alexshengzhili commited on
Commit
1909eb1
1 Parent(s): f3f6a12

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+ ### Framework versions
7
+
8
+
9
+ - PEFT 0.4.0
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "liuhaotian/llava-llama-2-13b-chat-lightning-preview",
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": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "k_proj",
19
+ "down_proj",
20
+ "up_proj",
21
+ "o_proj",
22
+ "gate_proj",
23
+ "v_proj",
24
+ "mm_projector"
25
+ ],
26
+ "task_type": "CAUSAL_LM"
27
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52c5d53a5b3acf8e45006945d8cb629ddd42bd5a4061b6af0793e308ae16a090
3
+ size 501676373
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "liuhaotian/llava-llama-2-13b-chat-lightning-preview",
3
+ "architectures": [
4
+ "LlavaLlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "freeze_mm_mlp_adapter": false,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "image_aspect_ratio": "pad",
12
+ "image_grid_pinpoints": null,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 13824,
15
+ "max_position_embeddings": 4096,
16
+ "mm_hidden_size": 1024,
17
+ "mm_resampler_type": null,
18
+ "mm_use_im_patch_token": false,
19
+ "mm_use_im_start_end": false,
20
+ "mm_vision_select_feature": "patch",
21
+ "mm_vision_select_layer": -2,
22
+ "mm_vision_tower": "openai/clip-vit-large-patch14",
23
+ "model_type": "llava",
24
+ "num_attention_heads": 40,
25
+ "num_hidden_layers": 40,
26
+ "num_key_value_heads": 40,
27
+ "pad_token_id": 0,
28
+ "pretraining_tp": 1,
29
+ "rms_norm_eps": 1e-05,
30
+ "rope_scaling": null,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "float16",
33
+ "transformers_version": "4.31.0",
34
+ "tune_mm_mlp_adapter": false,
35
+ "tune_mm_vision_resampler": false,
36
+ "use_cache": true,
37
+ "use_mm_proj": true,
38
+ "vocab_size": 32000
39
+ }
non_lora_trainables.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc6b9cc23771073378c3887f3524986a3b61cac85cbc085f322b318241bc6845
3
+ size 455
trainer_state.json ADDED
@@ -0,0 +1,1423 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9989281886387996,
5
+ "global_step": 233,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 1.4285714285714286e-06,
13
+ "loss": 0.9647,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 2.8571428571428573e-06,
19
+ "loss": 0.9612,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 4.2857142857142855e-06,
25
+ "loss": 0.9788,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.02,
30
+ "learning_rate": 5.7142857142857145e-06,
31
+ "loss": 1.0404,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.02,
36
+ "learning_rate": 7.1428571428571436e-06,
37
+ "loss": 1.0253,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.03,
42
+ "learning_rate": 8.571428571428571e-06,
43
+ "loss": 0.9271,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.03,
48
+ "learning_rate": 1e-05,
49
+ "loss": 0.9537,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.03,
54
+ "learning_rate": 9.999516923531906e-06,
55
+ "loss": 1.0348,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.04,
60
+ "learning_rate": 9.998067787472772e-06,
61
+ "loss": 1.0089,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.04,
66
+ "learning_rate": 9.995652871840006e-06,
67
+ "loss": 0.9514,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.05,
72
+ "learning_rate": 9.992272643269181e-06,
73
+ "loss": 0.9565,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.05,
78
+ "learning_rate": 9.987927754923844e-06,
79
+ "loss": 0.9587,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.06,
84
+ "learning_rate": 9.982619046369321e-06,
85
+ "loss": 0.9813,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.06,
90
+ "learning_rate": 9.976347543410487e-06,
91
+ "loss": 0.9689,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.06,
96
+ "learning_rate": 9.96911445789354e-06,
97
+ "loss": 1.0083,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.07,
102
+ "learning_rate": 9.960921187471841e-06,
