Training in progress, step 24

README.md

@@ -0,0 +1,53 @@
+---
+library_name: transformers
+license: mit
+base_model: roberta-base
+tags:
+- generated_from_trainer
+model-index:
+- name: basil_topic_subsamples_model_alpha_0_01_idx_2
+  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. -->
+
+# basil_topic_subsamples_model_alpha_0_01_idx_2
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
+
+## 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: 2e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.47.0
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ba8ef7a31e8e716e0165cb4cb9601808856f6c9463e7979ac88b38146d0b16f
+size 498612824

runs/Jan15_14-42-33_348d6ed2eaac/events.out.tfevents.1736952154.348d6ed2eaac.31.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fc91011ed79b65d6d7c970194c362faf053d923af2d079341fbfff7185226a3
+size 5512

runs/Jan15_14-48-51_348d6ed2eaac/events.out.tfevents.1736952532.348d6ed2eaac.31.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb69bf6800ec4e420057f3f8f36029cb377346c0c213720808ccd5cdb54f5c12
+size 5512

runs/Jan15_14-49-33_348d6ed2eaac/events.out.tfevents.1736952574.348d6ed2eaac.31.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:280a0589fe46b0cb2089c0dc46edf3ce1bb2d6bc77738e00a3327bb3467117ab
+size 5563

runs/Jan15_14-49-59_348d6ed2eaac/events.out.tfevents.1736952600.348d6ed2eaac.31.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd5fa81f41725792809a3336c7f00c5713a7cfa96dce676eeafa7288644ecce9
+size 5563

runs/Jan15_14-50-27_348d6ed2eaac/events.out.tfevents.1736952628.348d6ed2eaac.31.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c42b90b1419937c24b28a05e0e4a53d791b10ff709a72685c5bc5c26e3d92299
+size 5563

runs/Jan15_14-50-52_348d6ed2eaac/events.out.tfevents.1736952653.348d6ed2eaac.31.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f8035e263290c7c5e17879328f7c2d2ac82fe0fab584645583ed40951c89de
+size 5563

runs/Jan15_14-51-19_348d6ed2eaac/events.out.tfevents.1736952680.348d6ed2eaac.31.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:521e2721f56b97b21cd4c1f4f864eb364b780aff6a5dfe4e0502d92432d37bba
+size 5563

runs/Jan15_14-52-01_348d6ed2eaac/events.out.tfevents.1736952722.348d6ed2eaac.31.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a179017c43d9e7d0d505efc4732c2dc29ff4aa55f64c40cdbf62da4c46d35ba7
+size 5561

runs/Jan15_14-52-44_348d6ed2eaac/events.out.tfevents.1736952765.348d6ed2eaac.31.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e5677421f40ec1e67dabb952e6886da605eca282cd4fc29d0baf9671aafb9cf
+size 5561

runs/Jan15_14-53-31_348d6ed2eaac/events.out.tfevents.1736952812.348d6ed2eaac.31.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e160fe484c07723e32f7301b2f452d1fd53fcca4df08f759da51db0865b0520
+size 5561

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40386207fd30be705809a176a638f7ed4ddcf19b5c79ce30d571d65c98070b0e
+size 5432