Initial commit
Browse files- checkpoint-1000/config.json +28 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/pytorch_model.bin +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/trainer_state.json +616 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-500/config.json +28 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/pytorch_model.bin +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/trainer_state.json +316 -0
- checkpoint-500/training_args.bin +3 -0
checkpoint-1000/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilroberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
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": 6,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.31.0",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 50265
|
28 |
+
}
|
checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:089edb46472719994ad1a5647bd1f3da3b974d6861589b1c519eeed556066ce7
|
3 |
+
size 657021061
|
checkpoint-1000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdcdf99309c41e7fdb7ac721eace4dd39515c326ff5fd2516a04cb94c0c2eb50
|
3 |
+
size 328515505
|
checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad9a9ff6a6513b689c2016529a0a6b465a57394af2d01ae7058a1fc0966c9555
|
3 |
+
size 14575
|
checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdd2486feac625e1d9e4b30d13cb40c2896acf18a8a85bd4e5fb2693ea307e5e
|
3 |
+
size 627
|
checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,616 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.4246575342465753,
|
5 |
+
"global_step": 1000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.03,
|
12 |
+
"learning_rate": 1.0000000000000002e-06,
|
13 |
+
"loss": 0.7063,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.07,
|
18 |
+
"learning_rate": 2.0000000000000003e-06,
|
19 |
+
"loss": 0.6727,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.1,
|
24 |
+
"learning_rate": 3e-06,
|
25 |
+
"loss": 0.6957,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.14,
|
30 |
+
"learning_rate": 4.000000000000001e-06,
|
31 |
+
"loss": 0.6775,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.17,
|
36 |
+
"learning_rate": 5e-06,
|
37 |
+
"loss": 0.6918,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.21,
|
42 |
+
"learning_rate": 6e-06,
|
43 |
+
"loss": 0.6939,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.24,
|
48 |
+
"learning_rate": 7.000000000000001e-06,
|
49 |
+
"loss": 0.6684,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.27,
|
54 |
+
"learning_rate": 8.000000000000001e-06,
|
55 |
+
"loss": 0.6312,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.31,
|
60 |
+
"learning_rate": 9e-06,
|
61 |
+
"loss": 0.5444,
|
62 |
+
"step": 90
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.34,
|
66 |
+
"learning_rate": 1e-05,
|
67 |
+
"loss": 0.435,
|
68 |
+
"step": 100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.38,
|
72 |
+
"learning_rate": 1.1000000000000001e-05,
|
73 |
+
"loss": 0.3208,
|
74 |
+
"step": 110
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.41,
|
78 |
+
"learning_rate": 1.2e-05,
|
79 |
+
"loss": 0.3709,
|
80 |
+
"step": 120
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.45,
|
84 |
+
"learning_rate": 1.3000000000000001e-05,
|
85 |
+
"loss": 0.4004,
|
86 |
+
"step": 130
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.48,
|
90 |
+
"learning_rate": 1.4000000000000001e-05,
|
91 |
+
"loss": 0.3061,
|
92 |
+
"step": 140
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.51,
|
96 |
+
"learning_rate": 1.5e-05,
|
97 |
+
"loss": 0.3556,
|
98 |
+
"step": 150
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.55,
|
102 |
+
"learning_rate": 1.6000000000000003e-05,
|
103 |
+
"loss": 0.2945,
|
104 |
+
"step": 160
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.58,
|
108 |
+
"learning_rate": 1.7000000000000003e-05,
|
109 |
+
"loss": 0.3984,
|
110 |
+
"step": 170
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.62,
|
114 |
+
"learning_rate": 1.8e-05,
|
115 |
+
"loss": 0.3539,
|
116 |
+
"step": 180
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.65,
|
120 |
+
"learning_rate": 1.9e-05,
|
121 |
+
"loss": 0.4119,
|
122 |
+
"step": 190
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.68,
|
126 |
+
