Upload 12 files

checkpoint-138/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Not Relevant",
+    "1": "Least Relevant",
+    "2": "Highly Relevant",
+    "3": "Most Relevant"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Highly Relevant": 2,
+    "Least Relevant": 1,
+    "Most Relevant": 3,
+    "Not Relevant": 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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50105
+}

checkpoint-138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74587a09d22c3eca60e1cd8c3b27cd407fe7c678912d229697e06fa5e8a6bdc4
+size 498123784

checkpoint-138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8543425ad86385d895bcac0d832f19b39d868abb198be9dd506cf62071a89de
+size 656071115

checkpoint-138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e325eca5c1e1d677104d98d0f02888e44fdcd0b23b93cfe0589e6f0463ef927
+size 14645

checkpoint-138/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4712e6b2418df3f045bd21f132a4d18bee59b18a685eb8d67faa7c1913b1bc05
+size 1383

checkpoint-138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc16d56c1765b260f68aa1e0f274d2d4534e58b6b71833224e705880ef81d3bf
+size 1465

checkpoint-138/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-138/tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 64,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

checkpoint-138/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_global_step": 23,
+  "best_metric": 0.8660714285714286,
+  "best_model_checkpoint": ".\\finbert-ft-v3\\checkpoint-23",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 138,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8666666666666667,
+      "eval_f1": 0.8660714285714286,
+      "eval_loss": 0.4121950566768646,
+      "eval_precision": 0.9,
+      "eval_recall": 0.875,
+      "eval_runtime": 0.0699,
+      "eval_samples_per_second": 214.66,
+      "eval_steps_per_second": 28.621,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7333333333333333,
+      "eval_f1": 0.7222222222222221,
+      "eval_loss": 0.6659547090530396,
+      "eval_precision": 0.825,
+      "eval_recall": 0.75,
+      "eval_runtime": 0.0495,
+      "eval_samples_per_second": 302.768,
+      "eval_steps_per_second": 40.369,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7333333333333333,
+      "eval_f1": 0.7222222222222221,
+      "eval_loss": 1.1926629543304443,
+      "eval_precision": 0.825,
+      "eval_recall": 0.75,
+      "eval_runtime": 0.0478,
+      "eval_samples_per_second": 314.102,
+      "eval_steps_per_second": 41.88,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8,
+      "eval_f1": 0.7777777777777777,
+      "eval_loss": 0.7819080352783203,
+      "eval_precision": 0.8166666666666667,
+      "eval_recall": 0.7916666666666666,
+      "eval_runtime": 0.0488,
+      "eval_samples_per_second": 307.139,
+      "eval_steps_per_second": 40.952,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8666666666666667,
+      "eval_f1": 0.8531746031746031,
+      "eval_loss": 0.918350875377655,
+      "eval_precision": 0.8875,
+      "eval_recall": 0.875,
+      "eval_runtime": 0.0534,
+      "eval_samples_per_second": 280.969,
+      "eval_steps_per_second": 37.463,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8666666666666667,
+      "eval_f1": 0.8531746031746031,
+      "eval_loss": 0.9260435104370117,
+      "eval_precision": 0.8875,
+      "eval_recall": 0.875,
+      "eval_runtime": 0.0514,
+      "eval_samples_per_second": 291.852,
+      "eval_steps_per_second": 38.914,
+      "step": 138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 35915303983104.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a36d0132994a1bd7a59fe4db5a5c2981fe4747425b913034796fac386de924e
+size 5649