End of training

README.md

@@ -1,6 +1,4 @@
 ---
-license: apache-2.0
-base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 model-index:
@@ -13,14 +11,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ner-bert-ingredients
 
-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:
-- eval_loss: 1.5282
-- eval_runtime: 84.2371
-- eval_samples_per_second: 59.356
-- eval_steps_per_second: 0.938
-- epoch: 6.06
-- step: 4500
+- eval_loss: 2.3785
+- eval_runtime: 84.0031
+- eval_samples_per_second: 59.522
+- eval_steps_per_second: 0.94
+- epoch: 7.08
+- step: 5250
 
 ## Model description
 

config.json

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

logs/events.out.tfevents.1704638284.80d534b5f596.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4aaf750cd2f6e4f5bd5705b609fdc3eb01bb4b1c3a25298f3fea438f5bdabdb
+size 1717324

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae13ecd9fc839ef94736671faab0dcc0acd342d63ac53d36f3f434917fb712b3
+oid sha256:50065a45f9f3efe6cb5d824760c2d913022aca1532af3c49e580ae48d003cc04
 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": 1.6346299648284912,
   "best_model_checkpoint": "ner-bert-ingredients/checkpoint-3750",
-  "epoch": 6.062647356012126,
+  "epoch": 7.07510946446615,
   "eval_steps": 750,
-  "global_step": 4500,
+  "global_step": 5250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,20 @@
       "eval_samples_per_second": 59.356,
       "eval_steps_per_second": 0.938,
       "step": 4500
+    },
+    {
+      "epoch": 7.08,
+      "learning_rate": 4.949460916442048e-05,
+      "loss": 3.7548,
+      "step": 5250
+    },
+    {
+      "epoch": 7.08,
+      "eval_loss": 2.378469228744507,
+      "eval_runtime": 84.0031,
+      "eval_samples_per_second": 59.522,
+      "eval_steps_per_second": 0.94,
+      "step": 5250
     }
   ],
   "logging_steps": 750,
@@ -98,7 +112,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 750,
-  "total_flos": 1.9475913345048576e+17,
+  "total_flos": 2.2721898902556672e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null