DopeorNope commited on
Commit
df3a2c7
·
1 Parent(s): 9bb51c5

Upload 8 files

Browse files
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: True
10
+ - load_in_4bit: False
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: fp4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float32
18
+ ### Framework versions
19
+
20
+
21
+ - PEFT 0.5.0.dev0
adapter_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "HyperbeeAI/Tulpar-7b-v1",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "gate_proj",
18
+ "down_proj",
19
+ "up_proj"
20
+ ],
21
+ "task_type": "CAUSAL_LM"
22
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11cc0aa2369eaa624538480716abd1e218fe9e9b5c7cdfa6db2b2945bbb6576d
3
+ size 92867533
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efc8ceeb1080161473ae850182221c0fb446661ccf1298337c20f3975238d3f9
3
+ size 185759493
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eafe26b8308c92c918da4a9e18b8f027e0c1211eb894d641d1dee0d8155f1951
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dd2df8d43e17fb56e08e9080d2d40810571b72775719dc2bf55421ca73b8575
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,1819 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.22538385688125087,
5
+ "eval_steps": 500,
6
+ "global_step": 300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 9.999499123466067e-06,
14
+ "loss": 2.6235,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 9.998998246932132e-06,
20
+ "loss": 2.5824,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.0,
25
+ "learning_rate": 9.998497370398198e-06,
26
+ "loss": 2.5507,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.0,
31
+ "learning_rate": 9.997996493864263e-06,
32
+ "loss": 2.3573,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.0,
37
+ "learning_rate": 9.997495617330328e-06,
38
+ "loss": 2.6327,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.0,
43
+ "learning_rate": 9.996994740796394e-06,
44
+ "loss": 2.1046,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.01,
49
+ "learning_rate": 9.99649386426246e-06,
50
+ "loss": 2.3557,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.01,
55
+ "learning_rate": 9.995992987728525e-06,
56
+ "loss": 2.6839,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.01,
61
+ "learning_rate": 9.995492111194592e-06,
62
+ "loss": 2.7093,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.01,
67
+ "learning_rate": 9.994991234660656e-06,
68
+ "loss": 2.6468,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.01,
73
+ "learning_rate": 9.994490358126723e-06,
74
+ "loss": 2.4149,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.01,
79
+ "learning_rate": 9.993989481592789e-06,
80
+ "loss": 2.778,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.01,
85
+ "learning_rate": 9.993488605058854e-06,
86
+ "loss": 2.5218,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.01,
91
+ "learning_rate": 9.99298772852492e-06,
92
+ "loss": 2.7134,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.01,
97
+ "learning_rate": 9.992486851990985e-06,
98
+ "loss": 2.7858,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.01,
103
+ "learning_rate": 9.99198597545705e-06,
104
+ "loss": 2.4673,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.01,
109
+ "learning_rate": 9.991485098923116e-06,
110
+ "loss": 2.2678,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.01,
115
+ "learning_rate": 9.990984222389182e-06,
116
+ "loss": 2.662,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.01,
121
+ "learning_rate": 9.990483345855247e-06,
122
+ "loss": 2.7838,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.02,
127
+ "learning_rate": 9.989982469321313e-06,
128
+ "loss": 2.7802,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.02,
133
+ "learning_rate": 9.98948159278738e-06,
134
+ "loss": 2.226,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.02,
139
+ "learning_rate": 9.988980716253444e-06,
140
+ "loss": 2.6759,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.02,
145
+ "learning_rate": 9.988479839719511e-06,
146
+ "loss": 2.5125,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.02,
151
+ "learning_rate": 9.987978963185576e-06,
152
+ "loss": 2.3148,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.02,
157
+ "learning_rate": 9.98747808665164e-06,
158
+ "loss": 2.1436,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.02,
163
+ "learning_rate": 9.986977210117707e-06,
164
+ "loss": 2.5292,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.02,
169
+ "learning_rate": 9.986476333583773e-06,
170
+ "loss": 2.6515,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.02,
175
+ "learning_rate": 9.985975457049838e-06,
176
+ "loss": 2.662,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.02,
181
+ "learning_rate": 9.985474580515904e-06,
182
+ "loss": 2.1409,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.02,
187
+ "learning_rate": 9.984973703981969e-06,
188