103
+ "loss": 1.0022,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.07,
108
+ "learning_rate": 9.951769315335843e-06,
109
+ "loss": 1.0201,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.08,
114
+ "learning_rate": 9.94166060990718e-06,
115
+ "loss": 0.9267,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.08,
120
+ "learning_rate": 9.930597024496933e-06,
121
+ "loss": 0.9543,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.09,
126
+ "learning_rate": 9.918580696928206e-06,
127
+ "loss": 0.9814,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.09,
132
+ "learning_rate": 9.905613949123036e-06,
133
+ "loss": 0.986,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.09,
138
+ "learning_rate": 9.891699286653714e-06,
139
+ "loss": 0.9464,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.1,
144
+ "learning_rate": 9.87683939825864e-06,
145
+ "loss": 0.9442,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.1,
150
+ "learning_rate": 9.861037155322777e-06,
151
+ "loss": 1.0023,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.11,
156
+ "learning_rate": 9.844295611322804e-06,
157
+ "loss": 0.9524,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.11,
162
+ "learning_rate": 9.826618001237101e-06,
163
+ "loss": 1.0088,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.12,
168
+ "learning_rate": 9.808007740920647e-06,
169
+ "loss": 0.9542,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.12,
174
+ "learning_rate": 9.788468426444968e-06,
175
+ "loss": 0.9861,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.12,
180
+ "learning_rate": 9.768003833403278e-06,
181
+ "loss": 0.9533,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.13,
186
+ "learning_rate": 9.746617916180906e-06,
187
+ "loss": 0.9402,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.13,
192
+ "learning_rate": 9.724314807191197e-06,
193
+ "loss": 1.0455,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.14,
198
+ "learning_rate": 9.701098816076995e-06,
199
+ "loss": 0.9379,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.14,
204
+ "learning_rate": 9.6769744288779e-06,
205
+ "loss": 0.988,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.15,
210
+ "learning_rate": 9.651946307163417e-06,
211
+ "loss": 0.9998,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.15,
216
+ "learning_rate": 9.626019287132202e-06,
217
+ "loss": 0.9943,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.15,
222
+ "learning_rate": 9.599198378677559e-06,
223
+ "loss": 0.999,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.16,
228
+ "learning_rate": 9.571488764419381e-06,
229
+ "loss": 0.9608,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.16,
234
+ "learning_rate": 9.542895798702702e-06,
235
+ "loss": 0.9852,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.17,
240
+ "learning_rate": 9.51342500656308e-06,
241
+ "loss": 0.9252,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.17,
246
+ "learning_rate": 9.483082082658984e-06,
247
+ "loss": 0.9802,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.18,
252
+ "learning_rate": 9.451872890171419e-06,
253
+ "loss": 0.955,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.18,
258
+ "learning_rate": 9.41980345967098e-06,
259
+ "loss": 0.9292,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.18,
264
+ "learning_rate": 9.386879987952549e-06,
265
+ "loss": 0.9818,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.19,
270
+ "learning_rate": 9.353108836837907e-06,
271
+ "loss": 0.952,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.19,
276
+ "learning_rate": 9.318496531946411e-06,
277
+ "loss": 0.9525,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.2,
282
+ "learning_rate": 9.283049761434059e-06,
283
+ "loss": 0.9136,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.2,
288
+ "learning_rate": 9.246775374701139e-06,
289
+ "loss": 0.9882,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.21,
294
+ "learning_rate": 9.209680381068698e-06,
