Upload 10 files

config.json

@@ -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:cc00d31ec6c55096a1dd4ad366316500a413155e9e504fb4b318e790659034d5
+size 466905100

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b1818057b2517e29ef7bc3bc638f8e7988199a15f9e90f6d498ea36115b848d
-size 933881285
+oid sha256:a773951628e019398980299eeb7e360951a6c7180203d6f494e0418d5659e8f1
+size 933939962

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e142ede7b5258f1993bc097bb1982682b3be6b8db767d1f28a07f4da04918c4
-size 14575
+oid sha256:8556b9ce063e9a3174297b1b4804ca0ce88037a08f18c1d859b216d1a9407b13
+size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a81b9e64a6d36ab9d27ca33efaa732434676daf622cfdf89ee1179762e733965
-size 627
+oid sha256:91aa10bda283c4c6d7bb1d45f481e3baef71e77946a9d038f500bc8e00072662
+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 +1,52 @@
 {
-  "best_metric": 0.0058293770998716354,
-  "best_model_checkpoint": "data/train-test///model/checkpoint-3351",
-  "epoch": 1.0,
-  "global_step": 3351,
+  "best_metric": 0.9816007359705612,
+  "best_model_checkpoint": "data/train-test/xlnet-base-cased//model/checkpoint-874",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 874,
   "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": 0.076,
-      "step": 500
-    },
-    {
-      "epoch": 0.3,
-      "learning_rate": 1.7015816174276335e-05,
-      "loss": 0.0181,
-      "step": 1000
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 1.5523724261414504e-05,
-      "loss": 0.0105,
-      "step": 1500
-    },
-    {
-      "epoch": 0.6,
-      "learning_rate": 1.4031632348552673e-05,
-      "loss": 0.0068,
-      "step": 2000
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 1.253954043569084e-05,
-      "loss": 0.0074,
-      "step": 2500
+      "epoch": 1.0,
+      "eval_accuracy": null,
+      "eval_f1": 0.9355716878402904,
+      "eval_loss": 0.025213107466697693,
+      "eval_precision": 0.9230080572963295,
+      "eval_recall": 0.9484820607175714,
+      "eval_runtime": 1.8189,
+      "eval_samples_per_second": 533.284,
+      "eval_steps_per_second": 17.043,
+      "step": 437
     },
     {
-      "epoch": 0.9,
-      "learning_rate": 1.1047448522829008e-05,
-      "loss": 0.0067,
-      "step": 3000
+      "epoch": 1.14,
+      "grad_norm": 1.2998504638671875,
+      "learning_rate": 8.558352402745997e-06,
+      "loss": 0.0831,
+      "step": 500
     },
     {
-      "epoch": 1.0,
+      "epoch": 2.0,
       "eval_accuracy": null,
-      "eval_f1": 0.9892673821745217,
-      "eval_loss": 0.0058293770998716354,
-      "eval_precision": 0.9878844361602982,
-      "eval_recall": 0.9906542056074766,
-      "eval_runtime": 0.6721,
-      "eval_samples_per_second": 1443.166,
-      "eval_steps_per_second": 181.512,
-      "step": 3351
+      "eval_f1": 0.9775538250114522,
+      "eval_loss": 0.015987424179911613,
+      "eval_precision": 0.9735401459854015,
+      "eval_recall": 0.9816007359705612,
+      "eval_runtime": 1.8215,
+      "eval_samples_per_second": 532.541,
+      "eval_steps_per_second": 17.019,
+      "step": 874
     }
   ],
-  "max_steps": 6702,
+  "logging_steps": 500,
+  "max_steps": 874,
+  "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
-  "total_flos": 730895731218864.0,
+  "save_steps": 500,
+  "total_flos": 841186234475568.0,
+  "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 sha256:95a948392a188468b6c62767fe55d4271d576399b3f70178aedb695206df8396
-size 3963
+oid sha256:bb2471f1d44fc04999f3013cd24731f3aaf98458fbb4696f19379c1fe6cd52fe
+size 4984