Training in progress, step 500

README.md

@@ -0,0 +1,95 @@
+---
+library_name: transformers
+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: 0.2387
+
+## 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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 40
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.0501        | 1.0   | 6    | 2.2966          |
+| 2.0486        | 2.0   | 12   | 1.7533          |
+| 1.5929        | 3.0   | 18   | 1.3909          |
+| 1.2724        | 4.0   | 24   | 1.1387          |
+| 1.0906        | 5.0   | 30   | 0.9902          |
+| 0.9501        | 6.0   | 36   | 0.8982          |
+| 0.8489        | 7.0   | 42   | 0.8078          |
+| 0.7684        | 8.0   | 48   | 0.7145          |
+| 0.6872        | 9.0   | 54   | 0.6570          |
+| 0.6574        | 10.0  | 60   | 0.6683          |
+| 0.6364        | 11.0  | 66   | 0.6542          |
+| 0.6217        | 12.0  | 72   | 0.5741          |
+| 0.561         | 13.0  | 78   | 0.5594          |
+| 0.548         | 14.0  | 84   | 0.5491          |
+| 0.5447        | 15.0  | 90   | 0.5075          |
+| 0.5114        | 16.0  | 96   | 0.5275          |
+| 0.4897        | 17.0  | 102  | 0.4606          |
+| 0.4736        | 18.0  | 108  | 0.4505          |
+| 0.4536        | 19.0  | 114  | 0.4420          |
+| 0.4438        | 20.0  | 120  | 0.4338          |
+| 0.4178        | 21.0  | 126  | 0.4388          |
+| 0.439         | 22.0  | 132  | 0.4336          |
+| 0.4315        | 23.0  | 138  | 0.3953          |
+| 0.4006        | 24.0  | 144  | 0.3763          |
+| 0.3923        | 25.0  | 150  | 0.3776          |
+| 0.3785        | 26.0  | 156  | 0.3616          |
+| 0.38          | 27.0  | 162  | 0.3504          |
+| 0.3546        | 28.0  | 168  | 0.3411          |
+| 0.3507        | 29.0  | 174  | 0.3395          |
+| 0.3518        | 30.0  | 180  | 0.3256          |
+| 0.3324        | 31.0  | 186  | 0.3084          |
+| 0.3161        | 32.0  | 192  | 0.2991          |
+| 0.3043        | 33.0  | 198  | 0.2820          |
+| 0.2977        | 34.0  | 204  | 0.2706          |
+| 0.2911        | 35.0  | 210  | 0.2644          |
+| 0.2843        | 36.0  | 216  | 0.2583          |
+| 0.2662        | 37.0  | 222  | 0.2491          |
+| 0.2737        | 38.0  | 228  | 0.2438          |
+| 0.2599        | 39.0  | 234  | 0.2397          |
+| 0.2647        | 40.0  | 240  | 0.2387          |
+
+
+### Framework versions
+
+- Transformers 4.57.2
+- Pytorch 2.9.1+cu128
+- Datasets 4.5.0
+- Tokenizers 0.22.1

config.json

@@ -3,92 +3,49 @@
     "EncoderDecoderModel"
   ],
   "decoder": {
-    "_name_or_path": "",
     "add_cross_attention": true,
-    "architectures": null,
     "attention_probs_dropout_prob": 0.1,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": 0,
     "classifier_dropout": null,
-    "dtype": null,
-    "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,
     "max_position_embeddings": 512,
     "model_type": "bert",
     "num_attention_heads": 4,
     "num_hidden_layers": 4,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "pad_token_id": 0,
-    "problem_type": null,
-    "return_dict": true,
-    "tie_word_embeddings": true,
+    "position_embedding_type": "absolute",
     "type_vocab_size": 2,
     "use_cache": true,
-    "vocab_size": 53
+    "vocab_size": 79
   },
   "decoder_start_token_id": 2,
   "dtype": "float32",
   "encoder": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
     "attention_probs_dropout_prob": 0.1,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": 0,
     "classifier_dropout": null,
-    "dtype": null,
-    "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,
     "max_position_embeddings": 512,
     "model_type": "bert",
     "num_attention_heads": 4,
     "num_hidden_layers": 4,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "pad_token_id": 0,
-    "problem_type": null,
-    "return_dict": true,
-    "tie_word_embeddings": true,
+    "position_embedding_type": "absolute",
     "type_vocab_size": 2,
     "use_cache": true,
-    "vocab_size": 53
+    "vocab_size": 79
   },
   "eos_token_id": 0,
   "is_encoder_decoder": true,
   "model_type": "encoder-decoder",
   "pad_token_id": 3,
-  "transformers_version": "5.0.0",
-  "unk_token_id": null,
-  "use_cache": false
+  "transformers_version": "4.57.2",
+  "unk_token_id": null
 }

generation_config.json

@@ -4,9 +4,6 @@
   "eos_token_id": [
     0
   ],
-  "output_attentions": false,
-  "output_hidden_states": false,
   "pad_token_id": 3,
-  "transformers_version": "5.0.0",
-  "use_cache": true
+  "transformers_version": "4.57.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:103c01ad2911e7bbd4d00a2f155af7fc317efb8edc43a4c8645b1228d97f3204
-size 31207604
+oid sha256:815ea68831b7fc324e3ce92509adacb8c5f8abb0c10333c5ae37c35adfcadf3d
+size 31260956

runs/Mar06_11-40-37_vicm/events.out.tfevents.1772793638.vicm.75786.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e6c0c621399a431ad7a9daa10745ed4400f26b79d4e3732374c11914c6ace55
+size 25246

runs/Mar06_20-32-57_vicm/events.out.tfevents.1772825580.vicm.20324.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:085fb258b20e167a85e888265a4cd61f0a06bc23c69cbbf69c08a783b0eea065
+size 22603