295
+ "loss": 0.9812,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.21,
300
+ "learning_rate": 9.171771948424138e-06,
301
+ "loss": 0.9652,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.21,
306
+ "learning_rate": 9.13305740183616e-06,
307
+ "loss": 0.9753,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.22,
312
+ "learning_rate": 9.093544222139338e-06,
313
+ "loss": 0.9142,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.22,
318
+ "learning_rate": 9.053240044488587e-06,
319
+ "loss": 1.0215,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.23,
324
+ "learning_rate": 9.012152656883824e-06,
325
+ "loss": 0.9178,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.23,
330
+ "learning_rate": 8.970289998665083e-06,
331
+ "loss": 0.9146,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.24,
336
+ "learning_rate": 8.927660158978392e-06,
337
+ "loss": 0.9399,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.24,
342
+ "learning_rate": 8.884271375212714e-06,
343
+ "loss": 0.9224,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.24,
348
+ "learning_rate": 8.84013203140821e-06,
349
+ "loss": 0.9368,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.25,
354
+ "learning_rate": 8.795250656636207e-06,
355
+ "loss": 0.9538,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 0.25,
360
+ "learning_rate": 8.749635923351108e-06,
361
+ "loss": 0.944,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 0.26,
366
+ "learning_rate": 8.70329664571461e-06,
367
+ "loss": 0.9462,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 0.26,
372
+ "learning_rate": 8.656241777892544e-06,
373
+ "loss": 0.9415,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 0.27,
378
+ "learning_rate": 8.608480412324652e-06,
379
+ "loss": 0.9376,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 0.27,
384
+ "learning_rate": 8.56002177796765e-06,
385
+ "loss": 0.9305,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 0.27,
390
+ "learning_rate": 8.510875238511911e-06,
391
+ "loss": 0.9203,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 0.28,
396
+ "learning_rate": 8.461050290572114e-06,
397
+ "loss": 0.9625,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 0.28,
402
+ "learning_rate": 8.410556561852212e-06,
403
+ "loss": 0.92,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 0.29,
408
+ "learning_rate": 8.359403809285054e-06,
409
+ "loss": 0.912,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 0.29,
414
+ "learning_rate": 8.30760191714706e-06,
415
+ "loss": 0.9316,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 0.3,
420
+ "learning_rate": 8.255160895148263e-06,
421
+ "loss": 0.9243,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 0.3,
426
+ "learning_rate": 8.202090876498144e-06,
427
+ "loss": 0.9209,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 0.3,
432
+ "learning_rate": 8.14840211594757e-06,
433
+ "loss": 0.937,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 0.31,
438
+ "learning_rate": 8.09410498780727e-06,
439
+ "loss": 0.93,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 0.31,
444
+ "learning_rate": 8.039209983943201e-06,
445
+ "loss": 0.9364,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 0.32,
450
+ "learning_rate": 7.983727711749194e-06,
451
+ "loss": 0.9497,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 0.32,
456
+ "learning_rate": 7.927668892097288e-06,
457
+ "loss": 0.9155,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 0.33,
462
+ "learning_rate": 7.871044357266124e-06,
463
+ "loss": 0.9404,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 0.33,
468
+ "learning_rate": 7.81386504884782e-06,
469
+ "loss": 0.9512,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 0.33,
474
+ "learning_rate": 7.75614201563372e-06,
475
+ "loss": 0.8969,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 0.34,
480
+ "learning_rate": 7.697886411479422e-06,
481
+ "loss": 0.9449,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 0.34,
