joelniklaus
commited on
Commit
•
20e3ff4
1
Parent(s):
ccfab11
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/Feb13_06-43-10_t1v-n-58269bec-w-0/1676270613.759851/events.out.tfevents.1676270613.t1v-n-58269bec-w-0.408756.1 +3 -0
- runs/Feb13_06-43-10_t1v-n-58269bec-w-0/events.out.tfevents.1676270613.t1v-n-58269bec-w-0.408756.0 +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-portuguese-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-portuguese-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 sha256:2a8608e02453ca0127d1b032a499af4278c25cdf1a9737cc488501471a74b1bc
|
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:d5751bc21a3d7b878ba4590c0e169e893532d11a00c5adb7cd5c327bf310f7d2
|
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 sha256:3c5e7ceb2de2087a9513939858085a4759c447a91c205493e170ce0730856097
|
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 sha256:3c5e7ceb2de2087a9513939858085a4759c447a91c205493e170ce0730856097
|
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 sha256:3c5e7ceb2de2087a9513939858085a4759c447a91c205493e170ce0730856097
|
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 sha256:3c5e7ceb2de2087a9513939858085a4759c447a91c205493e170ce0730856097
|
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 sha256:3c5e7ceb2de2087a9513939858085a4759c447a91c205493e170ce0730856097
|
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 sha256:3c5e7ceb2de2087a9513939858085a4759c447a91c205493e170ce0730856097
|
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 sha256:3c5e7ceb2de2087a9513939858085a4759c447a91c205493e170ce0730856097
|
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 sha256:3c5e7ceb2de2087a9513939858085a4759c447a91c205493e170ce0730856097
|
3 |
+
size 13611
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d3c7b27bde8b1f5a5595802aeb17178a4cf1850adf7366fbf6ace3edc933ed8
|
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-portuguese-roberta-base",
|
8 |
+
"pad_token": "<pad>",
|
9 |
+
"sep_token": "</s>",
|
10 |
+
"special_tokens_map_file": "data/plms/legal-portuguese-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": 0.05,
|
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": 0.0,
|
12 |
+
"learning_rate": 2.0000000000000003e-06,
|
13 |
+
"loss": 6.3672,
|
14 |
+
"step": 1000
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.0,
|
18 |
+
"learning_rate": 4.000000000000001e-06,
|
19 |
+
"loss": 4.2266,
|
20 |
+
"step": 2000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.0,
|
24 |
+
"learning_rate": 6e-06,
|
25 |
+
"loss": 3.455,
|
26 |
+
"step": 3000
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.0,
|
30 |
+
"learning_rate": 8.000000000000001e-06,
|
31 |
+
"loss": 3.1273,
|
32 |
+
"step": 4000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.01,
|
36 |
+
"learning_rate": 1e-05,
|
37 |
+
"loss": 2.9742,
|
38 |
+
"step": 5000
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.01,
|
42 |
+
"learning_rate": 1.2e-05,
|
43 |
+
"loss": 2.512,
|
44 |
+
"step": 6000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.01,
|
48 |
+
"learning_rate": 1.4000000000000001e-05,
|
49 |
+
"loss": 2.4775,
|
50 |
+
"step": 7000
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.01,
|
54 |
+
"learning_rate": 1.6000000000000003e-05,
|
55 |
+
"loss": 2.3822,
|
56 |
+
"step": 8000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.01,
|
60 |
+
"learning_rate": 1.8e-05,
|
61 |
+
"loss": 2.3201,
|
62 |
+
"step": 9000
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.01,
|
66 |
+
"learning_rate": 2e-05,
|
67 |
+
"loss": 1.9967,
|
68 |
+
"step": 10000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.01,
