SashkoMolodec
commited on
Commit
•
381c5aa
1
Parent(s):
78994e3
initial commit
Browse files- config.json +30 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer_config.json +1 -0
- trainer_state.json +181 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "kravchenko/uk-mt5-base",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
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 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"model_type": "mt5",
|
17 |
+
"num_decoder_layers": 12,
|
18 |
+
"num_heads": 12,
|
19 |
+
"num_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"relative_attention_max_distance": 128,
|
23 |
+
"relative_attention_num_buckets": 32,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"tokenizer_class": "T5Tokenizer",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.19.4",
|
28 |
+
"use_cache": false,
|
29 |
+
"vocab_size": 30000
|
30 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29157dcf3425018d331c87b8cad392ccd9a86d869208f9bd56342f42317dc375
|
3 |
+
size 2352161
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c84ab2676ef52e92cbfd8e7a99be03a2b1f952d23a766dc800ae04d0e5219b86
|
3 |
+
size 977332173
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81750b968cd0340e7a5983505039ca105a4fdbeb6c304d503438b2662ed2f542
|
3 |
+
size 14503
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4e620a65074cf282856bc0d62e362f5c3a32377f4b09edab30112b85ba00c60
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa8ea53d190098f2632bd1c44b62731a90a9257a96081183c1a361a24f7ea8ff
|
3 |
+
size 804017
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "sp_model_kwargs": {}, "special_tokens_map_file": "/root/.cache/huggingface/transformers/af67de6ceccc9b1f12679f3c9b1bcd0acc27e990b967b91fed2e8c326187dbdd.294ebaa4cd17bb284635004c92d2c4d522ec488c828dcce0c2471b6f28e3fe82", "name_or_path": "kravchenko/uk-mt5-base", "tokenizer_class": "T5Tokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,181 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.30846577882766724,
|
3 |
+
"best_model_checkpoint": "uk-mt5-small-gec/checkpoint-750",
|
4 |
+
"epoch": 1.950354609929078,
|
5 |
+
"global_step": 1650,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.18,
|
12 |
+
"learning_rate": 0.0009822695035460994,
|
13 |
+
"loss": 1.1542,
|
14 |
+
"step": 150
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.18,
|
18 |
+
"eval_google_bleu": 0.41727698590897433,
|
19 |
+
"eval_loss": 0.40988656878471375,
|
20 |
+
"eval_runtime": 182.204,
|
21 |
+
"eval_samples_per_second": 16.493,
|
22 |
+
"eval_steps_per_second": 0.516,
|
23 |
+
"step": 150
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.35,
|
27 |
+
"learning_rate": 0.0009645390070921985,
|
28 |
+
"loss": 0.4079,
|
29 |
+
"step": 300
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.35,
|
33 |
+
"eval_google_bleu": 0.417700589351588,
|
34 |
+
"eval_loss": 0.3693748116493225,
|
35 |
+
"eval_runtime": 184.6312,
|
36 |
+
"eval_samples_per_second": 16.276,
|
37 |
+
"eval_steps_per_second": 0.509,
|
38 |
+
"step": 300
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.53,
|
42 |
+
"learning_rate": 0.0009468085106382979,
|
43 |
+
"loss": 0.3947,
|
44 |
+
"step": 450
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.53,
|
48 |
+
"eval_google_bleu": 0.42065639483903294,
|
49 |
+
"eval_loss": 0.3382872939109802,
|
50 |
+
"eval_runtime": 182.6943,
|
51 |
+
"eval_samples_per_second": 16.448,
|
52 |
+
"eval_steps_per_second": 0.515,
|
53 |
+
"step": 450
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.71,
|
57 |
+
"learning_rate": 0.0009290780141843972,
|
58 |
+
"loss": 0.3699,
|
59 |
+
"step": 600
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.71,
|
63 |
+