486
+ "learning_rate": 7.639109493149537e-06,
487
+ "loss": 0.9162,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 0.35,
492
+ "learning_rate": 7.579822618142505e-06,
493
+ "loss": 0.9265,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 0.35,
498
+ "learning_rate": 7.520037242496e-06,
499
+ "loss": 0.9004,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 0.36,
504
+ "learning_rate": 7.459764918573264e-06,
505
+ "loss": 0.9159,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 0.36,
510
+ "learning_rate": 7.399017292830848e-06,
511
+ "loss": 0.9897,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 0.36,
516
+ "learning_rate": 7.3378061035681415e-06,
517
+ "loss": 0.8831,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 0.37,
522
+ "learning_rate": 7.276143178659195e-06,
523
+ "loss": 0.8804,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 0.37,
528
+ "learning_rate": 7.2140404332671986e-06,
529
+ "loss": 0.9042,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 0.38,
534
+ "learning_rate": 7.1515098675421125e-06,
535
+ "loss": 0.9084,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 0.38,
540
+ "learning_rate": 7.088563564301874e-06,
541
+ "loss": 0.9262,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 0.39,
546
+ "learning_rate": 7.0252136866976205e-06,
547
+ "loss": 0.9149,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 0.39,
552
+ "learning_rate": 6.961472475863406e-06,
553
+ "loss": 0.8765,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 0.39,
558
+ "learning_rate": 6.897352248550828e-06,
559
+ "loss": 0.9194,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 0.4,
564
+ "learning_rate": 6.832865394749065e-06,
565
+ "loss": 0.9056,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 0.4,
570
+ "learning_rate": 6.768024375290747e-06,
571
+ "loss": 0.886,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 0.41,
576
+ "learning_rate": 6.702841719444141e-06,
577
+ "loss": 0.8881,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 0.41,
582
+ "learning_rate": 6.637330022492112e-06,
583
+ "loss": 0.9144,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 0.42,
588
+ "learning_rate": 6.571501943298335e-06,
589
+ "loss": 0.9248,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 0.42,
594
+ "learning_rate": 6.50537020186121e-06,
595
+ "loss": 0.8927,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 0.42,
600
+ "learning_rate": 6.4389475768559675e-06,
601
+ "loss": 0.8876,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 0.43,
606
+ "learning_rate": 6.372246903165445e-06,
607
+ "loss": 0.9196,
608
+ "step": 100
609
+ },
610
+ {
611
+ "epoch": 0.43,
612
+ "learning_rate": 6.305281069399989e-06,
613
+ "loss": 0.9386,
614
+ "step": 101
615
+ },
616
+ {
617
+ "epoch": 0.44,
618
+ "learning_rate": 6.238063015406982e-06,
619
+ "loss": 0.911,
620
+ "step": 102
621
+ },
622
+ {
623
+ "epoch": 0.44,
624
+ "learning_rate": 6.17060572977047e-06,
625
+ "loss": 0.8829,
626
+ "step": 103
627
+ },
628
+ {
629
+ "epoch": 0.45,
630
+ "learning_rate": 6.1029222473013705e-06,
631
+ "loss": 0.914,
632
+ "step": 104
633
+ },
634
+ {
635
+ "epoch": 0.45,
636
+ "learning_rate": 6.035025646518747e-06,
637
+ "loss": 0.9027,
638
+ "step": 105
639
+ },
640
+ {
641
+ "epoch": 0.45,
642
+ "learning_rate": 5.966929047122641e-06,
643
+ "loss": 0.9088,
644
+ "step": 106
645
+ },
646
+ {
647
+ "epoch": 0.46,
648
+ "learning_rate": 5.898645607458941e-06,
649
+ "loss": 0.8972,
650
+ "step": 107
651
+ },
652
+ {
653
+ "epoch": 0.46,
654
+ "learning_rate": 5.830188521976794e-06,
655
+ "loss": 1.0138,
656
+ "step": 108
657
+ },
658
+ {
659
+ "epoch": 0.47,
660
+ "learning_rate": 5.761571018679025e-06,
661
+ "loss": 0.8856,
662
+ "step": 109
663
+ },
664
+ {
665
+ "epoch": 0.47,
666
+ "learning_rate": 5.6928063565660955e-06,
667
+ "loss": 0.9073,
668
+ "step": 110
669
+ },
670
+ {
671
+ "epoch": 0.48,
672
+ "learning_rate": 5.623907823074044e-06,
673
+ "loss": 0.9249,
674
+ "step": 111
675
