CreatorPhan commited on
Commit
f084c8f
1 Parent(s): 3a52eb4

Upload folder using huggingface_hub

Browse files
Files changed (45) hide show
  1. .gitattributes +4 -0
  2. checkpoint-100/README.md +34 -0
  3. checkpoint-100/adapter_config.json +23 -0
  4. checkpoint-100/adapter_model.bin +3 -0
  5. checkpoint-100/optimizer.pt +3 -0
  6. checkpoint-100/rng_state.pth +3 -0
  7. checkpoint-100/scheduler.pt +3 -0
  8. checkpoint-100/special_tokens_map.json +6 -0
  9. checkpoint-100/tokenizer.json +3 -0
  10. checkpoint-100/tokenizer_config.json +10 -0
  11. checkpoint-100/trainer_state.json +619 -0
  12. checkpoint-100/training_args.bin +3 -0
  13. checkpoint-200/README.md +34 -0
  14. checkpoint-200/adapter_config.json +23 -0
  15. checkpoint-200/adapter_model.bin +3 -0
  16. checkpoint-200/optimizer.pt +3 -0
  17. checkpoint-200/rng_state.pth +3 -0
  18. checkpoint-200/scheduler.pt +3 -0
  19. checkpoint-200/special_tokens_map.json +6 -0
  20. checkpoint-200/tokenizer.json +3 -0
  21. checkpoint-200/tokenizer_config.json +10 -0
  22. checkpoint-200/trainer_state.json +1219 -0
  23. checkpoint-200/training_args.bin +3 -0
  24. checkpoint-300/README.md +34 -0
  25. checkpoint-300/adapter_config.json +23 -0
  26. checkpoint-300/adapter_model.bin +3 -0
  27. checkpoint-300/optimizer.pt +3 -0
  28. checkpoint-300/rng_state.pth +3 -0
  29. checkpoint-300/scheduler.pt +3 -0
  30. checkpoint-300/special_tokens_map.json +6 -0
  31. checkpoint-300/tokenizer.json +3 -0
  32. checkpoint-300/tokenizer_config.json +10 -0
  33. checkpoint-300/trainer_state.json +1819 -0
  34. checkpoint-300/training_args.bin +3 -0
  35. checkpoint-400/README.md +34 -0
  36. checkpoint-400/adapter_config.json +23 -0
  37. checkpoint-400/adapter_model.bin +3 -0
  38. checkpoint-400/optimizer.pt +3 -0
  39. checkpoint-400/rng_state.pth +3 -0
  40. checkpoint-400/scheduler.pt +3 -0
  41. checkpoint-400/special_tokens_map.json +6 -0
  42. checkpoint-400/tokenizer.json +3 -0
  43. checkpoint-400/tokenizer_config.json +10 -0
  44. checkpoint-400/trainer_state.json +2419 -0
  45. checkpoint-400/training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-100/README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: True
22
+ - load_in_4bit: False
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: fp4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float32
30
+ ### Framework versions
31
+
32
+ - PEFT 0.6.0.dev0
33
+
34
+ - PEFT 0.6.0.dev0
checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "bigscience/bloomz-3b",
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": 0.0,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "dense_4h_to_h",
18
+ "dense",
19
+ "dense_h_to_4h",
20
+ "query_key_value"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
checkpoint-100/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:622f24ad39b1d813c6bb8f79a2df239fe2b4bb6d2dedbc9a5e33de708da4f720
3
+ size 39409357
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea1dce7e79dd3d2c9c9ceaf946eb67c70455769ce5e9a1efd4fc0f4ae74846c9
3
+ size 78844421
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7508d4b8dd267de5cc58e972da25236687927651336a28f292c92f7f23951475
3
+ size 14575
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d281983268f4ae148ac851b47bf18115a0b9369d83517193dcf3062cb237281c
3
+ size 627
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
checkpoint-100/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d81d9b2c9d9db79ea02c00d4c7e79bb77a718dc57ab01f5f3b1cd6649f08993
3
+ size 14500569
checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "tokenizer_class": "BloomTokenizer",
9
+ "unk_token": "<unk>"
10
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,619 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.857142857142857,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 0.002998214285714286,
14
+ "loss": 3.0944,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.06,
19
+ "learning_rate": 0.0029964285714285713,
20
+ "loss": 2.8734,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.09,
25
+ "learning_rate": 0.002994642857142857,
26
+ "loss": 8.7265,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.11,
31
+ "learning_rate": 0.002992857142857143,
32
+ "loss": 4.7587,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.14,
37
+ "learning_rate": 0.002991071428571429,
38
+ "loss": 4.3637,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.17,
43
+ "learning_rate": 0.0029892857142857143,
44
+ "loss": 3.315,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.2,
49
+ "learning_rate": 0.0029875,
50
+ "loss": 3.1726,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.23,
55
+ "learning_rate": 0.002985714285714286,
56
+ "loss": 2.9938,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.26,
61
+ "learning_rate": 0.0029839285714285714,
62
+ "loss": 3.0509,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.29,
67
+ "learning_rate": 0.0029821428571428573,
68
+ "loss": 2.93,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.31,
73
+ "learning_rate": 0.002980357142857143,
74
+ "loss": 2.8436,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.34,
79
+ "learning_rate": 0.0029785714285714285,
80
+ "loss": 2.8756,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.37,
85
+ "learning_rate": 0.0029767857142857144,
86
+ "loss": 2.8528,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.4,
91
+ "learning_rate": 0.002975,
92
+ "loss": 2.8405,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.43,
97
+ "learning_rate": 0.002973214285714286,
98
+ "loss": 2.8022,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.46,
103
+ "learning_rate": 0.0029714285714285715,
104
+ "loss": 2.8356,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.49,
109
+ "learning_rate": 0.0029696428571428573,
110
+ "loss": 2.7915,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.51,
115
+ "learning_rate": 0.002967857142857143,
116
+ "loss": 2.7848,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.54,
121
+ "learning_rate": 0.0029660714285714286,
122
+ "loss": 2.6604,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.57,
127
+ "learning_rate": 0.0029642857142857144,
128
+ "loss": 2.736,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.6,
133
+ "learning_rate": 0.0029625000000000003,
134
+ "loss": 2.7747,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.63,
139
+ "learning_rate": 0.0029607142857142857,
140
+ "loss": 2.6958,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.66,
145
+ "learning_rate": 0.0029589285714285716,
146
+ "loss": 2.7309,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.69,
