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: 4.5379
-- eval_runtime: 0.0186
-- eval_samples_per_second: 53.776
-- eval_steps_per_second: 53.776
-- epoch: 30.0
-- step: 30
+- eval_loss: 4.9241
+- eval_runtime: 0.0183
+- eval_samples_per_second: 54.52
+- eval_steps_per_second: 54.52
+- epoch: 20.0
+- step: 20
 
 ## 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.1705983189.70e47a1f5afe.42.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3fa33d657cb2c3ae5577284d9531a79f8b9865ba40f83ddec4b81b2801fee0c
-size 7868
+oid sha256:e66578068c59036e711d7af9c9cb68442ed56a604e80bb2b74ae0330518b2b6c
+size 8288

logs/events.out.tfevents.1705983278.70e47a1f5afe.42.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e68769640b6727a408aabdfeb8a234faff28c33d86ad948333832e904a709b0
+size 7086

logs/events.out.tfevents.1705983321.70e47a1f5afe.42.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f6f005cc9bd58b6b64b38c2e50dd6a68c1318b90114ba87fe296773e4abf580
+size 7086

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca597349ea03bf594dd26319fcd2e7cd81cf40596d0f2c852834fc2111d0504b
+oid sha256:b682db66b454975faf7da3a053ad47ae19381e41248c218350c29f4e02d2c921
 size 435756040

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": 4.4464287757873535,
-  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-10",
-  "epoch": 30.0,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
   "eval_steps": 10,
-  "global_step": 30,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,44 +11,30 @@
     {
       "epoch": 10.0,
       "learning_rate": 4e-05,
-      "loss": 0.3826,
+      "loss": 0.0466,
       "step": 10
     },
     {
       "epoch": 10.0,
-      "eval_loss": 4.4464287757873535,
-      "eval_runtime": 0.0184,
-      "eval_samples_per_second": 54.288,
-      "eval_steps_per_second": 54.288,
+      "eval_loss": 4.74609375,
+      "eval_runtime": 0.0189,
+      "eval_samples_per_second": 52.922,
+      "eval_steps_per_second": 52.922,
       "step": 10
     },
     {
       "epoch": 20.0,
-      "learning_rate": 3e-05,
-      "loss": 0.207,
+      "learning_rate": 4e-05,
+      "loss": 0.0213,
       "step": 20
     },
     {
       "epoch": 20.0,
-      "eval_loss": 4.521205425262451,
-      "eval_runtime": 0.018,
-      "eval_samples_per_second": 55.574,
-      "eval_steps_per_second": 55.574,
+      "eval_loss": 4.924107074737549,
+      "eval_runtime": 0.0183,
+      "eval_samples_per_second": 54.52,
+      "eval_steps_per_second": 54.52,
       "step": 20
-    },
-    {
-      "epoch": 30.0,
-      "learning_rate": 2e-05,
-      "loss": 0.1171,
-      "step": 30
-    },
-    {
-      "epoch": 30.0,
-      "eval_loss": 4.5379462242126465,
-      "eval_runtime": 0.0186,
-      "eval_samples_per_second": 53.776,
-      "eval_steps_per_second": 53.776,
-      "step": 30
     }
   ],
   "logging_steps": 10,
@@ -56,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 10,
-  "total_flos": 19713692873160.0,
+  "total_flos": 13142461915440.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null