+ },
676
+ {
677
+ "epoch": 0.48,
678
+ "learning_rate": 5.5548887315069575e-06,
679
+ "loss": 0.8923,
680
+ "step": 112
681
+ },
682
+ {
683
+ "epoch": 0.48,
684
+ "learning_rate": 5.48576241846443e-06,
685
+ "loss": 0.9531,
686
+ "step": 113
687
+ },
688
+ {
689
+ "epoch": 0.49,
690
+ "learning_rate": 5.416542241264524e-06,
691
+ "loss": 0.8698,
692
+ "step": 114
693
+ },
694
+ {
695
+ "epoch": 0.49,
696
+ "learning_rate": 5.347241575362729e-06,
697
+ "loss": 0.97,
698
+ "step": 115
699
+ },
700
+ {
701
+ "epoch": 0.5,
702
+ "learning_rate": 5.277873811767415e-06,
703
+ "loss": 0.9077,
704
+ "step": 116
705
+ },
706
+ {
707
+ "epoch": 0.5,
708
+ "learning_rate": 5.208452354452275e-06,
709
+ "loss": 0.8709,
710
+ "step": 117
711
+ },
712
+ {
713
+ "epoch": 0.51,
714
+ "learning_rate": 5.1389906177662705e-06,
715
+ "loss": 0.8485,
716
+ "step": 118
717
+ },
718
+ {
719
+ "epoch": 0.51,
720
+ "learning_rate": 5.069502023841576e-06,
721
+ "loss": 0.9081,
722
+ "step": 119
723
+ },
724
+ {
725
+ "epoch": 0.51,
726
+ "learning_rate": 5e-06,
727
+ "loss": 0.8596,
728
+ "step": 120
729
+ },
730
+ {
731
+ "epoch": 0.52,
732
+ "learning_rate": 4.9304979761584256e-06,
733
+ "loss": 0.9091,
734
+ "step": 121
735
+ },
736
+ {
737
+ "epoch": 0.52,
738
+ "learning_rate": 4.86100938223373e-06,
739
+ "loss": 0.9067,
740
+ "step": 122
741
+ },
742
+ {
743
+ "epoch": 0.53,
744
+ "learning_rate": 4.791547645547727e-06,
745
+ "loss": 0.9067,
746
+ "step": 123
747
+ },
748
+ {
749
+ "epoch": 0.53,
750
+ "learning_rate": 4.722126188232586e-06,
751
+ "loss": 0.9169,
752
+ "step": 124
753
+ },
754
+ {
755
+ "epoch": 0.54,
756
+ "learning_rate": 4.652758424637271e-06,
757
+ "loss": 0.8661,
758
+ "step": 125
759
+ },
760
+ {
761
+ "epoch": 0.54,
762
+ "learning_rate": 4.583457758735477e-06,
763
+ "loss": 0.8648,
764
+ "step": 126
765
+ },
766
+ {
767
+ "epoch": 0.54,
768
+ "learning_rate": 4.514237581535571e-06,
769
+ "loss": 0.9384,
770
+ "step": 127
771
+ },
772
+ {
773
+ "epoch": 0.55,
774
+ "learning_rate": 4.4451112684930424e-06,
775
+ "loss": 0.9088,
776
+ "step": 128
777
+ },
778
+ {
779
+ "epoch": 0.55,
780
+ "learning_rate": 4.3760921769259585e-06,
781
+ "loss": 0.8867,
782
+ "step": 129
783
+ },
784
+ {
785
+ "epoch": 0.56,
786
+ "learning_rate": 4.307193643433907e-06,
787
+ "loss": 0.9048,
788
+ "step": 130
789
+ },
790
+ {
791
+ "epoch": 0.56,
792
+ "learning_rate": 4.2384289813209754e-06,
793
+ "loss": 0.879,
794
+ "step": 131
795
+ },
796
+ {
797
+ "epoch": 0.57,
798
+ "learning_rate": 4.1698114780232085e-06,
799
+ "loss": 0.9342,
800
+ "step": 132
801
+ },
802
+ {
803
+ "epoch": 0.57,
804
+ "learning_rate": 4.101354392541061e-06,
805
+ "loss": 0.8803,
806
+ "step": 133
807
+ },
808
+ {
809
+ "epoch": 0.57,
810
+ "learning_rate": 4.033070952877362e-06,
811
+ "loss": 0.9021,
812
+ "step": 134
813
+ },
814
+ {
815
+ "epoch": 0.58,
816
+ "learning_rate": 3.964974353481254e-06,
817
+ "loss": 0.8531,
818
+ "step": 135
819
+ },
820
+ {
821
+ "epoch": 0.58,
822
+ "learning_rate": 3.89707775269863e-06,
823
+ "loss": 0.9417,
824
+ "step": 136
825
+ },
826
+ {
827
+ "epoch": 0.59,
828
+ "learning_rate": 3.829394270229531e-06,
829
+ "loss": 0.895,
830
+ "step": 137
831
+ },
832
+ {
833
+ "epoch": 0.59,
834
+ "learning_rate": 3.7619369845930195e-06,
835
+ "loss": 0.9225,
836
+ "step": 138
837
+ },
838
+ {
839
+ "epoch": 0.6,
840
+ "learning_rate": 3.694718930600012e-06,
841
+ "loss": 0.9061,
842
+ "step": 139
843
+ },
844
+ {
845
+ "epoch": 0.6,
846
+ "learning_rate": 3.6277530968345552e-06,
847
+ "loss": 0.9171,
848
+ "step": 140
849
+ },
850
+ {
851
+ "epoch": 0.6,
852
+ "learning_rate": 3.5610524231440324e-06,
853
+ "loss": 0.8518,
854
+ "step": 141
855
+ },
856
+ {
857
+ "epoch": 0.61,
858
+ "learning_rate": 3.4946297981387913e-06,
859
+ "loss": 0.9252,
860
+ "step": 142
861
+ },
862
+ {
863
+ "epoch": 0.61,
864
+ "learning_rate": 3.428498056701665e-06,
865
+ "loss": 0.8954,
866
+ "step": 143
867
+ },
868
+ {
869
+ "epoch": 0.62,
870
