Kasper7953
commited on
Commit
•
c94c54b
1
Parent(s):
180f0af
Training in progress, step 500
Browse files- .gitignore +1 -0
- added_tokens.json +4 -0
- config.json +42 -0
- last-checkpoint/added_tokens.json +4 -0
- last-checkpoint/config.json +42 -0
- last-checkpoint/generation_config.json +6 -0
- last-checkpoint/merges.txt +0 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/pytorch_model.bin +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +24 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +34 -0
- last-checkpoint/trainer_state.json +22 -0
- last-checkpoint/training_args.bin +3 -0
- last-checkpoint/vocab.json +0 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Mar10_20-00-32_05164142ea2f/1678478469.896145/events.out.tfevents.1678478469.05164142ea2f.889.1 +3 -0
- runs/Mar10_20-00-32_05164142ea2f/events.out.tfevents.1678478469.05164142ea2f.889.0 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +34 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 50257,
|
3 |
+
"[PAD]": 50258
|
4 |
+
}
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sberbank-ai/rugpt3medium_based_on_gpt2",
|
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 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"LABEL_0": 0
|
17 |
+
},
|
18 |
+
"layer_norm_epsilon": 1e-05,
|
19 |
+
"model_type": "gpt2",
|
20 |
+
"n_ctx": 2048,
|
21 |
+
"n_embd": 1024,
|
22 |
+
"n_head": 16,
|
23 |
+
"n_inner": null,
|
24 |
+
"n_layer": 24,
|
25 |
+
"n_positions": 2048,
|
26 |
+
"n_special": 0,
|
27 |
+
"output_past": true,
|
28 |
+
"predict_special_tokens": true,
|
29 |
+
"reorder_and_upcast_attn": false,
|
30 |
+
"resid_pdrop": 0.1,
|
31 |
+
"scale_attn_by_inverse_layer_idx": false,
|
32 |
+
"scale_attn_weights": true,
|
33 |
+
"summary_activation": null,
|
34 |
+
"summary_first_dropout": 0.1,
|
35 |
+
"summary_proj_to_labels": true,
|
36 |
+
"summary_type": "cls_index",
|
37 |
+
"summary_use_proj": true,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.26.1",
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 50257
|
42 |
+
}
|
last-checkpoint/added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 50257,
|
3 |
+
"[PAD]": 50258
|
4 |
+
}
|
last-checkpoint/config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sberbank-ai/rugpt3medium_based_on_gpt2",
|
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 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"LABEL_0": 0
|
17 |
+
},
|
18 |
+
"layer_norm_epsilon": 1e-05,
|
19 |
+
"model_type": "gpt2",
|
20 |
+
"n_ctx": 2048,
|
21 |
+
"n_embd": 1024,
|
22 |
+
"n_head": 16,
|
23 |
+
"n_inner": null,
|
24 |
+
"n_layer": 24,
|
25 |
+
"n_positions": 2048,
|
26 |
+
"n_special": 0,
|
27 |
+
"output_past": true,
|
28 |
+
"predict_special_tokens": true,
|
29 |
+
"reorder_and_upcast_attn": false,
|
30 |
+
"resid_pdrop": 0.1,
|
31 |
+
"scale_attn_by_inverse_layer_idx": false,
|
32 |
+
"scale_attn_weights": true,
|
33 |
+
"summary_activation": null,
|
34 |
+
"summary_first_dropout": 0.1,
|
35 |
+
"summary_proj_to_labels": true,
|
36 |
+
"summary_type": "cls_index",
|
37 |
+
"summary_use_proj": true,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.26.1",
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 50257
|
42 |
+
}
|
last-checkpoint/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.26.1"
|
6 |
+
}
|
last-checkpoint/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0024f37facf8b7897d024d92afbe9afb68d7c1fa069bf0a4fe9203ecefb90211
|
3 |
+
size 2847145157
|
last-checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b3457e69764f38e716e4994ac56bab7c516264e01541a474129ceff52fd2dd3
|
3 |
+
size 1524261149
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35df195e1a43c3947450a6ac50115fbae5ac42c9ef09c3f3442e5e38be6cfb99
|
3 |
+
size 14575
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4436e0834f74213631fad9d5594f1f20d2a7925b619ab3564498df85d4ad8544
|
3 |
+
size 627
|
last-checkpoint/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "[PAD]",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
last-checkpoint/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/tokenizer_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eos_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<|endoftext|>",
|
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": "sberbank-ai/rugpt3small_based_on_gpt2",
|
23 |
+
"pad_token": null,
|
24 |
+
"special_tokens_map_file": null,
|
25 |
+
"tokenizer_class": "GPT2Tokenizer",
|
26 |
+
"unk_token": {
|
27 |
+
"__type": "AddedToken",
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0749512816669165,
|
5 |
+
"global_step": 500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.07,
|
12 |
+
"learning_rate": 4.962524359166542e-05,
|
13 |
+
"loss": 2.9056,
|
14 |
+
"step": 500
|
15 |
+
}
|
16 |
+
],
|
17 |
+
"max_steps": 66710,
|
18 |
+
"num_train_epochs": 10,
|
19 |
+
"total_flos": 680200704000000.0,
|
20 |
+
"trial_name": null,
|
21 |
+
"trial_params": null
|
22 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c720066bb18b204985b6d262c61b0bd5878a6786ad051723c31c797e526c1080
|
3 |
+
size 3451
|
last-checkpoint/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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 sha256:6b3457e69764f38e716e4994ac56bab7c516264e01541a474129ceff52fd2dd3
|
3 |
+
size 1524261149
|
runs/Mar10_20-00-32_05164142ea2f/1678478469.896145/events.out.tfevents.1678478469.05164142ea2f.889.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a4d13db3d7f91b725681c274aa39e1026a015d060e60b4a87b85e6e9a174c3e
|
3 |
+
size 5631
|
runs/Mar10_20-00-32_05164142ea2f/events.out.tfevents.1678478469.05164142ea2f.889.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3452b56ba01a27ec45a66cdd35f7e2e29ed8b2a12f5f0752ac67b2d9beb6502b
|
3 |
+
size 4188
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "[PAD]",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eos_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<|endoftext|>",
|
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": "sberbank-ai/rugpt3small_based_on_gpt2",
|
23 |
+
"pad_token": null,
|
24 |
+
"special_tokens_map_file": null,
|
25 |
+
"tokenizer_class": "GPT2Tokenizer",
|
26 |
+
"unk_token": {
|
27 |
+
"__type": "AddedToken",
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c720066bb18b204985b6d262c61b0bd5878a6786ad051723c31c797e526c1080
|
3 |
+
size 3451
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|