End of training

README.md

@@ -0,0 +1,62 @@
+---
+library_name: transformers
+language:
+- en
+base_model: JeremiahZ/roberta-base-mnli
+tags:
+- generated_from_trainer
+datasets:
+- glue
+model-index:
+- name: roberta-base-relu-mnli
+  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. -->
+
+# roberta-base-relu-mnli
+
+This model is a fine-tuned version of [JeremiahZ/roberta-base-mnli](https://huggingface.co/JeremiahZ/roberta-base-mnli) on the GLUE MNLI dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 1.1089
+- eval_model_preparation_time: 0.002
+- eval_accuracy: 0.8668
+- eval_runtime: 74.9335
+- eval_samples_per_second: 131.21
+- eval_steps_per_second: 32.802
+- step: 0
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- optimizer: Use OptimizerNames.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: 3.0
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.50.0.dev0
+- Pytorch 2.6.0+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.0

all_results.json

@@ -0,0 +1,16 @@
+{
+    "eval_accuracy": 0.8705043301069791,
+    "eval_accuracy_mm": 0.8667615947925142,
+    "eval_loss": 1.0948832035064697,
+    "eval_loss_mm": 1.1088989973068237,
+    "eval_model_preparation_time": 0.002,
+    "eval_model_preparation_time_mm": 0.002,
+    "eval_runtime": 73.052,
+    "eval_runtime_mm": 74.9335,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 134.356,
+    "eval_samples_per_second_mm": 131.21,
+    "eval_steps_per_second": 33.593,
+    "eval_steps_per_second_mm": 32.802
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "/home/thw20/projects/AICrossSim/ckpt/roberta/finetune/mnli/lr_2e-5",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "mnli",
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "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": "4.50.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "eval_accuracy": 0.8705043301069791,
+    "eval_accuracy_mm": 0.8667615947925142,
+    "eval_loss": 1.0948832035064697,
+    "eval_loss_mm": 1.1088989973068237,
+    "eval_model_preparation_time": 0.002,
+    "eval_model_preparation_time_mm": 0.002,
+    "eval_runtime": 73.052,
+    "eval_runtime_mm": 74.9335,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 134.356,
+    "eval_samples_per_second_mm": 131.21,
+    "eval_steps_per_second": 33.593,
+    "eval_steps_per_second_mm": 32.802
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae903ca1546a4206610775ea966cb5621394e428c3f572cb1efa08d855a2e2f0
+size 498615900

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "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": "</s>",
+      "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
+    },
+    "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>",
+  "max_length": 128,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d95ff04652c4d4ddba226a1cd0f5cbbe1c0342ccaa689febad24593645864326
+size 5496