+ "loss": 2.7163,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.02,
193
+ "learning_rate": 9.984472827448035e-06,
194
+ "loss": 2.8434,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.02,
199
+ "learning_rate": 9.983971950914102e-06,
200
+ "loss": 2.477,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.02,
205
+ "learning_rate": 9.983471074380166e-06,
206
+ "loss": 2.3775,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.03,
211
+ "learning_rate": 9.982970197846231e-06,
212
+ "loss": 2.7939,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.03,
217
+ "learning_rate": 9.982469321312297e-06,
218
+ "loss": 2.8765,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.03,
223
+ "learning_rate": 9.981968444778362e-06,
224
+ "loss": 2.2087,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.03,
229
+ "learning_rate": 9.981467568244428e-06,
230
+ "loss": 2.3081,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.03,
235
+ "learning_rate": 9.980966691710495e-06,
236
+ "loss": 2.2391,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.03,
241
+ "learning_rate": 9.98046581517656e-06,
242
+ "loss": 2.4225,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.03,
247
+ "learning_rate": 9.979964938642626e-06,
248
+ "loss": 2.6623,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.03,
253
+ "learning_rate": 9.97946406210869e-06,
254
+ "loss": 2.5238,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.03,
259
+ "learning_rate": 9.978963185574757e-06,
260
+ "loss": 2.1961,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.03,
265
+ "learning_rate": 9.978462309040823e-06,
266
+ "loss": 2.3119,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.03,
271
+ "learning_rate": 9.977961432506888e-06,
272
+ "loss": 2.0684,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.03,
277
+ "learning_rate": 9.977460555972953e-06,
278
+ "loss": 2.392,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.03,
283
+ "learning_rate": 9.97695967943902e-06,
284
+ "loss": 2.5658,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.04,
289
+ "learning_rate": 9.976458802905084e-06,
290
+ "loss": 2.3127,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.04,
295
+ "learning_rate": 9.97595792637115e-06,
296
+ "loss": 2.3825,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.04,
301
+ "learning_rate": 9.975457049837217e-06,
302
+ "loss": 2.1146,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.04,
307
+ "learning_rate": 9.974956173303281e-06,
308
+ "loss": 2.2199,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.04,
313
+ "learning_rate": 9.974455296769348e-06,
314
+ "loss": 2.377,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.04,
319
+ "learning_rate": 9.973954420235412e-06,
320
+ "loss": 2.6586,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.04,
325
+ "learning_rate": 9.973453543701477e-06,
326
+ "loss": 2.2522,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.04,
331
+ "learning_rate": 9.972952667167544e-06,
332
+ "loss": 2.4157,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.04,
337
+ "learning_rate": 9.97245179063361e-06,
338
+ "loss": 2.1836,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.04,
343
+ "learning_rate": 9.971950914099675e-06,
344
+ "loss": 2.5933,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.04,
349
+ "learning_rate": 9.971450037565741e-06,
350
+ "loss": 2.4881,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.04,
355
+ "learning_rate": 9.970949161031806e-06,
356
+ "loss": 2.2361,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.04,
361
+ "learning_rate": 9.970448284497872e-06,
362
+ "loss": 2.4261,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.05,
367
+ "learning_rate": 9.969947407963938e-06,
368
+ "loss": 2.3877,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.05,
373
+ "learning_rate": 9.969446531430003e-06,
374
+ "loss": 2.1171,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.05,
379
+ "learning_rate": 9.96894565489607e-06,
380
+ "loss": 2.3454,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.05,
385
+ "learning_rate": 9.968444778362134e-06,
386
+ "loss": 2.0507,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.05,
391
+ "learning_rate": 9.9679439018282e-06,
392
+ "loss": 2.2696,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.05,
397
+ "learning_rate": 9.967443025294265e-06,
398
+ "loss": 2.3172,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.05,
403
+ "learning_rate": 9.966942148760332e-06,
404
+ "loss": 2.3766,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.05,
409
+ "learning_rate": 9.966441272226396e-06,
410
+ "loss": 2.0528,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.05,
415
+ "learning_rate": 9.965940395692463e-06,
416
+ "loss": 2.0653,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.05,
421
+ "learning_rate": 9.96543951915853e-06,
422
+ "loss": 2.0007,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.05,
427