+ "learning_rate": 3.3626699775078884e-06,
871
+ "loss": 0.9131,
872
+ "step": 144
873
+ },
874
+ {
875
+ "epoch": 0.62,
876
+ "learning_rate": 3.2971582805558622e-06,
877
+ "loss": 0.8737,
878
+ "step": 145
879
+ },
880
+ {
881
+ "epoch": 0.63,
882
+ "learning_rate": 3.2319756247092552e-06,
883
+ "loss": 0.901,
884
+ "step": 146
885
+ },
886
+ {
887
+ "epoch": 0.63,
888
+ "learning_rate": 3.167134605250938e-06,
889
+ "loss": 0.8971,
890
+ "step": 147
891
+ },
892
+ {
893
+ "epoch": 0.63,
894
+ "learning_rate": 3.102647751449174e-06,
895
+ "loss": 0.9102,
896
+ "step": 148
897
+ },
898
+ {
899
+ "epoch": 0.64,
900
+ "learning_rate": 3.0385275241365965e-06,
901
+ "loss": 0.8664,
902
+ "step": 149
903
+ },
904
+ {
905
+ "epoch": 0.64,
906
+ "learning_rate": 2.9747863133023803e-06,
907
+ "loss": 0.8842,
908
+ "step": 150
909
+ },
910
+ {
911
+ "epoch": 0.65,
912
+ "learning_rate": 2.9114364356981274e-06,
913
+ "loss": 0.8718,
914
+ "step": 151
915
+ },
916
+ {
917
+ "epoch": 0.65,
918
+ "learning_rate": 2.8484901324578883e-06,
919
+ "loss": 0.8987,
920
+ "step": 152
921
+ },
922
+ {
923
+ "epoch": 0.66,
924
+ "learning_rate": 2.7859595667328027e-06,
925
+ "loss": 0.8636,
926
+ "step": 153
927
+ },
928
+ {
929
+ "epoch": 0.66,
930
+ "learning_rate": 2.723856821340806e-06,
931
+ "loss": 0.8753,
932
+ "step": 154
933
+ },
934
+ {
935
+ "epoch": 0.66,
936
+ "learning_rate": 2.6621938964318593e-06,
937
+ "loss": 0.9054,
938
+ "step": 155
939
+ },
940
+ {
941
+ "epoch": 0.67,
942
+ "learning_rate": 2.600982707169154e-06,
943
+ "loss": 0.8859,
944
+ "step": 156
945
+ },
946
+ {
947
+ "epoch": 0.67,
948
+ "learning_rate": 2.5402350814267364e-06,
949
+ "loss": 0.8888,
950
+ "step": 157
951
+ },
952
+ {
953
+ "epoch": 0.68,
954
+ "learning_rate": 2.4799627575040014e-06,
955
+ "loss": 0.8704,
956
+ "step": 158
957
+ },
958
+ {
959
+ "epoch": 0.68,
960
+ "learning_rate": 2.4201773818574956e-06,
961
+ "loss": 0.8943,
962
+ "step": 159
963
+ },
964
+ {
965
+ "epoch": 0.69,
966
+ "learning_rate": 2.360890506850464e-06,
967
+ "loss": 0.9088,
968
+ "step": 160
969
+ },
970
+ {
971
+ "epoch": 0.69,
972
+ "learning_rate": 2.302113588520578e-06,
973
+ "loss": 0.8857,
974
+ "step": 161
975
+ },
976
+ {
977
+ "epoch": 0.69,
978
+ "learning_rate": 2.243857984366284e-06,
979
+ "loss": 0.8732,
980
+ "step": 162
981
+ },
982
+ {
983
+ "epoch": 0.7,
984
+ "learning_rate": 2.1861349511521817e-06,
985
+ "loss": 0.8909,
986
+ "step": 163
987
+ },
988
+ {
989
+ "epoch": 0.7,
990
+ "learning_rate": 2.128955642733877e-06,
991
+ "loss": 0.8663,
992
+ "step": 164
993
+ },
994
+ {
995
+ "epoch": 0.71,
996
+ "learning_rate": 2.072331107902713e-06,
997
+ "loss": 0.8845,
998
+ "step": 165
999
+ },
1000
+ {
1001
+ "epoch": 0.71,
1002
+ "learning_rate": 2.0162722882508072e-06,
1003
+ "loss": 0.8974,
1004
+ "step": 166
1005
+ },
1006
+ {
1007
+ "epoch": 0.72,
1008
+ "learning_rate": 1.960790016056801e-06,
1009
+ "loss": 0.9084,
1010
+ "step": 167
1011
+ },
1012
+ {
1013
+ "epoch": 0.72,
1014
+ "learning_rate": 1.90589501219273e-06,
1015
+ "loss": 0.8749,
1016
+ "step": 168
1017
+ },
1018
+ {
1019
+ "epoch": 0.72,
1020
+ "learning_rate": 1.8515978840524302e-06,
1021
+ "loss": 0.8915,
1022
+ "step": 169
1023
+ },
1024
+ {
1025
+ "epoch": 0.73,
1026
+ "learning_rate": 1.7979091235018564e-06,
1027
+ "loss": 0.8876,
1028
+ "step": 170
1029
+ },
1030
+ {
1031
+ "epoch": 0.73,
1032
+ "learning_rate": 1.7448391048517378e-06,
1033
+ "loss": 0.8762,
1034
+ "step": 171
1035
+ },
1036
+ {
1037
+ "epoch": 0.74,
1038
+ "learning_rate": 1.6923980828529424e-06,
1039
+ "loss": 0.8846,
1040
+ "step": 172
1041
+ },
1042
+ {
1043
+ "epoch": 0.74,
1044
+ "learning_rate": 1.640596190714947e-06,
1045
+ "loss": 0.9112,
1046
+ "step": 173
1047
+ },
1048
+ {
1049
+ "epoch": 0.75,
1050
+ "learning_rate": 1.589443438147789e-06,
1051
+ "loss": 0.9316,
1052
+ "step": 174
1053
+ },
1054
+ {
1055
+ "epoch": 0.75,
1056
+ "learning_rate": 1.5389497094278861e-06,
1057
+ "loss": 0.9098,
1058
+ "step": 175
