Initial commit
Browse files- output-small/checkpoint-3500/config.json +37 -0
- output-small/checkpoint-3500/merges.txt +0 -0
- output-small/checkpoint-3500/optimizer.pt +3 -0
- output-small/checkpoint-3500/pytorch_model.bin +3 -0
- output-small/checkpoint-3500/scheduler.pt +3 -0
- output-small/checkpoint-3500/special_tokens_map.json +1 -0
- output-small/checkpoint-3500/tokenizer.json +0 -0
- output-small/checkpoint-3500/tokenizer_config.json +1 -0
- output-small/checkpoint-3500/training_args.bin +3 -0
- output-small/checkpoint-3500/vocab.json +0 -0
- output-small/checkpoint-7000/config.json +37 -0
- output-small/checkpoint-7000/merges.txt +0 -0
- output-small/checkpoint-7000/optimizer.pt +3 -0
- output-small/checkpoint-7000/pytorch_model.bin +3 -0
- output-small/checkpoint-7000/scheduler.pt +3 -0
- output-small/checkpoint-7000/special_tokens_map.json +1 -0
- output-small/checkpoint-7000/tokenizer.json +0 -0
- output-small/checkpoint-7000/tokenizer_config.json +1 -0
- output-small/checkpoint-7000/training_args.bin +3 -0
- output-small/checkpoint-7000/vocab.json +0 -0
- output-small/config.json +37 -0
- output-small/eval_results.txt +1 -0
- output-small/merges.txt +0 -0
- output-small/pytorch_model.bin +3 -0
- output-small/special_tokens_map.json +1 -0
- output-small/tokenizer.json +0 -0
- output-small/tokenizer_config.json +1 -0
- output-small/training_args.bin +3 -0
- output-small/vocab.json +0 -0
output-small/checkpoint-3500/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_weights": true,
|
23 |
+
"summary_activation": null,
|
24 |
+
"summary_first_dropout": 0.1,
|
25 |
+
"summary_proj_to_labels": true,
|
26 |
+
"summary_type": "cls_index",
|
27 |
+
"summary_use_proj": true,
|
28 |
+
"task_specific_params": {
|
29 |
+
"conversational": {
|
30 |
+
"max_length": 1000
|
31 |
+
}
|
32 |
+
},
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.9.2",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 50257
|
37 |
+
}
|
output-small/checkpoint-3500/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
output-small/checkpoint-3500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d0c2ba2efba1f3102da76679938d8480fa8e22d16c4881661847eebb5c84d6a
|
3 |
+
size 995604017
|
output-small/checkpoint-3500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b18fa16e52bc03469e182e22ab703b487981a2a2598d43b953cbf292e2b1218
|
3 |
+
size 510403817
|
output-small/checkpoint-3500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddab8ed65720a54bb869d7f68941e9396bdce5bfc2d811025d03b88ba83652c1
|
3 |
+
size 623
|
output-small/checkpoint-3500/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
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}}
|
output-small/checkpoint-3500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
output-small/checkpoint-3500/tokenizer_config.json
ADDED
@@ -0,0 +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-small", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
|
output-small/checkpoint-3500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11e0d3fc868fe329cbb33ad49a99ebbc0aca294bc209c91f0bd28169fff5d6c2
|
3 |
+
size 1327
|
output-small/checkpoint-3500/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
output-small/checkpoint-7000/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_weights": true,
|
23 |
+
"summary_activation": null,
|
24 |
+
"summary_first_dropout": 0.1,
|
25 |
+
"summary_proj_to_labels": true,
|
26 |
+
"summary_type": "cls_index",
|
27 |
+
"summary_use_proj": true,
|
28 |
+
"task_specific_params": {
|
29 |
+
"conversational": {
|
30 |
+
"max_length": 1000
|
31 |
+
}
|
32 |
+
},
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.9.2",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 50257
|
37 |
+
}
|
output-small/checkpoint-7000/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
output-small/checkpoint-7000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b637f9c9de74da82aa1a94a48a438a7e466c133fbee5500b31ddd9afd444ad5
|
3 |
+
size 995604017
|
output-small/checkpoint-7000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b55cd8bf9e308924d8185ae4fce48ba89fe74e5725a5a8fba9710678d4051d44
|
3 |
+
size 510403817
|
output-small/checkpoint-7000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddb08aaea5b2f048722695b0a422952b8d3e3dbdbc13fca910d9e2c24abcaac1
|
3 |
+
size 623
|
output-small/checkpoint-7000/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
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}}
|
output-small/checkpoint-7000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
output-small/checkpoint-7000/tokenizer_config.json
ADDED
@@ -0,0 +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-small", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
|
output-small/checkpoint-7000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11e0d3fc868fe329cbb33ad49a99ebbc0aca294bc209c91f0bd28169fff5d6c2
|
3 |
+
size 1327
|
output-small/checkpoint-7000/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
output-small/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_weights": true,
|
23 |
+
"summary_activation": null,
|
24 |
+
"summary_first_dropout": 0.1,
|
25 |
+
"summary_proj_to_labels": true,
|
26 |
+
"summary_type": "cls_index",
|
27 |
+
"summary_use_proj": true,
|
28 |
+
"task_specific_params": {
|
29 |
+
"conversational": {
|
30 |
+
"max_length": 1000
|
31 |
+
}
|
32 |
+
},
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.9.2",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 50257
|
37 |
+
}
|
output-small/eval_results.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
perplexity = tensor(7.4193)
|
output-small/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
output-small/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:583a7c55c561bb7a6171c48576360747393ed291acc34519d3932078f2854282
|
3 |
+
size 510403817
|
output-small/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
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}}
|
output-small/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
output-small/tokenizer_config.json
ADDED
@@ -0,0 +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-small", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
|
output-small/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b30ae7335278e93e57405bb84d308eb05b1aa3d0b8e32575228150d9eb4d28d
|
3 |
+
size 1327
|
output-small/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|