Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+
+---
+tags:
+- autotrain
+- text-regression
+base_model: google-bert/bert-base-uncased
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Regression
+
+## Validation Metrics
+loss: 22499751936.0
+
+mse: 22499751936.0
+
+mae: 149999.171875
+
+r2: nan
+
+rmse: 149999.171875
+
+explained_variance: 1.0

checkpoint-3/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 1,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "target"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "target": 0
+  },
+  "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": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32a301580801511d60ed6e2afbb93a0e7e832d09d27064d73bc0b385e1a1a378
+size 437955572

checkpoint-3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e409acd55eebafe1ba01f801f0649ff512fdfc07e722f56e0aac584b5d88d1
+size 876026618

checkpoint-3/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8efc78f6204436041547a0d0c2f8dbac6e78b3895053d1217b3507e623a8fe79
+size 13990

checkpoint-3/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8a41b254d981983d12a5d0bed17f4768863ab9648e2daeb9b71c409365e3b73
+size 1064

checkpoint-3/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 22499751936.0,
+  "best_model_checkpoint": "autotrain-5yjy9-m2jwk/checkpoint-3",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 7656831.0,
+      "learning_rate": 5e-05,
+      "loss": 37499875328.0,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "eval_explained_variance": 1.0,
+      "eval_loss": 22499915776.0,
+      "eval_mae": 149999.71875,
+      "eval_mse": 22499915776.0,
+      "eval_r2": NaN,
+      "eval_rmse": 149999.71875,
+      "eval_runtime": 0.2445,
+      "eval_samples_per_second": 4.091,
+      "eval_steps_per_second": 4.091,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7429680.0,
+      "learning_rate": 2.5e-05,
+      "loss": 37499899904.0,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_explained_variance": 1.0,
+      "eval_loss": 22499813376.0,
+      "eval_mae": 149999.375,
+      "eval_mse": 22499813376.0,
+      "eval_r2": NaN,
+      "eval_rmse": 149999.375,
+      "eval_runtime": 0.2468,
+      "eval_samples_per_second": 4.051,
+      "eval_steps_per_second": 4.051,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8526306.0,
+      "learning_rate": 0.0,
+      "loss": 37499715584.0,
+      "step": 3
+    },
+    {
+      "epoch": 3.0,
+      "eval_explained_variance": 1.0,
+      "eval_loss": 22499751936.0,
+      "eval_mae": 149999.171875,
+      "eval_mse": 22499751936.0,
+      "eval_r2": NaN,
+      "eval_rmse": 149999.171875,
+      "eval_runtime": 0.2411,
+      "eval_samples_per_second": 4.148,
+      "eval_steps_per_second": 4.148,
+      "step": 3
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 3,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 591994559232.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b51e4c46751e18c0decfe96972b35bf842e7582e218fccecdd850c0a42c690e
+size 5240

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 1,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "target"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "target": 0
+  },
+  "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": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32a301580801511d60ed6e2afbb93a0e7e832d09d27064d73bc0b385e1a1a378
+size 437955572

runs/Aug04_08-44-03_r-michellehsieh-taide-lx-7b-chat-test-tyap727r-8c8b1-x1jib/events.out.tfevents.1722761044.r-michellehsieh-taide-lx-7b-chat-test-tyap727r-8c8b1-x1jib.104.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de5dd5ca3476905636fab1d6ce3c5210aefd340000bd906d4666094aacf09f73
-size 5059
+oid sha256:329ce09f1da163049609a26284b4203459dff0a136b75210a82bcce1fcbefd0b
+size 7561

runs/Aug04_08-44-03_r-michellehsieh-taide-lx-7b-chat-test-tyap727r-8c8b1-x1jib/events.out.tfevents.1722761061.r-michellehsieh-taide-lx-7b-chat-test-tyap727r-8c8b1-x1jib.104.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6530551a28a50cc931da02b9209a46693b6734521771780f37ee69520e296d9
+size 599

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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b51e4c46751e18c0decfe96972b35bf842e7582e218fccecdd850c0a42c690e
+size 5240

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-5yjy9-m2jwk/autotrain-data",
+    "model": "google-bert/bert-base-uncased",
+    "lr": 5e-05,
+    "epochs": 3,
+    "max_seq_length": 128,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "text_column": "autotrain_text",
+    "target_column": "autotrain_label",
+    "logging_steps": -1,
+    "project_name": "autotrain-5yjy9-m2jwk",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "MichelleHsieh",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}