samikhan121
commited on
Commit
•
b46fbf4
1
Parent(s):
2fb8d8e
trained on indicmarco for 2 epochs
Browse files- checkpoint-4000/config.json +29 -0
- checkpoint-4000/optimizer.pt +3 -0
- checkpoint-4000/pytorch_model.bin +3 -0
- checkpoint-4000/rng_state.pth +3 -0
- checkpoint-4000/scaler.pt +3 -0
- checkpoint-4000/scheduler.pt +3 -0
- checkpoint-4000/special_tokens_map.json +1 -0
- checkpoint-4000/spiece.model +3 -0
- checkpoint-4000/tokenizer.json +0 -0
- checkpoint-4000/tokenizer_config.json +1 -0
- checkpoint-4000/trainer_state.json +264 -0
- checkpoint-4000/training_args.bin +3 -0
- config.json +29 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
checkpoint-4000/config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "csebuetnlp/banglat5",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2048,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "gated-gelu",
|
13 |
+
"gradient_checkpointing": false,
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"layer_norm_epsilon": 1e-06,
|
17 |
+
"model_type": "t5",
|
18 |
+
"num_decoder_layers": 12,
|
19 |
+
"num_heads": 12,
|
20 |
+
"num_layers": 12,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_num_buckets": 32,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.16.0",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 32128
|
29 |
+
}
|
checkpoint-4000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fcfb6be105945579dfc4dc3f59f6a8855baf8a1cd6c686a8534db9ea254db5c
|
3 |
+
size 1980788441
|
checkpoint-4000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f7459856ae487651345537ffc64109198fbba2eb58b1a21b1e785478cc80586
|
3 |
+
size 990438349
|
checkpoint-4000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a956747b430cb60db8a0fb636f8cdadaf3a232a106344911fff66a6d543d067d
|
3 |
+
size 14503
|
checkpoint-4000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:065f8f26cceeb1f27fd509c28355e76259811bd58ce56cd862d4f918dd8697b9
|
3 |
+
size 559
|
checkpoint-4000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a3235bd7b0de3314aa893f2f2f39d61f825435aadbdb8dbe0bc333f10ce1beb
|
3 |
+
size 623
|
checkpoint-4000/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
checkpoint-4000/spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dcab96935a2a51b1461c84e44c952ea8a3640c8bc3e2c6ae7a21d855454ae27
|
3 |
+
size 1111492
|
checkpoint-4000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4000/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": "/home/cse/.cache/huggingface/transformers/ff0ed476d41a6f336fa52bd906c6c8f0a8684fe67bec634b201ed2d24331c915.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46", "name_or_path": "csebuetnlp/banglat5", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
|
checkpoint-4000/trainer_state.json
ADDED
@@ -0,0 +1,264 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.925743170056565,
|
5 |
+
"global_step": 4000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.05,
|
12 |
+
"learning_rate": 9.759268175252769e-05,
|
13 |
+
"loss": 9.8702,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.1,
|
18 |
+
"learning_rate": 9.518536350505537e-05,
|
19 |
+
"loss": 5.0407,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.14,
|
24 |
+
"learning_rate": 9.277804525758305e-05,
|
25 |
+
"loss": 3.9664,
|
26 |
+
"step": 300
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.19,
|
30 |
+
"learning_rate": 9.037072701011074e-05,
|
31 |
+
"loss": 3.6556,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.24,
|
36 |
+
"learning_rate": 8.796340876263843e-05,
|
37 |
+
"loss": 3.4608,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.29,
|
42 |
+
"learning_rate": 8.555609051516611e-05,
|
43 |
+
"loss": 3.3129,
|
44 |
+
"step": 600
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.34,
|
48 |
+
"learning_rate": 8.31487722676938e-05,
|
49 |
+
"loss": 3.2072,
|
50 |
+
"step": 700
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.39,
|
54 |
+
"learning_rate": 8.074145402022148e-05,
|
55 |
+
"loss": 3.1383,
|
56 |
+
"step": 800
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.43,
|
60 |
+
"learning_rate": 7.833413577274916e-05,
|
61 |
+
"loss": 3.0606,
|
62 |
+
"step": 900
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.48,
|
66 |
+
"learning_rate": 7.592681752527685e-05,
|
67 |
+
"loss": 2.9994,
|
68 |
+
"step": 1000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.53,
|
72 |
+
"learning_rate": 7.351949927780452e-05,
|
73 |
+
"loss": 2.9714,
|
74 |
+
"step": 1100
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.58,
|
78 |
+
"learning_rate": 7.111218103033221e-05,
|
79 |
+
"loss": 2.9432,
|
80 |
+
"step": 1200
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.63,
|
84 |
+
"learning_rate": 6.87048627828599e-05,
|
85 |
+
"loss": 2.8978,
|
86 |
+
"step": 1300
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.67,
|
90 |
+
"learning_rate": 6.629754453538758e-05,
|
91 |
+
"loss": 2.8998,
|
92 |
+
"step": 1400
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.72,
|
96 |
+
"learning_rate": 6.389022628791527e-05,
|
97 |
+
"loss": 2.8704,
|
98 |
+
"step": 1500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.77,
|
102 |
+
"learning_rate": 6.148290804044296e-05,
|
103 |
+
"loss": 2.8642,
|
104 |
+
"step": 1600
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.82,
|
108 |
+
"learning_rate": 5.907558979297063e-05,
|
109 |
+
"loss": 2.832,
|
110 |
+
"step": 1700
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.87,
|
114 |
+
