Model save

README.md

@@ -0,0 +1,68 @@
+---
+base_model: docketanalyzer/docket-lm-xs
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: label-complaint
+  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. -->
+
+# label-complaint
+
+This model is a fine-tuned version of [docketanalyzer/docket-lm-xs](https://huggingface.co/docketanalyzer/docket-lm-xs) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0635
+- F1: 0.9828
+
+## 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: 4
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.02
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.0787        | 1.42  | 60   | 0.0636          | 0.9739 |
+| 0.0053        | 2.84  | 120  | 0.0489          | 0.9828 |
+| 0.0029        | 4.26  | 180  | 0.0556          | 0.9828 |
+| 0.0019        | 5.68  | 240  | 0.0636          | 0.9828 |
+| 0.0014        | 7.1   | 300  | 0.0638          | 0.9828 |
+| 0.0012        | 8.52  | 360  | 0.0635          | 0.9828 |
+| 0.0012        | 9.94  | 420  | 0.0635          | 0.9828 |
+
+
+### Framework versions
+
+- Transformers 4.37.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.4
+- Tokenizers 0.15.1

added_tokens.json

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

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "docketanalyzer/docket-lm-xs",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "False",
+    "1": "True"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "False": 0,
+    "True": 1
+  },
+  "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": 6,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 384,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_loss": 0.063520148396492,
+    "eval_f1": 0.9827586206896551,
+    "eval_runtime": 0.5302,
+    "eval_samples_per_second": 316.883,
+    "eval_steps_per_second": 20.748,
+    "epoch": 9.94
+}

logs/events.out.tfevents.1707333959.nathan.47047.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1397f7cb02a7d6bb6e2a7149d866b730fd47fc57fa3ba24f9ba6fd4b3e6a38c5
+size 40017

logs/events.out.tfevents.1707334061.nathan.47047.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc41cc81fe4e77383df435e2690796d1d80f3f2ea26ecf48056274e87a29ee5
+size 405

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:775b6e2366b5a83c4357af857e43e4c1b0ee2fcbd6ae05e572b0eea078d1bc9f
+size 283347432

run_config.json

@@ -0,0 +1,21 @@
+{
+    "base_model": "docketanalyzer/docket-lm-xs",
+    "run_args": {
+        "max_length": 256
+    },
+    "training_args": {
+        "num_train_epochs": 10,
+        "per_device_train_batch_size": 4,
+        "per_device_eval_batch_size": 16,
+        "gradient_accumulation_steps": 4,
+        "learning_rate": 5e-05,
+        "weight_decay": 0.1,
+        "warmup_ratio": 0.02,
+        "evaluation_strategy": "steps",
+        "eval_steps": 60,
+        "save_steps": 60,
+        "save_total_limit": 1
+    },
+    "run_name": "complaint",
+    "run_type": "ClassificationRoutine"
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 +1,62 @@
+{
+  "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]",
+  "max_length": 256,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "stride": 0,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f32359f205619e9ab451ce60f0473430ad675ed490d4afde3895b1223c970e56
+size 4664