|
72 |
+
"learning_rate": 2.2000000000000003e-05,
|
73 |
+
"loss": 2.0182,
|
74 |
+
"step": 11000
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.01,
|
78 |
+
"learning_rate": 2.4e-05,
|
79 |
+
"loss": 1.9828,
|
80 |
+
"step": 12000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.01,
|
84 |
+
"learning_rate": 2.6000000000000002e-05,
|
85 |
+
"loss": 1.9629,
|
86 |
+
"step": 13000
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.01,
|
90 |
+
"learning_rate": 2.8000000000000003e-05,
|
91 |
+
"loss": 1.7017,
|
92 |
+
"step": 14000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.01,
|
96 |
+
"learning_rate": 3e-05,
|
97 |
+
"loss": 1.7443,
|
98 |
+
"step": 15000
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.02,
|
102 |
+
"learning_rate": 3.2000000000000005e-05,
|
103 |
+
"loss": 1.7487,
|
104 |
+
"step": 16000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.02,
|
108 |
+
"learning_rate": 3.4000000000000007e-05,
|
109 |
+
"loss": 1.7432,
|
110 |
+
"step": 17000
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.02,
|
114 |
+
"learning_rate": 3.6e-05,
|
115 |
+
"loss": 1.5099,
|
116 |
+
"step": 18000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.02,
|
120 |
+
"learning_rate": 3.8e-05,
|
121 |
+
"loss": 1.5699,
|
122 |
+
"step": 19000
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.02,
|
126 |
+
"learning_rate": 4e-05,
|
127 |
+
"loss": 1.5984,
|
128 |
+
"step": 20000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.02,
|
132 |
+
"learning_rate": 4.2e-05,
|
133 |
+
"loss": 1.6125,
|
134 |
+
"step": 21000
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.02,
|
138 |
+
"learning_rate": 4.4000000000000006e-05,
|
139 |
+
"loss": 1.3986,
|
140 |
+
"step": 22000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.02,
|
144 |
+
"learning_rate": 4.600000000000001e-05,
|
145 |
+
"loss": 1.4639,
|
146 |
+
"step": 23000
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.02,
|
150 |
+
"learning_rate": 4.8e-05,
|
151 |
+
"loss": 1.5011,
|
152 |
+
"step": 24000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.03,
|
156 |
+
"learning_rate": 5e-05,
|
157 |
+
"loss": 1.5123,
|
158 |
+
"step": 25000
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.03,
|
162 |
+
"learning_rate": 5.2000000000000004e-05,
|
163 |
+
"loss": 1.1547,
|
164 |
+
"step": 26000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.03,
|
168 |
+
"learning_rate": 5.4000000000000005e-05,
|
169 |
+
"loss": 1.0934,
|
170 |
+
"step": 27000
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.03,
|
174 |
+
"learning_rate": 5.6000000000000006e-05,
|
175 |
+
"loss": 1.1841,
|
176 |
+
"step": 28000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.03,
|
180 |
+
"learning_rate": 5.8e-05,
|
181 |
+
"loss": 1.1414,
|
182 |
+
"step": 29000
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.03,
|
186 |
+
"learning_rate": 6e-05,
|
187 |
+
"loss": 0.932,
|
188 |
+
"step": 30000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.03,
|
192 |
+
"learning_rate": 6.2e-05,
|
193 |
+
"loss": 0.9457,
|
194 |
+
"step": 31000
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.03,
|
198 |
+
"learning_rate": 6.400000000000001e-05,
|
199 |
+
"loss": 1.0372,
|
200 |
+
"step": 32000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.03,
|
204 |
+
"learning_rate": 6.6e-05,
|
205 |
+
"loss": 1.0318,
|
206 |
+
"step": 33000
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.03,
|
210 |
+
"learning_rate": 6.800000000000001e-05,
|
211 |
+
"loss": 0.853,
|
212 |
+
"step": 34000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.04,
|
216 |
+
"learning_rate": 7e-05,
|
217 |
+
