Initial commit

checkpoint-3500/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "microsoft/DialoGPT-small",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "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,
+  "resid_pdrop": 0.1,
+  "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": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8787691b0e85894e74bb07aca9e868c2700f19b78ce95f1d78ebd548ee3ecb08
+size 995604017

checkpoint-3500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abde30703b422757a233f0b984b2354c9795e4f388e7a6fbf9baf8cf35c40fab
+size 510403817

checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4f327a579ef7550c3a44995c4115ca406152f86816693936d9ba6e3ca9dd954
+size 623

checkpoint-3500/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}

checkpoint-3500/tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "microsoft/DialoGPT-small", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}

checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee54e57e887b4187a9043d261018957cfb1bc718b63d53cb2d8ef48367cb5496
+size 1327

eval_results.txt

@@ -1 +1 @@
-perplexity = tensor(1.2166)
+perplexity = tensor(1.3847)

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:490ed80f012496db44343f1b487477ec68a39cd9567f303a77698ce5b7b456e9
+oid sha256:a6baaf516b452f8f551a301357c7cead02e6546ac764f9ee1f3d5704d5f85e60
 size 510403817

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee54e57e887b4187a9043d261018957cfb1bc718b63d53cb2d8ef48367cb5496
+oid sha256:542f18d6777a2fdec5a60ca070db0c905eb4ca09a67d78510a679d53a167f9ac
 size 1327