Upload folder using huggingface_hub

README.md

@@ -0,0 +1,35 @@
+
+---
+tags:
+- autotrain
+- text-classification
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.6056355834007263
+
+f1_macro: 0.6670922231156776
+
+f1_micro: 0.7154326494201606
+
+f1_weighted: 0.7146269676505387
+
+precision_macro: 0.6692782206543363
+
+precision_micro: 0.7154326494201606
+
+precision_weighted: 0.7189916311836655
+
+recall_macro: 0.6719451360857057
+
+recall_micro: 0.7154326494201606
+
+recall_weighted: 0.7154326494201606
+
+accuracy: 0.7154326494201606

checkpoint-654/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment-latest",
+  "_num_labels": 3,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1",
+    "2": "2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2
+  },
+  "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": "4.41.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-654/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d984d5460827b656419f820f3b72277fdc52745debd49560ece7174d3f1af2e
+size 498615900

checkpoint-654/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb429a870cd9e3abcb33035075b47e9845469245b3a017c5224a3ad1353602f
+size 997346042

checkpoint-654/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d97084fa3e100b473765cc3ae291c883e2ad5abdd0b52d5aa7af09510ab6ec5f
+size 13990

checkpoint-654/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1430b6f5fb996089c04641a155d001cb4e583b9fabf4b301e1627438e60274f1
+size 1064

checkpoint-654/trainer_state.json

@@ -0,0 +1,242 @@
+{
+  "best_metric": 0.6056355834007263,
+  "best_model_checkpoint": "RoBERTaOPT3Labels/checkpoint-654",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 654,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0382262996941896,
+      "grad_norm": 8.683685302734375,
+      "learning_rate": 6.345177664974619e-06,
+      "loss": 1.667,
+      "step": 25
+    },
+    {
+      "epoch": 0.0764525993883792,
+      "grad_norm": 15.70411491394043,
+      "learning_rate": 1.2690355329949238e-05,
+      "loss": 0.7887,
+      "step": 50
+    },
+    {
+      "epoch": 0.11467889908256881,
+      "grad_norm": 14.142353057861328,
+      "learning_rate": 1.9035532994923858e-05,
+      "loss": 0.7685,
+      "step": 75
+    },
+    {
+      "epoch": 0.1529051987767584,
+      "grad_norm": 14.103597640991211,
+      "learning_rate": 2.5380710659898476e-05,
+      "loss": 0.6954,
+      "step": 100
+    },
+    {
+      "epoch": 0.191131498470948,
+      "grad_norm": 14.68567180633545,
+      "learning_rate": 3.17258883248731e-05,
+      "loss": 0.6102,
+      "step": 125
+    },
+    {
+      "epoch": 0.22935779816513763,
+      "grad_norm": 12.977874755859375,
+      "learning_rate": 3.8071065989847716e-05,
+      "loss": 0.7284,
+      "step": 150
+    },
+    {
+      "epoch": 0.26758409785932724,
+      "grad_norm": 14.094762802124023,
+      "learning_rate": 4.4416243654822335e-05,
+      "loss": 0.7859,
+      "step": 175
+    },
+    {
+      "epoch": 0.3058103975535168,
+      "grad_norm": 41.655555725097656,
+      "learning_rate": 4.991501416430595e-05,
+      "loss": 0.6049,
+      "step": 200
+    },
+    {
+      "epoch": 0.3440366972477064,
+      "grad_norm": 18.565250396728516,
+      "learning_rate": 4.920679886685552e-05,
+      "loss": 0.6832,
+      "step": 225
+    },
+    {
+      "epoch": 0.382262996941896,
+      "grad_norm": 14.68687629699707,
+      "learning_rate": 4.84985835694051e-05,
+      "loss": 0.6881,
+      "step": 250
+    },
+    {
+      "epoch": 0.42048929663608564,
+      "grad_norm": 7.241730213165283,
+      "learning_rate": 4.7790368271954674e-05,
+      "loss": 0.7151,
+      "step": 275
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 25.538393020629883,
+      "learning_rate": 4.7082152974504253e-05,
+      "loss": 0.6776,
+      "step": 300
+    },
+    {
+      "epoch": 0.4969418960244648,
+      "grad_norm": 8.805389404296875,
+      "learning_rate": 4.6373937677053826e-05,
+      "loss": 0.6033,
+      "step": 325
+    },
+    {
+      "epoch": 0.5351681957186545,
+      "grad_norm": 18.852054595947266,
+      "learning_rate": 4.5665722379603405e-05,
+      "loss": 0.7381,
+      "step": 350
+    },
+    {
+      "epoch": 0.573394495412844,
+      "grad_norm": 8.220598220825195,
+      "learning_rate": 4.495750708215298e-05,
+      "loss": 0.7556,
+      "step": 375
+    },
+    {
+      "epoch": 0.6116207951070336,
+      "grad_norm": 8.244980812072754,
+      "learning_rate": 4.424929178470255e-05,
+      "loss": 0.5313,
+      "step": 400
+    },
+    {
+      "epoch": 0.6498470948012233,
+      "grad_norm": 9.83115005493164,
+      "learning_rate": 4.354107648725212e-05,
+      "loss": 0.6622,
+      "step": 425
+    },
+    {
+      "epoch": 0.6880733944954128,
+      "grad_norm": 7.324151992797852,
+      "learning_rate": 4.283286118980171e-05,
+      "loss": 0.6755,
+      "step": 450
+    },
+    {
+      "epoch": 0.7262996941896025,
+      "grad_norm": 7.738851070404053,
+      "learning_rate": 4.212464589235128e-05,
+      "loss": 0.7383,
+      "step": 475
+    },
+    {
+      "epoch": 0.764525993883792,
+      "grad_norm": 11.587554931640625,
+      "learning_rate": 4.141643059490085e-05,
+      "loss": 0.5745,
+      "step": 500
+    },
+    {
+      "epoch": 0.8027522935779816,
+      "grad_norm": 8.74025821685791,
+      "learning_rate": 4.0708215297450424e-05,
+      "loss": 0.6931,
+      "step": 525
+    },
+    {
+      "epoch": 0.8409785932721713,
+      "grad_norm": 35.72504806518555,
+      "learning_rate": 4e-05,
+      "loss": 0.6555,
+      "step": 550
+    },
+    {
+      "epoch": 0.8792048929663608,
+      "grad_norm": 11.218914985656738,
+      "learning_rate": 3.9291784702549576e-05,
+      "loss": 0.6068,
+      "step": 575
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 6.998708248138428,
+      "learning_rate": 3.8583569405099155e-05,
+      "loss": 0.5668,
+      "step": 600
+    },
+    {
+      "epoch": 0.9556574923547401,
+      "grad_norm": 45.22652816772461,
+      "learning_rate": 3.787535410764873e-05,
+      "loss": 0.7055,
+      "step": 625
+    },
+    {
+      "epoch": 0.9938837920489296,
+      "grad_norm": 4.196397304534912,
+      "learning_rate": 3.7167138810198306e-05,
+      "loss": 0.714,
+      "step": 650
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7154326494201606,
+      "eval_f1_macro": 0.6670922231156776,
+      "eval_f1_micro": 0.7154326494201606,
+      "eval_f1_weighted": 0.7146269676505387,
+      "eval_loss": 0.6056355834007263,
+      "eval_precision_macro": 0.6692782206543363,
+      "eval_precision_micro": 0.7154326494201606,
+      "eval_precision_weighted": 0.7189916311836655,
+      "eval_recall_macro": 0.6719451360857057,
+      "eval_recall_micro": 0.7154326494201606,
+      "eval_recall_weighted": 0.7154326494201606,
+      "eval_runtime": 156.1583,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 0.455,
+      "step": 654
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1962,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 344152350388224.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-654/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4979d4354fd4a7b9e36ada145ae7fb2c9bb0457f56e743edba720af86d5db04f
+size 5176

