Nikita Moghe Moghe
commited on
Commit
•
87da19a
1
Parent(s):
5330033
First model version
Browse files- config.json +30 -0
- eval_results_mlm.txt +1 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.txt +3 -0
- trainer_state.json +622 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-multilingual-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"directionality": "bidi",
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pooler_fc_size": 768,
|
21 |
+
"pooler_num_attention_heads": 12,
|
22 |
+
"pooler_num_fc_layers": 3,
|
23 |
+
"pooler_size_per_head": 128,
|
24 |
+
"pooler_type": "first_token_transform",
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"transformers_version": "4.2.2",
|
27 |
+
"type_vocab_size": 2,
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 105879
|
30 |
+
}
|
eval_results_mlm.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
perplexity = 8703.36088420641
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31f8e5b1f0ee45f0fa904f4af6881b283120c7309d5c85fa1dc9c874ecd04632
|
3 |
+
size 669910510
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<S>", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
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, "name_or_path": "bert-base-multilingual-uncased"}
|
train_results.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
epoch = 20.0
|
2 |
+
train_runtime = 72937.5039
|
3 |
+
train_samples_per_second = 3.428
|
trainer_state.json
ADDED
@@ -0,0 +1,622 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 20.0,
|
5 |
+
"global_step": 250000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.2,
|
12 |
+
"learning_rate": 4.9500000000000004e-05,
|
13 |
+
"loss": 5.8035,
|
14 |
+
"step": 2500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.4,
|
18 |
+
"learning_rate": 4.9e-05,
|
19 |
+
"loss": 5.6846,
|
20 |
+
"step": 5000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.6,
|
24 |
+
"learning_rate": 4.85e-05,
|
25 |
+
"loss": 5.6715,
|
26 |
+
"step": 7500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.8,
|
30 |
+
"learning_rate": 4.8e-05,
|
31 |
+
"loss": 5.6443,
|
32 |
+
"step": 10000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.0,
|
36 |
+
"learning_rate": 4.75e-05,
|
37 |
+
"loss": 5.6103,
|
38 |
+
"step": 12500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.2,
|
42 |
+
"learning_rate": 4.7e-05,
|
43 |
+
"loss": 5.5002,
|
44 |
+
"step": 15000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.4,
|
48 |
+
"learning_rate": 4.6500000000000005e-05,
|
49 |
+
"loss": 5.4878,
|
50 |
+
"step": 17500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 1.6,
|
54 |
+
"learning_rate": 4.600000000000001e-05,
|
55 |
+
"loss": 5.5005,
|
56 |
+
"step": 20000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 1.8,
|
60 |
+
"learning_rate": 4.55e-05,
|
61 |
+
"loss": 5.5005,
|
62 |
+
"step": 22500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 2.0,
|
66 |
+
"learning_rate": 4.5e-05,
|
67 |
+
"loss": 5.4821,
|
68 |
+
"step": 25000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 2.2,
|
72 |
+
"learning_rate": 4.4500000000000004e-05,
|
73 |
+
"loss": 5.3239,
|
74 |
+
"step": 27500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 2.4,
|
78 |
+
"learning_rate": 4.4000000000000006e-05,
|
79 |
+
"loss": 5.3328,
|
80 |
+
"step": 30000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 2.6,
|
84 |
+
"learning_rate": 4.35e-05,
|
85 |
+
"loss": 5.3409,
|
86 |
+
"step": 32500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.8,
|
90 |
+
"learning_rate": 4.3e-05,
|
91 |
+
"loss": 5.3499,
|
92 |
+
"step": 35000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 3.0,
|
96 |
+
"learning_rate": 4.25e-05,
|
97 |
+
"loss": 5.3475,
|
98 |
+
"step": 37500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 3.2,
|
102 |
+
"learning_rate": 4.2e-05,
|
103 |
+
"loss": 5.1148,
|
104 |
+
"step": 40000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 3.4,
|
108 |
+
"learning_rate": 4.15e-05,
|
109 |
+
"loss": 5.122,
|
110 |
+
"step": 42500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 3.6,
|
114 |
+
"learning_rate": 4.1e-05,
|
115 |
+
"loss": 5.1339,
|
116 |
+
"step": 45000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 3.8,
|
120 |
+
"learning_rate": 4.05e-05,
|
121 |
+
"loss": 5.1598,