151
+ "learning_rate": 0.0029571428571428574,
152
+ "loss": 2.7294,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.71,
157
+ "learning_rate": 0.0029553571428571433,
158
+ "loss": 2.7493,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.74,
163
+ "learning_rate": 0.0029535714285714287,
164
+ "loss": 2.7351,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.77,
169
+ "learning_rate": 0.002951785714285714,
170
+ "loss": 2.6825,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.8,
175
+ "learning_rate": 0.00295,
176
+ "loss": 2.6658,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.83,
181
+ "learning_rate": 0.0029482142857142858,
182
+ "loss": 2.6127,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.86,
187
+ "learning_rate": 0.002946428571428571,
188
+ "loss": 2.6338,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.89,
193
+ "learning_rate": 0.002944642857142857,
194
+ "loss": 2.7094,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.91,
199
+ "learning_rate": 0.002942857142857143,
200
+ "loss": 2.6943,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.94,
205
+ "learning_rate": 0.0029410714285714283,
206
+ "loss": 2.7222,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.97,
211
+ "learning_rate": 0.002939285714285714,
212
+ "loss": 2.6541,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 1.0,
217
+ "learning_rate": 0.0029375,
218
+ "loss": 2.7111,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 1.03,
223
+ "learning_rate": 0.002935714285714286,
224
+ "loss": 2.5123,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 1.06,
229
+ "learning_rate": 0.0029339285714285713,
230
+ "loss": 2.493,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 1.09,
235
+ "learning_rate": 0.002932142857142857,
236
+ "loss": 2.4434,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 1.11,
241
+ "learning_rate": 0.002930357142857143,
242
+ "loss": 2.4883,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 1.14,
247
+ "learning_rate": 0.0029285714285714284,
248
+ "loss": 2.5004,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 1.17,
253
+ "learning_rate": 0.0029267857142857142,
254
+ "loss": 2.4667,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 1.2,
259
+ "learning_rate": 0.002925,
260
+ "loss": 2.4461,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 1.23,
265
+ "learning_rate": 0.002923214285714286,
266
+ "loss": 2.5361,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 1.26,
271
+ "learning_rate": 0.0029214285714285713,
272
+ "loss": 2.4597,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 1.29,
277
+ "learning_rate": 0.002919642857142857,
278
+ "loss": 2.4006,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 1.31,
283
+ "learning_rate": 0.002917857142857143,
284
+ "loss": 2.5019,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 1.34,
289
+ "learning_rate": 0.0029160714285714285,
290
+ "loss": 2.5209,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 1.37,
295
+ "learning_rate": 0.0029142857142857143,
296
+ "loss": 2.4753,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 1.4,
301
+ "learning_rate": 0.0029125,
302
+ "loss": 2.4104,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 1.43,
307
+ "learning_rate": 0.0029107142857142856,
308
+ "loss": 2.3938,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 1.46,
313
+ "learning_rate": 0.0029089285714285714,
314
+ "loss": 2.4999,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 1.49,
319
+ "learning_rate": 0.0029071428571428573,
320
+ "loss": 2.4292,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 1.51,
325
+ "learning_rate": 0.002905357142857143,
326
+ "loss": 2.4636,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 1.54,
331
+ "learning_rate": 0.0029035714285714285,
332
+ "loss": 2.5163,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 1.57,
337
+ "learning_rate": 0.0029017857142857144,
338
+ "loss": 2.5098,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 1.6,
343
+ "learning_rate": 0.0029000000000000002,
344
+ "loss": 2.447,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 1.63,
349
+ "learning_rate": 0.0028982142857142856,
350
+ "loss": 2.4262,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 1.66,
355
+ "learning_rate": 0.0028964285714285715,
356
+ "loss": 2.5146,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 1.69,
361
+ "learning_rate": 0.0028946428571428573,
362
+ "loss": 2.4225,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 1.71,
367
+ "learning_rate": 0.0028928571428571428,
368
+ "loss": 2.452,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 1.74,
373
+ "learning_rate": 0.0028910714285714286,
374
+ "loss": 2.4449,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 1.77,
379
+ "learning_rate": 0.0028892857142857145,
380
+ "loss": 2.4984,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 1.8,
385
+ "learning_rate": 0.0028875000000000003,
386
+ "loss": 2.4493,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 1.83,
391
+ "learning_rate": 0.0028857142857142857,
392
+ "loss": 2.4187,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 1.86,
397
+ "learning_rate": 0.0028839285714285716,
398
+ "loss": 2.5019,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 1.89,
403
+ "learning_rate": 0.0028821428571428574,
404
+ "loss": 2.4274,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 1.91,
409
+ "learning_rate": 0.002880357142857143,
410
+ "loss": 2.4485,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 1.94,
415
+ "learning_rate": 0.0028785714285714287,
416
+ "loss": 2.5096,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 1.97,
421
+ "learning_rate": 0.0028767857142857145,
422
+ "loss": 2.4862,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 2.0,
427
+ "learning_rate": 0.0028750000000000004,
428
+ "loss": 2.469,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 2.03,
433
+ "learning_rate": 0.002873214285714286,
434
+ "loss": 2.1795,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 2.06,
439
+ "learning_rate": 0.0028714285714285716,
440
+ "loss": 2.1106,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 2.09,
445
+ "learning_rate": 0.0028696428571428575,
446
+ "loss": 2.0896,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 2.11,
451
+ "learning_rate": 0.002867857142857143,
452
+ "loss": 2.2018,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 2.14,
457
+ "learning_rate": 0.0028660714285714288,
458
+ "loss": 2.0803,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 2.17,
463
+ "learning_rate": 0.0028642857142857146,
464