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

@@ -114,18 +114,18 @@
       "8": 14,
       "9": 15,
       "=": 16,
-      "10": 17,
-      "99": 18,
-      "11": 19,
-      "98": 20,
-      "12": 21,
-      "97": 22,
-      "13": 23,
-      "96": 24,
-      "14": 25,
-      "95": 26,
-      "94": 27,
-      "15": 28,
+      "99": 17,
+      "10": 18,
+      "98": 19,
+      "11": 20,
+      "97": 21,
+      "12": 22,
+      "96": 23,
+      "13": 24,
+      "95": 25,
+      "14": 26,
+      "15": 27,
+      "94": 28,
       "93": 29,
       "16": 30,
       "17": 31,
@@ -134,14 +134,14 @@
       "91": 34,
       "19": 35,
       "90": 36,
-      "20": 37,
-      "89": 38,
-      "88": 39,
-      "21": 40,
+      "89": 37,
+      "20": 38,
+      "21": 39,
+      "88": 40,
       "87": 41,
       "22": 42,
-      "23": 43,
-      "86": 44,
+      "86": 43,
+      "23": 44,
       "85": 45,
       "24": 46,
       "25": 47,
@@ -149,20 +149,42 @@
       "26": 49,
       "83": 50,
       "27": 51,
-      "82": 52
+      "82": 52,
+      "81": 53,
+      "28": 54,
+      "29": 55,
+      "80": 56,
+      "30": 57,
+      "79": 58,
+      "78": 59,
+      "31": 60,
+      "34": 61,
+      "76": 62,
+      "33": 63,
+      "75": 64,
+      "77": 65,
+      "32": 66,
+      "74": 67,
+      "35": 68,
+      "36": 69,
+      "38": 70,
+      "72": 71,
+      "39": 72,
+      "71": 73,
+      "73": 74,
+      "37": 75,
+      "40": 76,
+      "69": 77,
+      "70": 78
     },
     "merges": [
-      [
-        "1",
-        "0"
-      ],
       [
         "9",
         "9"
       ],
       [
         "1",
-        "1"
+        "0"
       ],
       [
         "9",
@@ -170,7 +192,7 @@
       ],
       [
         "1",
-        "2"
+        "1"
       ],
       [
         "9",
@@ -178,7 +200,7 @@
       ],
       [
         "1",
-        "3"
+        "2"
       ],
       [
         "9",
@@ -186,20 +208,24 @@
       ],
       [
         "1",
-        "4"
+        "3"
       ],
       [
         "9",
         "5"
       ],
       [
-        "9",
+        "1",
         "4"
       ],
       [
         "1",
         "5"
       ],
+      [
+        "9",
+        "4"
+      ],
       [
         "9",
         "3"
@@ -232,17 +258,13 @@
         "9",
         "0"
       ],
-      [
-        "2",
-        "0"
-      ],
       [
         "8",
         "9"
       ],
       [
-        "8",
-        "8"
+        "2",
+        "0"
       ],
       [
         "2",
@@ -250,20 +272,24 @@
       ],
       [
         "8",
-        "7"
+        "8"
       ],
       [
-        "2",
-        "2"
+        "8",
+        "7"
       ],
       [
         "2",
-        "3"
+        "2"
       ],
       [
         "8",
         "6"
       ],
+      [
+        "2",
+        "3"
+      ],
       [
         "8",
         "5"
@@ -295,6 +321,110 @@
       [
         "8",
         "2"
+      ],
+      [
+        "8",
+        "1"
+      ],
+      [
+        "2",
+        "8"
+      ],
+      [
+        "2",
+        "9"
+      ],
+      [
+        "8",
+        "0"
+      ],
+      [
+        "3",
+        "0"
+      ],
+      [
+        "7",
+        "9"
+      ],
+      [
+        "7",
+        "8"
+      ],
+      [
+        "3",
+        "1"
+      ],
+      [
+        "3",
+        "4"
+      ],
+      [
+        "7",
+        "6"
+      ],
+      [
+        "3",
+        "3"
+      ],
+      [
+        "7",
+        "5"
+      ],
+      [
+        "7",
+        "7"
+      ],
+      [
+        "3",
+        "2"
+      ],
+      [
+        "7",
+        "4"
+      ],
+      [
+        "3",
+        "5"
+      ],
+      [
+        "3",
+        "6"
+      ],
+      [
+        "3",
+        "8"
+      ],
+      [
+        "7",
+        "2"
+      ],
+      [
+        "3",
+        "9"
+      ],
+      [
+        "7",
+        "1"
+      ],
+      [
+        "7",
+        "3"
+      ],
+      [
+        "3",
+        "7"
+      ],
+      [
+        "4",
+        "0"
+      ],
+      [
+        "6",
+        "9"
+      ],
+      [
+        "7",
+        "0"
       ]
     ]
   }

tokenizer_config.json

@@ -1,8 +1,43 @@
 {
-  "backend": "tokenizers",
+  "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": false,
   "cls_token": "[CLS]",
   "eos_token": "[EOS]",
+  "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "tokenizer_class": "TokenizersBackend"
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64e9595e750a35613569607f993afec0f1b3799ad4045f502f7167862c781a8a
-size 5329
+oid sha256:dede89be1cd24623150d5bbe219fdf1f9af0bc7b374512bb168ffecdfa31eb58
+size 6033