Coolaps/TD3

README.md

@@ -0,0 +1,64 @@
+---
+license: apache-2.0
+base_model: bert-base-multilingual-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: comic-name-classification
+  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. -->
+
+# comic-name-classification
+
+This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0326
+- Accuracy: 0.9956
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0115        | 1.0   | 25   | 0.0377          | 0.9873   |
+| 0.006         | 2.0   | 50   | 0.0310          | 0.9933   |
+| 0.0118        | 3.0   | 75   | 0.0295          | 0.9937   |
+| 0.0021        | 4.0   | 100  | 0.0311          | 0.9952   |
+| 0.0018        | 5.0   | 125  | 0.0326          | 0.9956   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bert-base-multilingual-cased",
+  "bias": "all",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.2,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "value"
+  ],
+  "task_type": "TOKEN_CLS"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428a00974680f45e26b24ac44adcc69f252e7e72f609d644cbfa290cbce4feb9
+size 2793840

runs/Jan17_19-00-35_f7bfa325d91f/events.out.tfevents.1705518036.f7bfa325d91f.1143.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:234568dae7c9653bb4618f256f66f2c3b1a351ed434ed3dd3fb32d99cb9a7397
+size 4401

runs/Jan17_19-02-41_f7bfa325d91f/events.out.tfevents.1705518162.f7bfa325d91f.1143.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7963abeb7f70681529db4d706d40f1dd768212290718300f61e1ab303c253cfc
+size 4401

runs/Jan17_19-04-03_f7bfa325d91f/events.out.tfevents.1705518243.f7bfa325d91f.1143.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74af09d67347990e5cae96bfe8dcec33a6a38731266314495ab54d78ef7b50b2
+size 6334

runs/Jan17_19-05-51_f7bfa325d91f/events.out.tfevents.1705518352.f7bfa325d91f.1143.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f81ac8601d74712e6d6e9ede67853319d0ea354d2ce67bf0ffd64c6e3db442b
+size 6334

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25eed7fb6e115b7213900dc584840e030e5213440ff9954f1b74ccae33e22d06
+size 4536