"learning_rate": 2e-05,
|
127 |
+
"loss": 0.3457,
|
128 |
+
"step": 200
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.72,
|
132 |
+
"learning_rate": 2.1e-05,
|
133 |
+
"loss": 0.3241,
|
134 |
+
"step": 210
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.75,
|
138 |
+
"learning_rate": 2.2000000000000003e-05,
|
139 |
+
"loss": 0.4169,
|
140 |
+
"step": 220
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.79,
|
144 |
+
"learning_rate": 2.3000000000000003e-05,
|
145 |
+
"loss": 0.3863,
|
146 |
+
"step": 230
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.82,
|
150 |
+
"learning_rate": 2.4e-05,
|
151 |
+
"loss": 0.2749,
|
152 |
+
"step": 240
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.86,
|
156 |
+
"learning_rate": 2.5e-05,
|
157 |
+
"loss": 0.3399,
|
158 |
+
"step": 250
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.89,
|
162 |
+
"learning_rate": 2.6000000000000002e-05,
|
163 |
+
"loss": 0.2771,
|
164 |
+
"step": 260
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.92,
|
168 |
+
"learning_rate": 2.7000000000000002e-05,
|
169 |
+
"loss": 0.3155,
|
170 |
+
"step": 270
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.96,
|
174 |
+
"learning_rate": 2.8000000000000003e-05,
|
175 |
+
"loss": 0.3677,
|
176 |
+
"step": 280
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.99,
|
180 |
+
"learning_rate": 2.9e-05,
|
181 |
+
"loss": 0.2678,
|
182 |
+
"step": 290
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 1.03,
|
186 |
+
"learning_rate": 3e-05,
|
187 |
+
"loss": 0.2909,
|
188 |
+
"step": 300
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.06,
|
192 |
+
"learning_rate": 3.1e-05,
|
193 |
+
"loss": 0.2997,
|
194 |
+
"step": 310
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 1.1,
|
198 |
+
"learning_rate": 3.2000000000000005e-05,
|
199 |
+
"loss": 0.2799,
|
200 |
+
"step": 320
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 1.13,
|
204 |
+
"learning_rate": 3.3e-05,
|
205 |
+
"loss": 0.2793,
|
206 |
+
"step": 330
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 1.16,
|
210 |
+
"learning_rate": 3.4000000000000007e-05,
|
211 |
+
"loss": 0.2785,
|
212 |
+
"step": 340
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.2,
|
216 |
+
"learning_rate": 3.5e-05,
|
217 |
+
"loss": 0.292,
|
218 |
+
"step": 350
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.23,
|
222 |
+
"learning_rate": 3.6e-05,
|
223 |
+
"loss": 0.2058,
|
224 |
+
"step": 360
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 1.27,
|
228 |
+
"learning_rate": 3.7e-05,
|
229 |
+
"loss": 0.2439,
|
230 |
+
"step": 370
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.3,
|
234 |
+
"learning_rate": 3.8e-05,
|
235 |
+
"loss": 0.4566,
|
236 |
+
"step": 380
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 1.34,
|
240 |
+
"learning_rate": 3.9000000000000006e-05,
|
241 |
+
"loss": 0.5624,
|
242 |
+
"step": 390
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.37,
|
246 |
+
"learning_rate": 4e-05,
|
247 |
+
"loss": 0.2315,
|
248 |
+
"step": 400
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 1.4,
|
252 |
+
"learning_rate": 4.1e-05,
|
253 |
+
"loss": 0.184,
|
254 |
+
"step": 410
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.44,
|
258 |
+
"learning_rate": 4.2e-05,
|
259 |
+
"loss": 0.3491,
|
260 |
+
"step": 420
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.47,
|
264 |
+
"learning_rate": 4.3e-05,
|
265 |
+
"loss": 0.3401,
|
266 |
+
"step": 430
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 1.51,
|
270 |
+
"learning_rate": 4.4000000000000006e-05,
|
271 |
+
"loss": 0.2944,
|
272 |
+
"step": 440
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.54,
|
276 |
+
"learning_rate": 4.5e-05,
|
277 |
+
"loss": 0.244,
|
278 |
+
"step": 450
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.58,
|
282 |
+
"learning_rate": 4.600000000000001e-05,
|
283 |
+
"loss": 0.3155,
|
284 |
+
"step": 460
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.61,
|
288 |
+
"learning_rate": 4.7e-05,
|
289 |
+
"loss": 0.2387,
|
290 |
+
"step": 470
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.64,
|
294 |
+
"learning_rate": 4.8e-05,
|
295 |
+
"loss": 0.2712,
|
296 |
+
"step": 480
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.68,
