End of training
Browse files- .gitignore +1 -0
- config.json +41 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
- runs/Jan27_15-18-48_5da115df40b1/1674832742.7173645/events.out.tfevents.1674832742.5da115df40b1.552.1 +3 -0
- runs/Jan27_15-18-48_5da115df40b1/events.out.tfevents.1674832742.5da115df40b1.552.0 +3 -0
- runs/Jan27_15-18-48_5da115df40b1/events.out.tfevents.1674835201.5da115df40b1.552.2 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "jed351/gpt2-tiny-zh-hk",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 101,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 102,
|
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": 312,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 4,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"reorder_and_upcast_attn": false,
|
22 |
+
"resid_pdrop": 0.1,
|
23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
24 |
+
"scale_attn_weights": true,
|
25 |
+
"summary_activation": null,
|
26 |
+
"summary_first_dropout": 0.1,
|
27 |
+
"summary_proj_to_labels": true,
|
28 |
+
"summary_type": "cls_index",
|
29 |
+
"summary_use_proj": true,
|
30 |
+
"task_specific_params": {
|
31 |
+
"text-generation": {
|
32 |
+
"do_sample": true,
|
33 |
+
"max_length": 50
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"tokenizer_class": "BertTokenizerFast",
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.26.0",
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 21253
|
41 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 101,
|
4 |
+
"eos_token_id": 102,
|
5 |
+
"transformers_version": "4.26.0"
|
6 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f123b3185eabb3b15f0fa0a576e5ac5fbb69ecc18d8cfef40919db469883fce
|
3 |
+
size 50771749
|
runs/Jan27_15-18-48_5da115df40b1/1674832742.7173645/events.out.tfevents.1674832742.5da115df40b1.552.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d5c38e1984e3f9ba21d51c4ac290079e776d4e1beda8e6f4821e7f7facbf94b
|
3 |
+
size 5677
|
runs/Jan27_15-18-48_5da115df40b1/events.out.tfevents.1674832742.5da115df40b1.552.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0cbfb236ddc5858aa26744ce9260deb06f9aa0c89ecc0892a0790348a244709
|
3 |
+
size 8494
|
runs/Jan27_15-18-48_5da115df40b1/events.out.tfevents.1674835201.5da115df40b1.552.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:998838b7693a9d2ff8841a1bc21b8ae129d7680c745ef1e1b9362bc347310d45
|
3 |
+
size 311
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72fa1131049ba7baa363ac0e063a87f1055da9e93f2dfc4251fe04425500d689
|
3 |
+
size 3515
|