Upload 12 files

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "roberta-base",
+  "_name_or_path": "data/further_pretraining/roberta-base/checkpoint-16373",
   "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:bafbae8fe8dea92a388e93e105869d450b3c2c7e79cc85510d9ec67f5e8f5d4f
+size 496253316

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:733e497bb47cdce3c722d944ec16a0ca562b7bd2249630b31f86f7a86e258887
-size 992575493
+oid sha256:0cc39f5c534760a502bbd0c81c5ff95dc7860bf85f793d033ce71d75f666f5f3
+size 992625210

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20dd2fbd7f85a1ea702fb954d9d6f4ee89ef264b0c90fe34c1a7f559768e1b20
-size 14575
+oid sha256:4508b02e23b5fc2b51eaed019d385acf0c7d24d11b60eeb81389ce5cf020b7f4
+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.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

@@ -1,46 +1,66 @@
 {
-  "best_metric": 0.005157737527042627,
-  "best_model_checkpoint": "data/train-test///model/checkpoint-1676",
-  "epoch": 1.0,
+  "best_metric": 0.9963201471941122,
+  "best_model_checkpoint": "data/train-test/roberta-base-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": 0.0422,
+      "epoch": 0.6,
+      "grad_norm": 1.825121283531189,
+      "learning_rate": 1.4033412887828164e-05,
+      "loss": 0.0322,
       "step": 500
     },
     {
-      "epoch": 0.6,
-      "learning_rate": 1.4033412887828164e-05,
-      "loss": 0.0062,
+      "epoch": 1.0,
+      "eval_accuracy": null,
+      "eval_f1": 0.9926538108356291,
+      "eval_loss": 0.00715277437120676,
+      "eval_precision": 0.9908340971585701,
+      "eval_recall": 0.9944802207911684,
+      "eval_runtime": 1.6458,
+      "eval_samples_per_second": 589.386,
+      "eval_steps_per_second": 18.836,
+      "step": 838
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.7001124620437622,
+      "learning_rate": 8.066825775656326e-06,
+      "loss": 0.0046,
       "step": 1000
     },
     {
-      "epoch": 0.89,
-      "learning_rate": 1.1050119331742244e-05,
-      "loss": 0.0052,
+      "epoch": 1.79,
+      "grad_norm": 0.1312304437160492,
+      "learning_rate": 2.100238663484487e-06,
+      "loss": 0.0027,
       "step": 1500
     },
     {
-      "epoch": 1.0,
+      "epoch": 2.0,
       "eval_accuracy": null,
-      "eval_f1": 0.9925373134328359,
-      "eval_loss": 0.005157737527042627,
-      "eval_precision": 0.9906890130353817,
-      "eval_recall": 0.994392523364486,
-      "eval_runtime": 0.382,
-      "eval_samples_per_second": 2539.591,
-      "eval_steps_per_second": 159.706,
+      "eval_f1": 0.9963201471941122,
+      "eval_loss": 0.004037069622427225,
+      "eval_precision": 0.9963201471941122,
+      "eval_recall": 0.9963201471941122,
+      "eval_runtime": 1.6277,
+      "eval_samples_per_second": 595.928,
+      "eval_steps_per_second": 19.045,
       "step": 1676
     }
   ],
-  "max_steps": 3352,
+  "logging_steps": 500,
+  "max_steps": 1676,
+  "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
-  "total_flos": 787274342216514.0,
+  "save_steps": 500,
+  "total_flos": 2013781275950328.0,
+  "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:bb50de76f6ddda59be0ab4580535665e5b1e6934bc7aa1e68ecd5d14330a6190
-size 3963
+oid sha256:57817dee2c4bf33835c981bcbee2a13e690f7c763ce659b0aa87a28b502670d3
+size 4984