|
300 |
+
"learning_rate": 4.9e-05,
|
301 |
+
"loss": 0.3125,
|
302 |
+
"step": 490
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.71,
|
306 |
+
"learning_rate": 5e-05,
|
307 |
+
"loss": 0.2915,
|
308 |
+
"step": 500
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 1.75,
|
312 |
+
"learning_rate": 4.947916666666667e-05,
|
313 |
+
"loss": 0.3305,
|
314 |
+
"step": 510
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.78,
|
318 |
+
"learning_rate": 4.8958333333333335e-05,
|
319 |
+
"loss": 0.2439,
|
320 |
+
"step": 520
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 1.82,
|
324 |
+
"learning_rate": 4.8437500000000005e-05,
|
325 |
+
"loss": 0.2771,
|
326 |
+
"step": 530
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 1.85,
|
330 |
+
"learning_rate": 4.791666666666667e-05,
|
331 |
+
"loss": 0.357,
|
332 |
+
"step": 540
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.88,
|
336 |
+
"learning_rate": 4.739583333333333e-05,
|
337 |
+
"loss": 0.2287,
|
338 |
+
"step": 550
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.92,
|
342 |
+
"learning_rate": 4.6875e-05,
|
343 |
+
"loss": 0.3991,
|
344 |
+
"step": 560
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.95,
|
348 |
+
"learning_rate": 4.635416666666667e-05,
|
349 |
+
"loss": 0.3384,
|
350 |
+
"step": 570
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 1.99,
|
354 |
+
"learning_rate": 4.5833333333333334e-05,
|
355 |
+
"loss": 0.2882,
|
356 |
+
"step": 580
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 2.02,
|
360 |
+
"learning_rate": 4.5312500000000004e-05,
|
361 |
+
"loss": 0.2081,
|
362 |
+
"step": 590
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 2.05,
|
366 |
+
"learning_rate": 4.4791666666666673e-05,
|
367 |
+
"loss": 0.2584,
|
368 |
+
"step": 600
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 2.09,
|
372 |
+
"learning_rate": 4.4270833333333337e-05,
|
373 |
+
"loss": 0.153,
|
374 |
+
"step": 610
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 2.12,
|
378 |
+
"learning_rate": 4.375e-05,
|
379 |
+
"loss": 0.3285,
|
380 |
+
"step": 620
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 2.16,
|
384 |
+
"learning_rate": 4.322916666666667e-05,
|
385 |
+
"loss": 0.215,
|
386 |
+
"step": 630
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 2.19,
|
390 |
+
"learning_rate": 4.270833333333333e-05,
|
391 |
+
"loss": 0.0573,
|
392 |
+
"step": 640
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 2.23,
|
396 |
+
"learning_rate": 4.21875e-05,
|
397 |
+
"loss": 0.2465,
|
398 |
+
"step": 650
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 2.26,
|
402 |
+
"learning_rate": 4.166666666666667e-05,
|
403 |
+
"loss": 0.243,
|
404 |
+
"step": 660
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 2.29,
|
408 |
+
"learning_rate": 4.1145833333333335e-05,
|
409 |
+
"loss": 0.1553,
|
410 |
+
"step": 670
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 2.33,
|
414 |
+
"learning_rate": 4.0625000000000005e-05,
|
415 |
+
"loss": 0.2165,
|
416 |
+
"step": 680
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 2.36,
|
420 |
+
"learning_rate": 4.010416666666667e-05,
|
421 |
+
"loss": 0.2816,
|
422 |
+
"step": 690
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 2.4,
|
426 |
+
"learning_rate": 3.958333333333333e-05,
|
427 |
+
"loss": 0.1815,
|
428 |
+
"step": 700
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 2.43,
|
432 |
+
"learning_rate": 3.90625e-05,
|
433 |
+
"loss": 0.1879,
|
434 |
+
"step": 710
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 2.47,
|
438 |
+
"learning_rate": 3.854166666666667e-05,
|
439 |
+
"loss": 0.1997,
|
440 |
+
"step": 720
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 2.5,
|
444 |
+
"learning_rate": 3.8020833333333334e-05,
|
445 |
+
"loss": 0.2046,
|
446 |
+
"step": 730
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 2.53,
|
450 |
+
"learning_rate": 3.7500000000000003e-05,
|
451 |
+
"loss": 0.1886,
|
452 |
+
"step": 740
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 2.57,
|
456 |
+
"learning_rate": 3.697916666666667e-05,
|
457 |
+
"loss": 0.2487,
|
458 |
+
"step": 750
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 2.6,
|
462 |
+
"learning_rate": 3.6458333333333336e-05,
