Chauhan
commited on
Commit
•
14b027f
1
Parent(s):
9312ea8
Training in progress, step 1000
Browse files- config.json +41 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Mar10_11-47-17_424d238b6191/events.out.tfevents.1710071284.424d238b6191.2339.0 +3 -0
- runs/Mar10_11-48-36_424d238b6191/events.out.tfevents.1710071322.424d238b6191.2451.0 +3 -0
- runs/Mar10_11-50-06_424d238b6191/events.out.tfevents.1710071433.424d238b6191.2520.0 +3 -0
- runs/Mar10_12-02-20_424d238b6191/events.out.tfevents.1710072145.424d238b6191.2594.0 +3 -0
- runs/Mar10_12-08-13_424d238b6191/events.out.tfevents.1710072499.424d238b6191.2700.0 +3 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +19 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai-community/gpt2-medium",
|
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": 1024,
|
16 |
+
"n_head": 16,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 24,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"n_special": 0,
|
21 |
+
"predict_special_tokens": true,
|
22 |
+
"reorder_and_upcast_attn": false,
|
23 |
+
"resid_pdrop": 0.1,
|
24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
25 |
+
"scale_attn_weights": true,
|
26 |
+
"summary_activation": null,
|
27 |
+
"summary_first_dropout": 0.1,
|
28 |
+
"summary_proj_to_labels": true,
|
29 |
+
"summary_type": "cls_index",
|
30 |
+
"summary_use_proj": true,
|
31 |
+
"task_specific_params": {
|
32 |
+
"text-generation": {
|
33 |
+
"do_sample": true,
|
34 |
+
"max_length": 50
|
35 |
+
}
|
36 |
+
},
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.39.0.dev0",
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 50257
|
41 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57521f19038d324a4f173f7b0b98b2351a244987774dc2412c7529011e0f9696
|
3 |
+
size 1419322880
|
runs/Mar10_11-47-17_424d238b6191/events.out.tfevents.1710071284.424d238b6191.2339.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab10faf05a9c88b2fc393c6072d42730b46859d3df794dbf8bf4e136eb759788
|
3 |
+
size 4848
|
runs/Mar10_11-48-36_424d238b6191/events.out.tfevents.1710071322.424d238b6191.2451.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:525c4c6241822cfe2ec381a0aaaf0fec03742e6203ed527cc40f9427eb6e31ff
|
3 |
+
size 4848
|
runs/Mar10_11-50-06_424d238b6191/events.out.tfevents.1710071433.424d238b6191.2520.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ce0aefacaad23a40e6d77c3fb092582502bb729f31b38c400b67abebf168fc3
|
3 |
+
size 5108
|
runs/Mar10_12-02-20_424d238b6191/events.out.tfevents.1710072145.424d238b6191.2594.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:975ab6bbe9e63ff950f306da8ae115503d6cb1fe1a385fc801c951c1203b42b1
|
3 |
+
size 4897
|
runs/Mar10_12-08-13_424d238b6191/events.out.tfevents.1710072499.424d238b6191.2700.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15e4e52c6d44d0fdf19fc7e9d86c0b8275675ac4c1643c730d9f54c039c93b99
|
3 |
+
size 5318
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
}
|
12 |
+
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
+
"clean_up_tokenization_spaces": true,
|
15 |
+
"eos_token": "<|endoftext|>",
|
16 |
+
"model_max_length": 1024,
|
17 |
+
"tokenizer_class": "GPT2Tokenizer",
|
18 |
+
"unk_token": "<|endoftext|>"
|
19 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85dbe9fb0b327907a3db96e153b7a06b93a22caabf7a6e37be6a4bcc67730dde
|
3 |
+
size 4920
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|