"learning_rate": 5.666827154549832e-05,
|
115 |
+
"loss": 2.8027,
|
116 |
+
"step": 1800
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.91,
|
120 |
+
"learning_rate": 5.426095329802601e-05,
|
121 |
+
"loss": 2.7968,
|
122 |
+
"step": 1900
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.96,
|
126 |
+
"learning_rate": 5.185363505055368e-05,
|
127 |
+
"loss": 2.7954,
|
128 |
+
"step": 2000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.0,
|
132 |
+
"eval_loss": 2.46354079246521,
|
133 |
+
"eval_runtime": 2.8271,
|
134 |
+
"eval_samples_per_second": 353.714,
|
135 |
+
"eval_steps_per_second": 44.214,
|
136 |
+
"step": 2077
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 1.01,
|
140 |
+
"learning_rate": 4.9446316803081375e-05,
|
141 |
+
"loss": 2.7673,
|
142 |
+
"step": 2100
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.06,
|
146 |
+
"learning_rate": 4.7038998555609055e-05,
|
147 |
+
"loss": 2.7401,
|
148 |
+
"step": 2200
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 1.11,
|
152 |
+
"learning_rate": 4.4631680308136736e-05,
|
153 |
+
"loss": 2.7456,
|
154 |
+
"step": 2300
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 1.16,
|
158 |
+
"learning_rate": 4.222436206066442e-05,
|
159 |
+
"loss": 2.742,
|
160 |
+
"step": 2400
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 1.2,
|
164 |
+
"learning_rate": 3.98170438131921e-05,
|
165 |
+
"loss": 2.7218,
|
166 |
+
"step": 2500
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 1.25,
|
170 |
+
"learning_rate": 3.740972556571979e-05,
|
171 |
+
"loss": 2.7248,
|
172 |
+
"step": 2600
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 1.3,
|
176 |
+
"learning_rate": 3.500240731824748e-05,
|
177 |
+
"loss": 2.7145,
|
178 |
+
"step": 2700
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 1.35,
|
182 |
+
"learning_rate": 3.259508907077516e-05,
|
183 |
+
"loss": 2.7046,
|
184 |
+
"step": 2800
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.4,
|
188 |
+
"learning_rate": 3.0187770823302842e-05,
|
189 |
+
"loss": 2.7095,
|
190 |
+
"step": 2900
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 1.44,
|
194 |
+
"learning_rate": 2.7780452575830522e-05,
|
195 |
+
"loss": 2.7005,
|
196 |
+
"step": 3000
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 1.49,
|
200 |
+
"learning_rate": 2.537313432835821e-05,
|
201 |
+
"loss": 2.6941,
|
202 |
+
"step": 3100
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 1.54,
|
206 |
+
"learning_rate": 2.2965816080885893e-05,
|
207 |
+
"loss": 2.6727,
|
208 |
+
"step": 3200
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 1.59,
|
212 |
+
"learning_rate": 2.0558497833413577e-05,
|
213 |
+
"loss": 2.6959,
|
214 |
+
"step": 3300
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 1.64,
|
218 |
+
"learning_rate": 1.8151179585941264e-05,
|
219 |
+
"loss": 2.6839,
|
220 |
+
"step": 3400
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 1.69,
|
224 |
+
"learning_rate": 1.5743861338468945e-05,
|
225 |
+
"loss": 2.6781,
|
226 |
+
"step": 3500
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.73,
|
230 |
+
"learning_rate": 1.333654309099663e-05,
|
231 |
+
"loss": 2.6732,
|
232 |
+
"step": 3600
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 1.78,
|
236 |
+
"learning_rate": 1.0929224843524314e-05,
|
237 |
+
"loss": 2.6776,
|
238 |
+
"step": 3700
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 1.83,
|
242 |
+
"learning_rate": 8.521906596051998e-06,
|
243 |
+
"loss": 2.673,
|
244 |
+
"step": 3800
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 1.88,
|
248 |
+
"learning_rate": 6.114588348579683e-06,
|
249 |
+
"loss": 2.6832,
|
250 |
+
"step": 3900
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 1.93,
|
254 |
+
"learning_rate": 3.7072701011073664e-06,
|
255 |
+
"loss": 2.6659,
|
256 |
+
"step": 4000
|
257 |
+
}
|
258 |
+
],
|
259 |
+
"max_steps": 4154,
|
260 |
+
"num_train_epochs": 2,
|
261 |
+
"total_flos": 2.1297995361473126e+17,
|
262 |
+
"trial_name": null,
|
263 |
+
"trial_params": null
|
264 |
+
}
|
checkpoint-4000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af64407701951f621066c4162ac83b5a15d5e53e88b725b8747fc592fe12d5b0
|
3 |
+
size 3183
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "csebuetnlp/banglat5",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2048,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "gated-gelu",
|
13 |
+
"gradient_checkpointing": false,
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"layer_norm_epsilon": 1e-06,
|
17 |
+
"model_type": "t5",
|
18 |
+
"num_decoder_layers": 12,
|
19 |
+
"num_heads": 12,
|
20 |
+
"num_layers": 12,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_num_buckets": 32,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.16.0",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 32128
|
29 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bda1dd771e10a900459c5bf7507b689da168d85cbf0c303643ec3d0b79611e7
|
3 |
+
size 990438349
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dcab96935a2a51b1461c84e44c952ea8a3640c8bc3e2c6ae7a21d855454ae27
|
3 |
+
size 1111492
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": "/home/cse/.cache/huggingface/transformers/ff0ed476d41a6f336fa52bd906c6c8f0a8684fe67bec634b201ed2d24331c915.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46", "name_or_path": "csebuetnlp/banglat5", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af64407701951f621066c4162ac83b5a15d5e53e88b725b8747fc592fe12d5b0
|
3 |
+
size 3183
|