+ "learning_rate": 9.964938642624594e-06,
428
+ "loss": 2.0884,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.05,
433
+ "learning_rate": 9.96443776609066e-06,
434
+ "loss": 1.8656,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.05,
439
+ "learning_rate": 9.963936889556725e-06,
440
+ "loss": 2.1657,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.05,
445
+ "learning_rate": 9.96343601302279e-06,
446
+ "loss": 2.1507,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.06,
451
+ "learning_rate": 9.962935136488856e-06,
452
+ "loss": 1.9204,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.06,
457
+ "learning_rate": 9.962434259954922e-06,
458
+ "loss": 2.5252,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.06,
463
+ "learning_rate": 9.961933383420987e-06,
464
+ "loss": 1.9031,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.06,
469
+ "learning_rate": 9.961432506887054e-06,
470
+ "loss": 2.4874,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.06,
475
+ "learning_rate": 9.960931630353118e-06,
476
+ "loss": 1.8518,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.06,
481
+ "learning_rate": 9.960430753819185e-06,
482
+ "loss": 2.1641,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.06,
487
+ "learning_rate": 9.959929877285251e-06,
488
+ "loss": 1.9528,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.06,
493
+ "learning_rate": 9.959429000751316e-06,
494
+ "loss": 2.1871,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.06,
499
+ "learning_rate": 9.95892812421738e-06,
500
+ "loss": 2.5454,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.06,
505
+ "learning_rate": 9.958427247683447e-06,
506
+ "loss": 2.1169,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.06,
511
+ "learning_rate": 9.957926371149512e-06,
512
+ "loss": 2.0498,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.06,
517
+ "learning_rate": 9.957425494615578e-06,
518
+ "loss": 2.0923,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.06,
523
+ "learning_rate": 9.956924618081644e-06,
524
+ "loss": 1.9875,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.07,
529
+ "learning_rate": 9.956423741547709e-06,
530
+ "loss": 2.259,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.07,
535
+ "learning_rate": 9.955922865013775e-06,
536
+ "loss": 1.9799,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.07,
541
+ "learning_rate": 9.95542198847984e-06,
542
+ "loss": 1.7977,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.07,
547
+ "learning_rate": 9.954921111945906e-06,
548
+ "loss": 2.0986,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.07,
553
+ "learning_rate": 9.954420235411971e-06,
554
+ "loss": 2.0233,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.07,
559
+ "learning_rate": 9.953919358878038e-06,
560
+ "loss": 2.034,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.07,
565
+ "learning_rate": 9.953418482344102e-06,
566
+ "loss": 2.033,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.07,
571
+ "learning_rate": 9.952917605810169e-06,
572
+ "loss": 1.8471,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.07,
577
+ "learning_rate": 9.952416729276233e-06,
578
+ "loss": 2.0814,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.07,
583
+ "learning_rate": 9.9519158527423e-06,
584
+ "loss": 1.8964,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.07,
589
+ "learning_rate": 9.951414976208366e-06,
590
+ "loss": 1.9414,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.07,
595
+ "learning_rate": 9.95091409967443e-06,
596
+ "loss": 2.2039,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.07,
601
+ "learning_rate": 9.950413223140497e-06,
602
+ "loss": 1.9886,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.08,
607
+ "learning_rate": 9.949912346606564e-06,
608
+ "loss": 1.8127,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.08,
613
+ "learning_rate": 9.949411470072627e-06,
614
+ "loss": 1.7826,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.08,
619
+ "learning_rate": 9.948910593538693e-06,
620
+ "loss": 1.9851,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.08,
625
+ "learning_rate": 9.94840971700476e-06,
626
+ "loss": 1.722,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.08,
631
+ "learning_rate": 9.947908840470824e-06,
632
+ "loss": 1.9125,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.08,
637
+ "learning_rate": 9.94740796393689e-06,
638
+ "loss": 2.2851,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.08,
643
+ "learning_rate": 9.946907087402957e-06,
644
+ "loss": 1.725,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.08,
649
+ "learning_rate": 9.946406210869022e-06,
650
+ "loss": 1.9079,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.08,
655
+ "learning_rate": 9.945905334335088e-06,
656
+ "loss": 1.8015,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.08,
661
+ "learning_rate": 9.945404457801153e-06,
662