|
463 |
+
"loss": 0.212,
|
464 |
+
"step": 760
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 2.64,
|
468 |
+
"learning_rate": 3.59375e-05,
|
469 |
+
"loss": 0.171,
|
470 |
+
"step": 770
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 2.67,
|
474 |
+
"learning_rate": 3.541666666666667e-05,
|
475 |
+
"loss": 0.2213,
|
476 |
+
"step": 780
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 2.71,
|
480 |
+
"learning_rate": 3.489583333333333e-05,
|
481 |
+
"loss": 0.3446,
|
482 |
+
"step": 790
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 2.74,
|
486 |
+
"learning_rate": 3.4375e-05,
|
487 |
+
"loss": 0.2946,
|
488 |
+
"step": 800
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 2.77,
|
492 |
+
"learning_rate": 3.385416666666667e-05,
|
493 |
+
"loss": 0.1453,
|
494 |
+
"step": 810
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 2.81,
|
498 |
+
"learning_rate": 3.3333333333333335e-05,
|
499 |
+
"loss": 0.1054,
|
500 |
+
"step": 820
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 2.84,
|
504 |
+
"learning_rate": 3.2812500000000005e-05,
|
505 |
+
"loss": 0.1581,
|
506 |
+
"step": 830
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 2.88,
|
510 |
+
"learning_rate": 3.229166666666667e-05,
|
511 |
+
"loss": 0.2906,
|
512 |
+
"step": 840
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 2.91,
|
516 |
+
"learning_rate": 3.177083333333333e-05,
|
517 |
+
"loss": 0.194,
|
518 |
+
"step": 850
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 2.95,
|
522 |
+
"learning_rate": 3.125e-05,
|
523 |
+
"loss": 0.2613,
|
524 |
+
"step": 860
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 2.98,
|
528 |
+
"learning_rate": 3.072916666666667e-05,
|
529 |
+
"loss": 0.2135,
|
530 |
+
"step": 870
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 3.01,
|
534 |
+
"learning_rate": 3.0208333333333334e-05,
|
535 |
+
"loss": 0.2054,
|
536 |
+
"step": 880
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 3.05,
|
540 |
+
"learning_rate": 2.96875e-05,
|
541 |
+
"loss": 0.1041,
|
542 |
+
"step": 890
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 3.08,
|
546 |
+
"learning_rate": 2.916666666666667e-05,
|
547 |
+
"loss": 0.1748,
|
548 |
+
"step": 900
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 3.12,
|
552 |
+
"learning_rate": 2.8645833333333333e-05,
|
553 |
+
"loss": 0.1735,
|
554 |
+
"step": 910
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 3.15,
|
558 |
+
"learning_rate": 2.8125000000000003e-05,
|
559 |
+
"loss": 0.0759,
|
560 |
+
"step": 920
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 3.18,
|
564 |
+
"learning_rate": 2.760416666666667e-05,
|
565 |
+
"loss": 0.2027,
|
566 |
+
"step": 930
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 3.22,
|
570 |
+
"learning_rate": 2.7083333333333332e-05,
|
571 |
+
"loss": 0.0628,
|
572 |
+
"step": 940
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 3.25,
|
576 |
+
"learning_rate": 2.6562500000000002e-05,
|
577 |
+
"loss": 0.1241,
|
578 |
+
"step": 950
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 3.29,
|
582 |
+
"learning_rate": 2.604166666666667e-05,
|
583 |
+
"loss": 0.1004,
|
584 |
+
"step": 960
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 3.32,
|
588 |
+
"learning_rate": 2.552083333333333e-05,
|
589 |
+
"loss": 0.0394,
|
590 |
+
"step": 970
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 3.36,
|
594 |
+
"learning_rate": 2.5e-05,
|
595 |
+
"loss": 0.1247,
|
596 |
+
"step": 980
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 3.39,
|
600 |
+
"learning_rate": 2.4479166666666668e-05,
|
601 |
+
"loss": 0.1056,
|
602 |
+
"step": 990
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 3.42,
|
606 |
+
"learning_rate": 2.3958333333333334e-05,
|
607 |
+
"loss": 0.1697,
|
608 |
+
"step": 1000
|
609 |
+
}
|
610 |
+
],
|
611 |
+
"max_steps": 1460,
|
612 |
+
"num_train_epochs": 5,
|
613 |
+
"total_flos": 2119080976300032.0,
|
614 |
+
"trial_name": null,
|
615 |
+
"trial_params": null
|
616 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:567b5af93deb319a8b2ee9a493f202c5065ee9d3f488c6fcd9dc5c605c9fa3eb
|
3 |
+
size 3899
|
checkpoint-500/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilroberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