+ "loss": 2.1395,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 2.2,
469
+ "learning_rate": 0.0028625,
470
+ "loss": 2.1019,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 2.23,
475
+ "learning_rate": 0.002860714285714286,
476
+ "loss": 2.1383,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 2.26,
481
+ "learning_rate": 0.0028589285714285713,
482
+ "loss": 2.1109,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 2.29,
487
+ "learning_rate": 0.002857142857142857,
488
+ "loss": 2.0854,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 2.31,
493
+ "learning_rate": 0.0028553571428571426,
494
+ "loss": 2.1667,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 2.34,
499
+ "learning_rate": 0.0028535714285714284,
500
+ "loss": 2.1111,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 2.37,
505
+ "learning_rate": 0.0028517857142857143,
506
+ "loss": 2.1032,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 2.4,
511
+ "learning_rate": 0.00285,
512
+ "loss": 2.1708,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 2.43,
517
+ "learning_rate": 0.0028482142857142855,
518
+ "loss": 2.1118,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 2.46,
523
+ "learning_rate": 0.0028464285714285714,
524
+ "loss": 2.1481,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 2.49,
529
+ "learning_rate": 0.002844642857142857,
530
+ "loss": 2.1538,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 2.51,
535
+ "learning_rate": 0.0028428571428571426,
536
+ "loss": 2.1843,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 2.54,
541
+ "learning_rate": 0.0028410714285714285,
542
+ "loss": 2.1828,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 2.57,
547
+ "learning_rate": 0.0028392857142857143,
548
+ "loss": 2.2151,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 2.6,
553
+ "learning_rate": 0.0028375,
554
+ "loss": 2.1969,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 2.63,
559
+ "learning_rate": 0.0028357142857142856,
560
+ "loss": 2.1509,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 2.66,
565
+ "learning_rate": 0.0028339285714285714,
566
+ "loss": 2.2636,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 2.69,
571
+ "learning_rate": 0.0028321428571428573,
572
+ "loss": 2.2809,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 2.71,
577
+ "learning_rate": 0.0028303571428571427,
578
+ "loss": 2.2044,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 2.74,
583
+ "learning_rate": 0.0028285714285714286,
584
+ "loss": 2.2064,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 2.77,
589
+ "learning_rate": 0.0028267857142857144,
590
+ "loss": 2.2408,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 2.8,
595
+ "learning_rate": 0.002825,
596
+ "loss": 2.2446,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 2.83,
601
+ "learning_rate": 0.0028232142857142857,
602
+ "loss": 2.1965,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 2.86,
607
+ "learning_rate": 0.0028214285714285715,
608
+ "loss": 2.3093,
609
+ "step": 100
610
+ }
611
+ ],
612
+ "logging_steps": 1,
613
+ "max_steps": 1680,
614
+ "num_train_epochs": 48,
615
+ "save_steps": 100,
616
+ "total_flos": 5.771531478795264e+16,
617
+ "trial_name": null,
618
+ "trial_params": null
619
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8697dec26118787553757d80401d29ed990405410ca911afb8c282e3da6934e3
3
+ size 4091
checkpoint-200/README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: True
22
+ - load_in_4bit: False
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: fp4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float32
30
+ ### Framework versions
31
+
32
+ - PEFT 0.6.0.dev0
33
+
34
+ - PEFT 0.6.0.dev0
checkpoint-200/adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "bigscience/bloomz-3b",
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": 0.0,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "dense_4h_to_h",
18
+ "dense",
19
+ "dense_h_to_4h",
20
+ "query_key_value"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
checkpoint-200/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8beb03e0dedfb5b2da0d68ebcc49dbb502cea67ba9c0d70bed474bdde253aa1d
3
+ size 39409357
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:745db72555229d45c6a69054bcdee18c9e9f3193c81ae335546612e8aaa6d7c4
3
+ size 78844421
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6162bb9db25c89c41e126a7a00a5d0695219447bff9b18d08731531620758440
3
+ size 14575
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:461382c4e71db35cef694681fd3a0c229adb91f6f9d1e458e9d3c9be9149f8c4
3
+ size 627
checkpoint-200/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
checkpoint-200/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d81d9b2c9d9db79ea02c00d4c7e79bb77a718dc57ab01f5f3b1cd6649f08993
3
+ size 14500569
checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "tokenizer_class": "BloomTokenizer",
9
+ "unk_token": "<unk>"
10
+ }
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,1219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.714285714285714,
5
+ "eval_steps": 500,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 0.002998214285714286,
14
+ "loss": 3.0944,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.06,
19
+ "learning_rate": 0.0029964285714285713,
20
+ "loss": 2.8734,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.09,
25
+ "learning_rate": 0.002994642857142857,
26
+ "loss": 8.7265,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.11,
31
+ "learning_rate": 0.002992857142857143,
32
+ "loss": 4.7587,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.14,
37
+ "learning_rate": 0.002991071428571429,
38
+ "loss": 4.3637,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.17,
43
+ "learning_rate": 0.0029892857142857143,
44
+ "loss": 3.315,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.2,
49
+ "learning_rate": 0.0029875,
50
+ "loss": 3.1726,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.23,
55
+ "learning_rate": 0.002985714285714286,
56
+ "loss": 2.9938,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.26,
61
+ "learning_rate": 0.0029839285714285714,
62
+ "loss": 3.0509,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.29,
67
+ "learning_rate": 0.0029821428571428573,
68
+ "loss": 2.93,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.31,
73
+ "learning_rate": 0.002980357142857143,
74
+ "loss": 2.8436,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.34,
79
+ "learning_rate": 0.0029785714285714285,
80
+ "loss": 2.8756,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.37,
85
+ "learning_rate": 0.0029767857142857144,
86
