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: 4.3994
-- eval_runtime: 0.0358
-- eval_samples_per_second: 55.921
-- eval_steps_per_second: 27.961
-- epoch: 4.0
-- step: 4
+- eval_loss: 4.3799
+- eval_runtime: 0.0344
+- eval_samples_per_second: 58.156
+- eval_steps_per_second: 29.078
+- epoch: 1.0
+- step: 1
 
 ## Model description
 

config.json

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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db5998d5981ed4d7d2e689fcb8b2859cb00a779f5286f66518b13cad8fc88c65
+oid sha256:2ba26a04cab698755f4a7d92419db4a4ba392c75e099f1962f4ea06b132a0f6b
 size 435820636

runs/Jan05_08-07-59_414819e23027/events.out.tfevents.1704442090.414819e23027.9579.16

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3e444ad074ed53106c5d4f32f3a11355bc31b16ea7b79425c50be1b44692fe
-size 9056
+oid sha256:6ef802b840554e3c51bf02a13f02a625c351754cc11494990c7821ffb663cbc3
+size 9476

runs/Jan05_08-11-12_414819e23027/events.out.tfevents.1704442276.414819e23027.9579.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82da206fbae0e53c1564958ebd2ed5dcf8e463ba1692cfe7ecc6d96afebc2969
+size 7847

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": 4.0,
+  "epoch": 1.0,
   "eval_steps": 1,
-  "global_step": 4,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,65 +11,23 @@
     {
       "epoch": 1.0,
       "learning_rate": 4.9e-05,
-      "loss": 4.3439,
+      "loss": 2.9799,
       "step": 1
     },
     {
       "epoch": 1.0,
-      "eval_loss": 4.352994441986084,
-      "eval_runtime": 0.045,
-      "eval_samples_per_second": 44.444,
-      "eval_steps_per_second": 22.222,
+      "eval_loss": 4.379878520965576,
+      "eval_runtime": 0.0344,
+      "eval_samples_per_second": 58.156,
+      "eval_steps_per_second": 29.078,
       "step": 1
-    },
-    {
-      "epoch": 2.0,
-      "learning_rate": 4.8e-05,
-      "loss": 4.0741,
-      "step": 2
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 4.369075775146484,
-      "eval_runtime": 0.0298,
-      "eval_samples_per_second": 67.128,
-      "eval_steps_per_second": 33.564,
-      "step": 2
-    },
-    {
-      "epoch": 3.0,
-      "learning_rate": 4.7e-05,
-      "loss": 3.8404,
-      "step": 3
-    },
-    {
-      "epoch": 3.0,
-      "eval_loss": 4.391932964324951,
-      "eval_runtime": 0.0266,
-      "eval_samples_per_second": 75.108,
-      "eval_steps_per_second": 37.554,
-      "step": 3
-    },
-    {
-      "epoch": 4.0,
-      "learning_rate": 4.600000000000001e-05,
-      "loss": 3.6288,
-      "step": 4
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 4.39936637878418,
-      "eval_runtime": 0.0358,
-      "eval_samples_per_second": 55.921,
-      "eval_steps_per_second": 27.961,
-      "step": 4
     }
   ],
   "logging_steps": 1,
   "max_steps": 50,
   "num_train_epochs": 50,
   "save_steps": 20,
-  "total_flos": 2304197409600.0,
+  "total_flos": 576049352400.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc908e19763faf6f872a93d2c05e1926d0092455daf2d5c37462599bf9734099
+oid sha256:ee86837266bbc5e6172c9e09bcb500cf131b1fcc7f02b545c8245aad1f23abde
 size 4600