Training in progress, step 440

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 21128
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "yuanzhoulvpi/gpt2_chinese",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 21128,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 21128,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 21129
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d02d1cfc8ad7640ca947ad2a6d98b9d007831b437e28df2f33e0a056a7e5001e
+size 408292992

runs/Dec21_13-17-26_7688b827ad26/events.out.tfevents.1703164659.7688b827ad26.552.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f65055186731cc9cbf757610d7552ae533967125310dd436587cba17cdba1d0
+size 5277

runs/Dec21_13-18-49_7688b827ad26/events.out.tfevents.1703164735.7688b827ad26.552.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7bd9213763316341b3388b55232d8e55d4d4c36431ae53fa180ddeacb496cb3
+size 5011

runs/Dec21_13-19-34_7688b827ad26/events.out.tfevents.1703164780.7688b827ad26.552.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d62bcc1721de1ab4872a18539498e03d312608ea76609b07c095a0a0443edcb5
+size 5006

runs/Dec21_13-20-39_7688b827ad26/events.out.tfevents.1703164845.7688b827ad26.552.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4187725c644ccfff367782b2129613c52a1b6c4f4929a98554dfe5f07f8cfb8
+size 5691

runs/Dec21_13-23-03_7688b827ad26/events.out.tfevents.1703164993.7688b827ad26.552.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb3e63a33e11e404bdf3f45dcb0ba7880739b0b3751067f7bbc985f26713c029
+size 7133

runs/Dec21_13-32-09_7688b827ad26/events.out.tfevents.1703165535.7688b827ad26.552.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7afe441ae256e3ae10311227a63d17076f9cadcbfca2a9c6df0f48ae65b3618
+size 8351

runs/Dec21_13-36-33_7688b827ad26/events.out.tfevents.1703165800.7688b827ad26.552.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86127a08c88e864c3e5f8a4ebb82dadb56a1f0f0c2c018afa6359a2d0078f12b
+size 5271

runs/Dec21_13-41-33_7688b827ad26/events.out.tfevents.1703166100.7688b827ad26.552.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f828dabf9a578fcc460d339b50ad39a5a942475657464664545cccc71234f4fd
+size 18050

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<|endoftext|>",
+  "cls_token": "[CLS]",
+  "eos_token": "<|endoftext|>",
+  "mask_token": "[MASK]",
+  "pad_token": "<|endoftext|>",
+  "sep_token": "[SEP]",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,69 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "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
+    },
+    "21128": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<|endoftext|>",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2d62f8a555b7ce404ed9cc3c68016559c71e397c7d0609378106b939bf7bbd
+size 4536