Training in progress, step 780

README.md

@@ -1,6 +1,6 @@
 ---
-license: mit
-base_model: xlnet/xlnet-base-cased
+license: apache-2.0
+base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # model_ckpt
 
-This model is a fine-tuned version of [xlnet/xlnet-base-cased](https://huggingface.co/xlnet/xlnet-base-cased) on the None dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0004
-- Accuracy: 1.0
-- F1: 1.0
-- Precision: 1.0
-- Recall: 1.0
+- Loss: 0.0137
+- Accuracy: 0.9988
+- F1: 0.9988
+- Precision: 0.9988
+- Recall: 0.9988
 
 ## Model description
 
@@ -49,17 +49,32 @@ 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: 5
+- num_epochs: 20
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.4053        | 1.0   | 38   | 0.0204          | 0.9905   | 0.9881 | 0.9932    | 0.9905 |
-| 0.0186        | 2.0   | 76   | 0.0004          | 1.0      | 1.0    | 1.0       | 1.0    |
-| 0.006         | 3.0   | 114  | 0.0039          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
-| 0.0013        | 4.0   | 152  | 0.0051          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
-| 0.0004        | 5.0   | 190  | 0.0004          | 1.0      | 1.0    | 1.0       | 1.0    |
+| 0.5254        | 1.0   | 38   | 0.0387          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.016         | 2.0   | 76   | 0.0131          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0063        | 3.0   | 114  | 0.0119          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0022        | 4.0   | 152  | 0.0122          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0014        | 5.0   | 190  | 0.0123          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0011        | 6.0   | 228  | 0.0126          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0009        | 7.0   | 266  | 0.0126          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0007        | 8.0   | 304  | 0.0127          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0006        | 9.0   | 342  | 0.0129          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0005        | 10.0  | 380  | 0.0130          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0004        | 11.0  | 418  | 0.0131          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0004        | 12.0  | 456  | 0.0132          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0004        | 13.0  | 494  | 0.0133          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0003        | 14.0  | 532  | 0.0134          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0003        | 15.0  | 570  | 0.0135          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0003        | 16.0  | 608  | 0.0136          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0003        | 17.0  | 646  | 0.0136          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0003        | 18.0  | 684  | 0.0136          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0002        | 19.0  | 722  | 0.0137          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
+| 0.0003        | 20.0  | 760  | 0.0137          | 0.9988   | 0.9988 | 0.9988    | 0.9988 |
 
 
 ### Framework versions

config.json

@@ -1,19 +1,13 @@
 {
-  "_name_or_path": "xlnet/xlnet-base-cased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "XLNetForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attn_type": "bi",
-  "bi_data": false,
-  "bos_token_id": 1,
-  "clamp_len": -1,
-  "d_head": 64,
-  "d_inner": 3072,
-  "d_model": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
   "dropout": 0.1,
-  "end_n_top": 5,
-  "eos_token_id": 2,
-  "ff_activation": "gelu",
+  "hidden_dim": 3072,
   "id2label": {
     "0": "CAM",
     "1": "DOT",
@@ -35,30 +29,17 @@
     "Sales": 7,
     "default": 3
   },
-  "layer_norm_eps": 1e-12,
-  "mem_len": null,
-  "model_type": "xlnet",
-  "n_head": 12,
-  "n_layer": 12,
-  "pad_token_id": 5,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
   "problem_type": "single_label_classification",
-  "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
-    }
-  },
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.42.3",
-  "untie_r": true,
-  "use_mems_eval": true,
-  "use_mems_train": false,
-  "vocab_size": 32000
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae66367ee31c211a1b0c590dd69a9924ee585ddf015bc704da26c26f8616c97e
-size 469283056
+oid sha256:55c5b9e18e3d1f86497f4660c5016bf91ff6f55f22ccf3f37f50c93c9bab7a6b
+size 267851024

runs/Jul17_16-23-22_Qodequayserver2/events.out.tfevents.1721213603.Qodequayserver2.290273.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb3707772aff9ea776bcf608c6a25e985b21015b8fcf025249996a0176ded5da
+size 18998

special_tokens_map.json

@@ -1,19 +1,7 @@
 {
-  "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>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,71 +1,39 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<cls>",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": "<sep>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "5": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "6": {
-      "content": "<mask>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "7": {
-      "content": "<eod>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "8": {
-      "content": "<eop>",
+    "103": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -73,21 +41,15 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<eop>",
-    "<eod>"
-  ],
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<cls>",
-  "do_lower_case": false,
-  "eos_token": "</s>",
-  "keep_accents": false,
-  "mask_token": "<mask>",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "remove_space": true,
-  "sep_token": "<sep>",
-  "tokenizer_class": "XLNetTokenizer",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "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]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08bfaa698ac2c9eb55901749e266d0c3b8f4deb35dbaf0009d2b9420c620c349
+oid sha256:04f4dc070500cd41fd9c151f521e6d53336c540568850b9413fa8efc27d58fa5
 size 5112