Second commit
Browse files- checkpoint-10500/config.json +4 -4
- checkpoint-10500/optimizer.pt +2 -2
- checkpoint-10500/pytorch_model.bin +2 -2
- checkpoint-10500/scheduler.pt +1 -1
- checkpoint-10500/tokenizer_config.json +1 -1
- checkpoint-10500/training_args.bin +1 -1
- checkpoint-3500/config.json +4 -4
- checkpoint-3500/optimizer.pt +2 -2
- checkpoint-3500/pytorch_model.bin +2 -2
- checkpoint-3500/scheduler.pt +1 -1
- checkpoint-3500/tokenizer_config.json +1 -1
- checkpoint-3500/training_args.bin +1 -1
- checkpoint-7000/config.json +4 -4
- checkpoint-7000/optimizer.pt +2 -2
- checkpoint-7000/pytorch_model.bin +2 -2
- checkpoint-7000/scheduler.pt +1 -1
- checkpoint-7000/tokenizer_config.json +1 -1
- checkpoint-7000/training_args.bin +1 -1
- config.json +4 -4
- eval_results.txt +1 -1
- pytorch_model.bin +2 -2
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
checkpoint-10500/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "microsoft/DialoGPT-
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
@@ -13,10 +13,10 @@
|
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
15 |
"n_ctx": 1024,
|
16 |
-
"n_embd":
|
17 |
-
"n_head":
|
18 |
"n_inner": null,
|
19 |
-
"n_layer":
|
20 |
"n_positions": 1024,
|
21 |
"resid_pdrop": 0.1,
|
22 |
"scale_attn_weights": true,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/DialoGPT-medium",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
|
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
15 |
"n_ctx": 1024,
|
16 |
+
"n_embd": 1024,
|
17 |
+
"n_head": 16,
|
18 |
"n_inner": null,
|
19 |
+
"n_layer": 24,
|
20 |
"n_positions": 1024,
|
21 |
"resid_pdrop": 0.1,
|
22 |
"scale_attn_weights": true,
|
checkpoint-10500/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b90eb50f4d489723e75c4a25b77b4a241c4f3d9c058262514dd54d136c132cfa
|
3 |
+
size 2838754801
|
checkpoint-10500/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46b29628df2e6eaae35616190513cac2e91e769bd00e3f538926deb3d4cc15d2
|
3 |
+
size 1444581337
|
checkpoint-10500/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:652d5c46825f44df89208f091f5a4a831a7c672cc729058e6c4421cbe5dea34d
|
3 |
size 623
|
checkpoint-10500/tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
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-
|
|
|
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-medium", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
|
checkpoint-10500/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1327
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9568d522549353e20f5776653ff9ca0a85d47d6665a290395fb832486f32551
|
3 |
size 1327
|
checkpoint-3500/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "microsoft/DialoGPT-
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
@@ -13,10 +13,10 @@
|
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
15 |
"n_ctx": 1024,
|
16 |
-
"n_embd":
|
17 |
-
"n_head":
|
18 |
"n_inner": null,
|
19 |
-
"n_layer":
|
20 |
"n_positions": 1024,
|
21 |
"resid_pdrop": 0.1,
|
22 |
"scale_attn_weights": true,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/DialoGPT-medium",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
|
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
15 |
"n_ctx": 1024,
|
16 |
+
"n_embd": 1024,
|
17 |
+
"n_head": 16,
|
18 |
"n_inner": null,
|
19 |
+
"n_layer": 24,
|
20 |
"n_positions": 1024,
|
21 |
"resid_pdrop": 0.1,
|
22 |
"scale_attn_weights": true,
|
checkpoint-3500/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b04e29e6601c5b7222057262e36180fd35a2bb262f57322a80ea9c82aa1a23c0
|
3 |
+
size 2838754801
|
checkpoint-3500/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47db6e35d19a6abd787fae234370b2dba68328e62746308dff7f5a2d772e7e5c
|
3 |
+
size 1444581337
|
checkpoint-3500/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e27897415c88da60598103b15f4592412d08150976cb81ec3438c19da2b7cdce
|
3 |
size 623
|
checkpoint-3500/tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
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-
|
|
|
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-medium", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
|
checkpoint-3500/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1327
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9568d522549353e20f5776653ff9ca0a85d47d6665a290395fb832486f32551
|
3 |
size 1327
|
checkpoint-7000/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "microsoft/DialoGPT-
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
@@ -13,10 +13,10 @@
|
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
15 |
"n_ctx": 1024,
|
16 |
-
"n_embd":
|
17 |
-
"n_head":
|
18 |
"n_inner": null,
|
19 |
-
"n_layer":
|
20 |
"n_positions": 1024,
|
21 |
"resid_pdrop": 0.1,
|
22 |
"scale_attn_weights": true,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/DialoGPT-medium",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
|
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
15 |
"n_ctx": 1024,
|
16 |
+
"n_embd": 1024,
|
17 |
+
"n_head": 16,
|
18 |
"n_inner": null,
|
19 |
+
"n_layer": 24,
|
20 |
"n_positions": 1024,
|
21 |
"resid_pdrop": 0.1,
|
22 |
"scale_attn_weights": true,
|
checkpoint-7000/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b30431b8c91e1a5890e4bb4025b6d7b2606e3ab99067b4d2c9f16a666b7305f8
|
3 |
+
size 2838754801
|
checkpoint-7000/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55037db7a14d29934a9d3aef48fccd8dc1d08f98007a4050bfccc4d25bc02a2e
|
3 |
+
size 1444581337
|
checkpoint-7000/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6c0685f137ce4a3e593c99b4a9e1573a934a7345a9af53f69e9bd12255b142b
|
3 |
size 623
|
checkpoint-7000/tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
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-
|
|
|
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-medium", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
|
checkpoint-7000/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1327
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9568d522549353e20f5776653ff9ca0a85d47d6665a290395fb832486f32551
|
3 |
size 1327
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "microsoft/DialoGPT-
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
@@ -13,10 +13,10 @@
|
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
15 |
"n_ctx": 1024,
|
16 |
-
"n_embd":
|
17 |
-
"n_head":
|
18 |
"n_inner": null,
|
19 |
-
"n_layer":
|
20 |
"n_positions": 1024,
|
21 |
"resid_pdrop": 0.1,
|
22 |
"scale_attn_weights": true,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/DialoGPT-medium",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
|
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
15 |
"n_ctx": 1024,
|
16 |
+
"n_embd": 1024,
|
17 |
+
"n_head": 16,
|
18 |
"n_inner": null,
|
19 |
+
"n_layer": 24,
|
20 |
"n_positions": 1024,
|
21 |
"resid_pdrop": 0.1,
|
22 |
"scale_attn_weights": true,
|
eval_results.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
perplexity = tensor(
|
|
|
1 |
+
perplexity = tensor(5.0177)
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5593ab345ab8db12cab6be4160c896657b488787b167075c8288b17ee676d4f4
|
3 |
+
size 1444581337
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
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-
|
|
|
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-medium", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1327
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9568d522549353e20f5776653ff9ca0a85d47d6665a290395fb832486f32551
|
3 |
size 1327
|