+ "loss": 2.8528,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.4,
91
+ "learning_rate": 0.002975,
92
+ "loss": 2.8405,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.43,
97
+ "learning_rate": 0.002973214285714286,
98
+ "loss": 2.8022,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.46,
103
+ "learning_rate": 0.0029714285714285715,
104
+ "loss": 2.8356,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.49,
109
+ "learning_rate": 0.0029696428571428573,
110
+ "loss": 2.7915,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.51,
115
+ "learning_rate": 0.002967857142857143,
116
+ "loss": 2.7848,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.54,
121
+ "learning_rate": 0.0029660714285714286,
122
+ "loss": 2.6604,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.57,
127
+ "learning_rate": 0.0029642857142857144,
128
+ "loss": 2.736,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.6,
133
+ "learning_rate": 0.0029625000000000003,
134
+ "loss": 2.7747,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.63,
139
+ "learning_rate": 0.0029607142857142857,
140
+ "loss": 2.6958,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.66,
145
+ "learning_rate": 0.0029589285714285716,
146
+ "loss": 2.7309,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.69,
151
+ "learning_rate": 0.0029571428571428574,
152
+ "loss": 2.7294,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.71,
157
+ "learning_rate": 0.0029553571428571433,
158
+ "loss": 2.7493,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.74,
163
+ "learning_rate": 0.0029535714285714287,
164
+ "loss": 2.7351,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.77,
169
+ "learning_rate": 0.002951785714285714,
170
+ "loss": 2.6825,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.8,
175
+ "learning_rate": 0.00295,
176
+ "loss": 2.6658,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.83,
181
+ "learning_rate": 0.0029482142857142858,
182
+ "loss": 2.6127,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.86,
187
+ "learning_rate": 0.002946428571428571,
188
+ "loss": 2.6338,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.89,
193
+ "learning_rate": 0.002944642857142857,
194
+ "loss": 2.7094,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.91,
199
+ "learning_rate": 0.002942857142857143,
200
+ "loss": 2.6943,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.94,
205
+ "learning_rate": 0.0029410714285714283,
206
+ "loss": 2.7222,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.97,
211
+ "learning_rate": 0.002939285714285714,
212
+ "loss": 2.6541,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 1.0,
217
+ "learning_rate": 0.0029375,
218
+ "loss": 2.7111,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 1.03,
223
+ "learning_rate": 0.002935714285714286,
224
+ "loss": 2.5123,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 1.06,
229
+ "learning_rate": 0.0029339285714285713,
230
+ "loss": 2.493,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 1.09,
235
+ "learning_rate": 0.002932142857142857,
236
+ "loss": 2.4434,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 1.11,
241
+ "learning_rate": 0.002930357142857143,
242
+ "loss": 2.4883,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 1.14,
247
+ "learning_rate": 0.0029285714285714284,
248
+ "loss": 2.5004,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 1.17,
253
+ "learning_rate": 0.0029267857142857142,
254
+ "loss": 2.4667,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 1.2,
259
+ "learning_rate": 0.002925,
260
+ "loss": 2.4461,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 1.23,
265
+ "learning_rate": 0.002923214285714286,
266
+ "loss": 2.5361,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 1.26,
271
+ "learning_rate": 0.0029214285714285713,
272
+ "loss": 2.4597,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 1.29,
277
+ "learning_rate": 0.002919642857142857,
278
+ "loss": 2.4006,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 1.31,
283
+ "learning_rate": 0.002917857142857143,
284
+ "loss": 2.5019,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 1.34,
289
+ "learning_rate": 0.0029160714285714285,
290
+ "loss": 2.5209,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 1.37,
295
+ "learning_rate": 0.0029142857142857143,
296
+ "loss": 2.4753,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 1.4,
301
+ "learning_rate": 0.0029125,
302
+ "loss": 2.4104,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 1.43,
307
+ "learning_rate": 0.0029107142857142856,
308
+ "loss": 2.3938,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 1.46,
313
+ "learning_rate": 0.0029089285714285714,
314
+ "loss": 2.4999,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 1.49,
319
+ "learning_rate": 0.0029071428571428573,
320
+ "loss": 2.4292,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 1.51,
325
+ "learning_rate": 0.002905357142857143,
326
+ "loss": 2.4636,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 1.54,
331
+ "learning_rate": 0.0029035714285714285,
332
+ "loss": 2.5163,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 1.57,
337
+ "learning_rate": 0.0029017857142857144,
338
+ "loss": 2.5098,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 1.6,
343
+ "learning_rate": 0.0029000000000000002,
344
+ "loss": 2.447,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 1.63,
349
+ "learning_rate": 0.0028982142857142856,
350
+ "loss": 2.4262,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 1.66,
355
+ "learning_rate": 0.0028964285714285715,
356
+ "loss": 2.5146,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 1.69,
361
+ "learning_rate": 0.0028946428571428573,
362
+ "loss": 2.4225,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 1.71,
367
+ "learning_rate": 0.0028928571428571428,
368
+ "loss": 2.452,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 1.74,
373
+ "learning_rate": 0.0028910714285714286,
374
+ "loss": 2.4449,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 1.77,
379
+ "learning_rate": 0.0028892857142857145,
380
+ "loss": 2.4984,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 1.8,
385
+ "learning_rate": 0.0028875000000000003,
386
+ "loss": 2.4493,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 1.83,
391
+ "learning_rate": 0.0028857142857142857,
392
+ "loss": 2.4187,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 1.86,
397
+ "learning_rate": 0.0028839285714285716,
398
+ "loss": 2.5019,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 1.89,
403
+ "learning_rate": 0.0028821428571428574,
404
