inital commit

README.md

@@ -1,3 +1,76 @@
 ---
 license: mit
+base_model: microsoft/deberta-v3-large
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: BBC_CLS_deberta_v3_large_v2
+  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. -->
+
+# BBC_CLS_deberta_v3_large_v2
+
+This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0857
+- Accuracy: 0.9866
+- Precision: 0.9723
+- Recall: 0.9780
+- F1: 0.9751
+
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 1.235         | 1.0   | 66   | 0.6331          | 0.7964   | 0.4047    | 0.4873 | 0.4418 |
+| 0.4336        | 2.0   | 132  | 0.2201          | 0.8971   | 0.6754    | 0.7091 | 0.6910 |
+| 0.2133        | 3.0   | 198  | 0.0990          | 0.9776   | 0.9476    | 0.9786 | 0.9602 |
+| 0.1083        | 4.0   | 264  | 0.1038          | 0.9821   | 0.9656    | 0.9651 | 0.9653 |
+| 0.0848        | 5.0   | 330  | 0.0907          | 0.9866   | 0.9782    | 0.9714 | 0.9747 |
+| 0.1087        | 6.0   | 396  | 0.1270          | 0.9799   | 0.9672    | 0.9689 | 0.9671 |
+| 0.1011        | 7.0   | 462  | 0.1289          | 0.9754   | 0.9677    | 0.9660 | 0.9667 |
+| 0.0827        | 8.0   | 528  | 0.0990          | 0.9799   | 0.9818    | 0.9479 | 0.9632 |
+| 0.0621        | 9.0   | 594  | 0.0857          | 0.9866   | 0.9723    | 0.9780 | 0.9751 |
+| 0.0444        | 10.0  | 660  | 0.1071          | 0.9843   | 0.9769    | 0.9663 | 0.9715 |
+
+
+### Framework versions
+
+- Transformers 4.35.0.dev0
+- Pytorch 1.13.1
+- Datasets 2.13.0
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 1,
+  "[MASK]": 128000,
+  "[PAD]": 0,
+  "[SEP]": 2,
+  "[UNK]": 3
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-large",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Cargo",
+    "1": "Open Pos",
+    "2": "Time Charter",
+    "3": "Spam"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0.dev0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b02e60ea41c996960ec95a8d582f6cf7d12b880695e85ce3665792a4117b879a
+size 3480856123

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8ed3ca0df041bd4fbccb3cc002bd68656570223139d7b5016821575c728f691
+size 1740399989

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93e85b854d09c59c61f6928e21a8b24c26c39f575da928524dc8b935ca5f35b
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b44221305308757e0422afef9c458c76bfdd35eac0f0a0b8dbc4a6f6580308d
+size 627

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

spm.model

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

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "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"
+}

trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_metric": 0.08565760403871536,
+  "best_model_checkpoint": "BBC_CLS_deberta_v3_large_v2/checkpoint-594",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 660,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 6.6e-06,
+      "loss": 1.235,
+      "step": 66
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.796420581655481,
+      "eval_f1": 0.4417921999471439,
+      "eval_loss": 0.633094072341919,
+      "eval_precision": 0.4046829607174435,
+      "eval_recall": 0.4873423547822885,
+      "eval_runtime": 6.7539,
+      "eval_samples_per_second": 66.184,
+      "eval_steps_per_second": 2.073,
+      "step": 66
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.32e-05,
+      "loss": 0.4336,
+      "step": 132
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8970917225950783,
+      "eval_f1": 0.6910171764080433,
+      "eval_loss": 0.22008153796195984,
+      "eval_precision": 0.6753658536585365,
+      "eval_recall": 0.7090775277247049,
+      "eval_runtime": 6.7716,
+      "eval_samples_per_second": 66.011,
+      "eval_steps_per_second": 2.067,
+      "step": 132
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.9800000000000004e-05,
+      "loss": 0.2133,
+      "step": 198
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9776286353467561,
+      "eval_f1": 0.9601648947616865,
+      "eval_loss": 0.0990455150604248,
+      "eval_precision": 0.9476303317535546,
+      "eval_recall": 0.9785651349741774,
+      "eval_runtime": 6.7752,
+      "eval_samples_per_second": 65.976,
+      "eval_steps_per_second": 2.066,
+      "step": 198
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.64e-05,
+      "loss": 0.1083,
+      "step": 264
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9821029082774049,
+      "eval_f1": 0.9653218049514888,
+      "eval_loss": 0.10380033403635025,
+      "eval_precision": 0.9655642046538242,
+      "eval_recall": 0.9650874727825403,
+      "eval_runtime": 6.7715,
+      "eval_samples_per_second": 66.012,
+      "eval_steps_per_second": 2.067,
+      "step": 264
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.3e-05,
+      "loss": 0.0848,
+      "step": 330
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9865771812080537,
+      "eval_f1": 0.9747350357333067,
+      "eval_loss": 0.09066177904605865,
+      "eval_precision": 0.9782430301452915,
+      "eval_recall": 0.9713632225190546,
+      "eval_runtime": 6.7664,
+      "eval_samples_per_second": 66.062,
+      "eval_steps_per_second": 2.069,
+      "step": 330
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.960000000000001e-05,
+      "loss": 0.1087,
+      "step": 396
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9798657718120806,
+      "eval_f1": 0.9671245324193838,
+      "eval_loss": 0.12698371708393097,
+      "eval_precision": 0.9672288359788359,
+      "eval_recall": 0.9688744042217826,
+      "eval_runtime": 6.7679,
+      "eval_samples_per_second": 66.047,
+      "eval_steps_per_second": 2.069,
+      "step": 396
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.6200000000000005e-05,
+      "loss": 0.1011,
+      "step": 462
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9753914988814317,
+      "eval_f1": 0.9666995780164981,
+      "eval_loss": 0.12892137467861176,
+      "eval_precision": 0.9676667575151919,
+      "eval_recall": 0.9659549559260323,
+      "eval_runtime": 6.7567,
+      "eval_samples_per_second": 66.157,
+      "eval_steps_per_second": 2.072,
+      "step": 462
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.125e-05,
+      "loss": 0.0827,
+      "step": 528
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9798657718120806,
+      "eval_f1": 0.9631601759286037,
+      "eval_loss": 0.09904194623231888,
+      "eval_precision": 0.9818050507874383,
+      "eval_recall": 0.9479257225190546,
+      "eval_runtime": 6.7541,
+      "eval_samples_per_second": 66.182,
+      "eval_steps_per_second": 2.073,
+      "step": 528
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.0625e-05,
+      "loss": 0.0621,
+      "step": 594
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9865771812080537,
+      "eval_f1": 0.9750903668573623,
+      "eval_loss": 0.08565760403871536,
+      "eval_precision": 0.9722969853754562,
+      "eval_recall": 0.9780020135988667,
+      "eval_runtime": 6.7572,
+      "eval_samples_per_second": 66.152,
+      "eval_steps_per_second": 2.072,
+      "step": 594
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0444,
+      "step": 660
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9843400447427293,
+      "eval_f1": 0.9714752151121933,
+      "eval_loss": 0.10706986486911774,
+      "eval_precision": 0.9768891875746715,
+      "eval_recall": 0.9662611817027281,
+      "eval_runtime": 6.7612,
+      "eval_samples_per_second": 66.112,
+      "eval_steps_per_second": 2.071,
+      "step": 660
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 660,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 9724835143127040.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27bea8c60e03ea217df3db5019fef3497c5c9ac1c3196db388e5f56c754a7b61
+size 4027