Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: FacebookAI/roberta-base
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.6081525683403015
+
+f1_macro: 0.7293016589919367
+
+f1_micro: 0.7567567567567568
+
+f1_weighted: 0.7525753769969824
+
+precision_macro: 0.7459781321674904
+
+precision_micro: 0.7567567567567568
+
+precision_weighted: 0.7607241180619724
+
+recall_macro: 0.727181992488115
+
+recall_micro: 0.7567567567567568
+
+recall_weighted: 0.7567567567567568
+
+accuracy: 0.7567567567567568

checkpoint-500/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "_num_labels": 3,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 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": "4.43.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a5aa8ff6a507964120c4c97aaab82d2790c755924c4738d826c0920e1b5446b
+size 498615900

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6da33b32d352781be988c07f8344a4e8e5d19cd1195db3243807e0c956b05a2
+size 997351674

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:367b28d280931a703605ee8ee940940d8ea52024c8da75f917a462db2a14b170
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54c133e7e2d9c3eba5443128ed31a095ddedda08531ab3529dc1ebcbbdb9546f
+size 1064

checkpoint-500/trainer_state.json

@@ -0,0 +1,365 @@
+{
+  "best_metric": 0.6081525683403015,
+  "best_model_checkpoint": "autotrain-cwa7t-r6nu7/checkpoint-500",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.048,
+      "grad_norm": 5.120242118835449,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.077,
+      "step": 12
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 3.48054838180542,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 1.0941,
+      "step": 24
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 4.692188262939453,
+      "learning_rate": 1.44e-05,
+      "loss": 1.0877,
+      "step": 36
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 4.942972183227539,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 1.0566,
+      "step": 48
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 10.25078296661377,
+      "learning_rate": 2.36e-05,
+      "loss": 0.9183,
+      "step": 60
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 25.465534210205078,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.9146,
+      "step": 72
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 21.620311737060547,
+      "learning_rate": 3.2800000000000004e-05,
+      "loss": 0.8352,
+      "step": 84
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 12.405364036560059,
+      "learning_rate": 3.76e-05,
+      "loss": 0.8715,
+      "step": 96
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 20.498157501220703,
+      "learning_rate": 4.24e-05,
+      "loss": 0.7661,
+      "step": 108
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 14.002096176147461,
+      "learning_rate": 4.72e-05,
+      "loss": 0.6987,
+      "step": 120
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 15.950400352478027,
+      "learning_rate": 4.977777777777778e-05,
+      "loss": 0.7478,
+      "step": 132
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 14.89918327331543,
+      "learning_rate": 4.928888888888889e-05,
+      "loss": 0.8167,
+      "step": 144
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 21.52458381652832,
+      "learning_rate": 4.875555555555556e-05,
+      "loss": 0.8677,
+      "step": 156
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 9.06266975402832,
+      "learning_rate": 4.8222222222222225e-05,
+      "loss": 0.7637,
+      "step": 168
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 17.687030792236328,
+      "learning_rate": 4.768888888888889e-05,
+      "loss": 0.7588,
+      "step": 180
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 18.937341690063477,
+      "learning_rate": 4.715555555555556e-05,
+      "loss": 0.7809,
+      "step": 192
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 20.595829010009766,
+      "learning_rate": 4.662222222222222e-05,
+      "loss": 0.6525,
+      "step": 204
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 14.021669387817383,
+      "learning_rate": 4.608888888888889e-05,
+      "loss": 0.7512,
+      "step": 216
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 17.159658432006836,
+      "learning_rate": 4.555555555555556e-05,
+      "loss": 0.6444,
+      "step": 228
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 15.096858978271484,
+      "learning_rate": 4.502222222222223e-05,
+      "loss": 0.7502,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7367367367367368,
+      "eval_f1_macro": 0.6780399587593059,
+      "eval_f1_micro": 0.7367367367367368,
+      "eval_f1_weighted": 0.7159182064227351,
+      "eval_loss": 0.7116303443908691,
+      "eval_precision_macro": 0.7407168006456986,
+      "eval_precision_micro": 0.7367367367367368,
+      "eval_precision_weighted": 0.738750739597193,
+      "eval_recall_macro": 0.6747808186254532,
+      "eval_recall_micro": 0.7367367367367368,
+      "eval_recall_weighted": 0.7367367367367368,
+      "eval_runtime": 1.2649,
+      "eval_samples_per_second": 789.799,
+      "eval_steps_per_second": 25.299,
+      "step": 250
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 3.268965244293213,
+      "learning_rate": 4.448888888888889e-05,
+      "loss": 0.6109,
+      "step": 252
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 9.524105072021484,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6676,
+      "step": 264
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 13.357897758483887,
+      "learning_rate": 4.346666666666667e-05,
+      "loss": 0.6534,
+      "step": 276
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 12.989001274108887,
+      "learning_rate": 4.293333333333334e-05,
+      "loss": 0.5564,
+      "step": 288
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 13.040504455566406,
+      "learning_rate": 4.24e-05,
+      "loss": 0.5432,
+      "step": 300
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 27.441036224365234,
+      "learning_rate": 4.186666666666667e-05,
+      "loss": 0.5495,
+      "step": 312
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 12.519679069519043,
+      "learning_rate": 4.133333333333333e-05,
+      "loss": 0.548,
+      "step": 324
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 19.905864715576172,
+      "learning_rate": 4.08e-05,
+      "loss": 0.7036,
+      "step": 336
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 19.19709014892578,
+      "learning_rate": 4.026666666666667e-05,
+      "loss": 0.6243,
+      "step": 348
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 25.307151794433594,
+      "learning_rate": 3.9733333333333335e-05,
+      "loss": 0.5592,
+      "step": 360
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 12.860663414001465,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 0.5251,
+      "step": 372
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 14.503999710083008,
+      "learning_rate": 3.866666666666667e-05,
+      "loss": 0.5004,
+      "step": 384
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 16.512439727783203,
+      "learning_rate": 3.8133333333333336e-05,
+      "loss": 0.5418,
+      "step": 396
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 10.380609512329102,
+      "learning_rate": 3.76e-05,
+      "loss": 0.6202,
+      "step": 408
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 14.396175384521484,
+      "learning_rate": 3.706666666666667e-05,
+      "loss": 0.6095,
+      "step": 420
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 15.407332420349121,
+      "learning_rate": 3.653333333333334e-05,
+      "loss": 0.6155,
+      "step": 432
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 21.06899642944336,
+      "learning_rate": 3.6e-05,
+      "loss": 0.5009,
+      "step": 444
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 9.709734916687012,
+      "learning_rate": 3.546666666666667e-05,
+      "loss": 0.4664,
+      "step": 456
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 30.69609260559082,
+      "learning_rate": 3.493333333333333e-05,
+      "loss": 0.6268,
+      "step": 468
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 10.711507797241211,
+      "learning_rate": 3.4399999999999996e-05,
+      "loss": 0.5064,
+      "step": 480
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 10.850369453430176,
+      "learning_rate": 3.3866666666666665e-05,
+      "loss": 0.5403,
+      "step": 492
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7567567567567568,
+      "eval_f1_macro": 0.7293016589919367,
+      "eval_f1_micro": 0.7567567567567568,
+      "eval_f1_weighted": 0.7525753769969824,
+      "eval_loss": 0.6081525683403015,
+      "eval_precision_macro": 0.7459781321674904,
+      "eval_precision_micro": 0.7567567567567568,
+      "eval_precision_weighted": 0.7607241180619724,
+      "eval_recall_macro": 0.727181992488115,
+      "eval_recall_micro": 0.7567567567567568,
+      "eval_recall_weighted": 0.7567567567567568,
+      "eval_runtime": 1.2636,
+      "eval_samples_per_second": 790.605,
+      "eval_steps_per_second": 25.325,
+      "step": 500
+    }
+  ],
+  "logging_steps": 12,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 525305938493952.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69dc0c7701ff0b516e1fd3fddf224fa8633958e13e996e7d91698a9d753b538b
+size 5240