"eval_google_bleu": 0.4213219269019765,
|
64 |
+
"eval_loss": 0.329349160194397,
|
65 |
+
"eval_runtime": 182.8557,
|
66 |
+
"eval_samples_per_second": 16.434,
|
67 |
+
"eval_steps_per_second": 0.514,
|
68 |
+
"step": 600
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.89,
|
72 |
+
"learning_rate": 0.0009113475177304966,
|
73 |
+
"loss": 0.384,
|
74 |
+
"step": 750
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.89,
|
78 |
+
"eval_google_bleu": 0.41960295446754137,
|
79 |
+
"eval_loss": 0.30846577882766724,
|
80 |
+
"eval_runtime": 182.9587,
|
81 |
+
"eval_samples_per_second": 16.424,
|
82 |
+
"eval_steps_per_second": 0.514,
|
83 |
+
"step": 750
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 1.06,
|
87 |
+
"learning_rate": 0.0008936170212765957,
|
88 |
+
"loss": 0.301,
|
89 |
+
"step": 900
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 1.06,
|
93 |
+
"eval_google_bleu": 0.41823031122631055,
|
94 |
+
"eval_loss": 0.30877065658569336,
|
95 |
+
"eval_runtime": 182.6834,
|
96 |
+
"eval_samples_per_second": 16.449,
|
97 |
+
"eval_steps_per_second": 0.515,
|
98 |
+
"step": 900
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.24,
|
102 |
+
"learning_rate": 0.000875886524822695,
|
103 |
+
"loss": 0.2613,
|
104 |
+
"step": 1050
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.24,
|
108 |
+
"eval_google_bleu": 0.41964051019514087,
|
109 |
+
"eval_loss": 0.31575024127960205,
|
110 |
+
"eval_runtime": 182.4274,
|
111 |
+
"eval_samples_per_second": 16.472,
|
112 |
+
"eval_steps_per_second": 0.515,
|
113 |
+
"step": 1050
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 1.42,
|
117 |
+
"learning_rate": 0.0008581560283687944,
|
118 |
+
"loss": 0.2715,
|
119 |
+
"step": 1200
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 1.42,
|
123 |
+
"eval_google_bleu": 0.41992548295187704,
|
124 |
+
"eval_loss": 0.3233252167701721,
|
125 |
+
"eval_runtime": 182.3422,
|
126 |
+
"eval_samples_per_second": 16.48,
|
127 |
+
"eval_steps_per_second": 0.516,
|
128 |
+
"step": 1200
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.6,
|
132 |
+
"learning_rate": 0.0008404255319148936,
|
133 |
+
"loss": 0.2861,
|
134 |
+
"step": 1350
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.6,
|
138 |
+
"eval_google_bleu": 0.41982505463129355,
|
139 |
+
"eval_loss": 0.31152355670928955,
|
140 |
+
"eval_runtime": 182.3799,
|
141 |
+
"eval_samples_per_second": 16.477,
|
142 |
+
"eval_steps_per_second": 0.515,
|
143 |
+
"step": 1350
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 1.77,
|
147 |
+
"learning_rate": 0.0008226950354609929,
|
148 |
+
"loss": 0.2903,
|
149 |
+
"step": 1500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.77,
|
153 |
+
"eval_google_bleu": 0.41824821175792654,
|
154 |
+
"eval_loss": 0.33445030450820923,
|
155 |
+
"eval_runtime": 182.1203,
|
156 |
+
"eval_samples_per_second": 16.5,
|
157 |
+
"eval_steps_per_second": 0.516,
|
158 |
+
"step": 1500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.95,
|
162 |
+
"learning_rate": 0.0008049645390070922,
|
163 |
+
"loss": 0.2811,
|
164 |
+
"step": 1650
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 1.95,
|
168 |
+
"eval_google_bleu": 0.42025291085487376,
|
169 |
+
"eval_loss": 0.3121837377548218,
|
170 |
+
"eval_runtime": 182.2332,
|
171 |
+
"eval_samples_per_second": 16.49,
|
172 |
+
"eval_steps_per_second": 0.516,
|
173 |
+
"step": 1650
|
174 |
+
}
|
175 |
+
],
|
176 |
+
"max_steps": 8460,
|
177 |
+
"num_train_epochs": 10,
|
178 |
+
"total_flos": 6751858532244480.0,
|
179 |
+
"trial_name": null,
|
180 |
+
"trial_params": null
|
181 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0d450feadac456cd19ce450df1036af15bdd3370dd2356a65ffe56aa035065c
|
3 |
+
size 3247
|