Upload folder using huggingface_hub

all_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 5.0,
+    "eval_f1": 0.8386706976482636,
+    "eval_loss": 0.007343434263020754,
+    "eval_precision": 0.8440755855767851,
+    "eval_recall": 0.8356998695176805,
+    "eval_runtime": 53.7722,
+    "eval_samples_per_second": 92.985,
+    "eval_steps_per_second": 2.92
+}

checkpoint-2225/config.json

@@ -0,0 +1,51 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "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": "O",
+    "1": "B-LOC",
+    "2": "B-MISC",
+    "3": "B-ORG",
+    "4": "B-PER",
+    "5": "B-TIME",
+    "6": "I-LOC",
+    "7": "I-MISC",
+    "8": "I-ORG",
+    "9": "I-PER",
+    "10": "I-TIME"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 1,
+    "B-MISC": 2,
+    "B-ORG": 3,
+    "B-PER": 4,
+    "B-TIME": 5,
+    "I-LOC": 6,
+    "I-MISC": 7,
+    "I-ORG": 8,
+    "I-PER": 9,
+    "I-TIME": 10,
+    "O": 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": "4.55.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

checkpoint-2225/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:357f7a097e4d3d1bc7657ed9a884df187de76c14dc8fdd7efc3655d42bc253f9
+size 430935892

checkpoint-2225/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c1ddabcf825e71defdbc511dfd3ad0c5fe5e28f32fc0f5e1053c4085e8e0a7
+size 861994699

checkpoint-2225/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88b6546b442b94ec2c1b7558c7b90258c35682bdb1fc5619e5c40a84d3b42e7d
+size 14645

checkpoint-2225/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def9d791b01293610f2ec807babe891f2fe119b9a8c9e01a4a4609301d71eec2
+size 1465

checkpoint-2225/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-2225/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": false,
+  "extra_special_tokens": {},
+  "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]"
+}

checkpoint-2225/trainer_state.json

@@ -0,0 +1,126 @@
+{
+  "best_global_step": 890,
+  "best_metric": 0.01059602852910757,
+  "best_model_checkpoint": "projects/PetHarbor/abilation/model/checkpoint-890",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2225,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.8074838359489795,
+      "eval_loss": 0.012898492626845837,
+      "eval_precision": 0.784729522262996,
+      "eval_recall": 0.8343749166767597,
+      "eval_runtime": 16.7545,
+      "eval_samples_per_second": 98.899,
+      "eval_steps_per_second": 3.104,
+      "step": 445
+    },
+    {
+      "epoch": 1.1235955056179776,
+      "grad_norm": 0.22999469935894012,
+      "learning_rate": 4.994393258426966e-05,
+      "loss": 0.0746,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.8716156719691427,
+      "eval_loss": 0.01059602852910757,
+      "eval_precision": 0.8564399929788535,
+      "eval_recall": 0.8888046385535433,
+      "eval_runtime": 17.4323,
+      "eval_samples_per_second": 95.054,
+      "eval_steps_per_second": 2.983,
+      "step": 890
+    },
+    {
+      "epoch": 2.247191011235955,
+      "grad_norm": 0.7581475377082825,
+      "learning_rate": 4.988775280898877e-05,
+      "loss": 0.0104,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.8913446050377285,
+      "eval_loss": 0.013407337479293346,
+      "eval_precision": 0.9226423853601201,
+      "eval_recall": 0.877210010380415,
+      "eval_runtime": 17.5608,
+      "eval_samples_per_second": 94.358,
+      "eval_steps_per_second": 2.961,
+      "step": 1335
+    },
+    {
+      "epoch": 3.370786516853933,
+      "grad_norm": 0.10075754672288895,
+      "learning_rate": 4.983157303370787e-05,
+      "loss": 0.0047,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.8976870931487725,
+      "eval_loss": 0.013252191245555878,
+      "eval_precision": 0.8843595176063854,
+      "eval_recall": 0.9122072821208133,
+      "eval_runtime": 17.6962,
+      "eval_samples_per_second": 93.636,
+      "eval_steps_per_second": 2.938,
+      "step": 1780
+    },
+    {
+      "epoch": 4.49438202247191,
+      "grad_norm": 0.009224419482052326,
+      "learning_rate": 4.9775393258426966e-05,
+      "loss": 0.0037,
+      "step": 2000
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.8902396967555823,
+      "eval_loss": 0.014422020874917507,
+      "eval_precision": 0.8674601590060164,
+      "eval_recall": 0.9241467187184571,
+      "eval_runtime": 17.4028,
+      "eval_samples_per_second": 95.215,
+      "eval_steps_per_second": 2.988,
+      "step": 2225
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 445000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1000,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 3
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.858493744357376e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2225/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa8c24a0f283f6584293d8d21bbaa14ea9d8d54fb0aa153818517a4f7e9a034
+size 5713

eval_report.csv

@@ -0,0 +1,9 @@
+,precision,recall,f1-score,support
+LOC,0.4318181818181818,0.7169811320754716,0.5390070921985816,53.0
+MISC,0.8416666666666667,0.9017857142857143,0.8706896551724138,112.0
+ORG,0.7716049382716049,0.7668711656441718,0.7692307692307693,163.0
+PER,0.8552354181307098,0.8812454742939899,0.8680456490727533,1381.0
+TIME,0.8652751423149905,0.8769230769230769,0.8710601719197707,520.0
+micro avg,0.8349137931034483,0.8689995513683266,0.8516157397230161,2229.0
+macro avg,0.7531200694404306,0.8287613126444849,0.7836066675188578,2229.0
+weighted avg,0.8407123470989715,0.8689995513683266,0.8538320158897279,2229.0

test_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 5.0,
+    "eval_f1": 0.8386706976482636,
+    "eval_loss": 0.007343434263020754,
+    "eval_precision": 0.8440755855767851,
+    "eval_recall": 0.8356998695176805,
+    "eval_runtime": 53.7722,
+    "eval_samples_per_second": 92.985,
+    "eval_steps_per_second": 2.92
+}