nimrazaheer
commited on
Commit
•
8e188bf
1
Parent(s):
bdfda57
Initial commit
Browse files- checkpoint-3500/config.json +38 -0
- checkpoint-3500/merges.txt +0 -0
- checkpoint-3500/optimizer.pt +3 -0
- checkpoint-3500/pytorch_model.bin +3 -0
- checkpoint-3500/scheduler.pt +3 -0
- checkpoint-3500/special_tokens_map.json +1 -0
- checkpoint-3500/tokenizer.json +0 -0
- checkpoint-3500/tokenizer_config.json +1 -0
- checkpoint-3500/training_args.bin +3 -0
- checkpoint-3500/vocab.json +0 -0
- eval_results.txt +1 -1
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
checkpoint-3500/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": "4.16.2",
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 50257
|
38 |
+
}
|
checkpoint-3500/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b446668e2734a00dda55d5c71c9208d599b71908306d521c7be000e1d17ba09
|
3 |
+
size 995604017
|
checkpoint-3500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64af7c4eba8f24a975680aebdbd4f2d5679d65dac3acb65d98c9e5216f8f0244
|
3 |
+
size 510403817
|
checkpoint-3500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7aecab54d728f485fafe7d859f527651d38bb9abf148cd6b4ffcc90b31243db7
|
3 |
+
size 623
|
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}}
|
checkpoint-3500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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"}
|
checkpoint-3500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d40b2d1ce6f07398cf2897deefda41986e1f7d58df0a8709200b81382758fab3
|
3 |
+
size 1327
|
checkpoint-3500/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
eval_results.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
perplexity = tensor(
|
|
|
1 |
+
perplexity = tensor(5.2400)
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510403817
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffc5e925118dde84801751041da6efe8ea29dce2e3a7a2f2cdfd21f8cdfd3b3e
|
3 |
size 510403817
|
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 sha256:079c72d405f53b9038c75690761413bfdf0852363634c6501b54696b284a7596
|
3 |
size 1327
|