End of training
Browse files- .gitignore +1 -0
- config.json +31 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Feb26_23-55-22_62d83bf72530/1677455738.6966555/events.out.tfevents.1677455738.62d83bf72530.3385.1 +3 -0
- runs/Feb26_23-55-22_62d83bf72530/events.out.tfevents.1677455738.62d83bf72530.3385.0 +3 -0
- runs/Feb26_23-58-07_62d83bf72530/1677455891.5433004/events.out.tfevents.1677455891.62d83bf72530.3385.3 +3 -0
- runs/Feb26_23-58-07_62d83bf72530/events.out.tfevents.1677455891.62d83bf72530.3385.2 +3 -0
- runs/Feb27_00-02-31_62d83bf72530/1677456155.7653015/events.out.tfevents.1677456155.62d83bf72530.3385.5 +3 -0
- runs/Feb27_00-02-31_62d83bf72530/events.out.tfevents.1677456155.62d83bf72530.3385.4 +3 -0
- runs/Feb27_00-02-31_62d83bf72530/events.out.tfevents.1677456310.62d83bf72530.3385.6 +3 -0
- special_tokens_map.json +24 -0
- tokenizer_config.json +41 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/opt-350m",
|
3 |
+
"_remove_final_layer_norm": false,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "relu",
|
6 |
+
"architectures": [
|
7 |
+
"OPTForCausalLM"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"bos_token_id": 2,
|
11 |
+
"do_layer_norm_before": false,
|
12 |
+
"dropout": 0.1,
|
13 |
+
"enable_bias": true,
|
14 |
+
"eos_token_id": 2,
|
15 |
+
"ffn_dim": 4096,
|
16 |
+
"hidden_size": 1024,
|
17 |
+
"init_std": 0.02,
|
18 |
+
"layer_norm_elementwise_affine": true,
|
19 |
+
"layerdrop": 0.0,
|
20 |
+
"max_position_embeddings": 2048,
|
21 |
+
"model_type": "opt",
|
22 |
+
"num_attention_heads": 16,
|
23 |
+
"num_hidden_layers": 24,
|
24 |
+
"pad_token_id": 1,
|
25 |
+
"prefix": "</s>",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.26.1",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 50272,
|
30 |
+
"word_embed_proj_dim": 512
|
31 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 1,
|
6 |
+
"transformers_version": "4.26.1"
|
7 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d8f1752df920360e647f00e44afb33e7450988383d049c9c0c53fdec2a011b6
|
3 |
+
size 1324917277
|
runs/Feb26_23-55-22_62d83bf72530/1677455738.6966555/events.out.tfevents.1677455738.62d83bf72530.3385.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a988de98eba7d707be74278e64320240c45f86c979b72c81fd84d610bdf69ff
|
3 |
+
size 5713
|
runs/Feb26_23-55-22_62d83bf72530/events.out.tfevents.1677455738.62d83bf72530.3385.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7ed702c7f6ce9acb7d51e6743cbcc6e09d1e3aee0a6ac24d31bc37bb0c88b9c
|
3 |
+
size 4729
|
runs/Feb26_23-58-07_62d83bf72530/1677455891.5433004/events.out.tfevents.1677455891.62d83bf72530.3385.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4fd22ed584ef2f495ab8a45a56c4e2d3018d1ed554e3541b95118b9f265e431
|
3 |
+
size 5713
|
runs/Feb26_23-58-07_62d83bf72530/events.out.tfevents.1677455891.62d83bf72530.3385.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ef7758784a63a4801366de08a949bbcc1fa7b0382fc594624b7e00002624c54
|
3 |
+
size 5641
|
runs/Feb27_00-02-31_62d83bf72530/1677456155.7653015/events.out.tfevents.1677456155.62d83bf72530.3385.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd10a09218c1776048dfc19a3abf17917e95a194ea3d3324c19012dd3f34ede7
|
3 |
+
size 5713
|
runs/Feb27_00-02-31_62d83bf72530/events.out.tfevents.1677456155.62d83bf72530.3385.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:deff69f628521c80ad81d93f1b2e449055a7e67a0104482b69625c076b233687
|
3 |
+
size 5149
|
runs/Feb27_00-02-31_62d83bf72530/events.out.tfevents.1677456310.62d83bf72530.3385.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f878533bd1d3974feedf0ff0662e1ba629155bd05b60be7f11d5b091fb08a516
|
3 |
+
size 306
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "</s>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "</s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eos_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "</s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"errors": "replace",
|
21 |
+
"model_max_length": 1000000000000000019884624838656,
|
22 |
+
"name_or_path": "facebook/opt-350m",
|
23 |
+
"pad_token": {
|
24 |
+
"__type": "AddedToken",
|
25 |
+
"content": "<pad>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": true,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
"special_tokens_map_file": null,
|
32 |
+
"tokenizer_class": "GPT2Tokenizer",
|
33 |
+
"unk_token": {
|
34 |
+
"__type": "AddedToken",
|
35 |
+
"content": "</s>",
|
36 |
+
"lstrip": false,
|
37 |
+
"normalized": true,
|
38 |
+
"rstrip": false,
|
39 |
+
"single_word": false
|
40 |
+
}
|
41 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13dda0aec9abc7ce5ac7fa26a6425afe660d6f9c9b096465b322669a441b6502
|
3 |
+
size 3515
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|