1059
+ },
1060
+ {
1061
+ "epoch": 0.75,
1062
+ "learning_rate": 1.4891247614880904e-06,
1063
+ "loss": 0.9075,
1064
+ "step": 176
1065
+ },
1066
+ {
1067
+ "epoch": 0.76,
1068
+ "learning_rate": 1.4399782220323515e-06,
1069
+ "loss": 0.8749,
1070
+ "step": 177
1071
+ },
1072
+ {
1073
+ "epoch": 0.76,
1074
+ "learning_rate": 1.3915195876753495e-06,
1075
+ "loss": 0.8767,
1076
+ "step": 178
1077
+ },
1078
+ {
1079
+ "epoch": 0.77,
1080
+ "learning_rate": 1.3437582221074574e-06,
1081
+ "loss": 0.8622,
1082
+ "step": 179
1083
+ },
1084
+ {
1085
+ "epoch": 0.77,
1086
+ "learning_rate": 1.2967033542853918e-06,
1087
+ "loss": 0.8908,
1088
+ "step": 180
1089
+ },
1090
+ {
1091
+ "epoch": 0.78,
1092
+ "learning_rate": 1.250364076648894e-06,
1093
+ "loss": 0.8607,
1094
+ "step": 181
1095
+ },
1096
+ {
1097
+ "epoch": 0.78,
1098
+ "learning_rate": 1.2047493433637935e-06,
1099
+ "loss": 0.9185,
1100
+ "step": 182
1101
+ },
1102
+ {
1103
+ "epoch": 0.78,
1104
+ "learning_rate": 1.1598679685917901e-06,
1105
+ "loss": 0.8728,
1106
+ "step": 183
1107
+ },
1108
+ {
1109
+ "epoch": 0.79,
1110
+ "learning_rate": 1.1157286247872873e-06,
1111
+ "loss": 0.8557,
1112
+ "step": 184
1113
+ },
1114
+ {
1115
+ "epoch": 0.79,
1116
+ "learning_rate": 1.0723398410216085e-06,
1117
+ "loss": 0.8861,
1118
+ "step": 185
1119
+ },
1120
+ {
1121
+ "epoch": 0.8,
1122
+ "learning_rate": 1.0297100013349181e-06,
1123
+ "loss": 0.8568,
1124
+ "step": 186
1125
+ },
1126
+ {
1127
+ "epoch": 0.8,
1128
+ "learning_rate": 9.878473431161767e-07,
1129
+ "loss": 0.8527,
1130
+ "step": 187
1131
+ },
1132
+ {
1133
+ "epoch": 0.81,
1134
+ "learning_rate": 9.467599555114137e-07,
1135
+ "loss": 0.8622,
1136
+ "step": 188
1137
+ },
1138
+ {
1139
+ "epoch": 0.81,
1140
+ "learning_rate": 9.064557778606631e-07,
1141
+ "loss": 0.951,
1142
+ "step": 189
1143
+ },
1144
+ {
1145
+ "epoch": 0.81,
1146
+ "learning_rate": 8.669425981638413e-07,
1147
+ "loss": 0.9074,
1148
+ "step": 190
1149
+ },
1150
+ {
1151
+ "epoch": 0.82,
1152
+ "learning_rate": 8.282280515758639e-07,
1153
+ "loss": 0.8839,
1154
+ "step": 191
1155
+ },
1156
+ {
1157
+ "epoch": 0.82,
1158
+ "learning_rate": 7.903196189313039e-07,
1159
+ "loss": 0.9193,
1160
+ "step": 192
1161
+ },
1162
+ {
1163
+ "epoch": 0.83,
1164
+ "learning_rate": 7.532246252988617e-07,
1165
+ "loss": 0.8785,
1166
+ "step": 193
1167
+ },
1168
+ {
1169
+ "epoch": 0.83,
1170
+ "learning_rate": 7.16950238565941e-07,
1171
+ "loss": 0.8461,
1172
+ "step": 194
1173
+ },
1174
+ {
1175
+ "epoch": 0.84,
1176
+ "learning_rate": 6.815034680535915e-07,
1177
+ "loss": 0.8308,
1178
+ "step": 195
1179
+ },
1180
+ {
1181
+ "epoch": 0.84,
1182
+ "learning_rate": 6.46891163162095e-07,
1183
+ "loss": 0.8792,
1184
+ "step": 196
1185
+ },
1186
+ {
1187
+ "epoch": 0.84,
1188
+ "learning_rate": 6.131200120474512e-07,
1189
+ "loss": 0.9292,
1190
+ "step": 197
1191
+ },
1192
+ {
1193
+ "epoch": 0.85,
1194
+ "learning_rate": 5.801965403290221e-07,
1195
+ "loss": 0.8785,
1196
+ "step": 198
1197
+ },
1198
+ {
1199
+ "epoch": 0.85,
1200
+ "learning_rate": 5.481271098285818e-07,
1201
+ "loss": 0.8839,
1202
+ "step": 199
1203
+ },
1204
+ {
1205
+ "epoch": 0.86,
1206
+ "learning_rate": 5.169179173410178e-07,
1207
+ "loss": 0.8629,
1208
+ "step": 200
1209
+ },
1210
+ {
1211
+ "epoch": 0.86,
1212
+ "learning_rate": 4.865749934369224e-07,
1213
+ "loss": 0.8593,
1214
+ "step": 201
1215
+ },
1216
+ {
1217
+ "epoch": 0.87,
1218
+ "learning_rate": 4.571042012972993e-07,
1219
+ "loss": 0.8764,
1220
+ "step": 202
1221
+ },
1222
+ {
1223
+ "epoch": 0.87,
1224
+ "learning_rate": 4.2851123558061927e-07,
1225
+ "loss": 0.8521,
1226
+ "step": 203
1227
+ },
1228
+ {
1229
+ "epoch": 0.87,
1230
+ "learning_rate": 4.008016213224408e-07,
1231
+ "loss": 0.8982,
1232
+ "step": 204
1233
+ },
1234
+ {
1235
+ "epoch": 0.88,
1236
+ "learning_rate": 3.739807128677986e-07,
1237
+ "loss": 0.8703,
1238
+ "step": 205
1239
+ },
1240
+ {
1241
+ "epoch": 0.88,
1242
+ "learning_rate": 3.480536928365824e-07,