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": 6,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.31.0",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 50265
|
28 |
+
}
|
checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32c320644fe9dd7dd33ce0c61d9dfd50fc18a1f0bc708611bf49bb3169e9696c
|
3 |
+
size 657021061
|
checkpoint-500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18ffb6d06ca8a3fc1ae68a96ca7771963e5b6d273987cc2e361b8528e4a58a79
|
3 |
+
size 328515505
|
checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4059ff6e2370a8bf902a38f6cac1e0e2bccdf4501e8ecd70eb45d912004678ad
|
3 |
+
size 14575
|
checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c05be3962c0b78b7a603157e0a8d651a7e7f492381267255975412abcca2156
|
3 |
+
size 627
|
checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,316 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.7123287671232876,
|
5 |
+
"global_step": 500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.03,
|
12 |
+
"learning_rate": 1.0000000000000002e-06,
|
13 |
+
"loss": 0.7063,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.07,
|
18 |
+
"learning_rate": 2.0000000000000003e-06,
|
19 |
+
"loss": 0.6727,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.1,
|
24 |
+
"learning_rate": 3e-06,
|
25 |
+
"loss": 0.6957,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.14,
|
30 |
+
"learning_rate": 4.000000000000001e-06,
|
31 |
+
"loss": 0.6775,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.17,
|
36 |
+
"learning_rate": 5e-06,
|
37 |
+
"loss": 0.6918,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.21,
|
42 |
+
"learning_rate": 6e-06,
|
43 |
+
"loss": 0.6939,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.24,
|
48 |
+
"learning_rate": 7.000000000000001e-06,
|
49 |
+
"loss": 0.6684,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.27,
|
54 |
+
"learning_rate": 8.000000000000001e-06,
|
55 |
+
"loss": 0.6312,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.31,
|
60 |
+
"learning_rate": 9e-06,
|
61 |
+
"loss": 0.5444,
|
62 |
+
"step": 90
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.34,
|
66 |
+
"learning_rate": 1e-05,
|
67 |
+
"loss": 0.435,
|
68 |
+
"step": 100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.38,
|
72 |
+
"learning_rate": 1.1000000000000001e-05,
|
73 |
+
"loss": 0.3208,
|
74 |
+
"step": 110
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.41,
|
78 |
+
"learning_rate": 1.2e-05,
|
79 |
+
"loss": 0.3709,
|
80 |
+
"step": 120
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.45,
|
84 |
+
"learning_rate": 1.3000000000000001e-05,
|
85 |
+
"loss": 0.4004,
|
86 |
+
"step": 130
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.48,
|
90 |
+
"learning_rate": 1.4000000000000001e-05,
|
91 |
+
"loss": 0.3061,
|
92 |
+
"step": 140
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.51,
|
96 |
+
"learning_rate": 1.5e-05,
|
97 |
+
"loss": 0.3556,
|
98 |
+
"step": 150
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.55,
|
102 |
+
"learning_rate": 1.6000000000000003e-05,
|
103 |
+
"loss": 0.2945,
|
104 |
+
"step": 160
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.58,
|
108 |
+
"learning_rate": 1.7000000000000003e-05,
|
109 |
+
"loss": 0.3984,
|
110 |
+
"step": 170
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.62,
|
114 |
+
"learning_rate": 1.8e-05,
|
115 |
+
"loss": 0.3539,
|
116 |
+
"step": 180
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.65,
|
120 |
+
"learning_rate": 1.9e-05,
|
121 |
+
"loss": 0.4119,
|
122 |
+
"step": 190
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.68,
|
126 |
+
"learning_rate": 2e-05,
|
127 |
+
"loss": 0.3457,
|
128 |
+
"step": 200
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.72,
|
132 |
+
"learning_rate": 2.1e-05,
|
133 |
+
"loss": 0.3241,
|
134 |
+
"step": 210
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.75,
|
138 |
+
"learning_rate": 2.2000000000000003e-05,
|
139 |
+
"loss": 0.4169,
|
140 |
+
"step": 220
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.79,
|
144 |
+
"learning_rate": 2.3000000000000003e-05,
|
145 |
+
"loss": 0.3863,
|
146 |
+
"step": 230
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.82,
|
150 |