"loss": 0.8694,
|
218 |
+
"step": 35000
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.04,
|
222 |
+
"learning_rate": 7.2e-05,
|
223 |
+
"loss": 0.9591,
|
224 |
+
"step": 36000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.04,
|
228 |
+
"learning_rate": 7.4e-05,
|
229 |
+
"loss": 0.9554,
|
230 |
+
"step": 37000
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.04,
|
234 |
+
"learning_rate": 7.6e-05,
|
235 |
+
"loss": 0.7879,
|
236 |
+
"step": 38000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.04,
|
240 |
+
"learning_rate": 7.800000000000001e-05,
|
241 |
+
"loss": 0.8222,
|
242 |
+
"step": 39000
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.04,
|
246 |
+
"learning_rate": 8e-05,
|
247 |
+
"loss": 0.9203,
|
248 |
+
"step": 40000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.04,
|
252 |
+
"learning_rate": 8.2e-05,
|
253 |
+
"loss": 0.8901,
|
254 |
+
"step": 41000
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.04,
|
258 |
+
"learning_rate": 8.4e-05,
|
259 |
+
"loss": 0.7294,
|
260 |
+
"step": 42000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.04,
|
264 |
+
"learning_rate": 8.6e-05,
|
265 |
+
"loss": 0.8641,
|
266 |
+
"step": 43000
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.04,
|
270 |
+
"learning_rate": 8.800000000000001e-05,
|
271 |
+
"loss": 0.9008,
|
272 |
+
"step": 44000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.04,
|
276 |
+
"learning_rate": 9e-05,
|
277 |
+
"loss": 0.8812,
|
278 |
+
"step": 45000
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.05,
|
282 |
+
"learning_rate": 9.200000000000001e-05,
|
283 |
+
"loss": 0.7237,
|
284 |
+
"step": 46000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.05,
|
288 |
+
"learning_rate": 9.4e-05,
|
289 |
+
"loss": 0.7512,
|
290 |
+
"step": 47000
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.05,
|
294 |
+
"learning_rate": 9.6e-05,
|
295 |
+
"loss": 0.8537,
|
296 |
+
"step": 48000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.05,
|
300 |
+
"learning_rate": 9.8e-05,
|
301 |
+
"loss": 0.875,
|
302 |
+
"step": 49000
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.05,
|
306 |
+
"learning_rate": 0.0001,
|
307 |
+
"loss": 0.6754,
|
308 |
+
"step": 50000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.05,
|
312 |
+
"eval_loss": 0.7630542516708374,
|
313 |
+
"eval_runtime": 18.8077,
|
314 |
+
"eval_samples_per_second": 265.849,
|
315 |
+
"eval_steps_per_second": 2.127,
|
316 |
+
"step": 50000
|
317 |
+
}
|
318 |
+
],
|
319 |
+
"max_steps": 1000000,
|
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 sha256:28b1cc129db6b36e7b0d1ccb730f31a8a7b0a8e3252e0827900e1a464956502d
|
3 |
+
size 3439
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5751bc21a3d7b878ba4590c0e169e893532d11a00c5adb7cd5c327bf310f7d2
|
3 |
+
size 442675755
|
runs/Feb13_06-43-10_t1v-n-58269bec-w-0/1676270613.759851/events.out.tfevents.1676270613.t1v-n-58269bec-w-0.408756.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a56b96a081c9feaa010cd80aace67cc3ef1cbcde40633ef4149f94fcd4230af0
|
3 |
+
size 5458
|
runs/Feb13_06-43-10_t1v-n-58269bec-w-0/events.out.tfevents.1676270613.t1v-n-58269bec-w-0.408756.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:808576ad864f545b895d8c4ae26f014e386f4924b72f6d41455eafb1a808eb25
|
3 |
+
size 12024
|
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-portuguese-roberta-base",
|
8 |
+
"pad_token": "<pad>",
|
9 |
+
"sep_token": "</s>",
|
10 |
+
"special_tokens_map_file": "data/plms/legal-portuguese-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 sha256:28b1cc129db6b36e7b0d1ccb730f31a8a7b0a8e3252e0827900e1a464956502d
|
3 |
+
size 3439
|