Update model and tokenizer

logs/events.out.tfevents.1721998301.cce3337b9a02.157.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dec12f1e14dcab665e739c9a8b5e7f418d919443f31924ef9bf87c468267690c
+size 5959

logs/events.out.tfevents.1721998341.cce3337b9a02.157.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c56c6483aeaec3796fa21f527479a9b7ff495c24fcd9859bb4c965e294cf40
+size 10960

logs/events.out.tfevents.1722242538.1e3c4db5059c.468.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54fad8e73ebcd4ae24b5eac61e933fa35dc60aab708303bb645b25f8e81b212b
+size 10911

logs/events.out.tfevents.1722255318.6e17b7a5c46d.1118.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:026d0713a48d756068c1a43a64d74cb76e40900d3686a169ca3053a933b388cf
+size 10911

logs/events.out.tfevents.1722265698.47109c206b48.1457.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9901e2c5f1684bef148969cec93cb3cbca39a8124597da689f1ab88acd18411e
+size 9291

logs/events.out.tfevents.1722440330.c8b573fa0d84.1534.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08694e8b9a9f2e28e24008e7bf9b0e67a56a20f80e237796fda2955c25393065
+size 10911

logs/events.out.tfevents.1724249839.4d4c0a2e9def.239.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5a74aed3595453502e87bad53005515e26ae5a75078265ee05aa2d56148f70a
+size 6580

logs/events.out.tfevents.1724250323.4d4c0a2e9def.239.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6277e14ca9d24068087cc6be7f9f38e8d92386160927c5867b4f5056c2f595
+size 88

results/checkpoint-154/config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

results/checkpoint-154/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

results/checkpoint-154/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

results/checkpoint-154/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98f01ff5ce227ceb86297dcffc4b183939337de0f07d7c52948aca1b0412f659
+size 5176

results/checkpoint-231/config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

results/checkpoint-231/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:242e08e641133670e3f3f77271aab38bd00c2cf6eba322a96664d7a5182a276a
+size 438014016

results/checkpoint-231/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:655c478d59a9838f8c5e2bb07fbae8a6a9c7f8f8a74c8f183e11d1c63f04db30
+size 876143482

results/checkpoint-231/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bec10ad3b595f619b606a8f0dc5706764d6ac93461fd7df1cda7f924dfdef430
+size 13990

results/checkpoint-231/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6dc5d70ea6d95614d83cf3921988645c741697057908e15f26601c404024d6b
+size 1064

results/checkpoint-231/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

results/checkpoint-231/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

results/checkpoint-231/trainer_state.json

@@ -0,0 +1,194 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 231,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12987012987012986,
+      "grad_norm": 8.817961692810059,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 2.8591,
+      "step": 10
+    },
+    {
+      "epoch": 0.2597402597402597,
+      "grad_norm": 11.00772762298584,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.8562,
+      "step": 20
+    },
+    {
+      "epoch": 0.38961038961038963,
+      "grad_norm": 10.66635799407959,
+      "learning_rate": 3e-06,
+      "loss": 2.867,
+      "step": 30
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "grad_norm": 8.26025104522705,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.7538,
+      "step": 40
+    },
+    {
+      "epoch": 0.6493506493506493,
+      "grad_norm": 10.763989448547363,
+      "learning_rate": 5e-06,
+      "loss": 2.6737,
+      "step": 50
+    },
+    {
+      "epoch": 0.7792207792207793,
+      "grad_norm": 10.080073356628418,
+      "learning_rate": 6e-06,
+      "loss": 2.6648,
+      "step": 60
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 8.357165336608887,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 2.5777,
+      "step": 70
+    },
+    {
+      "epoch": 1.0389610389610389,
+      "grad_norm": 10.30080509185791,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.3947,
+      "step": 80
+    },
+    {
+      "epoch": 1.1688311688311688,
+      "grad_norm": 17.036989212036133,
+      "learning_rate": 9e-06,
+      "loss": 2.2674,
+      "step": 90
+    },
+    {
+      "epoch": 1.2987012987012987,
+      "grad_norm": 9.885930061340332,
+      "learning_rate": 1e-05,
+      "loss": 2.0075,
+      "step": 100
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 10.072978973388672,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 1.9707,
+      "step": 110
+    },
+    {
+      "epoch": 1.5584415584415585,
+      "grad_norm": 10.257423400878906,
+      "learning_rate": 1.2e-05,
+      "loss": 1.67,
+      "step": 120
+    },
+    {
+      "epoch": 1.6883116883116882,
+      "grad_norm": 7.1921820640563965,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 1.5383,
+      "step": 130
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 8.42944049835205,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 1.5019,
+      "step": 140
+    },
+    {
+      "epoch": 1.948051948051948,
+      "grad_norm": 8.962895393371582,
+      "learning_rate": 1.5e-05,
+      "loss": 1.0832,
+      "step": 150
+    },
+    {
+      "epoch": 2.0779220779220777,
+      "grad_norm": 12.685582160949707,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.0589,
+      "step": 160
+    },
+    {
+      "epoch": 2.207792207792208,
+      "grad_norm": 7.99977445602417,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 1.0717,
+      "step": 170
+    },
+    {
+      "epoch": 2.3376623376623376,
+      "grad_norm": 4.187084197998047,
+      "learning_rate": 1.8e-05,
+      "loss": 1.0521,
+      "step": 180
+    },
+    {
+      "epoch": 2.4675324675324677,
+      "grad_norm": 6.426929950714111,
+      "learning_rate": 1.9e-05,
+      "loss": 0.9361,
+      "step": 190
+    },
+    {
+      "epoch": 2.5974025974025974,
+      "grad_norm": 4.999221324920654,
+      "learning_rate": 2e-05,
+      "loss": 0.7682,
+      "step": 200
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 3.239588975906372,
+      "learning_rate": 2.1e-05,
+      "loss": 0.4877,
+      "step": 210
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 16.341793060302734,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.603,
+      "step": 220
+    },
+    {
+      "epoch": 2.987012987012987,
+      "grad_norm": 4.9825520515441895,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 0.7032,
+      "step": 230
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 231,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 42464352759840.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

