joelniklaus
commited on
Commit
•
e2d481a
1
Parent(s):
17becbd
Training in progress, step 50000
Browse files- .gitignore +1 -0
- config.json +27 -0
- last-checkpoint/config.json +27 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/pytorch_model.bin +3 -0
- last-checkpoint/rng_state_0.pth +3 -0
- last-checkpoint/rng_state_1.pth +3 -0
- last-checkpoint/rng_state_2.pth +3 -0
- last-checkpoint/rng_state_3.pth +3 -0
- last-checkpoint/rng_state_4.pth +3 -0
- last-checkpoint/rng_state_5.pth +3 -0
- last-checkpoint/rng_state_6.pth +3 -0
- last-checkpoint/rng_state_7.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +9 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +13 -0
- last-checkpoint/trainer_state.json +324 -0
- last-checkpoint/training_args.bin +3 -0
- pytorch_model.bin +3 -0
- runs/Feb06_07-50-48_t1v-n-ddbbc52f-w-0/1675669872.2929602/events.out.tfevents.1675669872.t1v-n-ddbbc52f-w-0.12174.1 +3 -0
- runs/Feb06_07-50-48_t1v-n-ddbbc52f-w-0/events.out.tfevents.1675669872.t1v-n-ddbbc52f-w-0.12174.0 +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "data/plms/legal-greek-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.20.1",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 32000
|
27 |
+
}
|
last-checkpoint/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "data/plms/legal-greek-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.20.1",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 32000
|
27 |
+
}
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3eaddf7efc56544567f4a4183997b8e54e580c56d9a9067098902fce85030eb
|
3 |
+
size 885324633
|
last-checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb52a91ca7db3e27020e977bb9700207dd283e260489890071175dacdc1c8848
|
3 |
+
size 442675755
|
last-checkpoint/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74107da37598d5bb6bc779934fa91686ae3470dc25d0f1b64c3fe18e46a365d1
|
3 |
+
size 13611
|
last-checkpoint/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74107da37598d5bb6bc779934fa91686ae3470dc25d0f1b64c3fe18e46a365d1
|
3 |
+
size 13611
|
last-checkpoint/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74107da37598d5bb6bc779934fa91686ae3470dc25d0f1b64c3fe18e46a365d1
|
3 |
+
size 13611
|
last-checkpoint/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74107da37598d5bb6bc779934fa91686ae3470dc25d0f1b64c3fe18e46a365d1
|
3 |
+
size 13611
|
last-checkpoint/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74107da37598d5bb6bc779934fa91686ae3470dc25d0f1b64c3fe18e46a365d1
|
3 |
+
size 13611
|
last-checkpoint/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74107da37598d5bb6bc779934fa91686ae3470dc25d0f1b64c3fe18e46a365d1
|
3 |
+
size 13611
|
last-checkpoint/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74107da37598d5bb6bc779934fa91686ae3470dc25d0f1b64c3fe18e46a365d1
|
3 |
+
size 13611
|
last-checkpoint/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74107da37598d5bb6bc779934fa91686ae3470dc25d0f1b64c3fe18e46a365d1
|
3 |
+
size 13611
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4eda5fed79fbfae57d1a589b135999ab70f7c329a9938c428058fd62dc77c658
|
3 |
+
size 623
|
last-checkpoint/special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
last-checkpoint/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"name_or_path": "data/plms/legal-greek-roberta-base",
|
8 |
+
"pad_token": "<pad>",
|
9 |
+
"sep_token": "</s>",
|
10 |
+
"special_tokens_map_file": "data/plms/legal-greek-roberta-base_32k/special_tokens_map.json",
|
11 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
12 |
+
"unk_token": "<unk>"
|
13 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,324 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 12.00088,
|
5 |
+
"global_step": 50000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.01,
|
12 |
+
"learning_rate": 1e-05,
|
13 |
+
"loss": 8.4652,
|
14 |
+
"step": 1000
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.01,
|
18 |
+
"learning_rate": 2e-05,
|
19 |
+
"loss": 6.089,
|
20 |
+
"step": 2000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.01,
|
24 |
+
"learning_rate": 3e-05,
|
25 |
+
"loss": 5.551,
|
26 |
+
"step": 3000
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.02,
|
30 |
+
"learning_rate": 4e-05,
|
31 |
+
"loss": 4.8056,
|
32 |
+
"step": 4000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.0,
|
36 |
+
"learning_rate": 5e-05,
|
37 |
+
"loss": 4.0329,
|
38 |
