Upload 12 files

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "roberta-large",
+  "_name_or_path": "data/further_pretraining/roberta-large/checkpoint-4678",
   "architectures": [
     "RobertaForTokenClassification"
   ],
@@ -30,7 +30,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.30.2",
+  "transformers_version": "4.39.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c819517d251abbd2ac4c61ff6ce7f58aa7de715f4d4f5af130f5ed066a713dec
+size 1417300884

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8b3afdcf861ae2fb7615af0a9af193b0ed91811b51bf08df305bba7e79e2fb0
-size 2834735429
+oid sha256:cec5a9c7f1e183f8603f47c0daa973e2b992af8f0338375f08f1b12c43a2d087
+size 2834832935

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:535668448099908a7c1073e58ae7c2fe30d9dd5b4d8377f0ad0f321344df25ba
-size 14575
+oid sha256:c42a88072d467bd76274de862e37ee53c3e1d7f33ad54c8b28c097a74bbcc46b
+size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a81b9e64a6d36ab9d27ca33efaa732434676daf622cfdf89ee1179762e733965
-size 627
+oid sha256:af8e36d67e7350aa7ba27dfd844d165ee5ffe669ec863b55108a58646f643dd9
+size 1064

tokenizer.json

@@ -14,7 +14,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -23,7 +23,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -32,7 +32,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -41,7 +41,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {

tokenizer_config.json

@@ -1,5 +1,47 @@
 {
   "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",

trainer_state.json

@@ -1,64 +1,45 @@
 {
-  "best_metric": 0.014085530303418636,
-  "best_model_checkpoint": "data/train-test///model/checkpoint-3351",
-  "epoch": 1.0,
-  "global_step": 3351,
+  "best_metric": 0.937442502299908,
+  "best_model_checkpoint": "data/train-test/roberta-large-output//model/checkpoint-232",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 232,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.15,
-      "learning_rate": 1.850790808713817e-05,
-      "loss": 0.0395,
-      "step": 500
-    },
-    {
-      "epoch": 0.3,
-      "learning_rate": 1.7015816174276335e-05,
-      "loss": 0.0125,
-      "step": 1000
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 1.5523724261414504e-05,
-      "loss": 0.009,
-      "step": 1500
-    },
-    {
-      "epoch": 0.6,
-      "learning_rate": 1.4031632348552673e-05,
-      "loss": 0.0056,
-      "step": 2000
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 1.253954043569084e-05,
-      "loss": 0.0056,
-      "step": 2500
-    },
-    {
-      "epoch": 0.9,
-      "learning_rate": 1.1047448522829008e-05,
-      "loss": 0.0197,
-      "step": 3000
+      "epoch": 1.0,
+      "eval_accuracy": null,
+      "eval_f1": 0.902638762511374,
+      "eval_loss": 0.05000825226306915,
+      "eval_precision": 0.8928892889288929,
+      "eval_recall": 0.9126034958601656,
+      "eval_runtime": 4.4114,
+      "eval_samples_per_second": 219.883,
+      "eval_steps_per_second": 7.027,
+      "step": 116
     },
     {
-      "epoch": 1.0,
+      "epoch": 2.0,
       "eval_accuracy": null,
-      "eval_f1": 0.9771134983652499,
-      "eval_loss": 0.014085530303418636,
-      "eval_precision": 0.9840075258701787,
-      "eval_recall": 0.9703153988868275,
-      "eval_runtime": 1.14,
-      "eval_samples_per_second": 850.884,
-      "eval_steps_per_second": 107.018,
-      "step": 3351
+      "eval_f1": 0.9276285844333181,
+      "eval_loss": 0.03446832671761513,
+      "eval_precision": 0.918018018018018,
+      "eval_recall": 0.937442502299908,
+      "eval_runtime": 4.4048,
+      "eval_samples_per_second": 220.215,
+      "eval_steps_per_second": 7.038,
+      "step": 232
     }
   ],
-  "max_steps": 6702,
+  "logging_steps": 500,
+  "max_steps": 232,
+  "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
-  "total_flos": 2207357174625474.0,
+  "save_steps": 500,
+  "total_flos": 853475550077862.0,
+  "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:bb8bb5ea0455a2f363fb152a305bef728199f81ce224543eb10a042f60f7272b
-size 3963
+oid sha256:b250203d90fac6c5a543f3f4385532a2720339f6f459179f95dd9d53b9e68027
+size 4984