Training in progress, step 5000

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<|BOS|>": 50257,
+  "<|EOS|>": 50258,
+  "<|PAD|>": 50260,
+  "<|SEP|>": 50261,
+  "<|UNK|>": 50259
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "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": "4.29.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478eef04a6336e0de76188815bc1b6dd7e691eb7fd4e487c59d64155236df362
+size 510398013

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<|BOS|>",
+  "eos_token": "<|EOS|>",
+  "pad_token": "<|EOS|>",
+  "sep_token": "<|SEP|>",
+  "unk_token": "<|UNK|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b4459ed067b237c74d486d3af8983bf3e6b87bd3256f75b658caa275fe033b1
+size 3899