End of training

README.md

@@ -1,6 +1,4 @@
 ---
-license: apache-2.0
-base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +11,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ner-bert-ingredientstesting
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 9.6947
 
 ## Model description
 
@@ -40,7 +40,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 50
 - mixed_precision_training: Native AMP
 
 ### Training results

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "/kaggle/working/ner-bert-ingredientstesting",
   "architectures": [
     "BertForTokenClassification"
   ],

logs/events.out.tfevents.1705498568.ed78651fcb5b.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e03d099642d8c62eed1cd53da6fb61b861d281018436e51b3954e422d17a6500
+size 1717358

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a39fb56d4a6d853376c05edfa3d9c7f19663dde1fc7390f48f13c7ac53cae078
+oid sha256:dfb4fb1ece8a9c6c9217b4b1d2a851afb9bf4e9e25fed762c0956c70b2892ef6
 size 535667604

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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
+  }
 }

tokenizer_config.json

@@ -45,11 +45,18 @@
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
+  "max_length": 512,
   "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]"
 }

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9996631862579993,
+  "epoch": 1.0107780397440216,
   "eval_steps": 750,
-  "global_step": 742,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -16,14 +16,28 @@
       "train_runtime": 6114.1675,
       "train_samples_per_second": 15.538,
       "train_steps_per_second": 0.121
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 4.9989218328840974e-05,
+      "loss": 10.3965,
+      "step": 750
+    },
+    {
+      "epoch": 1.01,
+      "eval_loss": 9.694682121276855,
+      "eval_runtime": 84.6491,
+      "eval_samples_per_second": 59.067,
+      "eval_steps_per_second": 0.933,
+      "step": 750
     }
   ],
   "logging_steps": 750,
-  "max_steps": 742,
+  "max_steps": 37100,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 3.211629347340288e+16,
+  "total_flos": 3.246256078848e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5cdffc1d5610491dce8a2d5fba106c7daa7c5df5aa173ecccf1bf30d7a688e2
+oid sha256:6d8b2637195f6863cffd1bc8a94e43113975024730eec08107e77fd2d167de4a
 size 4283