init
Browse files- checkpoint-10500/optimizer.pt +1 -1
- checkpoint-10500/pytorch_model.bin +1 -1
- checkpoint-10500/scheduler.pt +1 -1
- checkpoint-10500/training_args.bin +1 -1
- checkpoint-14000/config.json +38 -0
- checkpoint-14000/merges.txt +0 -0
- checkpoint-14000/optimizer.pt +3 -0
- checkpoint-14000/pytorch_model.bin +3 -0
- checkpoint-14000/scheduler.pt +3 -0
- checkpoint-14000/special_tokens_map.json +23 -0
- checkpoint-14000/tokenizer.json +0 -0
- checkpoint-14000/tokenizer_config.json +34 -0
- checkpoint-14000/training_args.bin +3 -0
- checkpoint-14000/vocab.json +0 -0
- checkpoint-3500/optimizer.pt +1 -1
- checkpoint-3500/pytorch_model.bin +1 -1
- checkpoint-3500/scheduler.pt +1 -1
- checkpoint-3500/training_args.bin +1 -1
- checkpoint-7000/optimizer.pt +1 -1
- checkpoint-7000/pytorch_model.bin +1 -1
- checkpoint-7000/scheduler.pt +1 -1
- checkpoint-7000/training_args.bin +1 -1
- eval_results.txt +1 -1
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
checkpoint-10500/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 995605189
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7075afc18c11b89c20bc6fa6b27eda362b466b1ac74bbd5495eabe67283b9359
|
3 |
size 995605189
|
checkpoint-10500/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510398013
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af2d509a3789ff52e541f54b6662224d592b24a036dd64b86525d11ee2432206
|
3 |
size 510398013
|
checkpoint-10500/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c08cabdb9c832aa7e674fed1ee1c4f18fa1240fa2983702868b1c63c88514af3
|
3 |
size 627
|
checkpoint-10500/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1339
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a45ed4be299adf385700de0d705844ba1f24473a8f6d31654fd60045381beb1
|
3 |
size 1339
|
checkpoint-14000/config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/DialoGPT-small",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"conversational": {
|
31 |
+
"max_length": 1000
|
32 |
+
}
|
33 |
+
},
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.25.1",
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 50257
|
38 |
+
}
|
checkpoint-14000/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-14000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af1c436622c1486c76e1454d889b1762133618f336838eac430f6b72b24784d9
|
3 |
+
size 995605189
|
checkpoint-14000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29d5f0e1a594114f295199e32fdb2f4e5d404867c3797418586368f8bc0512f0
|
3 |
+
size 510398013
|
checkpoint-14000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aed53f9224bf48e2c13d6a3e88dd6174220e89d2eadb66ec4c70420345b47bcb
|
3 |
+
size 627
|
checkpoint-14000/special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
checkpoint-14000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-14000/tokenizer_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eos_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"errors": "replace",
|
21 |
+
"model_max_length": 1024,
|
22 |
+
"name_or_path": "microsoft/DialoGPT-small",
|
23 |
+
"pad_token": null,
|
24 |
+
"special_tokens_map_file": null,
|
25 |
+
"tokenizer_class": "GPT2Tokenizer",
|
26 |
+
"unk_token": {
|
27 |
+
"__type": "AddedToken",
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
checkpoint-14000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a45ed4be299adf385700de0d705844ba1f24473a8f6d31654fd60045381beb1
|
3 |
+
size 1339
|
checkpoint-14000/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3500/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 995605189
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6294a2f7e20c418bbd84a37b986e786cf29489860fd5c2c072370d305cde3f5e
|
3 |
size 995605189
|
checkpoint-3500/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510398013
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66eeeeb1154077ddc91be9844063024073ce0de502f1215d0ffa2893fc356f3c
|
3 |
size 510398013
|
checkpoint-3500/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cddf239ef2a1a98e04d1148859d9721bea5c2e57b40d99b881b5bb9a0b512be
|
3 |
size 627
|
checkpoint-3500/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1339
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a45ed4be299adf385700de0d705844ba1f24473a8f6d31654fd60045381beb1
|
3 |
size 1339
|
checkpoint-7000/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 995605189
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14352c9dc3a005274eec08e3b45dd67989c5bc4e3124c92c4af7a7fcb3aa0e08
|
3 |
size 995605189
|
checkpoint-7000/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510398013
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:807e85bd386312781c5538a7a863426aab13646aa5dd0227542a333f54f5f3b1
|
3 |
size 510398013
|
checkpoint-7000/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f058c8a1b67762a52601ecd3a139b6c446e44cc6340af5edc22d46955463364
|
3 |
size 627
|
checkpoint-7000/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1339
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a45ed4be299adf385700de0d705844ba1f24473a8f6d31654fd60045381beb1
|
3 |
size 1339
|
eval_results.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
perplexity = tensor(2.
|
|
|
1 |
+
perplexity = tensor(2.0515)
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510398013
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6179da52f7911941a2d4bf8d9df9a1b381440b78a2e02b9efaae0f0a3c2755a2
|
3 |
size 510398013
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1339
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a45ed4be299adf385700de0d705844ba1f24473a8f6d31654fd60045381beb1
|
3 |
size 1339
|