+ "loss": 1.5967,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.08,
667
+ "learning_rate": 9.944903581267219e-06,
668
+ "loss": 1.8457,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.08,
673
+ "learning_rate": 9.944402704733284e-06,
674
+ "loss": 1.8627,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.08,
679
+ "learning_rate": 9.94390182819935e-06,
680
+ "loss": 1.5547,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.08,
685
+ "learning_rate": 9.943400951665415e-06,
686
+ "loss": 1.6641,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.09,
691
+ "learning_rate": 9.942900075131481e-06,
692
+ "loss": 1.7707,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.09,
697
+ "learning_rate": 9.942399198597546e-06,
698
+ "loss": 1.7543,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.09,
703
+ "learning_rate": 9.941898322063612e-06,
704
+ "loss": 1.8925,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.09,
709
+ "learning_rate": 9.941397445529679e-06,
710
+ "loss": 1.9086,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.09,
715
+ "learning_rate": 9.940896568995743e-06,
716
+ "loss": 1.4877,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.09,
721
+ "learning_rate": 9.94039569246181e-06,
722
+ "loss": 1.4494,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.09,
727
+ "learning_rate": 9.939894815927874e-06,
728
+ "loss": 1.5664,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.09,
733
+ "learning_rate": 9.939393939393939e-06,
734
+ "loss": 1.5048,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.09,
739
+ "learning_rate": 9.938893062860006e-06,
740
+ "loss": 1.9184,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.09,
745
+ "learning_rate": 9.938392186326072e-06,
746
+ "loss": 1.8772,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.09,
751
+ "learning_rate": 9.937891309792137e-06,
752
+ "loss": 1.7658,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.09,
757
+ "learning_rate": 9.937390433258203e-06,
758
+ "loss": 1.9113,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.09,
763
+ "learning_rate": 9.936889556724268e-06,
764
+ "loss": 1.6996,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.1,
769
+ "learning_rate": 9.936388680190334e-06,
770
+ "loss": 1.7981,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.1,
775
+ "learning_rate": 9.9358878036564e-06,
776
+ "loss": 1.8737,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.1,
781
+ "learning_rate": 9.935386927122465e-06,
782
+ "loss": 1.6294,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.1,
787
+ "learning_rate": 9.93488605058853e-06,
788
+ "loss": 1.7749,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.1,
793
+ "learning_rate": 9.934385174054596e-06,
794
+ "loss": 1.5654,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.1,
799
+ "learning_rate": 9.933884297520661e-06,
800
+ "loss": 1.9468,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.1,
805
+ "learning_rate": 9.933383420986727e-06,
806
+ "loss": 1.7524,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.1,
811
+ "learning_rate": 9.932882544452794e-06,
812
+ "loss": 1.7435,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.1,
817
+ "learning_rate": 9.932381667918858e-06,
818
+ "loss": 1.5219,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.1,
823
+ "learning_rate": 9.931880791384925e-06,
824
+ "loss": 1.4879,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.1,
829
+ "learning_rate": 9.931379914850991e-06,
830
+ "loss": 1.9382,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.1,
835
+ "learning_rate": 9.930879038317056e-06,
836
+ "loss": 1.6203,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.1,
841
+ "learning_rate": 9.93037816178312e-06,
842
+ "loss": 1.6583,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.11,
847
+ "learning_rate": 9.929877285249187e-06,
848
+ "loss": 1.7075,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.11,
853
+ "learning_rate": 9.929376408715252e-06,
854
+ "loss": 1.7242,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.11,
859
+ "learning_rate": 9.928875532181318e-06,
860
+ "loss": 1.6956,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.11,
865
+ "learning_rate": 9.928374655647384e-06,
866
+ "loss": 1.4683,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.11,
871
+ "learning_rate": 9.92787377911345e-06,
872
+ "loss": 1.4896,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.11,
877
+ "learning_rate": 9.927372902579516e-06,
878
+ "loss": 1.4702,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.11,
883
+ "learning_rate": 9.92687202604558e-06,
884
+ "loss": 1.4213,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.11,
889
+ "learning_rate": 9.926371149511647e-06,
890
+ "loss": 1.6507,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.11,
895
+ "learning_rate": 9.925870272977713e-06,
896
+ "loss": 1.205,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.11,
901
+ "learning_rate": 9.925369396443778e-06,
