added model files
Browse files- .gitattributes +3 -0
- README.md +7 -1
- config.json +28 -0
- convert_to_TF.py +5 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +142 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitattributes
CHANGED
@@ -25,3 +25,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
29 |
+
training_args.bin filter=lfs diff=lfs merge=lfs -text
|
30 |
+
tf_model.h5 filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,3 +1,9 @@
|
|
1 |
---
|
|
|
|
|
|
|
2 |
license: mit
|
3 |
-
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
|
3 |
+
language:
|
4 |
+
- java
|
5 |
license: mit
|
6 |
+
datasets:
|
7 |
+
- anjandash/java-8m-methods-v1
|
8 |
+
|
9 |
+
---
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/Users/anjandash/Desktop/HF_MODELS/JavaBERT-small",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 3,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-12,
|
17 |
+
"max_position_embeddings": 512,
|
18 |
+
"model_type": "bert",
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 24,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.15.0.dev0",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 64000
|
28 |
+
}
|
convert_to_TF.py
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import TFAutoModelForSequenceClassification
|
2 |
+
|
3 |
+
checkpoint_path = "/Users/anjandash/Desktop/HF_MODELS/JavaBERT-small"
|
4 |
+
tf_model = TFAutoModelForSequenceClassification.from_pretrained(checkpoint_path, from_pt=True)
|
5 |
+
tf_model.save_pretrained(checkpoint_path)
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8591a113fe3ee50b45784491ad89be36cbb7d890bc169cf12016df2f6ece395
|
3 |
+
size 881415723
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3fdc85a7ec7cc911fbfeff8dd59150740406934026703275230b6de44e3185e
|
3 |
+
size 15523
|
scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e7c32d009e082d64df2d932bfa47a085fa94a846f8738f93ddbbcf35c4de54d
|
3 |
+
size 559
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00f19f3443fa68df47a4d4adad8bf0004a93170b3b8916e34a300491882a5702
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6934f86d1df4265b1c9c7d752e1d0dfc5da506aec6194097a3a71f16c7b0972
|
3 |
+
size 881549424
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/home/akarmakar/Project2/tokenizer/jemma-java-bert-tokenizer", "tokenizer_class": "BertTokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 6.430952072143555,
|
3 |
+
"best_model_checkpoint": "finetuned-bert__java-8m-methods__jemma-java-bert-tokenizer__XXXM/checkpoint-45000",
|
4 |
+
"epoch": 2.626185404569461,
|
5 |
+
"global_step": 45000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.29,
|
12 |
+
"learning_rate": 0.0004998919902242132,
|
13 |
+
"loss": 5.8968,
|
14 |
+
"step": 5000
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.29,
|
18 |
+
"eval_loss": 6.462705612182617,
|
19 |
+
"eval_runtime": 1805.2005,
|
20 |
+
"eval_samples_per_second": 27.514,
|
21 |
+
"eval_steps_per_second": 6.879,
|
22 |
+
"step": 5000
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 0.58,
|
26 |
+
"learning_rate": 0.0004994534515508689,
|
27 |
+
"loss": 5.9119,
|
28 |
+
"step": 10000
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 0.58,
|
32 |
+
"eval_loss": 6.476224422454834,
|
33 |
+
"eval_runtime": 1804.4274,
|
34 |
+
"eval_samples_per_second": 27.526,
|
35 |
+
"eval_steps_per_second": 6.882,
|
36 |
+
"step": 10000
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 0.88,
|
40 |
+
"learning_rate": 0.0004986784236353977,
|
41 |
+
"loss": 5.9089,
|
42 |
+
"step": 15000
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 0.88,
|
46 |
+
"eval_loss": 6.472481727600098,
|
47 |
+
"eval_runtime": 1804.1115,
|
48 |
+
"eval_samples_per_second": 27.531,
|
49 |
+
"eval_steps_per_second": 6.883,
|
50 |
+
"step": 15000
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 1.17,
|
54 |
+
"learning_rate": 0.0004975676423415004,
|
55 |
+
"loss": 5.9054,
|
56 |
+
"step": 20000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 1.17,
|
60 |
+
"eval_loss": 6.4574785232543945,
|
61 |
+
"eval_runtime": 1804.4293,
|
62 |
+
"eval_samples_per_second": 27.526,
|
63 |
+
"eval_steps_per_second": 6.882,
|
64 |
+
"step": 20000
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 1.46,
|
68 |
+
"learning_rate": 0.0004961227282936757,
|
69 |
+
"loss": 5.9018,
|
70 |
+
"step": 25000
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 1.46,
|
74 |
+
"eval_loss": 6.441328525543213,
|
75 |
+
"eval_runtime": 1805.0751,
|
76 |
+
"eval_samples_per_second": 27.516,
|
77 |
+
"eval_steps_per_second": 6.879,
|
78 |
+
"step": 25000
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 1.75,
|
82 |
+
"learning_rate": 0.0004943460202721656,
|
83 |
+
"loss": 5.9057,
|
84 |
+
"step": 30000
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 1.75,
|
88 |
+
"eval_loss": 6.43818998336792,
|
89 |
+
"eval_runtime": 1791.0913,
|
90 |
+
"eval_samples_per_second": 27.731,
|
91 |
+
"eval_steps_per_second": 6.933,
|
92 |
+
"step": 30000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 2.04,
|
96 |
+
"learning_rate": 0.0004922392052032267,
|
97 |
+
"loss": 5.9076,
|
98 |
+
"step": 35000
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 2.04,
|
102 |
+
"eval_loss": 6.455899238586426,
|
103 |
+
"eval_runtime": 1805.3008,
|
104 |
+
"eval_samples_per_second": 27.513,
|
105 |
+
"eval_steps_per_second": 6.879,
|
106 |
+
"step": 35000
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 2.33,
|
110 |
+
"learning_rate": 0.0004898059684069413,
|
111 |
+
"loss": 5.8996,
|
112 |
+
"step": 40000
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 2.33,
|
116 |
+
"eval_loss": 6.460456848144531,
|
117 |
+
"eval_runtime": 1805.5197,
|
118 |
+
"eval_samples_per_second": 27.51,
|
119 |
+
"eval_steps_per_second": 6.878,
|
120 |
+
"step": 40000
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 2.63,
|
124 |
+
"learning_rate": 0.00048704920398382135,
|
125 |
+
"loss": 5.9083,
|
126 |
+
"step": 45000
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 2.63,
|
130 |
+
"eval_loss": 6.430952072143555,
|
131 |
+
"eval_runtime": 1807.4508,
|
132 |
+
"eval_samples_per_second": 27.48,
|
133 |
+
"eval_steps_per_second": 6.87,
|
134 |
+
"step": 45000
|
135 |
+
}
|
136 |
+
],
|
137 |
+
"max_steps": 428375,
|
138 |
+
"num_train_epochs": 25,
|
139 |
+
"total_flos": 7.5543354473762e+17,
|
140 |
+
"trial_name": null,
|
141 |
+
"trial_params": null
|
142 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20995a35255e755147fe73406a5b5e0d9face3602f8680abb97f54e0f4ea86b1
|
3 |
+
size 3119
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|