+ "loss": 2.4274,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 1.91,
409
+ "learning_rate": 0.002880357142857143,
410
+ "loss": 2.4485,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 1.94,
415
+ "learning_rate": 0.0028785714285714287,
416
+ "loss": 2.5096,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 1.97,
421
+ "learning_rate": 0.0028767857142857145,
422
+ "loss": 2.4862,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 2.0,
427
+ "learning_rate": 0.0028750000000000004,
428
+ "loss": 2.469,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 2.03,
433
+ "learning_rate": 0.002873214285714286,
434
+ "loss": 2.1795,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 2.06,
439
+ "learning_rate": 0.0028714285714285716,
440
+ "loss": 2.1106,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 2.09,
445
+ "learning_rate": 0.0028696428571428575,
446
+ "loss": 2.0896,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 2.11,
451
+ "learning_rate": 0.002867857142857143,
452
+ "loss": 2.2018,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 2.14,
457
+ "learning_rate": 0.0028660714285714288,
458
+ "loss": 2.0803,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 2.17,
463
+ "learning_rate": 0.0028642857142857146,
464
+ "loss": 2.1395,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 2.2,
469
+ "learning_rate": 0.0028625,
470
+ "loss": 2.1019,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 2.23,
475
+ "learning_rate": 0.002860714285714286,
476
+ "loss": 2.1383,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 2.26,
481
+ "learning_rate": 0.0028589285714285713,
482
+ "loss": 2.1109,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 2.29,
487
+ "learning_rate": 0.002857142857142857,
488
+ "loss": 2.0854,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 2.31,
493
+ "learning_rate": 0.0028553571428571426,
494
+ "loss": 2.1667,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 2.34,
499
+ "learning_rate": 0.0028535714285714284,
500
+ "loss": 2.1111,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 2.37,
505
+ "learning_rate": 0.0028517857142857143,
506
+ "loss": 2.1032,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 2.4,
511
+ "learning_rate": 0.00285,
512
+ "loss": 2.1708,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 2.43,
517
+ "learning_rate": 0.0028482142857142855,
518
+ "loss": 2.1118,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 2.46,
523
+ "learning_rate": 0.0028464285714285714,
524
+ "loss": 2.1481,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 2.49,
529
+ "learning_rate": 0.002844642857142857,
530
+ "loss": 2.1538,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 2.51,
535
+ "learning_rate": 0.0028428571428571426,
536
+ "loss": 2.1843,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 2.54,
541
+ "learning_rate": 0.0028410714285714285,
542
+ "loss": 2.1828,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 2.57,
547
+ "learning_rate": 0.0028392857142857143,
548
+ "loss": 2.2151,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 2.6,
553
+ "learning_rate": 0.0028375,
554
+ "loss": 2.1969,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 2.63,
559
+ "learning_rate": 0.0028357142857142856,
560
+ "loss": 2.1509,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 2.66,
565
+ "learning_rate": 0.0028339285714285714,
566
+ "loss": 2.2636,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 2.69,
571
+ "learning_rate": 0.0028321428571428573,
572
+ "loss": 2.2809,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 2.71,
577
+ "learning_rate": 0.0028303571428571427,
578
+ "loss": 2.2044,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 2.74,
583
+ "learning_rate": 0.0028285714285714286,
584
+ "loss": 2.2064,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 2.77,
589
+ "learning_rate": 0.0028267857142857144,
590
+ "loss": 2.2408,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 2.8,
595
+ "learning_rate": 0.002825,
596
+ "loss": 2.2446,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 2.83,
601
+ "learning_rate": 0.0028232142857142857,
602
+ "loss": 2.1965,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 2.86,
607
+ "learning_rate": 0.0028214285714285715,
608
+ "loss": 2.3093,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 2.89,
613
+ "learning_rate": 0.0028196428571428574,
614
+ "loss": 2.2188,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 2.91,
619
+ "learning_rate": 0.0028178571428571428,
620
+ "loss": 2.3098,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 2.94,
625
+ "learning_rate": 0.0028160714285714286,
626
+ "loss": 2.2268,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 2.97,
631
+ "learning_rate": 0.0028142857142857145,
632
+ "loss": 2.2574,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 3.0,
637
+ "learning_rate": 0.0028125,
638
+ "loss": 2.2982,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 3.03,
643
+ "learning_rate": 0.0028107142857142857,
644
+ "loss": 1.879,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 3.06,
649
+ "learning_rate": 0.0028089285714285716,
650
+ "loss": 1.8074,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 3.09,
655
+ "learning_rate": 0.002807142857142857,
656
+ "loss": 1.8174,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 3.11,
661
+ "learning_rate": 0.002805357142857143,
662
+ "loss": 1.784,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 3.14,
667
+ "learning_rate": 0.0028035714285714287,
668
+ "loss": 1.8469,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 3.17,
673
+ "learning_rate": 0.0028017857142857146,
674
+ "loss": 1.8614,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 3.2,
679
+ "learning_rate": 0.0028,
680
+ "loss": 1.8648,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 3.23,
685
+ "learning_rate": 0.002798214285714286,
686
+ "loss": 1.8172,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 3.26,
691
+ "learning_rate": 0.0027964285714285717,
692
+ "loss": 1.8579,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 3.29,
697
+ "learning_rate": 0.002794642857142857,
698
+ "loss": 1.8261,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 3.31,
703
+ "learning_rate": 0.002792857142857143,
704
+ "loss": 1.8993,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 3.34,
709
+ "learning_rate": 0.0027910714285714288,
710
+ "loss": 1.8144,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 3.37,
715
+ "learning_rate": 0.0027892857142857146,
716
+ "loss": 1.8583,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 3.4,
721
+ "learning_rate": 0.0027875,