902
+ "loss": 1.5932,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.11,
907
+ "learning_rate": 9.924868519909842e-06,
908
+ "loss": 1.4051,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.11,
913
+ "learning_rate": 9.924367643375909e-06,
914
+ "loss": 1.4086,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.11,
919
+ "learning_rate": 9.923866766841974e-06,
920
+ "loss": 1.6856,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.11,
925
+ "learning_rate": 9.92336589030804e-06,
926
+ "loss": 1.5934,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.12,
931
+ "learning_rate": 9.922865013774106e-06,
932
+ "loss": 1.4521,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.12,
937
+ "learning_rate": 9.922364137240171e-06,
938
+ "loss": 1.5741,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.12,
943
+ "learning_rate": 9.921863260706237e-06,
944
+ "loss": 1.6032,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.12,
949
+ "learning_rate": 9.921362384172302e-06,
950
+ "loss": 1.2137,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.12,
955
+ "learning_rate": 9.920861507638367e-06,
956
+ "loss": 1.6434,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.12,
961
+ "learning_rate": 9.920360631104433e-06,
962
+ "loss": 1.4675,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.12,
967
+ "learning_rate": 9.9198597545705e-06,
968
+ "loss": 1.2068,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.12,
973
+ "learning_rate": 9.919358878036564e-06,
974
+ "loss": 1.4733,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.12,
979
+ "learning_rate": 9.91885800150263e-06,
980
+ "loss": 1.4762,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.12,
985
+ "learning_rate": 9.918357124968695e-06,
986
+ "loss": 1.5861,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.12,
991
+ "learning_rate": 9.917856248434762e-06,
992
+ "loss": 1.4042,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.12,
997
+ "learning_rate": 9.917355371900828e-06,
998
+ "loss": 1.2002,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.12,
1003
+ "learning_rate": 9.916854495366893e-06,
1004
+ "loss": 1.5041,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.13,
1009
+ "learning_rate": 9.91635361883296e-06,
1010
+ "loss": 1.6376,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.13,
1015
+ "learning_rate": 9.915852742299024e-06,
1016
+ "loss": 1.5164,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.13,
1021
+ "learning_rate": 9.915351865765089e-06,
1022
+ "loss": 1.1812,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.13,
1027
+ "learning_rate": 9.914850989231155e-06,
1028
+ "loss": 1.4088,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.13,
1033
+ "learning_rate": 9.914350112697221e-06,
1034
+ "loss": 1.2608,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.13,
1039
+ "learning_rate": 9.913849236163286e-06,
1040
+ "loss": 1.6522,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.13,
1045
+ "learning_rate": 9.913348359629352e-06,
1046
+ "loss": 1.4633,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.13,
1051
+ "learning_rate": 9.912847483095417e-06,
1052
+ "loss": 1.3296,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.13,
1057
+ "learning_rate": 9.912346606561484e-06,
1058
+ "loss": 1.5279,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.13,
1063
+ "learning_rate": 9.91184573002755e-06,
1064
+ "loss": 1.2697,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.13,
1069
+ "learning_rate": 9.911344853493615e-06,
1070
+ "loss": 1.5185,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.13,
1075
+ "learning_rate": 9.91084397695968e-06,
1076
+ "loss": 1.5693,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.13,
1081
+ "learning_rate": 9.910343100425746e-06,
1082
+ "loss": 1.3556,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.14,
1087
+ "learning_rate": 9.909842223891812e-06,
1088
+ "loss": 1.2393,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.14,
1093
+ "learning_rate": 9.909341347357877e-06,
1094
+ "loss": 1.3718,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.14,
1099
+ "learning_rate": 9.908840470823943e-06,
1100
+ "loss": 1.5344,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.14,
1105
+ "learning_rate": 9.908339594290008e-06,
1106
+ "loss": 1.306,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.14,
1111
+ "learning_rate": 9.907838717756074e-06,
1112
+ "loss": 1.4257,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.14,
1117
+ "learning_rate": 9.90733784122214e-06,
1118
+ "loss": 1.5165,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.14,
1123
+ "learning_rate": 9.906836964688205e-06,
1124
+ "loss": 1.2443,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.14,
1129
+ "learning_rate": 9.90633608815427e-06,
1130
+ "loss": 1.4456,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.14,
1135
+ "learning_rate": 9.905835211620336e-06,
