first GPT2 model with ~2M words
Browse files- all_results.json +15 -0
- config.json +31 -0
- eval_results.json +10 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- train_results.json +8 -0
- trainer_state.json +49 -0
- vocab.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.324633431085044,
|
4 |
+
"eval_loss": 4.011027812957764,
|
5 |
+
"eval_runtime": 4.2815,
|
6 |
+
"eval_samples": 90,
|
7 |
+
"eval_samples_per_second": 21.021,
|
8 |
+
"eval_steps_per_second": 2.803,
|
9 |
+
"perplexity": 55.20358037015378,
|
10 |
+
"train_loss": 5.383951053103885,
|
11 |
+
"train_runtime": 1331.1447,
|
12 |
+
"train_samples": 2962,
|
13 |
+
"train_samples_per_second": 6.675,
|
14 |
+
"train_steps_per_second": 1.668
|
15 |
+
}
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 50256,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"eos_token_id": 50256,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"layer_norm_epsilon": 1e-05,
|
12 |
+
"model_type": "gpt2",
|
13 |
+
"n_embd": 768,
|
14 |
+
"n_head": 12,
|
15 |
+
"n_inner": null,
|
16 |
+
"n_layer": 12,
|
17 |
+
"n_positions": 1024,
|
18 |
+
"reorder_and_upcast_attn": false,
|
19 |
+
"resid_pdrop": 0.1,
|
20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
21 |
+
"scale_attn_weights": true,
|
22 |
+
"summary_activation": null,
|
23 |
+
"summary_first_dropout": 0.1,
|
24 |
+
"summary_proj_to_labels": true,
|
25 |
+
"summary_type": "cls_index",
|
26 |
+
"summary_use_proj": true,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.29.0.dev0",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 50257
|
31 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.324633431085044,
|
4 |
+
"eval_loss": 4.011027812957764,
|
5 |
+
"eval_runtime": 4.2815,
|
6 |
+
"eval_samples": 90,
|
7 |
+
"eval_samples_per_second": 21.021,
|
8 |
+
"eval_steps_per_second": 2.803,
|
9 |
+
"perplexity": 55.20358037015378
|
10 |
+
}
|
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": "4.29.0.dev0"
|
6 |
+
}
|
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 sha256:8bf0b0af6a8962bbbbdcb71b61c21662f1bbcc0cd9c76631eae5696396c6b8eb
|
3 |
+
size 510396521
|
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 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 1024,
|
7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 5.383951053103885,
|
4 |
+
"train_runtime": 1331.1447,
|
5 |
+
"train_samples": 2962,
|
6 |
+
"train_samples_per_second": 6.675,
|
7 |
+
"train_steps_per_second": 1.668
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.99797434166104,
|
5 |
+
"global_step": 2220,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.68,
|
12 |
+
"learning_rate": 3.873873873873874e-05,
|
13 |
+
"loss": 6.1827,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.35,
|
18 |
+
"learning_rate": 2.7477477477477483e-05,
|
19 |
+
"loss": 5.3106,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.03,
|
24 |
+
"learning_rate": 1.6216216216216218e-05,
|
25 |
+
"loss": 5.1566,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.7,
|
30 |
+
"learning_rate": 4.954954954954955e-06,
|
31 |
+
"loss": 5.057,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 3.0,
|
36 |
+
"step": 2220,
|
37 |
+
"total_flos": 4640546488320000.0,
|
38 |
+
"train_loss": 5.383951053103885,
|
39 |
+
"train_runtime": 1331.1447,
|
40 |
+
"train_samples_per_second": 6.675,
|
41 |
+
"train_steps_per_second": 1.668
|
42 |
+
}
|
43 |
+
],
|
44 |
+
"max_steps": 2220,
|
45 |
+
"num_train_epochs": 3,
|
46 |
+
"total_flos": 4640546488320000.0,
|
47 |
+
"trial_name": null,
|
48 |
+
"trial_params": null
|
49 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|