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: babe_source_subsamples_model_alpha_0_05_idx_3
+  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. -->
+
+# babe_source_subsamples_model_alpha_0_05_idx_3
+
+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 sha256:5e282187ed5c19abaccab81fe6a9df80a6cc75959a5f1e4fdbecea82ebdf13f3
+size 498612824

runs/Jan15_15-13-31_348d6ed2eaac/events.out.tfevents.1736954012.348d6ed2eaac.31.39

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2b08911ef7304b14499aa4b71c56f4daef14cca34cd074a4199ee77e307239e
+size 5563

runs/Jan15_15-14-12_348d6ed2eaac/events.out.tfevents.1736954053.348d6ed2eaac.31.40

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4cec4e0f1c8f968d8927b207c6c0b601735a63fb78de82681b0ec3ccb4b5c68
+size 5563

runs/Jan15_15-14-55_348d6ed2eaac/events.out.tfevents.1736954096.348d6ed2eaac.31.41

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0901a03d6b73620c05936cb773ba783172492e24b136ad97d262365311860fc2
+size 5563

runs/Jan15_15-15-41_348d6ed2eaac/events.out.tfevents.1736954142.348d6ed2eaac.31.42

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54bf7aaaedcdf55f0c3784f5e8224e43c32097d59d18dad0d98e84617ff8d0e1
+size 5563

runs/Jan15_15-16-28_348d6ed2eaac/events.out.tfevents.1736954189.348d6ed2eaac.31.43

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f6a9a1fbd2ad8d3f896ae557feaa71b2e069600c7af996afe87d2c23c84a40
+size 5563

runs/Jan15_15-17-10_348d6ed2eaac/events.out.tfevents.1736954231.348d6ed2eaac.31.44

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec012d87909a53d94ca19191f7ef69daf8064d88cf61e93d12b501a2dab4a115
+size 5563

runs/Jan15_15-17-58_348d6ed2eaac/events.out.tfevents.1736954279.348d6ed2eaac.31.45

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c64fc6db3ff3f79e1c616e1aeb65154327b657bc8f210325ca0d14db6fc1cd0c
+size 5561

runs/Jan15_15-18-39_348d6ed2eaac/events.out.tfevents.1736954320.348d6ed2eaac.31.46

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76b065114f0c90c771d38b0ab03b309e36b0a03762c9802cfaaacca7151dbecc
+size 5561

runs/Jan15_15-19-28_348d6ed2eaac/events.out.tfevents.1736954368.348d6ed2eaac.31.47

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4f4410e353ca450a724126d85f2811d927b1bcd37cac9816d2519c29583dcb3
+size 5561

runs/Jan15_15-20-12_348d6ed2eaac/events.out.tfevents.1736954413.348d6ed2eaac.31.48

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f25013bc101d22bf94676964cd8ceef01297906285bcf1793593b7e3d10372
+size 5561

runs/Jan15_15-20-57_348d6ed2eaac/events.out.tfevents.1736954458.348d6ed2eaac.31.49

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b96b02223a59b89f7ebb8091e7e36652cba05fe9032a35134784b7048df5ab
+size 5561

runs/Jan15_15-21-40_348d6ed2eaac/events.out.tfevents.1736954501.348d6ed2eaac.31.50

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3413e8700e7b5797856140f297f6c1ae7d27fdee0fb33271125de93ca27e32a6
+size 5561

runs/Jan15_15-22-22_348d6ed2eaac/events.out.tfevents.1736954544.348d6ed2eaac.31.51

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a716779649ad1a090123d1fc64a6524fc1dc905c1f074900e32f70a7d481be0
+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:b257f8d6125f7038ef6c9635a8877d5b48e397610388ae2c2df463ee81bb09fb
+size 5432