Upload 10 files

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "xlnet-large-cased",
+  "_name_or_path": "data/further_pretraining/xlnet-large-cased/checkpoint-4706",
   "architectures": [
     "XLNetForTokenClassification"
   ],
@@ -45,7 +45,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.30.2",
+  "transformers_version": "4.39.1",
   "untie_r": true,
   "use_mems_eval": true,
   "use_mems_train": false,

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b26a97cc1731582f81c2cdf3218be279d30d8060ee9746e58eb3f9c7ca99f43
+size 1441133004

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e2faa41336c927c289261e2147f320bdf4b19a5c75013f9fa48e5b7504eb7e0
-size 2882410053
+oid sha256:9f7a1271d60ff87a2733a1cd8aec6abe341c8ff4feddaa9b2eaa9ead4481b195
+size 2882521638

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0edd2ceb30d6babc1f3e5958a8417a2569537b5352b92d741a4661c167a82c5
-size 14575
+oid sha256:0c196bf769a36bd6546a97ba0f5572414b970ed2454097564e55b302a5d4f62a
+size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a81b9e64a6d36ab9d27ca33efaa732434676daf622cfdf89ee1179762e733965
-size 627
+oid sha256:5be2f897f916fdd0db20a90cc5571404430bc18f53f310ccdce81881dd982463
+size 1064

tokenizer.json

@@ -123,7 +123,8 @@
       {
         "type": "Metaspace",
         "replacement": "▁",
-        "add_prefix_space": true
+        "add_prefix_space": true,
+        "prepend_scheme": "always"
       }
     ]
   },
@@ -205,7 +206,8 @@
   "decoder": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true
+    "add_prefix_space": true,
+    "prepend_scheme": "always"
   },
   "model": {
     "type": "Unigram",
@@ -128211,6 +128213,7 @@
         "•",
         -14.79216480255127
       ]
-    ]
+    ],
+    "byte_fallback": false
   }
 }

tokenizer_config.json

@@ -1,4 +1,78 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "additional_special_tokens": [
     "<eop>",
     "<eod>"
@@ -9,14 +83,7 @@
   "do_lower_case": false,
   "eos_token": "</s>",
   "keep_accents": false,
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "remove_space": true,

trainer_state.json

@@ -1,64 +1,87 @@
 {
-  "best_metric": 0.004898133222013712,
-  "best_model_checkpoint": "data/train-test///model/checkpoint-3351",
-  "epoch": 1.0,
-  "global_step": 3351,
+  "best_metric": 0.9972401103955841,
+  "best_model_checkpoint": "data/train-test/xlnet-large-cased//model/checkpoint-3352",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 3352,
   "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": 0.1149,
+      "epoch": 0.3,
+      "grad_norm": 0.6528932452201843,
+      "learning_rate": 2.552505966587112e-05,
+      "loss": 0.0674,
       "step": 500
     },
     {
-      "epoch": 0.3,
-      "learning_rate": 1.7015816174276335e-05,
-      "loss": 0.0198,
+      "epoch": 0.6,
+      "grad_norm": 0.035294823348522186,
+      "learning_rate": 2.1050119331742245e-05,
+      "loss": 0.0058,
       "step": 1000
     },
     {
-      "epoch": 0.45,
-      "learning_rate": 1.5523724261414504e-05,
-      "loss": 0.0101,
+      "epoch": 0.89,
+      "grad_norm": 0.07718423008918762,
+      "learning_rate": 1.6575178997613365e-05,
+      "loss": 0.0041,
       "step": 1500
     },
     {
-      "epoch": 0.6,
-      "learning_rate": 1.4031632348552673e-05,
-      "loss": 0.0063,
+      "epoch": 1.0,
+      "eval_accuracy": null,
+      "eval_f1": 0.9853211009174311,
+      "eval_loss": 0.00522511824965477,
+      "eval_precision": 0.9826166514181153,
+      "eval_recall": 0.9880404783808647,
+      "eval_runtime": 8.7222,
+      "eval_samples_per_second": 111.211,
+      "eval_steps_per_second": 6.994,
+      "step": 1676
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.03843804448843002,
+      "learning_rate": 1.2100238663484488e-05,
+      "loss": 0.003,
       "step": 2000
     },
     {
-      "epoch": 0.75,
-      "learning_rate": 1.253954043569084e-05,
-      "loss": 0.0067,
+      "epoch": 1.49,
+      "grad_norm": 0.008623383939266205,
+      "learning_rate": 7.625298329355609e-06,
+      "loss": 0.0015,
       "step": 2500
     },
     {
-      "epoch": 0.9,
-      "learning_rate": 1.1047448522829008e-05,
-      "loss": 0.0068,
+      "epoch": 1.79,
+      "grad_norm": 0.005918263457715511,
+      "learning_rate": 3.1503579952267305e-06,
+      "loss": 0.0012,
       "step": 3000
     },
     {
-      "epoch": 1.0,
+      "epoch": 2.0,
       "eval_accuracy": null,
-      "eval_f1": 0.9943977591036415,
-      "eval_loss": 0.004898133222013712,
-      "eval_precision": 0.9943977591036415,
-      "eval_recall": 0.9943977591036415,
-      "eval_runtime": 1.5284,
-      "eval_samples_per_second": 634.661,
-      "eval_steps_per_second": 79.823,
-      "step": 3351
+      "eval_f1": 0.9972401103955841,
+      "eval_loss": 0.002058240817859769,
+      "eval_precision": 0.9972401103955841,
+      "eval_recall": 0.9972401103955841,
+      "eval_runtime": 8.7323,
+      "eval_samples_per_second": 111.082,
+      "eval_steps_per_second": 6.986,
+      "step": 3352
     }
   ],
-  "max_steps": 6702,
+  "logging_steps": 500,
+  "max_steps": 3352,
+  "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
-  "total_flos": 2597776456686000.0,
+  "save_steps": 500,
+  "total_flos": 6566441558618250.0,
+  "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 sha256:4d97d2a8f287fdc8b9e66604d38c2f4463bc68b55cef78f20bc93ec03f39e104
-size 3963
+oid sha256:93902a43abf31e011f1d767fe0af9922c3522a026e3f77bdedf32ca0b56b3d09
+size 4984