End of training

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: distilbert-base-cased
+license: mit
+base_model: xlnet-base-cased
 tags:
 - generated_from_trainer
 model-index:
@@ -13,10 +13,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Sentiment-Analysis-Model
 
-This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
+This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6165
-- F1 Score: 0.7461
+- eval_loss: 1.0174
+- eval_rmse: 0.9484
+- eval_runtime: 170.9043
+- eval_samples_per_second: 11.702
+- eval_steps_per_second: 1.463
+- epoch: 0.01
+- step: 8
 
 ## Model description
 
@@ -41,37 +46,11 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
-
-### Training results
-
-| Training Loss | Epoch | Step  | Validation Loss | F1 Score |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.733         | 0.5   | 500   | 0.7461          | 0.6612   |
-| 0.6823        | 1.0   | 1000  | 0.6636          | 0.7253   |
-| 0.5754        | 1.5   | 1500  | 0.6213          | 0.7460   |
-| 0.5697        | 2.0   | 2000  | 0.6165          | 0.7461   |
-| 0.4239        | 2.5   | 2500  | 0.8810          | 0.7400   |
-| 0.4093        | 3.0   | 3000  | 0.7785          | 0.7348   |
-| 0.2783        | 3.5   | 3500  | 1.1766          | 0.7252   |
-| 0.285         | 4.0   | 4000  | 1.2137          | 0.7278   |
-| 0.1894        | 4.5   | 4500  | 1.4556          | 0.7297   |
-| 0.2023        | 5.0   | 5000  | 1.5257          | 0.7396   |
-| 0.1016        | 5.5   | 5500  | 1.6962          | 0.7321   |
-| 0.1499        | 6.0   | 6000  | 1.6760          | 0.7244   |
-| 0.0797        | 6.5   | 6500  | 1.7829          | 0.7375   |
-| 0.0815        | 7.0   | 7000  | 1.9103          | 0.7328   |
-| 0.0547        | 7.5   | 7500  | 2.0296          | 0.7196   |
-| 0.0556        | 8.0   | 8000  | 2.0332          | 0.7326   |
-| 0.0309        | 8.5   | 8500  | 2.1700          | 0.7290   |
-| 0.0448        | 9.0   | 9000  | 2.1797          | 0.7282   |
-| 0.0335        | 9.5   | 9500  | 2.2633          | 0.7272   |
-| 0.0226        | 10.0  | 10000 | 2.2663          | 0.7308   |
-
+- num_epochs: 20
 
 ### Framework versions
 
-- Transformers 4.32.1
+- Transformers 4.33.1
 - Pytorch 2.0.1+cu118
-- Datasets 2.14.4
+- Datasets 2.14.5
 - Tokenizers 0.13.3

config.json

@@ -1,13 +1,19 @@
 {
-  "_name_or_path": "distilbert-base-cased",
-  "activation": "gelu",
+  "_name_or_path": "xlnet-base-cased",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "XLNetForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
+  "attn_type": "bi",
+  "bi_data": false,
+  "bos_token_id": 1,
+  "clamp_len": -1,
+  "d_head": 64,
+  "d_inner": 3072,
+  "d_model": 768,
   "dropout": 0.1,
-  "hidden_dim": 3072,
+  "end_n_top": 5,
+  "eos_token_id": 2,
+  "ff_activation": "gelu",
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -19,18 +25,30 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "output_past": true,
-  "pad_token_id": 0,
+  "layer_norm_eps": 1e-12,
+  "mem_len": null,
+  "model_type": "xlnet",
+  "n_head": 12,
+  "n_layer": 12,
+  "pad_token_id": 5,
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "reuse_len": null,
+  "same_length": false,
+  "start_n_top": 5,
+  "summary_activation": "tanh",
+  "summary_last_dropout": 0.1,
+  "summary_type": "last",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 250
+    }
+  },
   "torch_dtype": "float32",
-  "transformers_version": "4.32.1",
-  "vocab_size": 28996
+  "transformers_version": "4.33.1",
+  "untie_r": true,
+  "use_mems_eval": true,
+  "use_mems_train": false,
+  "vocab_size": 32000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd16a765eaa528da93be2a5706cac6a328233b93a50b0ceadc2cadbdd2da0d8
-size 263170733
+oid sha256:5ff5f0b1e96bf36e2bbdc09aeed571424ec9a6a73d1c890367422bc50409aa7d
+size 469311893

special_tokens_map.json

@@ -1,7 +1,19 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<cls>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,13 +1,26 @@
 {
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
+  "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": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
+  "eos_token": "</s>",
+  "keep_accents": false,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "<sep>",
+  "tokenizer_class": "XLNetTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd763c5c57928a2b881a7ab45ee833f9c844c61dd2264fc9369c71d123ce57d5
+oid sha256:1316ea35a5d9561ed39b86ff160f255eaa9c3e9a1c376318b8f161ae5e9c9dfe
 size 4027