1243
+ "loss": 0.8618,
1244
+ "step": 206
1245
+ },
1246
+ {
1247
+ "epoch": 0.89,
1248
+ "learning_rate": 3.230255711220992e-07,
1249
+ "loss": 0.8876,
1250
+ "step": 207
1251
+ },
1252
+ {
1253
+ "epoch": 0.89,
1254
+ "learning_rate": 2.9890118392300493e-07,
1255
+ "loss": 0.8856,
1256
+ "step": 208
1257
+ },
1258
+ {
1259
+ "epoch": 0.9,
1260
+ "learning_rate": 2.756851928088056e-07,
1261
+ "loss": 0.8938,
1262
+ "step": 209
1263
+ },
1264
+ {
1265
+ "epoch": 0.9,
1266
+ "learning_rate": 2.533820838190959e-07,
1267
+ "loss": 0.9029,
1268
+ "step": 210
1269
+ },
1270
+ {
1271
+ "epoch": 0.9,
1272
+ "learning_rate": 2.3199616659672352e-07,
1273
+ "loss": 0.8963,
1274
+ "step": 211
1275
+ },
1276
+ {
1277
+ "epoch": 0.91,
1278
+ "learning_rate": 2.1153157355503274e-07,
1279
+ "loss": 0.8669,
1280
+ "step": 212
1281
+ },
1282
+ {
1283
+ "epoch": 0.91,
1284
+ "learning_rate": 1.9199225907935492e-07,
1285
+ "loss": 0.8846,
1286
+ "step": 213
1287
+ },
1288
+ {
1289
+ "epoch": 0.92,
1290
+ "learning_rate": 1.7338199876289984e-07,
1291
+ "loss": 0.8796,
1292
+ "step": 214
1293
+ },
1294
+ {
1295
+ "epoch": 0.92,
1296
+ "learning_rate": 1.5570438867719695e-07,
1297
+ "loss": 0.9144,
1298
+ "step": 215
1299
+ },
1300
+ {
1301
+ "epoch": 0.93,
1302
+ "learning_rate": 1.3896284467722398e-07,
1303
+ "loss": 0.912,
1304
+ "step": 216
1305
+ },
1306
+ {
1307
+ "epoch": 0.93,
1308
+ "learning_rate": 1.2316060174136e-07,
1309
+ "loss": 0.9186,
1310
+ "step": 217
1311
+ },
1312
+ {
1313
+ "epoch": 0.93,
1314
+ "learning_rate": 1.0830071334628655e-07,
1315
+ "loss": 0.8841,
1316
+ "step": 218
1317
+ },
1318
+ {
1319
+ "epoch": 0.94,
1320
+ "learning_rate": 9.43860508769645e-08,
1321
+ "loss": 0.8699,
1322
+ "step": 219
1323
+ },
1324
+ {
1325
+ "epoch": 0.94,
1326
+ "learning_rate": 8.141930307179468e-08,
1327
+ "loss": 0.8885,
1328
+ "step": 220
1329
+ },
1330
+ {
1331
+ "epoch": 0.95,
1332
+ "learning_rate": 6.940297550306895e-08,
1333
+ "loss": 0.8901,
1334
+ "step": 221
1335
+ },
1336
+ {
1337
+ "epoch": 0.95,
1338
+ "learning_rate": 5.833939009282086e-08,
1339
+ "loss": 0.8852,
1340
+ "step": 222
1341
+ },
1342
+ {
1343
+ "epoch": 0.96,
1344
+ "learning_rate": 4.823068466415615e-08,
1345
+ "loss": 0.9279,
1346
+ "step": 223
1347
+ },
1348
+ {
1349
+ "epoch": 0.96,
1350
+ "learning_rate": 3.907881252816048e-08,
1351
+ "loss": 0.8549,
1352
+ "step": 224
1353
+ },
1354
+ {
1355
+ "epoch": 0.96,
1356
+ "learning_rate": 3.088554210646133e-08,
1357
+ "loss": 0.9369,
1358
+ "step": 225
1359
+ },
1360
+ {
1361
+ "epoch": 0.97,
1362
+ "learning_rate": 2.3652456589512983e-08,
1363
+ "loss": 0.9129,
1364
+ "step": 226
1365
+ },
1366
+ {
1367
+ "epoch": 0.97,
1368
+ "learning_rate": 1.7380953630678488e-08,
1369
+ "loss": 0.8472,
1370
+ "step": 227
1371
+ },
1372
+ {
1373
+ "epoch": 0.98,
1374
+ "learning_rate": 1.2072245076156786e-08,
1375
+ "loss": 0.8672,
1376
+ "step": 228
1377
+ },
1378
+ {
1379
+ "epoch": 0.98,
1380
+ "learning_rate": 7.727356730820035e-09,
1381
+ "loss": 0.8965,
1382
+ "step": 229
1383
+ },
1384
+ {
1385
+ "epoch": 0.99,
1386
+ "learning_rate": 4.347128159993829e-09,
1387
+ "loss": 0.8852,
1388
+ "step": 230
1389
+ },
1390
+ {
1391
+ "epoch": 0.99,
1392
+ "learning_rate": 1.9322125272297488e-09,
1393
+ "loss": 0.9028,
1394
+ "step": 231
1395
+ },
1396
+ {
1397
+ "epoch": 0.99,
1398
+ "learning_rate": 4.830764680946453e-10,
1399
+ "loss": 0.8491,
1400
+ "step": 232
1401
+ },
1402
+ {
1403
+ "epoch": 1.0,
1404
+ "learning_rate": 0.0,
1405
+ "loss": 0.8746,
1406
+ "step": 233
1407
+ },
1408
+ {
1409
+ "epoch": 1.0,
1410
+ "step": 233,
1411
+ "total_flos": 4.1801555584619643e+18,
1412
+ "train_loss": 0.9163404472907726,
1413
+ "train_runtime": 12375.9474,
1414
+ "train_samples_per_second": 4.824,
1415
+ "train_steps_per_second": 0.019
1416
+ }
1417
+ ],
1418
+ "max_steps": 233,
1419
+ "num_train_epochs": 1,
1420
+ "total_flos": 4.1801555584619643e+18,
1421
+ "trial_name": null,
1422
+ "trial_params": null
1423
+ }