End of training

README.md

@@ -1,4 +1,6 @@
 ---
+license: apache-2.0
+base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 model-index:
@@ -11,14 +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:
-- eval_loss: 4.4745
-- eval_runtime: 0.0352
-- eval_samples_per_second: 56.755
-- eval_steps_per_second: 28.378
-- epoch: 5.0
-- step: 5
+- eval_loss: 9.3213
+- eval_runtime: 84.1492
+- eval_samples_per_second: 59.418
+- eval_steps_per_second: 0.939
+- epoch: 0.01
+- step: 20
 
 ## Model description
 
@@ -38,9 +40,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 16
+- eval_batch_size: 64
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 50
@@ -48,7 +52,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.16.1
+- Transformers 4.36.0
+- Pytorch 2.0.0
+- Datasets 2.1.0
 - Tokenizers 0.15.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:212a1c7f39f2726ed5816603afecb3c1759c9ce41e6f17b37163aa50ffcfc75e
-size 435820636
+oid sha256:25943189126c4384255357954d6c628633236cbb8027f235dc99cf574637c22e
+size 535667604

runs/Jan05_08-46-52_4b3636b992a4/events.out.tfevents.1704444413.4b3636b992a4.42.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89d9f8ea07bfa242430ef05204fd97e5d5552dca669a841a76ae527e6111b169
+size 1716862

runs/Jan05_08-50-41_4b3636b992a4/events.out.tfevents.1704444643.4b3636b992a4.42.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:856e7858451d707152700e3747b6eeb7dcf06578d042e16f9b387a3a1150b830
+size 1716862

runs/Jan05_08-54-19_4b3636b992a4/events.out.tfevents.1704444861.4b3636b992a4.42.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc937929d2c592d7ba0dd2ae4a8799791891307637275d1e875810ff27bd4faf
+size 1717282

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

@@ -1,89 +1,35 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
-  "eval_steps": 1,
-  "global_step": 5,
+  "epoch": 0.013472549680026945,
+  "eval_steps": 20,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 1.0,
-      "learning_rate": 4.9e-05,
-      "loss": 1.6172,
-      "step": 1
+      "epoch": 0.01,
+      "learning_rate": 4.9986522911051216e-05,
+      "loss": 9.8102,
+      "step": 20
     },
     {
-      "epoch": 1.0,
-      "eval_loss": 4.416090965270996,
-      "eval_runtime": 0.0471,
-      "eval_samples_per_second": 42.424,
-      "eval_steps_per_second": 21.212,
-      "step": 1
-    },
-    {
-      "epoch": 2.0,
-      "learning_rate": 4.8e-05,
-      "loss": 1.8901,
-      "step": 2
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 4.417668342590332,
-      "eval_runtime": 0.0311,
-      "eval_samples_per_second": 64.258,
-      "eval_steps_per_second": 32.129,
-      "step": 2
-    },
-    {
-      "epoch": 3.0,
-      "learning_rate": 4.7e-05,
-      "loss": 1.8305,
-      "step": 3
-    },
-    {
-      "epoch": 3.0,
-      "eval_loss": 4.438927173614502,
-      "eval_runtime": 0.03,
-      "eval_samples_per_second": 66.75,
-      "eval_steps_per_second": 33.375,
-      "step": 3
-    },
-    {
-      "epoch": 4.0,
-      "learning_rate": 4.600000000000001e-05,
-      "loss": 1.757,
-      "step": 4
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 4.466496467590332,
-      "eval_runtime": 0.0321,
-      "eval_samples_per_second": 62.331,
-      "eval_steps_per_second": 31.165,
-      "step": 4
-    },
-    {
-      "epoch": 5.0,
-      "learning_rate": 4.9e-05,
-      "loss": 1.5364,
-      "step": 5
-    },
-    {
-      "epoch": 5.0,
-      "eval_loss": 4.474534034729004,
-      "eval_runtime": 0.0352,
-      "eval_samples_per_second": 56.755,
-      "eval_steps_per_second": 28.378,
-      "step": 5
+      "epoch": 0.01,
+      "eval_loss": 9.321273803710938,
+      "eval_runtime": 84.1492,
+      "eval_samples_per_second": 59.418,
+      "eval_steps_per_second": 0.939,
+      "step": 20
     }
   ],
-  "logging_steps": 1,
-  "max_steps": 50,
+  "logging_steps": 20,
+  "max_steps": 74200,
+  "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 20,
-  "total_flos": 2880246762000.0,
+  "total_flos": 432834143846400.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd8735572c360aff55483202835ae93d2da4df07d250cdf37afb9452e9a7fdf
-size 4600
+oid sha256:e7e0cc5c26c36bde050839a58f0c4f021e92cbaffecf465dbdc0090a08f22c21
+size 4283