+
"learning_rate": 2.4e-05,
|
151 |
+
"loss": 0.2749,
|
152 |
+
"step": 240
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.86,
|
156 |
+
"learning_rate": 2.5e-05,
|
157 |
+
"loss": 0.3399,
|
158 |
+
"step": 250
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.89,
|
162 |
+
"learning_rate": 2.6000000000000002e-05,
|
163 |
+
"loss": 0.2771,
|
164 |
+
"step": 260
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.92,
|
168 |
+
"learning_rate": 2.7000000000000002e-05,
|
169 |
+
"loss": 0.3155,
|
170 |
+
"step": 270
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.96,
|
174 |
+
"learning_rate": 2.8000000000000003e-05,
|
175 |
+
"loss": 0.3677,
|
176 |
+
"step": 280
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.99,
|
180 |
+
"learning_rate": 2.9e-05,
|
181 |
+
"loss": 0.2678,
|
182 |
+
"step": 290
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 1.03,
|
186 |
+
"learning_rate": 3e-05,
|
187 |
+
"loss": 0.2909,
|
188 |
+
"step": 300
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.06,
|
192 |
+
"learning_rate": 3.1e-05,
|
193 |
+
"loss": 0.2997,
|
194 |
+
"step": 310
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 1.1,
|
198 |
+
"learning_rate": 3.2000000000000005e-05,
|
199 |
+
"loss": 0.2799,
|
200 |
+
"step": 320
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 1.13,
|
204 |
+
"learning_rate": 3.3e-05,
|
205 |
+
"loss": 0.2793,
|
206 |
+
"step": 330
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 1.16,
|
210 |
+
"learning_rate": 3.4000000000000007e-05,
|
211 |
+
"loss": 0.2785,
|
212 |
+
"step": 340
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.2,
|
216 |
+
"learning_rate": 3.5e-05,
|
217 |
+
"loss": 0.292,
|
218 |
+
"step": 350
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.23,
|
222 |
+
"learning_rate": 3.6e-05,
|
223 |
+
"loss": 0.2058,
|
224 |
+
"step": 360
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 1.27,
|
228 |
+
"learning_rate": 3.7e-05,
|
229 |
+
"loss": 0.2439,
|
230 |
+
"step": 370
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.3,
|
234 |
+
"learning_rate": 3.8e-05,
|
235 |
+
"loss": 0.4566,
|
236 |
+
"step": 380
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 1.34,
|
240 |
+
"learning_rate": 3.9000000000000006e-05,
|
241 |
+
"loss": 0.5624,
|
242 |
+
"step": 390
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.37,
|
246 |
+
"learning_rate": 4e-05,
|
247 |
+
"loss": 0.2315,
|
248 |
+
"step": 400
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 1.4,
|
252 |
+
"learning_rate": 4.1e-05,
|
253 |
+
"loss": 0.184,
|
254 |
+
"step": 410
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.44,
|
258 |
+
"learning_rate": 4.2e-05,
|
259 |
+
"loss": 0.3491,
|
260 |
+
"step": 420
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.47,
|
264 |
+
"learning_rate": 4.3e-05,
|
265 |
+
"loss": 0.3401,
|
266 |
+
"step": 430
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 1.51,
|
270 |
+
"learning_rate": 4.4000000000000006e-05,
|
271 |
+
"loss": 0.2944,
|
272 |
+
"step": 440
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.54,
|
276 |
+
"learning_rate": 4.5e-05,
|
277 |
+
"loss": 0.244,
|
278 |
+
"step": 450
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.58,
|
282 |
+
"learning_rate": 4.600000000000001e-05,
|
283 |
+
"loss": 0.3155,
|
284 |
+
"step": 460
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.61,
|
288 |
+
"learning_rate": 4.7e-05,
|
289 |
+
"loss": 0.2387,
|
290 |
+
"step": 470
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.64,
|
294 |
+
"learning_rate": 4.8e-05,
|
295 |
+
"loss": 0.2712,
|
296 |
+
"step": 480
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.68,
|
300 |
+
"learning_rate": 4.9e-05,
|
301 |
+
"loss": 0.3125,
|
302 |
+
"step": 490
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.71,
|
306 |
+
"learning_rate": 5e-05,
|
307 |
+
"loss": 0.2915,
|
308 |
+
"step": 500
|
309 |
+
}
|
310 |
+
],
|
311 |
+
"max_steps": 1460,
|
312 |
+
"num_train_epochs": 5,
|
313 |
+
"total_flos": 1059606721849344.0,
|
314 |
+
"trial_name": null,
|
315 |
+
"trial_params": null
|
316 |
+
}
|
checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:567b5af93deb319a8b2ee9a493f202c5065ee9d3f488c6fcd9dc5c605c9fa3eb
|
3 |
+
size 3899
|