End of training

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: mit
+base_model: microsoft/deberta-v3-small
+tags:
+- generated_from_trainer
+model-index:
+- name: my_DeBERTa_model
+  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. -->
+
+# my_DeBERTa_model
+
+This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.7012
+- eval_model_preparation_time: 0.0087
+- eval_accuracy: 0.4814
+- eval_f1: 0.0747
+- eval_precision: 0.0400
+- eval_recall: 0.5741
+- eval_runtime: 19.2911
+- eval_samples_per_second: 55.777
+- eval_steps_per_second: 18.61
+- step: 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: 2e-05
+- train_batch_size: 3
+- eval_batch_size: 3
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.0.2
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,170 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-small",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Rebar",
+    "1": "CRS",
+    "2": "Raw Mat",
+    "3": "Mining",
+    "4": "Tinplate",
+    "5": "Merchant Bar",
+    "6": "Opinion",
+    "7": "Wire Rod",
+    "8": "Scrap",
+    "9": "Steel Dynamics",
+    "10": "Steelmaking",
+    "11": "Decarbonization",
+    "12": "Conferences",
+    "13": "Iron Ore",
+    "14": "labor dispute",
+    "15": "Manufacturing",
+    "16": "World",
+    "17": "HRS",
+    "18": "Galva Metal",
+    "19": "Hollow section",
+    "20": "Alloys",
+    "21": "Trading",
+    "22": "Distribution",
+    "23": "Production",
+    "24": "Slab",
+    "25": "Imp/exp Statistics",
+    "26": "Semis",
+    "27": "Steel Futures",
+    "28": "Automotive",
+    "29": "Sail",
+    "30": "Quotas & Duties",
+    "31": "Longs",
+    "32": "Hrc",
+    "33": "Plate",
+    "34": "Shipbuilding",
+    "35": "Galvanized",
+    "36": "M&A",
+    "37": "Stainless",
+    "38": "Construction",
+    "39": "Beams",
+    "40": "Economics",
+    "41": "Baosteel ",
+    "42": "Coking Coal",
+    "43": "Billet",
+    "44": "research",
+    "45": "Investments",
+    "46": "Pig Iron",
+    "47": "Tubing",
+    "48": "Flats",
+    "49": "Crude Steel",
+    "50": "Consumption",
+    "51": "Economia",
+    "52": "Fabrication",
+    "53": "Crc",
+    "54": "Met Coke",
+    "55": "Pellet",
+    "56": "Wire   ",
+    "57": "Manganese Ore",
+    "58": "Stainless ",
+    "59": "Freight",
+    "60": "Fitch Ratings",
+    "61": "Fin. Reports",
+    "62": "Coated",
+    "63": "Tubular",
+    "64": "Pipe"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Alloys": 20,
+    "Automotive": 28,
+    "Baosteel ": 41,
+    "Beams": 39,
+    "Billet": 43,
+    "CRS": 1,
+    "Coated": 62,
+    "Coking Coal": 42,
+    "Conferences": 12,
+    "Construction": 38,
+    "Consumption": 50,
+    "Crc": 53,
+    "Crude Steel": 49,
+    "Decarbonization": 11,
+    "Distribution": 22,
+    "Economia": 51,
+    "Economics": 40,
+    "Fabrication": 52,
+    "Fin. Reports": 61,
+    "Fitch Ratings": 60,
+    "Flats": 48,
+    "Freight": 59,
+    "Galva Metal": 18,
+    "Galvanized": 35,
+    "HRS": 17,
+    "Hollow section": 19,
+    "Hrc": 32,
+    "Imp/exp Statistics": 25,
+    "Investments": 45,
+    "Iron Ore": 13,
+    "Longs": 31,
+    "M&A": 36,
+    "Manganese Ore": 57,
+    "Manufacturing": 15,
+    "Merchant Bar": 5,
+    "Met Coke": 54,
+    "Mining": 3,
+    "Opinion": 6,
+    "Pellet": 55,
+    "Pig Iron": 46,
+    "Pipe": 64,
+    "Plate": 33,
+    "Production": 23,
+    "Quotas & Duties": 30,
+    "Raw Mat": 2,
+    "Rebar": 0,
+    "Sail": 29,
+    "Scrap": 8,
+    "Semis": 26,
+    "Shipbuilding": 34,
+    "Slab": 24,
+    "Stainless": 37,
+    "Stainless ": 58,
+    "Steel Dynamics": 9,
+    "Steel Futures": 27,
+    "Steelmaking": 10,
+    "Tinplate": 4,
+    "Trading": 21,
+    "Tubing": 47,
+    "Tubular": 63,
+    "Wire   ": 56,
+    "Wire Rod": 7,
+    "World": 16,
+    "labor dispute": 14,
+    "research": 44
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "problem_type": "multi_label_classification",
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1640d22730aeeadfdeee66a255d8e2c7b3ab7fd215c40a194713cbe7ad38e300
+size 567792356

runs/Oct28_11-20-21_8c3b0a1c799e/events.out.tfevents.1730115250.8c3b0a1c799e.966.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99d2172999aaedf0a7bea6b60a5713c809d0bbcd89deb901a6d04bf3171b41b5
+size 549

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc70365dbdb6ad9637ab20acd4c514f38c5dd2a143572b405b869fa45cb1d770
+size 5176