|
122 |
+
"step": 47500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 4.0,
|
126 |
+
"learning_rate": 4e-05,
|
127 |
+
"loss": 5.1829,
|
128 |
+
"step": 50000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 4.2,
|
132 |
+
"learning_rate": 3.9500000000000005e-05,
|
133 |
+
"loss": 4.8405,
|
134 |
+
"step": 52500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 4.4,
|
138 |
+
"learning_rate": 3.9000000000000006e-05,
|
139 |
+
"loss": 4.8717,
|
140 |
+
"step": 55000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 4.6,
|
144 |
+
"learning_rate": 3.85e-05,
|
145 |
+
"loss": 4.9215,
|
146 |
+
"step": 57500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 4.8,
|
150 |
+
"learning_rate": 3.8e-05,
|
151 |
+
"loss": 4.9175,
|
152 |
+
"step": 60000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 5.0,
|
156 |
+
"learning_rate": 3.7500000000000003e-05,
|
157 |
+
"loss": 4.9463,
|
158 |
+
"step": 62500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 5.2,
|
162 |
+
"learning_rate": 3.7e-05,
|
163 |
+
"loss": 4.5458,
|
164 |
+
"step": 65000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 5.4,
|
168 |
+
"learning_rate": 3.65e-05,
|
169 |
+
"loss": 4.5754,
|
170 |
+
"step": 67500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 5.6,
|
174 |
+
"learning_rate": 3.6e-05,
|
175 |
+
"loss": 4.6175,
|
176 |
+
"step": 70000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 5.8,
|
180 |
+
"learning_rate": 3.55e-05,
|
181 |
+
"loss": 4.6592,
|
182 |
+
"step": 72500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 6.0,
|
186 |
+
"learning_rate": 3.5e-05,
|
187 |
+
"loss": 4.6839,
|
188 |
+
"step": 75000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 6.2,
|
192 |
+
"learning_rate": 3.45e-05,
|
193 |
+
"loss": 4.2337,
|
194 |
+
"step": 77500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 6.4,
|
198 |
+
"learning_rate": 3.4000000000000007e-05,
|
199 |
+
"loss": 4.2718,
|
200 |
+
"step": 80000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 6.6,
|
204 |
+
"learning_rate": 3.35e-05,
|
205 |
+
"loss": 4.3148,
|
206 |
+
"step": 82500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 6.8,
|
210 |
+
"learning_rate": 3.3e-05,
|
211 |
+
"loss": 4.3662,
|
212 |
+
"step": 85000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 7.0,
|
216 |
+
"learning_rate": 3.2500000000000004e-05,
|
217 |
+
"loss": 4.3476,
|
218 |
+
"step": 87500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 7.2,
|
222 |
+
"learning_rate": 3.2000000000000005e-05,
|
223 |
+
"loss": 3.894,
|
224 |
+
"step": 90000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 7.4,
|
228 |
+
"learning_rate": 3.15e-05,
|
229 |
+
"loss": 3.9493,
|
230 |
+
"step": 92500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 7.6,
|
234 |
+
"learning_rate": 3.1e-05,
|
235 |
+
"loss": 4.0003,
|
236 |
+
"step": 95000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 7.8,
|
240 |
+
"learning_rate": 3.05e-05,
|
241 |
+
"loss": 4.0301,
|
242 |
+
"step": 97500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 8.0,
|
246 |
+
"learning_rate": 3e-05,
|
247 |
+
"loss": 4.0559,
|
248 |
+
"step": 100000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 8.2,
|
252 |
+
"learning_rate": 2.95e-05,
|
253 |
+
"loss": 3.5674,
|
254 |
+
"step": 102500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 8.4,
|
258 |
+
"learning_rate": 2.9e-05,
|
259 |
+
"loss": 3.6282,
|
260 |
+
"step": 105000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 8.6,
|
264 |
+
"learning_rate": 2.8499999999999998e-05,
|
265 |
+
"loss": 3.6712,
|
266 |
+
"step": 107500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 8.8,
|
270 |
+
"learning_rate": 2.8000000000000003e-05,
|
271 |
+
"loss": 3.7138,
|
272 |
+
"step": 110000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 9.0,
|
276 |
+
"learning_rate": 2.7500000000000004e-05,
|
277 |
+
"loss": 3.7451,
|
278 |
+
"step": 112500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 9.2,
|
282 |
+
"learning_rate": 2.7000000000000002e-05,
|
283 |
+
"loss": 3.2761,
|
284 |
+
"step": 115000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 9.4,
|
288 |
+
"learning_rate": 2.6500000000000004e-05,
|
289 |
+
"loss": 3.3254,
|
290 |
+
"step": 117500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 9.6,
|
294 |
