End of training

README.md

@@ -14,6 +14,13 @@ 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.
+It achieves the following results on the evaluation set:
+- eval_loss: 4.4464
+- eval_runtime: 0.0176
+- eval_samples_per_second: 56.724
+- eval_steps_per_second: 56.724
+- epoch: 10.0
+- step: 10
 
 ## Model description
 
@@ -43,10 +50,6 @@ The following hyperparameters were used during training:
 - num_epochs: 50
 - mixed_precision_training: Native AMP
 
-### Training results
-
-
-
 ### Framework versions
 
 - Transformers 4.36.0

config.json

@@ -63,28 +63,7 @@
     "50": "LABEL_50",
     "51": "LABEL_51",
     "52": "LABEL_52",
-    "53": "LABEL_53",
-    "54": "LABEL_54",
-    "55": "LABEL_55",
-    "56": "LABEL_56",
-    "57": "LABEL_57",
-    "58": "LABEL_58",
-    "59": "LABEL_59",
-    "60": "LABEL_60",
-    "61": "LABEL_61",
-    "62": "LABEL_62",
-    "63": "LABEL_63",
-    "64": "LABEL_64",
-    "65": "LABEL_65",
-    "66": "LABEL_66",
-    "67": "LABEL_67",
-    "68": "LABEL_68",
-    "69": "LABEL_69",
-    "70": "LABEL_70",
-    "71": "LABEL_71",
-    "72": "LABEL_72",
-    "73": "LABEL_73",
-    "74": "LABEL_74"
+    "53": "LABEL_53"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
@@ -139,29 +118,8 @@
     "LABEL_51": 51,
     "LABEL_52": 52,
     "LABEL_53": 53,
-    "LABEL_54": 54,
-    "LABEL_55": 55,
-    "LABEL_56": 56,
-    "LABEL_57": 57,
-    "LABEL_58": 58,
-    "LABEL_59": 59,
     "LABEL_6": 6,
-    "LABEL_60": 60,
-    "LABEL_61": 61,
-    "LABEL_62": 62,
-    "LABEL_63": 63,
-    "LABEL_64": 64,
-    "LABEL_65": 65,
-    "LABEL_66": 66,
-    "LABEL_67": 67,
-    "LABEL_68": 68,
-    "LABEL_69": 69,
     "LABEL_7": 7,
-    "LABEL_70": 70,
-    "LABEL_71": 71,
-    "LABEL_72": 72,
-    "LABEL_73": 73,
-    "LABEL_74": 74,
     "LABEL_8": 8,
     "LABEL_9": 9
   },

logs/events.out.tfevents.1705982868.70e47a1f5afe.42.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21b3f3ff7b8fb5dbecad8aef3836d435dac2c5d5fb697882eadaaf21055007d0
+size 7028

logs/events.out.tfevents.1705982894.70e47a1f5afe.42.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2330695fbad9f24ae1b10f12ef6d1ba3a29aa60bcef4ee3f64dae7b35fa5d04e
+size 7028

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69cbee484a05deb848b73eb4e78a97aa6ca7fa2fb97bbca3d868f9ca29cd79bf
-size 435820636
+oid sha256:b1f2ed33d49476ecdf341fac292ec64b65edf6c4f0c485b9fcbbab100d62d596
+size 435756040

trainer_state.json

@@ -1,29 +1,34 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 50.0,
-  "eval_steps": 750,
-  "global_step": 50,
+  "epoch": 10.0,
+  "eval_steps": 10,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 50.0,
-      "step": 50,
-      "total_flos": 39756597592500.0,
-      "train_loss": 0.21248756408691405,
-      "train_runtime": 8.9613,
-      "train_samples_per_second": 50.216,
-      "train_steps_per_second": 5.58
+      "epoch": 10.0,
+      "learning_rate": 4e-05,
+      "loss": 0.3826,
+      "step": 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
     }
   ],
-  "logging_steps": 750,
+  "logging_steps": 10,
   "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
-  "save_steps": 750,
-  "total_flos": 39756597592500.0,
+  "save_steps": 10,
+  "total_flos": 6571230957720.0,
   "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 sha256:539f836c129844c7433ce90ce7a776a98d7e07cfa66853d433c5135b23816fc8
+oid sha256:665509b7779b6a7e7ab19bb9a60700f3660066d0bf783678aea312e07320debf
 size 4283