1136
+ "loss": 1.4192,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.14,
1141
+ "learning_rate": 9.905334335086401e-06,
1142
+ "loss": 1.5941,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.14,
1147
+ "learning_rate": 9.904833458552468e-06,
1148
+ "loss": 1.4748,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.14,
1153
+ "learning_rate": 9.904332582018534e-06,
1154
+ "loss": 1.2414,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.14,
1159
+ "learning_rate": 9.903831705484599e-06,
1160
+ "loss": 1.4399,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.14,
1165
+ "learning_rate": 9.903330828950665e-06,
1166
+ "loss": 1.483,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.15,
1171
+ "learning_rate": 9.90282995241673e-06,
1172
+ "loss": 1.5834,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.15,
1177
+ "learning_rate": 9.902329075882796e-06,
1178
+ "loss": 1.55,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.15,
1183
+ "learning_rate": 9.901828199348863e-06,
1184
+ "loss": 1.371,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.15,
1189
+ "learning_rate": 9.901327322814927e-06,
1190
+ "loss": 1.4385,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.15,
1195
+ "learning_rate": 9.900826446280992e-06,
1196
+ "loss": 1.4588,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.15,
1201
+ "learning_rate": 9.900325569747058e-06,
1202
+ "loss": 1.362,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.15,
1207
+ "learning_rate": 9.899824693213123e-06,
1208
+ "loss": 1.4924,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 0.15,
1213
+ "learning_rate": 9.89932381667919e-06,
1214
+ "loss": 1.4495,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 0.15,
1219
+ "learning_rate": 9.898822940145256e-06,
1220
+ "loss": 1.2711,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 0.15,
1225
+ "learning_rate": 9.89832206361132e-06,
1226
+ "loss": 1.1789,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 0.15,
1231
+ "learning_rate": 9.897821187077387e-06,
1232
+ "loss": 1.6727,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 0.15,
1237
+ "learning_rate": 9.897320310543452e-06,
1238
+ "loss": 1.3458,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 0.15,
1243
+ "learning_rate": 9.896819434009516e-06,
1244
+ "loss": 1.4132,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 0.16,
1249
+ "learning_rate": 9.896318557475583e-06,
1250
+ "loss": 1.3401,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 0.16,
1255
+ "learning_rate": 9.895817680941649e-06,
1256
+ "loss": 1.3987,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 0.16,
1261
+ "learning_rate": 9.895316804407714e-06,
1262
+ "loss": 1.7068,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 0.16,
1267
+ "learning_rate": 9.89481592787378e-06,
1268
+ "loss": 1.4563,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 0.16,
1273
+ "learning_rate": 9.894315051339845e-06,
1274
+ "loss": 1.2889,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 0.16,
1279
+ "learning_rate": 9.893814174805911e-06,
1280
+ "loss": 1.1332,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 0.16,
1285
+ "learning_rate": 9.893313298271978e-06,
1286
+ "loss": 1.3066,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 0.16,
1291
+ "learning_rate": 9.892812421738042e-06,
1292
+ "loss": 1.3334,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 0.16,
1297
+ "learning_rate": 9.892311545204109e-06,
1298
+ "loss": 1.3667,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 0.16,
1303
+ "learning_rate": 9.891810668670173e-06,
1304
+ "loss": 1.286,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 0.16,
1309
+ "learning_rate": 9.891309792136238e-06,
1310
+ "loss": 1.1615,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 0.16,
1315
+ "learning_rate": 9.890808915602304e-06,
1316
+ "loss": 1.4357,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 0.16,
1321
+ "learning_rate": 9.89030803906837e-06,
1322
+ "loss": 1.3783,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 0.17,
1327
+ "learning_rate": 9.889807162534436e-06,
1328
+ "loss": 1.2917,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 0.17,
1333
+ "learning_rate": 9.889306286000502e-06,
1334
+ "loss": 1.3097,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 0.17,
1339
+ "learning_rate": 9.888805409466568e-06,
1340
+ "loss": 1.181,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 0.17,
1345
+ "learning_rate": 9.888304532932633e-06,
1346
+ "loss": 1.4424,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 0.17,
1351
+ "learning_rate": 9.8878036563987e-06,
1352
+ "loss": 1.3605,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 0.17,
1357
+ "learning_rate": 9.887302779864764e-06,
1358
+ "loss": 1.3231,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 0.17,
1363
+ "learning_rate": 9.886801903330829e-06,
1364
+ "loss": 1.3303,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 0.17,