+
"step": 5000
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.01,
|
42 |
+
"learning_rate": 6e-05,
|
43 |
+
"loss": 2.3276,
|
44 |
+
"step": 6000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.01,
|
48 |
+
"learning_rate": 7e-05,
|
49 |
+
"loss": 1.7263,
|
50 |
+
"step": 7000
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 1.02,
|
54 |
+
"learning_rate": 8e-05,
|
55 |
+
"loss": 1.6089,
|
56 |
+
"step": 8000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 2.0,
|
60 |
+
"learning_rate": 9e-05,
|
61 |
+
"loss": 1.5133,
|
62 |
+
"step": 9000
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 2.01,
|
66 |
+
"learning_rate": 0.0001,
|
67 |
+
"loss": 1.2832,
|
68 |
+
"step": 10000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 2.01,
|
72 |
+
"learning_rate": 9.999316524962345e-05,
|
73 |
+
"loss": 1.1773,
|
74 |
+
"step": 11000
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 2.02,
|
78 |
+
"learning_rate": 9.997266286704631e-05,
|
79 |
+
"loss": 1.2188,
|
80 |
+
"step": 12000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 3.0,
|
84 |
+
"learning_rate": 9.993849845741524e-05,
|
85 |
+
"loss": 1.2291,
|
86 |
+
"step": 13000
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 3.01,
|
90 |
+
"learning_rate": 9.989068136093873e-05,
|
91 |
+
"loss": 1.1196,
|
92 |
+
"step": 14000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 3.01,
|
96 |
+
"learning_rate": 9.98292246503335e-05,
|
97 |
+
"loss": 1.0393,
|
98 |
+
"step": 15000
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 3.02,
|
102 |
+
"learning_rate": 9.975414512725057e-05,
|
103 |
+
"loss": 1.0729,
|
104 |
+
"step": 16000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 4.0,
|
108 |
+
"learning_rate": 9.966546331768191e-05,
|
109 |
+
"loss": 1.1187,
|
110 |
+
"step": 17000
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 4.01,
|
114 |
+
"learning_rate": 9.956320346634876e-05,
|
115 |
+
"loss": 1.0602,
|
116 |
+
"step": 18000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 4.01,
|
120 |
+
"learning_rate": 9.944739353007344e-05,
|
121 |
+
"loss": 0.9615,
|
122 |
+
"step": 19000
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 4.02,
|
126 |
+
"learning_rate": 9.931806517013612e-05,
|
127 |
+
"loss": 0.9844,
|
128 |
+
"step": 20000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 5.0,
|
132 |
+
"learning_rate": 9.917525374361912e-05,
|
133 |
+
"loss": 1.052,
|
134 |
+
"step": 21000
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 5.01,
|
138 |
+
"learning_rate": 9.901899829374047e-05,
|
139 |
+
"loss": 1.0116,
|
140 |
+
"step": 22000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 5.01,
|
144 |
+
"learning_rate": 9.884934153917997e-05,
|
145 |
+
"loss": 0.9324,
|
146 |
+
"step": 23000
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 5.02,
|
150 |
+
"learning_rate": 9.86663298624003e-05,
|
151 |
+
"loss": 0.9189,
|
152 |
+
"step": 24000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 6.0,
|
156 |
+
"learning_rate": 9.847001329696653e-05,
|
157 |
+
"loss": 1.0033,
|
158 |
+
"step": 25000
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 6.01,
|
162 |
+
"learning_rate": 9.826044551386744e-05,
|
163 |
+
"loss": 0.9903,
|
164 |
+
"step": 26000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 6.01,
|
168 |
+
"learning_rate": 9.803768380684242e-05,
|
169 |
+
"loss": 0.9018,
|
170 |
+
"step": 27000
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 6.02,
|
174 |
+
"learning_rate": 9.780178907671789e-05,
|
175 |
+
"loss": 0.8627,
|
176 |
+
"step": 28000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 6.02,
|
180 |
+
"learning_rate": 9.755282581475769e-05,
|
181 |
+
"loss": 0.9721,
|
182 |
+
"step": 29000
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 7.0,
|
186 |
+
"learning_rate": 9.729086208503174e-05,
|
187 |
+
"loss": 0.9775,
|
188 |
+
"step": 30000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 7.01,
|
192 |
+
"learning_rate": 9.701596950580806e-05,
|
193 |
+
"loss": 0.8738,
|
194 |
+
"step": 31000
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 7.01,
|
198 |
+
"learning_rate": 9.672822322997305e-05,
|
199 |
+
"loss": 0.8174,
|
200 |
+
"step": 32000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 7.02,
|
204 |
+
"learning_rate": 9.642770192448536e-05,
|
205 |
+
"loss": 0.9494,
|
206 |
+
"step": 33000
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 8.0,