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "_num_labels": 3,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 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": "4.43.1",
+  "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 sha256:1a5aa8ff6a507964120c4c97aaab82d2790c755924c4738d826c0920e1b5446b
+size 498615900

runs/Aug02_22-49-19_r-adamlucek-autotrain-advanced-roberta-llama-pplv1kej-ae6ff-jpn/events.out.tfevents.1722638960.r-adamlucek-autotrain-advanced-roberta-llama-pplv1kej-ae6ff-jpn.74.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90e7c2c406a89c4f05ec5cd2ae3ab75af6465d635b5db26cfce582cfef3aae7c
-size 5155
+oid sha256:c1893be209807ef2d2d6bfc9a719e1cfa207aab5986143e68cfc43a42ff76a29
+size 31578

runs/Aug02_22-49-19_r-adamlucek-autotrain-advanced-roberta-llama-pplv1kej-ae6ff-jpn/events.out.tfevents.1722639081.r-adamlucek-autotrain-advanced-roberta-llama-pplv1kej-ae6ff-jpn.74.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f6e13c56609e3f098c402493bdb85dec592dcaa6875526d0b69abe738a737e9
+size 921

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

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": 512,
+  "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 sha256:69dc0c7701ff0b516e1fd3fddf224fa8633958e13e996e7d91698a9d753b538b
+size 5240

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-cwa7t-r6nu7/autotrain-data",
+    "model": "FacebookAI/roberta-base",
+    "lr": 5e-05,
+    "epochs": 5,
+    "max_seq_length": 128,
+    "batch_size": 16,
+    "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-cwa7t-r6nu7",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "AdamLucek",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}