Training in progress, step 5000

config.json

@@ -21,7 +21,7 @@
   "num_hidden_layers": 4,
   "pad_token_id": 1,
   "torch_dtype": "float32",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.40.1",
   "use_cache": true,
   "vocab_size": 50272,
   "word_embed_proj_dim": 768

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f663c891a8870fbf25c25890ca26b14b495e602671913b72770c58cb1df2afc6
+oid sha256:384b6e7e3983c9631856ea5b9fc35e5caccd2bfe6e7d8c944957e561643ecda0
 size 161757984

runs/May01_14-28-49_a92bf2eb7ffa/events.out.tfevents.1714573729.a92bf2eb7ffa.2200.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae238be4d23fa4933cdc16d972956b6ead903748635896631d2ea9f0671e13b7
+size 4600

runs/May01_14-36-08_a92bf2eb7ffa/events.out.tfevents.1714574169.a92bf2eb7ffa.4577.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:110e0ebcf5958804b92fe13a3d3a22b819662aeb55664c2bae98fd2e0e401098
+size 4600

runs/May01_14-40-59_a92bf2eb7ffa/events.out.tfevents.1714574459.a92bf2eb7ffa.5886.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b141768bc709530755e924bc5a095617dbd19f1cb8a942e01948739dfd6cc46
+size 4600

runs/May01_14-41-08_a92bf2eb7ffa/events.out.tfevents.1714574468.a92bf2eb7ffa.5886.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c565c09ad2813a6cc3f0ec42804f24b0f9bbf15e03907ab5980884822388c18
+size 4600

runs/May01_14-48-08_a92bf2eb7ffa/events.out.tfevents.1714574888.a92bf2eb7ffa.5886.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9f811c24d4e41d3eab4fef4ca53aa4e44db5201e7b4c1acbf96bac40a0aa533
+size 5082

special_tokens_map.json

@@ -1,6 +1,7 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,20 +1,55 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "50256": {
-      "content": "<|endoftext|>",
+    "0": {
+      "content": "[PAD]",
       "lstrip": false,
-      "normalized": true,
+      "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
     }
   },
-  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 1024,
-  "pad_token": "<|endoftext|>",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c95ed6701116ee7b8a8b7a245b0e5735fc6fa102fbb496a7484a4146c747ed8
-size 4920
+oid sha256:51f2255d4932b7c335148f25556352c80872b7bc035c4fd097b6953e4d8ed174
+size 4984