722
+ "loss": 1.8589,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 3.43,
727
+ "learning_rate": 0.002785714285714286,
728
+ "loss": 1.9069,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 3.46,
733
+ "learning_rate": 0.0027839285714285717,
734
+ "loss": 1.9004,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 3.49,
739
+ "learning_rate": 0.002782142857142857,
740
+ "loss": 1.9378,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 3.51,
745
+ "learning_rate": 0.002780357142857143,
746
+ "loss": 1.9161,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 3.54,
751
+ "learning_rate": 0.002778571428571429,
752
+ "loss": 1.9886,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 3.57,
757
+ "learning_rate": 0.0027767857142857143,
758
+ "loss": 1.8636,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 3.6,
763
+ "learning_rate": 0.002775,
764
+ "loss": 1.9642,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 3.63,
769
+ "learning_rate": 0.002773214285714286,
770
+ "loss": 1.959,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 3.66,
775
+ "learning_rate": 0.002771428571428572,
776
+ "loss": 1.9787,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 3.69,
781
+ "learning_rate": 0.0027696428571428572,
782
+ "loss": 2.0272,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 3.71,
787
+ "learning_rate": 0.002767857142857143,
788
+ "loss": 2.0362,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 3.74,
793
+ "learning_rate": 0.002766071428571429,
794
+ "loss": 2.0369,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 3.77,
799
+ "learning_rate": 0.0027642857142857143,
800
+ "loss": 2.0721,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 3.8,
805
+ "learning_rate": 0.0027624999999999998,
806
+ "loss": 1.9939,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 3.83,
811
+ "learning_rate": 0.0027607142857142856,
812
+ "loss": 2.0403,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 3.86,
817
+ "learning_rate": 0.0027589285714285715,
818
+ "loss": 2.1132,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 3.89,
823
+ "learning_rate": 0.002757142857142857,
824
+ "loss": 2.0741,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 3.91,
829
+ "learning_rate": 0.0027553571428571427,
830
+ "loss": 2.0754,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 3.94,
835
+ "learning_rate": 0.0027535714285714286,
836
+ "loss": 2.1321,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 3.97,
841
+ "learning_rate": 0.0027517857142857144,
842
+ "loss": 2.0665,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 4.0,
847
+ "learning_rate": 0.00275,
848
+ "loss": 2.1085,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 4.03,
853
+ "learning_rate": 0.0027482142857142857,
854
+ "loss": 1.653,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 4.06,
859
+ "learning_rate": 0.0027464285714285715,
860
+ "loss": 1.5934,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 4.09,
865
+ "learning_rate": 0.002744642857142857,
866
+ "loss": 1.6795,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 4.11,
871
+ "learning_rate": 0.002742857142857143,
872
+ "loss": 1.6043,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 4.14,
877
+ "learning_rate": 0.0027410714285714287,
878
+ "loss": 1.586,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 4.17,
883
+ "learning_rate": 0.002739285714285714,
884
+ "loss": 1.6061,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 4.2,
889
+ "learning_rate": 0.0027375,
890
+ "loss": 1.6438,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 4.23,
895
+ "learning_rate": 0.0027357142857142858,
896
+ "loss": 1.6097,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 4.26,
901
+ "learning_rate": 0.0027339285714285716,
902
+ "loss": 1.7163,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 4.29,
907
+ "learning_rate": 0.002732142857142857,
908
+ "loss": 1.6485,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 4.31,
913
+ "learning_rate": 0.002730357142857143,
914
+ "loss": 1.6555,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 4.34,
919
+ "learning_rate": 0.0027285714285714287,
920
+ "loss": 1.689,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 4.37,
925
+ "learning_rate": 0.002726785714285714,
926
+ "loss": 1.7174,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 4.4,
931
+ "learning_rate": 0.002725,
932
+ "loss": 1.7205,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 4.43,
937
+ "learning_rate": 0.002723214285714286,
938
+ "loss": 1.7064,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 4.46,
943
+ "learning_rate": 0.0027214285714285717,
944
+ "loss": 1.7045,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 4.49,
949
+ "learning_rate": 0.002719642857142857,
950
+ "loss": 1.7749,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 4.51,
955
+ "learning_rate": 0.002717857142857143,
956
+ "loss": 1.7826,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 4.54,
961
+ "learning_rate": 0.002716071428571429,
962
+ "loss": 1.7882,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 4.57,
967
+ "learning_rate": 0.0027142857142857142,
968
+ "loss": 1.8073,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 4.6,
973
+ "learning_rate": 0.0027125,
974
+ "loss": 1.7931,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 4.63,
979
+ "learning_rate": 0.002710714285714286,
980
+ "loss": 1.8388,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 4.66,
985
+ "learning_rate": 0.0027089285714285713,
986
+ "loss": 1.8267,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 4.69,
991
+ "learning_rate": 0.002707142857142857,
992
+ "loss": 1.8208,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 4.71,
997
+ "learning_rate": 0.002705357142857143,
998
+ "loss": 1.8404,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 4.74,
1003
+ "learning_rate": 0.002703571428571429,
1004
+ "loss": 1.8375,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 4.77,
1009
+ "learning_rate": 0.0027017857142857143,
1010
+ "loss": 1.9444,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 4.8,
1015
+ "learning_rate": 0.0027,
1016
+ "loss": 1.8325,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 4.83,
1021
+ "learning_rate": 0.002698214285714286,
1022
+ "loss": 1.8705,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 4.86,
1027
+ "learning_rate": 0.0026964285714285714,
1028
+ "loss": 1.9368,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 4.89,
1033
+ "learning_rate": 0.0026946428571428573,
1034
+ "loss": 1.8758,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 4.91,
1039
