Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: sentence-transformers/all-mpnet-base-v2
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.05203713849186897
+
+f1: 0.9890664423885618
+
+precision: 0.9865771812080537
+
+recall: 0.9915682967959528
+
+auc: 0.9994258079801541
+
+accuracy: 0.9891485809682805

checkpoint-450/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
+  "_num_labels": 2,
+  "architectures": [
+    "MPNetForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "opposed",
+    "1": "supportive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "opposed": 0,
+    "supportive": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "vocab_size": 30527
+}

checkpoint-450/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e438e454c4ec8f2141b26d1139ec3aa39690b64abb1ebefd906b1c14d85e82ce
+size 437975200

checkpoint-450/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe39803e13dedfbf705c61175f25d93ff6790d79349b32fef4ae2487b9418a35
+size 876072122

checkpoint-450/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01be59648fcf5743b2e5b82e1ca5a89db665cb4c835c1b65a8bfdcd7db02853f
+size 15024

checkpoint-450/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ffae3ae6cee5ece55a737d955779b079b1017c61f12c017fb6cdb628e1e00f
+size 15024

checkpoint-450/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bf1464e80d1d2574177ac3259057dabe984b784a2a00705d3de207d30c10d1f
+size 15024

checkpoint-450/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:336a79d755f390f2e359a388015a78c12e1110d5f131adf8a85e2de7b0261a23
+size 15024

checkpoint-450/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a890cd1f190ef073f922788849691ede3597ea6ae7cbcf63845c911bb80751
+size 1064

checkpoint-450/trainer_state.json

@@ -0,0 +1,207 @@
+{
+  "best_metric": 0.03989905118942261,
+  "best_model_checkpoint": "klimacoder-v0-2-1/checkpoint-450",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 1.1921207904815674,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.6855,
+      "step": 25
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 2.5017459392547607,
+      "learning_rate": 4.938271604938271e-05,
+      "loss": 0.54,
+      "step": 50
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.509257435798645,
+      "learning_rate": 4.654320987654321e-05,
+      "loss": 0.2217,
+      "step": 75
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.20545396208763123,
+      "learning_rate": 4.345679012345679e-05,
+      "loss": 0.1143,
+      "step": 100
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": Infinity,
+      "learning_rate": 4.049382716049383e-05,
+      "loss": 0.0751,
+      "step": 125
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.169285848736763,
+      "learning_rate": 3.740740740740741e-05,
+      "loss": 0.0866,
+      "step": 150
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9808013355592654,
+      "eval_auc": 0.9981018215266262,
+      "eval_f1": 0.9805249788314987,
+      "eval_loss": 0.0736752524971962,
+      "eval_precision": 0.9846938775510204,
+      "eval_recall": 0.9763912310286678,
+      "eval_runtime": 0.5963,
+      "eval_samples_per_second": 2009.125,
+      "eval_steps_per_second": 31.864,
+      "step": 150
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.08550403267145157,
+      "learning_rate": 3.432098765432099e-05,
+      "loss": 0.0503,
+      "step": 175
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.06706776469945908,
+      "learning_rate": 3.123456790123457e-05,
+      "loss": 0.0723,
+      "step": 200
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.05572424456477165,
+      "learning_rate": 2.814814814814815e-05,
+      "loss": 0.0235,
+      "step": 225
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.062113117426633835,
+      "learning_rate": 2.5061728395061727e-05,
+      "loss": 0.0877,
+      "step": 250
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.0703682079911232,
+      "learning_rate": 2.1975308641975308e-05,
+      "loss": 0.0646,
+      "step": 275
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 6.333071708679199,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 0.0631,
+      "step": 300
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9874791318864775,
+      "eval_auc": 0.9970370576839993,
+      "eval_f1": 0.9872988992379339,
+      "eval_loss": 0.05900123342871666,
+      "eval_precision": 0.9914965986394558,
+      "eval_recall": 0.9831365935919055,
+      "eval_runtime": 0.5975,
+      "eval_samples_per_second": 2005.175,
+      "eval_steps_per_second": 31.802,
+      "step": 300
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.05191728472709656,
+      "learning_rate": 1.580246913580247e-05,
+      "loss": 0.0645,
+      "step": 325
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.05018889531493187,
+      "learning_rate": 1.2716049382716049e-05,
+      "loss": 0.068,
+      "step": 350
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.04393320530653,
+      "learning_rate": 9.62962962962963e-06,
+      "loss": 0.0364,
+      "step": 375
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.044134195894002914,
+      "learning_rate": 6.54320987654321e-06,
+      "loss": 0.0387,
+      "step": 400
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 1.5181336402893066,
+      "learning_rate": 3.45679012345679e-06,
+      "loss": 0.0128,
+      "step": 425
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.045596569776535034,
+      "learning_rate": 3.703703703703704e-07,
+      "loss": 0.0285,
+      "step": 450
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9908180300500835,
+      "eval_auc": 0.9993268574136274,
+      "eval_f1": 0.9907016060862215,
+      "eval_loss": 0.03989905118942261,
+      "eval_precision": 0.9932203389830508,
+      "eval_recall": 0.9881956155143339,
+      "eval_runtime": 0.6094,
+      "eval_samples_per_second": 1965.953,
+      "eval_steps_per_second": 31.18,
+      "step": 450
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 450,
+  "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": 947199814926336.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-450/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fae391e1f563e832733b46ef6dfc1f12a972ce573467d55324c60253208dcb0
+size 5304

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
+  "_num_labels": 2,
+  "architectures": [
+    "MPNetForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "opposed",
+    "1": "supportive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "opposed": 0,
+    "supportive": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "vocab_size": 30527
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e438e454c4ec8f2141b26d1139ec3aa39690b64abb1ebefd906b1c14d85e82ce
+size 437975200

runs/Dec02_20-07-43_r-cbpuschmann-sfautotrain-4tcl6nqj-12bcb-iodqw/events.out.tfevents.1733170064.r-cbpuschmann-sfautotrain-4tcl6nqj-12bcb-iodqw.238.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e60700e8ef30fae4fcb84367e3ad87047d59d4f2acb6a03de91092ae9ce21d9
-size 5165
+oid sha256:edf381263429ddb077f2d9de38e113777e21f79a8cba7c211eb72c1299fe7ed1
+size 10854

runs/Dec02_20-07-43_r-cbpuschmann-sfautotrain-4tcl6nqj-12bcb-iodqw/events.out.tfevents.1733170099.r-cbpuschmann-sfautotrain-4tcl6nqj-12bcb-iodqw.238.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15405e6229127b59f1f74b1da158460f7ff8d2092317287893e84a0ba249b47e
+size 607

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 +1,72 @@
+{
+  "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": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "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,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "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 sha256:9fae391e1f563e832733b46ef6dfc1f12a972ce573467d55324c60253208dcb0
+size 5304

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "klimacoder-v0-2-1/autotrain-data",
+    "model": "sentence-transformers/all-mpnet-base-v2",
+    "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": "klimacoder-v0-2-1",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "cbpuschmann",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}