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment-latest",
+  "_num_labels": 3,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1",
+    "2": "2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2
+  },
+  "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": "4.41.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d984d5460827b656419f820f3b72277fdc52745debd49560ece7174d3f1af2e
+size 498615900

runs/May26_18-46-41_r-stepharn-roberta-opt-v2-gowaj610-24b33-mgxdt/events.out.tfevents.1716749202.r-stepharn-roberta-opt-v2-gowaj610-24b33-mgxdt.416.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44f91039250658ae2636bcf5f1a5dcfdf5649181c0cd36ae028cd269115b0dc1
-size 22776
+oid sha256:e9ab8f3024cc55c02d0c5406a2afc69c5715aa3845079f8f0c4310d09c96a66a
+size 24385

runs/May26_18-46-41_r-stepharn-roberta-opt-v2-gowaj610-24b33-mgxdt/events.out.tfevents.1716758478.r-stepharn-roberta-opt-v2-gowaj610-24b33-mgxdt.416.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74ea2c3d74dd75e1011cc301d1f6064703fe1e95c3f1c3e74a7079f23a816b33
+size 921

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4979d4354fd4a7b9e36ada145ae7fb2c9bb0457f56e743edba720af86d5db04f
+size 5176

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "RoBERTaOPT3Labels/autotrain-data",
+    "model": "cardiffnlp/twitter-roberta-base-sentiment-latest",
+    "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": "RoBERTaOPT3Labels",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "evaluation_strategy": "epoch",
+    "username": "StephArn",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}