add model gpt2
Browse files- all_results.json +14 -0
- config.json +33 -0
- eval_results.json +9 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +25 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_loss": 4.20829439163208,
|
4 |
+
"eval_runtime": 0.3352,
|
5 |
+
"eval_samples": 2,
|
6 |
+
"eval_samples_per_second": 5.967,
|
7 |
+
"eval_steps_per_second": 2.984,
|
8 |
+
"perplexity": 67.24175384995638,
|
9 |
+
"train_loss": 3.8089685440063477,
|
10 |
+
"train_runtime": 55.2428,
|
11 |
+
"train_samples": 24,
|
12 |
+
"train_samples_per_second": 1.738,
|
13 |
+
"train_steps_per_second": 1.738
|
14 |
+
}
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "cahya/gpt2-small-indonesian-522M",
|
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 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.15.0.dev0",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 50257
|
33 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_loss": 4.20829439163208,
|
4 |
+
"eval_runtime": 0.3352,
|
5 |
+
"eval_samples": 2,
|
6 |
+
"eval_samples_per_second": 5.967,
|
7 |
+
"eval_steps_per_second": 2.984,
|
8 |
+
"perplexity": 67.24175384995638
|
9 |
+
}
|
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 sha256:69a1bd0c533fe67aefe6285986f6dfb1e6d662954d4c85d88a7ff8f72ec28ee4
|
3 |
+
size 510403817
|
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}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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, "max_len": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/57902062674d8ea91c522ec7c31f93f4b3947d525b682597edac4bc76b6d99c2.2b8bf81243d08385c806171bc7ced6d2a0dcc7f896ca637f4e777418f7f0cc3c", "name_or_path": "cahya/gpt2-small-indonesian-522M", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"train_loss": 3.8089685440063477,
|
4 |
+
"train_runtime": 55.2428,
|
5 |
+
"train_samples": 24,
|
6 |
+
"train_samples_per_second": 1.738,
|
7 |
+
"train_steps_per_second": 1.738
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 96,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 4.0,
|
12 |
+
"step": 96,
|
13 |
+
"total_flos": 25084035072000.0,
|
14 |
+
"train_loss": 3.8089685440063477,
|
15 |
+
"train_runtime": 55.2428,
|
16 |
+
"train_samples_per_second": 1.738,
|
17 |
+
"train_steps_per_second": 1.738
|
18 |
+
}
|
19 |
+
],
|
20 |
+
"max_steps": 96,
|
21 |
+
"num_train_epochs": 4,
|
22 |
+
"total_flos": 25084035072000.0,
|
23 |
+
"trial_name": null,
|
24 |
+
"trial_params": null
|
25 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6554eea579696a92ef4d78b8e2a78add162d04503f997fb6c93d22b22fb58aad
|
3 |
+
size 2927
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|