1369
+ "learning_rate": 9.886301026796895e-06,
1370
+ "loss": 1.5354,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 0.17,
1375
+ "learning_rate": 9.885800150262962e-06,
1376
+ "loss": 1.3655,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 0.17,
1381
+ "learning_rate": 9.885299273729026e-06,
1382
+ "loss": 1.3456,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 0.17,
1387
+ "learning_rate": 9.884798397195093e-06,
1388
+ "loss": 1.3463,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 0.17,
1393
+ "learning_rate": 9.884297520661157e-06,
1394
+ "loss": 1.2825,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 0.17,
1399
+ "learning_rate": 9.883796644127224e-06,
1400
+ "loss": 1.4984,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 0.18,
1405
+ "learning_rate": 9.88329576759329e-06,
1406
+ "loss": 1.3438,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 0.18,
1411
+ "learning_rate": 9.882794891059355e-06,
1412
+ "loss": 1.356,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 0.18,
1417
+ "learning_rate": 9.88229401452542e-06,
1418
+ "loss": 1.4768,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 0.18,
1423
+ "learning_rate": 9.881793137991486e-06,
1424
+ "loss": 1.4532,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 0.18,
1429
+ "learning_rate": 9.88129226145755e-06,
1430
+ "loss": 1.1431,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 0.18,
1435
+ "learning_rate": 9.880791384923617e-06,
1436
+ "loss": 1.341,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 0.18,
1441
+ "learning_rate": 9.880290508389683e-06,
1442
+ "loss": 1.2889,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 0.18,
1447
+ "learning_rate": 9.879789631855748e-06,
1448
+ "loss": 1.4215,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 0.18,
1453
+ "learning_rate": 9.879288755321814e-06,
1454
+ "loss": 1.1116,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 0.18,
1459
+ "learning_rate": 9.87878787878788e-06,
1460
+ "loss": 1.5555,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 0.18,
1465
+ "learning_rate": 9.878287002253946e-06,
1466
+ "loss": 1.3331,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 0.18,
1471
+ "learning_rate": 9.87778612572001e-06,
1472
+ "loss": 1.3002,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 0.18,
1477
+ "learning_rate": 9.877285249186077e-06,
1478
+ "loss": 1.5123,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 0.18,
1483
+ "learning_rate": 9.876784372652141e-06,
1484
+ "loss": 1.2954,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 0.19,
1489
+ "learning_rate": 9.876283496118208e-06,
1490
+ "loss": 1.3768,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 0.19,
1495
+ "learning_rate": 9.875782619584272e-06,
1496
+ "loss": 1.1999,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 0.19,
1501
+ "learning_rate": 9.875281743050339e-06,
1502
+ "loss": 1.2151,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 0.19,
1507
+ "learning_rate": 9.874780866516405e-06,
1508
+ "loss": 1.1457,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 0.19,
1513
+ "learning_rate": 9.87427998998247e-06,
1514
+ "loss": 1.2943,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 0.19,
1519
+ "learning_rate": 9.873779113448536e-06,
1520
+ "loss": 1.2995,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 0.19,
1525
+ "learning_rate": 9.873278236914603e-06,
1526
+ "loss": 1.3549,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 0.19,
1531
+ "learning_rate": 9.872777360380666e-06,
1532
+ "loss": 1.4157,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 0.19,
1537
+ "learning_rate": 9.872276483846732e-06,
1538
+ "loss": 1.2343,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 0.19,
1543
+ "learning_rate": 9.871775607312798e-06,
1544
+ "loss": 1.4704,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 0.19,
1549
+ "learning_rate": 9.871274730778863e-06,
1550
+ "loss": 1.3183,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 0.19,
1555
+ "learning_rate": 9.87077385424493e-06,
1556
+ "loss": 1.281,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 0.19,
1561
+ "learning_rate": 9.870272977710996e-06,
1562
+ "loss": 1.2269,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 0.2,
1567
+ "learning_rate": 9.86977210117706e-06,
1568
+ "loss": 1.3954,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 0.2,
1573
+ "learning_rate": 9.869271224643127e-06,
1574
+ "loss": 1.2609,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 0.2,
1579
+ "learning_rate": 9.868770348109192e-06,
1580
+ "loss": 1.1484,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 0.2,
1585
+ "learning_rate": 9.868269471575258e-06,
1586
+ "loss": 1.3233,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 0.2,
1591
+ "learning_rate": 9.867768595041323e-06,
1592
+ "loss": 1.3622,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 0.2,
1597