+
"learning_rate": 2.6000000000000002e-05,
|
295 |
+
"loss": 3.3704,
|
296 |
+
"step": 120000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 9.8,
|
300 |
+
"learning_rate": 2.5500000000000003e-05,
|
301 |
+
"loss": 3.375,
|
302 |
+
"step": 122500
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 10.0,
|
306 |
+
"learning_rate": 2.5e-05,
|
307 |
+
"loss": 3.4389,
|
308 |
+
"step": 125000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 10.2,
|
312 |
+
"learning_rate": 2.45e-05,
|
313 |
+
"loss": 2.9809,
|
314 |
+
"step": 127500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 10.4,
|
318 |
+
"learning_rate": 2.4e-05,
|
319 |
+
"loss": 3.0355,
|
320 |
+
"step": 130000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 10.6,
|
324 |
+
"learning_rate": 2.35e-05,
|
325 |
+
"loss": 3.103,
|
326 |
+
"step": 132500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 10.8,
|
330 |
+
"learning_rate": 2.3000000000000003e-05,
|
331 |
+
"loss": 3.0881,
|
332 |
+
"step": 135000
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 11.0,
|
336 |
+
"learning_rate": 2.25e-05,
|
337 |
+
"loss": 3.144,
|
338 |
+
"step": 137500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 11.2,
|
342 |
+
"learning_rate": 2.2000000000000003e-05,
|
343 |
+
"loss": 2.7198,
|
344 |
+
"step": 140000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 11.4,
|
348 |
+
"learning_rate": 2.15e-05,
|
349 |
+
"loss": 2.7712,
|
350 |
+
"step": 142500
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 11.6,
|
354 |
+
"learning_rate": 2.1e-05,
|
355 |
+
"loss": 2.8035,
|
356 |
+
"step": 145000
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 11.8,
|
360 |
+
"learning_rate": 2.05e-05,
|
361 |
+
"loss": 2.8412,
|
362 |
+
"step": 147500
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 12.0,
|
366 |
+
"learning_rate": 2e-05,
|
367 |
+
"loss": 2.8714,
|
368 |
+
"step": 150000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 12.2,
|
372 |
+
"learning_rate": 1.9500000000000003e-05,
|
373 |
+
"loss": 2.4583,
|
374 |
+
"step": 152500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 12.4,
|
378 |
+
"learning_rate": 1.9e-05,
|
379 |
+
"loss": 2.5254,
|
380 |
+
"step": 155000
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 12.6,
|
384 |
+
"learning_rate": 1.85e-05,
|
385 |
+
"loss": 2.5436,
|
386 |
+
"step": 157500
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 12.8,
|
390 |
+
"learning_rate": 1.8e-05,
|
391 |
+
"loss": 2.6066,
|
392 |
+
"step": 160000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 13.0,
|
396 |
+
"learning_rate": 1.75e-05,
|
397 |
+
"loss": 2.6249,
|
398 |
+
"step": 162500
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 13.2,
|
402 |
+
"learning_rate": 1.7000000000000003e-05,
|
403 |
+
"loss": 2.2585,
|
404 |
+
"step": 165000
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 13.4,
|
408 |
+
"learning_rate": 1.65e-05,
|
409 |
+
"loss": 2.3274,
|
410 |
+
"step": 167500
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 13.6,
|
414 |
+
"learning_rate": 1.6000000000000003e-05,
|
415 |
+
"loss": 2.3387,
|
416 |
+
"step": 170000
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 13.8,
|
420 |
+
"learning_rate": 1.55e-05,
|
421 |
+
"loss": 2.3526,
|
422 |
+
"step": 172500
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 14.0,
|
426 |
+
"learning_rate": 1.5e-05,
|
427 |
+
"loss": 2.3839,
|
428 |
+
"step": 175000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 14.2,
|
432 |
+
"learning_rate": 1.45e-05,
|
433 |
+
"loss": 2.0807,
|
434 |
+
"step": 177500
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 14.4,
|
438 |
+
"learning_rate": 1.4000000000000001e-05,
|
439 |
+
"loss": 2.1081,
|
440 |
+
"step": 180000
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 14.6,
|
444 |
+
"learning_rate": 1.3500000000000001e-05,
|
445 |
+
"loss": 2.1325,
|
446 |
+
"step": 182500
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 14.8,
|
450 |
+
"learning_rate": 1.3000000000000001e-05,
|
451 |
+
"loss": 2.1671,
|
452 |
+
"step": 185000
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 15.0,
|
456 |
+
"learning_rate": 1.25e-05,
|
457 |
+
"loss": 2.1625,
|
458 |
+
"step": 187500
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 15.2,
|
462 |
+
"learning_rate": 1.2e-05,
|
