Upload 11 files

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-large-uncased",
+  "_name_or_path": "data/further_pretraining/bert-large-uncased/checkpoint-4310",
   "architectures": [
     "BertForTokenClassification"
   ],
@@ -29,7 +29,7 @@
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.30.2",
+  "transformers_version": "4.39.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6606cb5b4b7ba238c6853ccae8f151f3b797667da020a75c18e251b36344dc74
+size 1336428268

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9576cd0dbd5f4c93b2be38fea11978b621a028486e6acc05c9d1257822f8627
-size 2672992581
+oid sha256:403acb0825ee1a1148bcfc6ef1768bd1e91a9d002c12af7fc1ce695cf93165d9
+size 2673090087

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:989474c474b2a7f63747f726408a1e702cf9862b4f2aac664325f5786914bd00
-size 14575
+oid sha256:f106e144c909f8f55dd5f4ecc55bb8ebddb4dcf08c1d52eb6fd10cce549922d9
+size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30269608c9e0540a595d8484ff39d209fca7698cf0f2639d73b5d81109885fed
-size 627
+oid sha256:b1f42bafe915d489bc148c745aee5cb40266ca728ccbcb98c9e87b2cedeab3b6
+size 1064

tokenizer_config.json

@@ -1,4 +1,46 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,

trainer_state.json

@@ -1,46 +1,66 @@
 {
-  "best_metric": 0.0068976194597780704,
-  "best_model_checkpoint": "data/train-test///model/checkpoint-1676",
-  "epoch": 1.0,
+  "best_metric": 0.9981600735970562,
+  "best_model_checkpoint": "data/train-test/bert-large-output//model/checkpoint-1676",
+  "epoch": 2.0,
+  "eval_steps": 500,
   "global_step": 1676,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.3,
-      "learning_rate": 1.7016706443914083e-05,
-      "loss": 0.0317,
+      "epoch": 0.6,
+      "grad_norm": 0.902126133441925,
+      "learning_rate": 1.4033412887828164e-05,
+      "loss": 0.0252,
       "step": 500
     },
     {
-      "epoch": 0.6,
-      "learning_rate": 1.4033412887828164e-05,
-      "loss": 0.0069,
+      "epoch": 1.0,
+      "eval_accuracy": null,
+      "eval_f1": 0.9935720844811754,
+      "eval_loss": 0.005533559713512659,
+      "eval_precision": 0.9917506874427131,
+      "eval_recall": 0.9954001839926403,
+      "eval_runtime": 4.2367,
+      "eval_samples_per_second": 228.952,
+      "eval_steps_per_second": 7.317,
+      "step": 838
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.0071577695198357105,
+      "learning_rate": 8.066825775656326e-06,
+      "loss": 0.0047,
       "step": 1000
     },
     {
-      "epoch": 0.89,
-      "learning_rate": 1.1050119331742244e-05,
-      "loss": 0.0057,
+      "epoch": 1.79,
+      "grad_norm": 0.009138579480350018,
+      "learning_rate": 2.100238663484487e-06,
+      "loss": 0.0027,
       "step": 1500
     },
     {
-      "epoch": 1.0,
+      "epoch": 2.0,
       "eval_accuracy": null,
-      "eval_f1": 0.9892573563755255,
-      "eval_loss": 0.0068976194597780704,
-      "eval_precision": 0.988795518207283,
-      "eval_recall": 0.9897196261682243,
-      "eval_runtime": 1.0104,
-      "eval_samples_per_second": 960.031,
-      "eval_steps_per_second": 60.373,
+      "eval_f1": 0.9967845659163987,
+      "eval_loss": 0.003087937133386731,
+      "eval_precision": 0.9954128440366973,
+      "eval_recall": 0.9981600735970562,
+      "eval_runtime": 4.2113,
+      "eval_samples_per_second": 230.333,
+      "eval_steps_per_second": 7.361,
       "step": 1676
     }
   ],
-  "max_steps": 3352,
+  "logging_steps": 500,
+  "max_steps": 1676,
+  "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
-  "total_flos": 2754552464105454.0,
+  "save_steps": 500,
+  "total_flos": 6896325795708240.0,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcd4c8e96bb6df9697ffa863eba7f459db1f041b35419ef338624481154b1e20
-size 3963
+oid sha256:4f55bf2d8dfc80e5de8019c4273048555c1efddf69b43556ddb53f2dba50d3bc
+size 4984