Upload 14 files

sst2/README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+language:
+- en
+license: apache-2.0
+base_model: google-bert/bert-base-cased
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+model-index:
+- name: sst2
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9254587155963303
+---
+
+<!-- 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. -->
+
+# sst2
+
+This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the GLUE SST2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3458
+- Accuracy: 0.9255
+
+## 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: 3e-05
+- train_batch_size: 64
+- eval_batch_size: 8
+- 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: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu118
+- Datasets 3.3.1
+- Tokenizers 0.21.0

sst2/all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9254587155963303,
+    "eval_loss": 0.34582674503326416,
+    "eval_runtime": 1.7414,
+    "eval_samples": 872,
+    "eval_samples_per_second": 500.735,
+    "eval_steps_per_second": 62.592,
+    "total_flos": 2.260855007690496e+16,
+    "train_loss": 0.1158968044255647,
+    "train_runtime": 1593.6448,
+    "train_samples": 67349,
+    "train_samples_per_second": 211.305,
+    "train_steps_per_second": 3.304
+}

sst2/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google-bert/bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "sst2",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "positive": 1
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

sst2/eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9254587155963303,
+    "eval_loss": 0.34582674503326416,
+    "eval_runtime": 1.7414,
+    "eval_samples": 872,
+    "eval_samples_per_second": 500.735,
+    "eval_steps_per_second": 62.592
+}

sst2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a808bd7aa9d7b7ef90e3c04108cddd42d0d691750e740933e06e1c5a7c1c194b
+size 440358464

sst2/runs/May14_16-40-12_cs-Precision-7960-Tower/events.out.tfevents.1747255216.cs-Precision-7960-Tower.131188.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d40e582510b4c0e9e501bd6f639228cf515d5ef11690bd1b809bc9fc5849c61
+size 7593

sst2/runs/May14_16-40-12_cs-Precision-7960-Tower/events.out.tfevents.1747256812.cs-Precision-7960-Tower.131188.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acec6d764e5f53d3372d3cb2d80414faf4708e335ab1b06a5f5ed2c146480875
+size 411

sst2/special_tokens_map.json

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

sst2/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "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]"
+}

sst2/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 2.260855007690496e+16,
+    "train_loss": 0.1158968044255647,
+    "train_runtime": 1593.6448,
+    "train_samples": 67349,
+    "train_samples_per_second": 211.305,
+    "train_steps_per_second": 3.304
+}

sst2/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 5265,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4748338081671415,
+      "grad_norm": 6.814696788787842,
+      "learning_rate": 2.715099715099715e-05,
+      "loss": 0.3253,
+      "step": 500
+    },
+    {
+      "epoch": 0.949667616334283,
+      "grad_norm": 4.430999279022217,
+      "learning_rate": 2.4301994301994302e-05,
+      "loss": 0.2149,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4245014245014245,
+      "grad_norm": 5.158424377441406,
+      "learning_rate": 2.1452991452991456e-05,
+      "loss": 0.1399,
+      "step": 1500
+    },
+    {
+      "epoch": 1.899335232668566,
+      "grad_norm": 2.9704854488372803,
+      "learning_rate": 1.8603988603988604e-05,
+      "loss": 0.1341,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3741690408357075,
+      "grad_norm": 5.91994047164917,
+      "learning_rate": 1.5754985754985755e-05,
+      "loss": 0.0936,
+      "step": 2500
+    },
+    {
+      "epoch": 2.849002849002849,
+      "grad_norm": 0.2740668058395386,
+      "learning_rate": 1.2905982905982905e-05,
+      "loss": 0.088,
+      "step": 3000
+    },
+    {
+      "epoch": 3.3238366571699904,
+      "grad_norm": 0.8711889386177063,
+      "learning_rate": 1.0056980056980058e-05,
+      "loss": 0.0658,
+      "step": 3500
+    },
+    {
+      "epoch": 3.798670465337132,
+      "grad_norm": 0.9366008639335632,
+      "learning_rate": 7.207977207977209e-06,
+      "loss": 0.0585,
+      "step": 4000
+    },
+    {
+      "epoch": 4.273504273504273,
+      "grad_norm": 0.3185219168663025,
+      "learning_rate": 4.358974358974359e-06,
+      "loss": 0.0436,
+      "step": 4500
+    },
+    {
+      "epoch": 4.748338081671415,
+      "grad_norm": 4.371499061584473,
+      "learning_rate": 1.50997150997151e-06,
+      "loss": 0.0366,
+      "step": 5000
+    },
+    {
+      "epoch": 5.0,
+      "step": 5265,
+      "total_flos": 2.260855007690496e+16,
+      "train_loss": 0.1158968044255647,
+      "train_runtime": 1593.6448,
+      "train_samples_per_second": 211.305,
+      "train_steps_per_second": 3.304
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5265,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.260855007690496e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

sst2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fb16db69f1390bdb968b116f5630f2717ee91945fc410ba21ae283f764273e3
+size 5304