463 |
+
"loss": 1.9216,
|
464 |
+
"step": 190000
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 15.4,
|
468 |
+
"learning_rate": 1.1500000000000002e-05,
|
469 |
+
"loss": 1.9387,
|
470 |
+
"step": 192500
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 15.6,
|
474 |
+
"learning_rate": 1.1000000000000001e-05,
|
475 |
+
"loss": 1.9563,
|
476 |
+
"step": 195000
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 15.8,
|
480 |
+
"learning_rate": 1.05e-05,
|
481 |
+
"loss": 1.9744,
|
482 |
+
"step": 197500
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 16.0,
|
486 |
+
"learning_rate": 1e-05,
|
487 |
+
"loss": 1.9931,
|
488 |
+
"step": 200000
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 16.2,
|
492 |
+
"learning_rate": 9.5e-06,
|
493 |
+
"loss": 1.7733,
|
494 |
+
"step": 202500
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 16.4,
|
498 |
+
"learning_rate": 9e-06,
|
499 |
+
"loss": 1.7925,
|
500 |
+
"step": 205000
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 16.6,
|
504 |
+
"learning_rate": 8.500000000000002e-06,
|
505 |
+
"loss": 1.7901,
|
506 |
+
"step": 207500
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 16.8,
|
510 |
+
"learning_rate": 8.000000000000001e-06,
|
511 |
+
"loss": 1.833,
|
512 |
+
"step": 210000
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 17.0,
|
516 |
+
"learning_rate": 7.5e-06,
|
517 |
+
"loss": 1.8452,
|
518 |
+
"step": 212500
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 17.2,
|
522 |
+
"learning_rate": 7.000000000000001e-06,
|
523 |
+
"loss": 1.6738,
|
524 |
+
"step": 215000
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 17.4,
|
528 |
+
"learning_rate": 6.5000000000000004e-06,
|
529 |
+
"loss": 1.6741,
|
530 |
+
"step": 217500
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 17.6,
|
534 |
+
"learning_rate": 6e-06,
|
535 |
+
"loss": 1.6924,
|
536 |
+
"step": 220000
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 17.8,
|
540 |
+
"learning_rate": 5.500000000000001e-06,
|
541 |
+
"loss": 1.6768,
|
542 |
+
"step": 222500
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 18.0,
|
546 |
+
"learning_rate": 5e-06,
|
547 |
+
"loss": 1.6922,
|
548 |
+
"step": 225000
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 18.2,
|
552 |
+
"learning_rate": 4.5e-06,
|
553 |
+
"loss": 1.567,
|
554 |
+
"step": 227500
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 18.4,
|
558 |
+
"learning_rate": 4.000000000000001e-06,
|
559 |
+
"loss": 1.5823,
|
560 |
+
"step": 230000
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 18.6,
|
564 |
+
"learning_rate": 3.5000000000000004e-06,
|
565 |
+
"loss": 1.6003,
|
566 |
+
"step": 232500
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 18.8,
|
570 |
+
"learning_rate": 3e-06,
|
571 |
+
"loss": 1.5739,
|
572 |
+
"step": 235000
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 19.0,
|
576 |
+
"learning_rate": 2.5e-06,
|
577 |
+
"loss": 1.5736,
|
578 |
+
"step": 237500
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 19.2,
|
582 |
+
"learning_rate": 2.0000000000000003e-06,
|
583 |
+
"loss": 1.5184,
|
584 |
+
"step": 240000
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 19.4,
|
588 |
+
"learning_rate": 1.5e-06,
|
589 |
+
"loss": 1.5043,
|
590 |
+
"step": 242500
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 19.6,
|
594 |
+
"learning_rate": 1.0000000000000002e-06,
|
595 |
+
"loss": 1.4998,
|
596 |
+
"step": 245000
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 19.8,
|
600 |
+
"learning_rate": 5.000000000000001e-07,
|
601 |
+
"loss": 1.4948,
|
602 |
+
"step": 247500
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 20.0,
|
606 |
+
"learning_rate": 0.0,
|
607 |
+
"loss": 1.5208,
|
608 |
+
"step": 250000
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 20.0,
|
612 |
+
"step": 250000,
|
613 |
+
"train_runtime": 72937.5039,
|
614 |
+
"train_samples_per_second": 3.428
|
615 |
+
}
|
616 |
+
],
|
617 |
+
"max_steps": 250000,
|
618 |
+
"num_train_epochs": 20,
|
619 |
+
"total_flos": 304359320699884944,
|
620 |
+
"trial_name": null,
|
621 |
+
"trial_params": null
|
622 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:873ef15fe79342054efa40e965c2b5a19a51817e44c9428073a9bbe3ce9ffafc
|
3 |
+
size 1839
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|