Upload folder using huggingface_hub

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "SAVSNET/PetBERT",
+  "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": "4.49.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d787fa373e2a20405729f5f8fd20634ed7d89854401f2e9f76598c6d8a2838fa
+size 430935892

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34d1a9d1c56d780ee32cc5ea9d148c155eab84dcb4f470f18cded1843f567057
+size 861991482

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3febb3b3f425e0c608f3cbfd4dada46dff84a0ab4e6f0d5af3509635b3625b1d
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f92cf41b26baf29a9e9859022afbcc34c3cf250a34ff0d0481210b689244adb
+size 1064

trainer_state.json

@@ -0,0 +1,176 @@
+{
+  "best_metric": 0.00631814356893301,
+  "best_model_checkpoint": "projects/PetEVAL/new_splits/1.annonymisation/models/PetBERT/checkpoint-1720",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 2752,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_f1": 0.026656853558445003,
+      "eval_loss": 2.3131918907165527,
+      "eval_precision": 0.0902669662721398,
+      "eval_recall": 0.08842821455048296,
+      "eval_runtime": 12.0984,
+      "eval_samples_per_second": 136.96,
+      "eval_steps_per_second": 4.298,
+      "step": 0
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.8744901409239865,
+      "eval_loss": 0.00956493616104126,
+      "eval_precision": 0.924093580277631,
+      "eval_recall": 0.8507210610221329,
+      "eval_runtime": 13.1724,
+      "eval_samples_per_second": 125.793,
+      "eval_steps_per_second": 3.948,
+      "step": 344
+    },
+    {
+      "epoch": 1.4534883720930232,
+      "grad_norm": 0.13440628349781036,
+      "learning_rate": 4.992732558139535e-05,
+      "loss": 0.0512,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.9214380148383657,
+      "eval_loss": 0.007954263128340244,
+      "eval_precision": 0.9385945722545549,
+      "eval_recall": 0.906823887476179,
+      "eval_runtime": 13.6821,
+      "eval_samples_per_second": 121.107,
+      "eval_steps_per_second": 3.801,
+      "step": 688
+    },
+    {
+      "epoch": 2.9069767441860463,
+      "grad_norm": 0.5610215067863464,
+      "learning_rate": 4.98546511627907e-05,
+      "loss": 0.0031,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.9389481710629304,
+      "eval_loss": 0.010447051376104355,
+      "eval_precision": 0.9747087173167618,
+      "eval_recall": 0.9103769387756578,
+      "eval_runtime": 13.7684,
+      "eval_samples_per_second": 120.348,
+      "eval_steps_per_second": 3.777,
+      "step": 1032
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.9195094134396675,
+      "eval_loss": 0.008201838470995426,
+      "eval_precision": 0.9279236120830319,
+      "eval_recall": 0.9142686302660742,
+      "eval_runtime": 13.9313,
+      "eval_samples_per_second": 118.941,
+      "eval_steps_per_second": 3.733,
+      "step": 1376
+    },
+    {
+      "epoch": 4.3604651162790695,
+      "grad_norm": 0.013739518821239471,
+      "learning_rate": 4.978197674418605e-05,
+      "loss": 0.0019,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.94402458580998,
+      "eval_loss": 0.00631814356893301,
+      "eval_precision": 0.9511782836087214,
+      "eval_recall": 0.9389296462653962,
+      "eval_runtime": 15.0907,
+      "eval_samples_per_second": 109.803,
+      "eval_steps_per_second": 3.446,
+      "step": 1720
+    },
+    {
+      "epoch": 5.813953488372093,
+      "grad_norm": 0.0020324508659541607,
+      "learning_rate": 4.97093023255814e-05,
+      "loss": 0.001,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_f1": 0.9457105386380245,
+      "eval_loss": 0.007111889310181141,
+      "eval_precision": 0.9460455625427084,
+      "eval_recall": 0.9459687123326699,
+      "eval_runtime": 14.2199,
+      "eval_samples_per_second": 116.527,
+      "eval_steps_per_second": 3.657,
+      "step": 2064
+    },
+    {
+      "epoch": 7.0,
+      "eval_f1": 0.9223422806557113,
+      "eval_loss": 0.011202913708984852,
+      "eval_precision": 0.9596132263722048,
+      "eval_recall": 0.893850072449603,
+      "eval_runtime": 14.2319,
+      "eval_samples_per_second": 116.429,
+      "eval_steps_per_second": 3.654,
+      "step": 2408
+    },
+    {
+      "epoch": 7.267441860465116,
+      "grad_norm": 0.013395079411566257,
+      "learning_rate": 4.963662790697674e-05,
+      "loss": 0.0011,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_f1": 0.9369894102286561,
+      "eval_loss": 0.007823295891284943,
+      "eval_precision": 0.93213302687968,
+      "eval_recall": 0.9433066007345208,
+      "eval_runtime": 15.2166,
+      "eval_samples_per_second": 108.894,
+      "eval_steps_per_second": 3.417,
+      "step": 2752
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 344000,
+  "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": 2.2993895044079616e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5d7a6d63c5d8abe86bc27987fca8ab5373350831d6ac76610b2f6f020217a56
+size 5304