|
210 |
+
"learning_rate": 9.611448774886924e-05,
|
211 |
+
"loss": 0.9505,
|
212 |
+
"step": 34000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 8.01,
|
216 |
+
"learning_rate": 9.578866633275288e-05,
|
217 |
+
"loss": 0.8665,
|
218 |
+
"step": 35000
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 8.01,
|
222 |
+
"learning_rate": 9.545032675245813e-05,
|
223 |
+
"loss": 0.7849,
|
224 |
+
"step": 36000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 8.02,
|
228 |
+
"learning_rate": 9.509956150664796e-05,
|
229 |
+
"loss": 0.9324,
|
230 |
+
"step": 37000
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 9.0,
|
234 |
+
"learning_rate": 9.473646649103818e-05,
|
235 |
+
"loss": 0.9189,
|
236 |
+
"step": 38000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 9.01,
|
240 |
+
"learning_rate": 9.43611409721806e-05,
|
241 |
+
"loss": 0.8631,
|
242 |
+
"step": 39000
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 9.01,
|
246 |
+
"learning_rate": 9.397368756032445e-05,
|
247 |
+
"loss": 0.7853,
|
248 |
+
"step": 40000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 9.02,
|
252 |
+
"learning_rate": 9.357421218136386e-05,
|
253 |
+
"loss": 0.8816,
|
254 |
+
"step": 41000
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 10.0,
|
258 |
+
"learning_rate": 9.316282404787871e-05,
|
259 |
+
"loss": 0.8999,
|
260 |
+
"step": 42000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 10.01,
|
264 |
+
"learning_rate": 9.273963562927695e-05,
|
265 |
+
"loss": 0.861,
|
266 |
+
"step": 43000
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 10.01,
|
270 |
+
"learning_rate": 9.230476262104677e-05,
|
271 |
+
"loss": 0.7854,
|
272 |
+
"step": 44000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 10.02,
|
276 |
+
"learning_rate": 9.185832391312644e-05,
|
277 |
+
"loss": 0.8388,
|
278 |
+
"step": 45000
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 11.0,
|
282 |
+
"learning_rate": 9.140044155740101e-05,
|
283 |
+
"loss": 0.8872,
|
284 |
+
"step": 46000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 11.01,
|
288 |
+
"learning_rate": 9.093124073433463e-05,
|
289 |
+
"loss": 0.8658,
|
290 |
+
"step": 47000
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 11.01,
|
294 |
+
"learning_rate": 9.045084971874738e-05,
|
295 |
+
"loss": 0.7754,
|
296 |
+
"step": 48000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 11.02,
|
300 |
+
"learning_rate": 8.995939984474624e-05,
|
301 |
+
"loss": 0.806,
|
302 |
+
"step": 49000
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 12.0,
|
306 |
+
"learning_rate": 8.945702546981969e-05,
|
307 |
+
"loss": 0.8724,
|
308 |
+
"step": 50000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 12.0,
|
312 |
+
"eval_loss": 0.6730242967605591,
|
313 |
+
"eval_runtime": 18.7856,
|
314 |
+
"eval_samples_per_second": 266.161,
|
315 |
+
"eval_steps_per_second": 2.129,
|
316 |
+
"step": 50000
|
317 |
+
}
|
318 |
+
],
|
319 |
+
"max_steps": 200000,
|
320 |
+
"num_train_epochs": 9223372036854775807,
|
321 |
+
"total_flos": 8.422699302912e+17,
|
322 |
+
"trial_name": null,
|
323 |
+
"trial_params": null
|
324 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48ad22a1d6011ac41f0bcbdf08d83ea0859ed7fa3a202466f11796b67792651d
|
3 |
+
size 3439
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb52a91ca7db3e27020e977bb9700207dd283e260489890071175dacdc1c8848
|
3 |
+
size 442675755
|
runs/Feb06_07-50-48_t1v-n-ddbbc52f-w-0/1675669872.2929602/events.out.tfevents.1675669872.t1v-n-ddbbc52f-w-0.12174.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5bf27d8e2c522a61ce84f96c53c157a1cd7d06318e17dcf8ba8cd6eb27f586a
|
3 |
+
size 5438
|
runs/Feb06_07-50-48_t1v-n-ddbbc52f-w-0/events.out.tfevents.1675669872.t1v-n-ddbbc52f-w-0.12174.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9758eb216b80b50235c6989c71649acb88c175ac64acf9b4cea9a088763523b
|
3 |
+
size 11998
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"name_or_path": "data/plms/legal-greek-roberta-base",
|
8 |
+
"pad_token": "<pad>",
|
9 |
+
"sep_token": "</s>",
|
10 |
+
"special_tokens_map_file": "data/plms/legal-greek-roberta-base_32k/special_tokens_map.json",
|
11 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
12 |
+
"unk_token": "<unk>"
|
13 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48ad22a1d6011ac41f0bcbdf08d83ea0859ed7fa3a202466f11796b67792651d
|
3 |
+
size 3439
|