End of training

README.md

@@ -1,4 +1,6 @@
 ---
+license: apache-2.0
+base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 model-index:
@@ -11,9 +13,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ner-bert-ingredients
 
-This model was trained from scratch on an unknown dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.6987
+- eval_loss: 4.4464
+- eval_runtime: 0.0184
+- eval_samples_per_second: 54.288
+- eval_steps_per_second: 54.288
+- epoch: 10.0
+- step: 10
 
 ## Model description
 
@@ -43,17 +50,6 @@ The following hyperparameters were used during training:
 - num_epochs: 50
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.3826        | 10.0  | 10   | 4.4464          |
-| 0.207         | 20.0  | 20   | 4.5212          |
-| 0.1171        | 30.0  | 30   | 4.5379          |
-| 0.0764        | 40.0  | 40   | 4.6038          |
-| 0.063         | 50.0  | 50   | 4.6987          |
-
-
 ### Framework versions
 
 - Transformers 4.36.0

config.json

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

logs/events.out.tfevents.1705983189.70e47a1f5afe.42.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f551b9e27c17ebfa551fc7d1e14ed51a482b4bc22699aa35a77795af53bf867
+size 7028

special_tokens_map.json

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

tokenizer_config.json

@@ -45,18 +45,11 @@
   "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": 4.4464287757873535,
-  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-10",
-  "epoch": 50.0,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
   "eval_steps": 10,
-  "global_step": 50,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17,75 +17,10 @@
     {
       "epoch": 10.0,
       "eval_loss": 4.4464287757873535,
-      "eval_runtime": 0.0176,
-      "eval_samples_per_second": 56.724,
-      "eval_steps_per_second": 56.724,
-      "step": 10
-    },
-    {
-      "epoch": 20.0,
-      "learning_rate": 3e-05,
-      "loss": 0.207,
-      "step": 20
-    },
-    {
-      "epoch": 20.0,
-      "eval_loss": 4.521205425262451,
-      "eval_runtime": 0.018,
-      "eval_samples_per_second": 55.513,
-      "eval_steps_per_second": 55.513,
-      "step": 20
-    },
-    {
-      "epoch": 30.0,
-      "learning_rate": 2e-05,
-      "loss": 0.1171,
-      "step": 30
-    },
-    {
-      "epoch": 30.0,
-      "eval_loss": 4.5379462242126465,
-      "eval_runtime": 0.0188,
-      "eval_samples_per_second": 53.052,
-      "eval_steps_per_second": 53.052,
-      "step": 30
-    },
-    {
-      "epoch": 40.0,
-      "learning_rate": 1e-05,
-      "loss": 0.0764,
-      "step": 40
-    },
-    {
-      "epoch": 40.0,
-      "eval_loss": 4.603794574737549,
-      "eval_runtime": 0.0208,
-      "eval_samples_per_second": 48.022,
-      "eval_steps_per_second": 48.022,
-      "step": 40
-    },
-    {
-      "epoch": 50.0,
-      "learning_rate": 4e-05,
-      "loss": 0.063,
-      "step": 50
-    },
-    {
-      "epoch": 50.0,
-      "eval_loss": 4.698660850524902,
       "eval_runtime": 0.0184,
-      "eval_samples_per_second": 54.299,
-      "eval_steps_per_second": 54.299,
-      "step": 50
-    },
-    {
-      "epoch": 50.0,
-      "step": 50,
-      "total_flos": 32856154788600.0,
-      "train_loss": 0.012607929706573486,
-      "train_runtime": 24.4386,
-      "train_samples_per_second": 18.413,
-      "train_steps_per_second": 2.046
+      "eval_samples_per_second": 54.288,
+      "eval_steps_per_second": 54.288,
+      "step": 10
     }
   ],
   "logging_steps": 10,
@@ -93,7 +28,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 10,
-  "total_flos": 32856154788600.0,
+  "total_flos": 6571230957720.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null