results/checkpoint-231/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e4c37110bf7f623eb276fdd089d0d230ba93456284e868edf869ade524c60e
+size 5176

results/checkpoint-77/config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

results/checkpoint-77/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0f91e5e27cfcddb763330f07153dfe8e6b2b29048246a723d48b1f83372a0ae
+size 438014016

results/checkpoint-77/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8779a247fb1f3be014745445cca82461dc457411d8c0e46d8401fcf1445f292b
+size 876143482

results/checkpoint-77/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991e09878f55fa62f5b1e691ca0b7da7c6f66c1f1c1e27b8dba8799c75bbd3a5
+size 13990

results/checkpoint-77/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99e104b2e854a3f8f053156570c80d8f729d2ea1b42d3d5e084801ce63d543e9
+size 1064

results/checkpoint-77/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

results/checkpoint-77/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

results/checkpoint-77/trainer_state.json

@@ -0,0 +1,92 @@
+{
+  "best_metric": 2.8195712566375732,
+  "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/text2excel/results/checkpoint-77",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 77,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12987012987012986,
+      "grad_norm": 10.064971923828125,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 3.0792,
+      "step": 10
+    },
+    {
+      "epoch": 0.2597402597402597,
+      "grad_norm": 11.230113983154297,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 3.0515,
+      "step": 20
+    },
+    {
+      "epoch": 0.38961038961038963,
+      "grad_norm": 12.046746253967285,
+      "learning_rate": 3e-06,
+      "loss": 3.015,
+      "step": 30
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "grad_norm": 9.873001098632812,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.8636,
+      "step": 40
+    },
+    {
+      "epoch": 0.6493506493506493,
+      "grad_norm": 13.206339836120605,
+      "learning_rate": 5e-06,
+      "loss": 2.7343,
+      "step": 50
+    },
+    {
+      "epoch": 0.7792207792207793,
+      "grad_norm": 10.480327606201172,
+      "learning_rate": 6e-06,
+      "loss": 2.7141,
+      "step": 60
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 8.450092315673828,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 2.58,
+      "step": 70
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.27450980392156865,
+      "eval_f1": 0.2746872504657971,
+      "eval_loss": 2.8195712566375732,
+      "eval_runtime": 24.9461,
+      "eval_samples_per_second": 6.133,
+      "eval_steps_per_second": 0.802,
+      "step": 77
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 231,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 14154784253280.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

results/checkpoint-77/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98f01ff5ce227ceb86297dcffc4b183939337de0f07d7c52948aca1b0412f659
+size 5176

tf_checkpoints/config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/Colab Notebooks/text2excel/mod_iter/t2e_cat_class_model0.1",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

tf_checkpoints/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77675ef8a83caf48e9a5d740375b7916a6326cef07b893d9ccab059386ec71fb
+size 438014016