+ "learning_rate": 0.002692857142857143,
1040
+ "loss": 1.999,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 4.94,
1045
+ "learning_rate": 0.0026910714285714285,
1046
+ "loss": 1.9547,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 4.97,
1051
+ "learning_rate": 0.0026892857142857144,
1052
+ "loss": 1.9332,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 5.0,
1057
+ "learning_rate": 0.0026875000000000002,
1058
+ "loss": 1.9704,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 5.03,
1063
+ "learning_rate": 0.002685714285714286,
1064
+ "loss": 1.4766,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 5.06,
1069
+ "learning_rate": 0.0026839285714285715,
1070
+ "loss": 1.4459,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 5.09,
1075
+ "learning_rate": 0.0026821428571428573,
1076
+ "loss": 1.4451,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 5.11,
1081
+ "learning_rate": 0.002680357142857143,
1082
+ "loss": 1.4761,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 5.14,
1087
+ "learning_rate": 0.0026785714285714286,
1088
+ "loss": 1.5092,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 5.17,
1093
+ "learning_rate": 0.0026767857142857144,
1094
+ "loss": 1.4439,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 5.2,
1099
+ "learning_rate": 0.0026750000000000003,
1100
+ "loss": 1.4539,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 5.23,
1105
+ "learning_rate": 0.002673214285714286,
1106
+ "loss": 1.4804,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 5.26,
1111
+ "learning_rate": 0.002671428571428571,
1112
+ "loss": 1.4958,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 5.29,
1117
+ "learning_rate": 0.002669642857142857,
1118
+ "loss": 1.5054,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 5.31,
1123
+ "learning_rate": 0.002667857142857143,
1124
+ "loss": 1.4673,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 5.34,
1129
+ "learning_rate": 0.0026660714285714287,
1130
+ "loss": 1.5703,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 5.37,
1135
+ "learning_rate": 0.002664285714285714,
1136
+ "loss": 1.5504,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 5.4,
1141
+ "learning_rate": 0.0026625,
1142
+ "loss": 1.6126,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 5.43,
1147
+ "learning_rate": 0.002660714285714286,
1148
+ "loss": 1.5777,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 5.46,
1153
+ "learning_rate": 0.002658928571428571,
1154
+ "loss": 1.5994,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 5.49,
1159
+ "learning_rate": 0.002657142857142857,
1160
+ "loss": 1.5939,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 5.51,
1165
+ "learning_rate": 0.002655357142857143,
1166
+ "loss": 1.6297,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 5.54,
1171
+ "learning_rate": 0.0026535714285714283,
1172
+ "loss": 1.6749,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 5.57,
1177
+ "learning_rate": 0.002651785714285714,
1178
+ "loss": 1.6525,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 5.6,
1183
+ "learning_rate": 0.00265,
1184
+ "loss": 1.657,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 5.63,
1189
+ "learning_rate": 0.002648214285714286,
1190
+ "loss": 1.6818,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 5.66,
1195
+ "learning_rate": 0.0026464285714285713,
1196
+ "loss": 1.6985,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 5.69,
1201
+ "learning_rate": 0.002644642857142857,
1202
+ "loss": 1.7456,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 5.71,
1207
+ "learning_rate": 0.002642857142857143,
1208
+ "loss": 1.678,
1209
+ "step": 200
1210
+ }
1211
+ ],
1212
+ "logging_steps": 1,
1213
+ "max_steps": 1680,
1214
+ "num_train_epochs": 48,
1215
+ "save_steps": 100,
1216
+ "total_flos": 1.1559978611371008e+17,
1217
+ "trial_name": null,
1218
+ "trial_params": null
1219
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8697dec26118787553757d80401d29ed990405410ca911afb8c282e3da6934e3
3
+ size 4091
checkpoint-300/README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: True
22
+ - load_in_4bit: False
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: fp4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float32
30
+ ### Framework versions
31
+
32
+ - PEFT 0.6.0.dev0
33
+
34
+ - PEFT 0.6.0.dev0
checkpoint-300/adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "bigscience/bloomz-3b",
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": 0.0,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "dense_4h_to_h",
18
+ "dense",
19
+ "dense_h_to_4h",
20
+ "query_key_value"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
checkpoint-300/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0d642c1b07b88983fa6edb59b581bdaecb284512d35327dc4f508fda98e9266
3
+ size 39409357
checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79d5a8610f0d216c22b751d0abc90c2d9a009a5699f6b62939e8a94b427bc748
3
+ size 78844421
checkpoint-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a7af71f21cdf78de367774dcbb1ac4824f28bc05827947c8755c708d7ea724a
3
+ size 14575
checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf234a469946307074a94d2e33bd577537826249e3b92876d08191f0c16910b
3
+ size 627
checkpoint-300/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
checkpoint-300/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d81d9b2c9d9db79ea02c00d4c7e79bb77a718dc57ab01f5f3b1cd6649f08993
3
+ size 14500569
checkpoint-300/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "tokenizer_class": "BloomTokenizer",
9
+ "unk_token": "<unk>"
10
+ }
checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,1819 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 8.571428571428571,
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": 0.03,
13
+ "learning_rate": 0.002998214285714286,
14
+ "loss": 3.0944,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.06,
19
+ "learning_rate": 0.0029964285714285713,
20
+ "loss": 2.8734,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.09,
25
+ "learning_rate": 0.002994642857142857,
26
+ "loss": 8.7265,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.11,
31
+ "learning_rate": 0.002992857142857143,
32
+ "loss": 4.7587,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.14,
37
+ "learning_rate": 0.002991071428571429,
38
+ "loss": 4.3637,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.17,
43
+ "learning_rate": 0.0029892857142857143,
44
+ "loss": 3.315,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.2,
49
+ "learning_rate": 0.0029875,
50
+ "loss": 3.1726,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.23,
