Upload ESG Topic Classifier (Macro-F1: 0.7070)

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

checkpoint-116/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

checkpoint-116/config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "E",
+    "1": "Financing",
+    "2": "G",
+    "3": "Non-ESG",
+    "4": "Policy",
+    "5": "S"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "E": 0,
+    "Financing": 1,
+    "G": 2,
+    "Non-ESG": 3,
+    "Policy": 4,
+    "S": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "PhobertTokenizer",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

checkpoint-116/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b3e053f61dd4786efe1c9b113ad1fb96a5e41596e01c4bee0ce8c21bfe23c32
+size 540035688

checkpoint-116/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc94cb46a5c31485a8ab15020878e9969827526c2ef770204faefccdf017fe45
+size 1080194443

checkpoint-116/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58996ea1d8a1f198adcd3da72f90a4dfc68d66d68449c4b9a0d9cec96efff5dc
+size 14645

checkpoint-116/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c120f066577ac6f1d3a84c1f5bff39b5f7f686ca8e41f2340190174f9955bf
+size 1383

checkpoint-116/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d526fe96d7dc816b0b1794909aea534792360c28513eda316e1bc4442e19b40e
+size 1465

checkpoint-116/special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-116/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-116/trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_global_step": 116,
+  "best_metric": 0.7213724329692548,
+  "best_model_checkpoint": "artifacts/topic_model/checkpoint-116",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 116,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 3.192338466644287,
+      "learning_rate": 1.9036697247706422e-05,
+      "loss": 1.7422,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6614173228346457,
+      "eval_loss": 1.518955945968628,
+      "eval_macro_f1": 0.5115357643035457,
+      "eval_runtime": 0.2774,
+      "eval_samples_per_second": 457.755,
+      "eval_steps_per_second": 28.835,
+      "step": 58
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 6.166723251342773,
+      "learning_rate": 1.674311926605505e-05,
+      "loss": 1.3965,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7874015748031497,
+      "eval_loss": 1.076490879058838,
+      "eval_macro_f1": 0.7213724329692548,
+      "eval_runtime": 0.2838,
+      "eval_samples_per_second": 447.547,
+      "eval_steps_per_second": 28.192,
+      "step": 116
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 464,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "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": 146974386052584.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-116/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b7800b938f17e70d00e0722489091060ea5af2edf3fe49031b99426c345276
+size 5841

checkpoint-232/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

checkpoint-232/config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "E",
+    "1": "Financing",
+    "2": "G",
+    "3": "Non-ESG",
+    "4": "Policy",
+    "5": "S"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "E": 0,
+    "Financing": 1,
+    "G": 2,
+    "Non-ESG": 3,
+    "Policy": 4,
+    "S": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "PhobertTokenizer",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

checkpoint-232/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e706ed0d492f17f2e4a6eaa5a7b321625c079eb1f665e73413b6ba4448ad3484
+size 540035688

checkpoint-232/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae6a292c80c8bdf65a07ae62c3e5aa6723ac7f20497a60bc7a48fdd086e95e92
+size 1080194443

checkpoint-232/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b9df7a5fc0e12369001d30795c3624c8074d72889945ba6f8a0a9206bda0692
+size 14645

checkpoint-232/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e69be38e373a375882c9ee1df046473b9e4a91ac8a69a76d9fcf6415e099ceba
+size 1383

checkpoint-232/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19b44d4cb8647f6a444e931a0ee30878ebe71a4b21c895da4e832ce9d02e748d
+size 1465

checkpoint-232/special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-232/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-232/trainer_state.json

@@ -0,0 +1,111 @@
+{
+  "best_global_step": 116,
+  "best_metric": 0.7213724329692548,
+  "best_model_checkpoint": "artifacts/topic_model/checkpoint-116",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 232,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 3.192338466644287,
+      "learning_rate": 1.9036697247706422e-05,
+      "loss": 1.7422,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6614173228346457,
+      "eval_loss": 1.518955945968628,
+      "eval_macro_f1": 0.5115357643035457,
+      "eval_runtime": 0.2774,
+      "eval_samples_per_second": 457.755,
+      "eval_steps_per_second": 28.835,
+      "step": 58
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 6.166723251342773,
+      "learning_rate": 1.674311926605505e-05,
+      "loss": 1.3965,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7874015748031497,
+      "eval_loss": 1.076490879058838,
+      "eval_macro_f1": 0.7213724329692548,
+      "eval_runtime": 0.2838,
+      "eval_samples_per_second": 447.547,
+      "eval_steps_per_second": 28.192,
+      "step": 116
+    },
+    {
+      "epoch": 2.586206896551724,
+      "grad_norm": 4.974067687988281,
+      "learning_rate": 1.4449541284403672e-05,
+      "loss": 1.0328,
+      "step": 150
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7716535433070866,
+      "eval_loss": 0.9624134302139282,
+      "eval_macro_f1": 0.6831862756284045,
+      "eval_runtime": 0.277,
+      "eval_samples_per_second": 458.418,
+      "eval_steps_per_second": 28.877,
+      "step": 174
+    },
+    {
+      "epoch": 3.4482758620689653,
+      "grad_norm": 5.769896984100342,
+      "learning_rate": 1.2155963302752293e-05,
+      "loss": 0.7568,
+      "step": 200
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8110236220472441,
+      "eval_loss": 0.754206120967865,
+      "eval_macro_f1": 0.7186752131258979,
+      "eval_runtime": 0.2791,
+      "eval_samples_per_second": 455.043,
+      "eval_steps_per_second": 28.664,
+      "step": 232
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 464,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 2
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 296034207668856.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-232/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b7800b938f17e70d00e0722489091060ea5af2edf3fe49031b99426c345276
+size 5841

config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "E",
+    "1": "Financing",
+    "2": "G",
+    "3": "Non-ESG",
+    "4": "Policy",
+    "5": "S"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "E": 0,
+    "Financing": 1,
+    "G": 2,
+    "Non-ESG": 3,
+    "Policy": 4,
+    "S": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "PhobertTokenizer",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b3e053f61dd4786efe1c9b113ad1fb96a5e41596e01c4bee0ce8c21bfe23c32
+size 540035688

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b7800b938f17e70d00e0722489091060ea5af2edf3fe49031b99426c345276
+size 5841

training_meta.json

@@ -0,0 +1,36 @@
+{
+  "model_name": "vinai/phobert-base-v2",
+  "max_length": 256,
+  "seed": 42,
+  "lr": 2e-05,
+  "epochs": 8,
+  "batch_size": 16,
+  "weight_decay": 0.01,
+  "warmup_ratio": 0.06,
+  "grad_clip": 1.0,
+  "label2id": {
+    "E": 0,
+    "Financing": 1,
+    "G": 2,
+    "Non-ESG": 3,
+    "Policy": 4,
+    "S": 5
+  },
+  "id2label": {
+    "0": "E",
+    "1": "Financing",
+    "2": "G",
+    "3": "Non-ESG",
+    "4": "Policy",
+    "5": "S"
+  },
+  "device": "cuda",
+  "class_weights": {
+    "E": 2.0625388622283936,
+    "Financing": 1.3524844646453857,
+    "G": 0.41045546531677246,
+    "Non-ESG": 0.2110014110803604,
+    "Policy": 1.5000282526016235,
+    "S": 0.46349185705184937
+  }
+}