5",
+      "1 5",
+      "9 4",
+      "1 6",
+      "9 3",
+      "9 2",
+      "1 7",
+      "1 8",
+      "9 1",
+      "1 9",
+      "9 0",
+      "8 9",
+      "2 0",
+      "2 1",
+      "8 8",
+      "2 2",
+      "8 7",
+      "8 6",
+      "2 3",
+      "2 4",
+      "8 5",
+      "2 5",
+      "8 4",
+      "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 sha256:1d1387e910a0e6e4c5bf2d781480ffda80ff2018ff79ab60de2c97b44fdd9fda
+size 5112