gigascake/roberta-base-klue-ynat-classification

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "klue/roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

.ipynb_checkpoints/tokenizer_config-checkpoint.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "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_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

README.md

@@ -1,5 +1,4 @@
 ---
-base_model: klue/roberta-base
 tags:
 - generated_from_trainer
 metrics:
@@ -14,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [klue/roberta-base](https://huggingface.co/klue/roberta-base) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4438
-- Accuracy: 0.85
+- Loss: 0.4734
+- Accuracy: 0.865
 
 ## Model description
 
@@ -37,8 +36,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 24
-- eval_batch_size: 24
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -51,6 +50,6 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - Transformers 4.40.1
-- Pytorch 2.1.2+rocm6.1.3
+- Pytorch 2.5.0+cu124
 - Datasets 2.19.0
 - Tokenizers 0.19.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "klue/roberta-base",
+  "_name_or_path": "./models/klue/roberta-base",
   "architectures": [
     "RobertaForSequenceClassification"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a8e17ad63ac377b5aab3f96aa51b065346a8ddeba9b0988aba45bfc118d38cb
+oid sha256:2a0a962138b8b8c883ee7de4347661aeea396eeab24ce772cf062dc059e4acff
 size 442518124

runs/Oct24_17-10-36_gpu01/events.out.tfevents.1729757444.gpu01.317017.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aaf73b9d6e1e4f14800bc67a238db2a4f6da5140796dae5b738d24946b5e950
+size 5351

runs/Oct26_16-02-50_gpu01/events.out.tfevents.1729926189.gpu01.11948.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:129738d6bd0e6a84afce853d9c53ef3d48a345dbc3b2895d7301ac510ec463be
+size 5351

runs/Oct26_16-53-42_gpu01/events.out.tfevents.1729929370.gpu01.3237.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a42579c24652849c1fba3ed5443216dae5887e02f5504f97f5977447be5fd507
+size 5351

runs/Oct26_17-01-37_gpu01/events.out.tfevents.1729929711.gpu01.9150.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c935897508cf10794d2d716c5df8942eb01a361277f3159ee5d4c54a6d3f79a
+size 5091

runs/Oct26_18-06-48_gpu01/events.out.tfevents.1729933621.gpu01.8358.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddb9621fb24c690a17781b5e2e8e64d07b587c12738ccad962067cb07cfb1d01
+size 5351

runs/Oct26_18-38-27_gpu01/events.out.tfevents.1729935517.gpu01.8547.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd7eed0399e7d85a179acbe98a665977b3d314f8ad0265d422cf3e73665efa4
+size 5351

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 1,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef2308e36b58366a88861611d692e8265285ff8bfe8f9c82fb9f9ef5927410b7
-size 4984
+oid sha256:3d5f3fc3f7ebb1a8cd5a017df01dd782c3ff8e538d5d07713870583301246055
+size 4920