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: 0.0188
-- eval_samples_per_second: 53.052
-- eval_steps_per_second: 53.052
-- epoch: 30.0
-- step: 30
+- eval_loss: 4.6987
+- eval_runtime: 0.0184
+- eval_samples_per_second: 54.299
+- eval_steps_per_second: 54.299
+- epoch: 50.0
+- step: 50
 
 ## 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.1705982894.70e47a1f5afe.42.10

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8cf1a326acf37230827be10bd766abddfc1f7f139188f0edb355399d001477f
-size 7868
+oid sha256:4160a39b5645f9319c76ff3d3cadb1a08c17e33ead50552c98de67ee0265f294
+size 8288

logs/events.out.tfevents.1705983035.70e47a1f5afe.42.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e3106771c36c1a648980573eab6d7576766a4a44e6df90f9c4ecf149a8fcd5
+size 7086

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca597349ea03bf594dd26319fcd2e7cd81cf40596d0f2c852834fc2111d0504b
+oid sha256:45d04dad0a7c2b4a89b02a87f0f119ab92b550cd7e094ff234eb79f7dd90d2a7
 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,
+  "epoch": 50.0,
   "eval_steps": 10,
-  "global_step": 30,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,6 +49,34 @@
       "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
     }
   ],
   "logging_steps": 10,
@@ -56,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 10,
-  "total_flos": 19713692873160.0,
+  "total_flos": 32856154788600.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null