+ "learning_rate": 9.86726771850739e-06,
1598
+ "loss": 1.3001,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 0.2,
1603
+ "learning_rate": 9.866766841973454e-06,
1604
+ "loss": 1.5199,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 0.2,
1609
+ "learning_rate": 9.86626596543952e-06,
1610
+ "loss": 1.4343,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 0.2,
1615
+ "learning_rate": 9.865765088905585e-06,
1616
+ "loss": 1.3625,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 0.2,
1621
+ "learning_rate": 9.865264212371651e-06,
1622
+ "loss": 1.3519,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 0.2,
1627
+ "learning_rate": 9.864763335837718e-06,
1628
+ "loss": 1.0975,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 0.2,
1633
+ "learning_rate": 9.864262459303782e-06,
1634
+ "loss": 1.1754,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 0.2,
1639
+ "learning_rate": 9.863761582769849e-06,
1640
+ "loss": 1.2909,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 0.21,
1645
+ "learning_rate": 9.863260706235914e-06,
1646
+ "loss": 1.351,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 0.21,
1651
+ "learning_rate": 9.862759829701978e-06,
1652
+ "loss": 1.4366,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 0.21,
1657
+ "learning_rate": 9.862258953168045e-06,
1658
+ "loss": 1.234,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 0.21,
1663
+ "learning_rate": 9.861758076634111e-06,
1664
+ "loss": 1.2537,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 0.21,
1669
+ "learning_rate": 9.861257200100176e-06,
1670
+ "loss": 1.3179,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 0.21,
1675
+ "learning_rate": 9.860756323566242e-06,
1676
+ "loss": 1.2767,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 0.21,
1681
+ "learning_rate": 9.860255447032307e-06,
1682
+ "loss": 1.2613,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 0.21,
1687
+ "learning_rate": 9.859754570498373e-06,
1688
+ "loss": 1.4828,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 0.21,
1693
+ "learning_rate": 9.85925369396444e-06,
1694
+ "loss": 1.4044,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 0.21,
1699
+ "learning_rate": 9.858752817430504e-06,
1700
+ "loss": 1.2874,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 0.21,
1705
+ "learning_rate": 9.858251940896569e-06,
1706
+ "loss": 1.3894,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 0.21,
1711
+ "learning_rate": 9.857751064362635e-06,
1712
+ "loss": 1.4082,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 0.21,
1717
+ "learning_rate": 9.8572501878287e-06,
1718
+ "loss": 1.4339,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 0.21,
1723
+ "learning_rate": 9.856749311294766e-06,
1724
+ "loss": 1.3389,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 0.22,
1729
+ "learning_rate": 9.856248434760833e-06,
1730
+ "loss": 1.6074,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 0.22,
1735
+ "learning_rate": 9.855747558226898e-06,
1736
+ "loss": 1.2211,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 0.22,
1741
+ "learning_rate": 9.855246681692964e-06,
1742
+ "loss": 1.2046,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 0.22,
1747
+ "learning_rate": 9.854745805159029e-06,
1748
+ "loss": 1.1644,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 0.22,
1753
+ "learning_rate": 9.854244928625095e-06,
1754
+ "loss": 1.3212,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 0.22,
1759
+ "learning_rate": 9.85374405209116e-06,
1760
+ "loss": 1.2408,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 0.22,
1765
+ "learning_rate": 9.853243175557226e-06,
1766
+ "loss": 1.1935,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 0.22,
1771
+ "learning_rate": 9.85274229902329e-06,
1772
+ "loss": 1.506,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 0.22,
1777
+ "learning_rate": 9.852241422489357e-06,
1778
+ "loss": 1.2551,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 0.22,
1783
+ "learning_rate": 9.851740545955422e-06,
1784
+ "loss": 1.3662,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 0.22,
1789
+ "learning_rate": 9.851239669421488e-06,
1790
+ "loss": 1.2536,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 0.22,
1795
+ "learning_rate": 9.850738792887555e-06,
1796
+ "loss": 1.111,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 0.22,
1801
+ "learning_rate": 9.85023791635362e-06,
1802
+ "loss": 1.2344,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 0.23,
1807
+ "learning_rate": 9.849737039819686e-06,
1808
+ "loss": 1.2443,
1809
+ "step": 300
1810
+ }
1811
+ ],
1812
+ "logging_steps": 1,
1813
+ "max_steps": 19965,
1814
+ "num_train_epochs": 15,
1815
+ "save_steps": 100,
1816
+ "total_flos": 5.708706873311232e+16,
1817
+ "trial_name": null,
1818
+ "trial_params": null
1819
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc9ad47b1a7a063a17bb223f172f1e41ce82d1f933bcc2258e5835441c20893b
3
+ size 4027