Training completed! on ARC-Easy dataset

README.md

@@ -0,0 +1,60 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: ai2_src-bert-finetuned-demo
+  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. -->
+
+# ai2_src-bert-finetuned-demo
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2310
+- Accuracy: 0.4550
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.3247        | 1.0   | 561  | 1.2310          | 0.4550   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0
+- Datasets 2.15.0
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.45502644777297974,
+    "eval_loss": 1.2310103178024292,
+    "eval_runtime": 5.5564,
+    "eval_samples_per_second": 102.045,
+    "eval_steps_per_second": 25.556
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.45502644777297974,
+    "eval_loss": 1.2310103178024292,
+    "eval_runtime": 5.5564,
+    "eval_samples_per_second": 102.045,
+    "eval_steps_per_second": 25.556
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:113943d983bb15a1b01878bf43e913558855aa04325a05154958d77c27ae6d83
+size 437955572

runs/May13_09-32-16_SBANDLAP-M-VHRH/events.out.tfevents.1715572965.SBANDLAP-M-VHRH.60286.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:242136ea4ce710e61d8e19de0db10e7aa5c36009ae056dbf95cccd976abd4280
+size 4250

runs/May13_09-54-13_SBANDLAP-M-VHRH/events.out.tfevents.1715574260.SBANDLAP-M-VHRH.67314.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69fab2d2204f358dcb68fd1310ed0a6ec572e99be56139ad323fb2aded2cb8a7
+size 4927

runs/May13_09-54-13_SBANDLAP-M-VHRH/events.out.tfevents.1715574482.SBANDLAP-M-VHRH.67314.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beecf6082ce751584f9c09d140ff38dd7e2dbb5f418ae10a8f3f359fae0cd42a
+size 411

runs/May13_10-02-31_SBANDLAP-M-VHRH/events.out.tfevents.1715574752.SBANDLAP-M-VHRH.69008.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1377678f50bae3b6ea3294ec69b80367624b196f05e41887b6506e16767e1e6
+size 5084

runs/May13_10-02-31_SBANDLAP-M-VHRH/events.out.tfevents.1715574892.SBANDLAP-M-VHRH.69008.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:166109bd2f23cf5c58eeb388e2fdfa588f87a03fcfb2b49a61a05ea88ab8e7fc
+size 411

runs/May14_06-07-03_SBANDLAP-M-VHRH/events.out.tfevents.1715647024.SBANDLAP-M-VHRH.10222.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:239d4737c21529ca5f95c82447117739985fa6f3bca708aa71785adc824e1200
+size 5084

runs/May14_06-07-03_SBANDLAP-M-VHRH/events.out.tfevents.1715647167.SBANDLAP-M-VHRH.10222.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c955c1a276c4ec3adeeeedddc3d18fbe509a10f89fb9d2e064a3f5e0c56cbc7
+size 411

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,43 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 561,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.436720142602496e-06,
+      "loss": 1.3247,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.45502644777297974,
+      "eval_loss": 1.2310103178024292,
+      "eval_runtime": 9.9985,
+      "eval_samples_per_second": 56.708,
+      "eval_steps_per_second": 14.202,
+      "step": 561
+    },
+    {
+      "epoch": 1.0,
+      "step": 561,
+      "total_flos": 216400733375928.0,
+      "train_loss": 1.3082047596759763,
+      "train_runtime": 136.3321,
+      "train_samples_per_second": 16.438,
+      "train_steps_per_second": 4.115
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 561,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 216400733375928.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf1d6163f629d4990fa845e057357c3adfc0ec6861e383ee97487d766259d3e
+size 4600