55
+ "learning_rate": 0.002985714285714286,
56
+ "loss": 2.9938,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.26,
61
+ "learning_rate": 0.0029839285714285714,
62
+ "loss": 3.0509,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.29,
67
+ "learning_rate": 0.0029821428571428573,
68
+ "loss": 2.93,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.31,
73
+ "learning_rate": 0.002980357142857143,
74
+ "loss": 2.8436,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.34,
79
+ "learning_rate": 0.0029785714285714285,
80
+ "loss": 2.8756,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.37,
85
+ "learning_rate": 0.0029767857142857144,
86
+ "loss": 2.8528,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.4,
91
+ "learning_rate": 0.002975,
92
+ "loss": 2.8405,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.43,
97
+ "learning_rate": 0.002973214285714286,
98
+ "loss": 2.8022,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.46,
103
+ "learning_rate": 0.0029714285714285715,
104
+ "loss": 2.8356,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.49,
109
+ "learning_rate": 0.0029696428571428573,
110
+ "loss": 2.7915,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.51,
115
+ "learning_rate": 0.002967857142857143,
116
+ "loss": 2.7848,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.54,
121
+ "learning_rate": 0.0029660714285714286,
122
+ "loss": 2.6604,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.57,
127
+ "learning_rate": 0.0029642857142857144,
128
+ "loss": 2.736,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.6,
133
+ "learning_rate": 0.0029625000000000003,
134
+ "loss": 2.7747,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.63,
139
+ "learning_rate": 0.0029607142857142857,
140
+ "loss": 2.6958,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.66,
145
+ "learning_rate": 0.0029589285714285716,
146
+ "loss": 2.7309,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.69,
151
+ "learning_rate": 0.0029571428571428574,
152
+ "loss": 2.7294,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.71,
157
+ "learning_rate": 0.0029553571428571433,
158
+ "loss": 2.7493,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.74,
163
+ "learning_rate": 0.0029535714285714287,
164
+ "loss": 2.7351,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.77,
169
+ "learning_rate": 0.002951785714285714,
170
+ "loss": 2.6825,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.8,
175
+ "learning_rate": 0.00295,
176
+ "loss": 2.6658,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.83,
181
+ "learning_rate": 0.0029482142857142858,
182
+ "loss": 2.6127,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.86,
187
+ "learning_rate": 0.002946428571428571,
188
+ "loss": 2.6338,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.89,
193
+ "learning_rate": 0.002944642857142857,
194
+ "loss": 2.7094,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.91,
199
+ "learning_rate": 0.002942857142857143,
200
+ "loss": 2.6943,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.94,
205
+ "learning_rate": 0.0029410714285714283,
206
+ "loss": 2.7222,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.97,
211
+ "learning_rate": 0.002939285714285714,
212
+ "loss": 2.6541,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 1.0,
217
+ "learning_rate": 0.0029375,
218
+ "loss": 2.7111,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 1.03,
223
+ "learning_rate": 0.002935714285714286,
224
+ "loss": 2.5123,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 1.06,
229
+ "learning_rate": 0.0029339285714285713,
230
+ "loss": 2.493,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 1.09,
235
+ "learning_rate": 0.002932142857142857,
236
+ "loss": 2.4434,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 1.11,
241
+ "learning_rate": 0.002930357142857143,
242
+ "loss": 2.4883,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 1.14,
247
+ "learning_rate": 0.0029285714285714284,
248
+ "loss": 2.5004,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 1.17,
253
+ "learning_rate": 0.0029267857142857142,
254
+ "loss": 2.4667,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 1.2,
259
+ "learning_rate": 0.002925,
260
+ "loss": 2.4461,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 1.23,
265
+ "learning_rate": 0.002923214285714286,
266
+ "loss": 2.5361,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 1.26,
271
+ "learning_rate": 0.0029214285714285713,
272
+ "loss": 2.4597,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 1.29,
277
+ "learning_rate": 0.002919642857142857,
278
+ "loss": 2.4006,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 1.31,
283
+ "learning_rate": 0.002917857142857143,
284
+ "loss": 2.5019,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 1.34,
289
+ "learning_rate": 0.0029160714285714285,
290
+ "loss": 2.5209,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 1.37,
295
+ "learning_rate": 0.0029142857142857143,
296
+ "loss": 2.4753,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 1.4,
301
+ "learning_rate": 0.0029125,
302
+ "loss": 2.4104,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 1.43,
307
+ "learning_rate": 0.0029107142857142856,
308
+ "loss": 2.3938,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 1.46,
313
+ "learning_rate": 0.0029089285714285714,
314
+ "loss": 2.4999,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 1.49,
319
+ "learning_rate": 0.0029071428571428573,
320
+ "loss": 2.4292,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 1.51,
325
+ "learning_rate": 0.002905357142857143,
326
+ "loss": 2.4636,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 1.54,
331
+ "learning_rate": 0.0029035714285714285,
332
+ "loss": 2.5163,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 1.57,
337
+ "learning_rate": 0.0029017857142857144,
338
+ "loss": 2.5098,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 1.6,
343
+ "learning_rate": 0.0029000000000000002,
344
+ "loss": 2.447,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 1.63,
349
+ "learning_rate": 0.0028982142857142856,
350
+ "loss": 2.4262,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 1.66,
355
+ "learning_rate": 0.0028964285714285715,
356
+ "loss": 2.5146,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 1.69,
361
+ "learning_rate": 0.0028946428571428573,
362
+ "loss": 2.4225,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 1.71,
367
+ "learning_rate": 0.0028928571428571428,
368
+ "loss": 2.452,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 1.74,
373
+ "learning_rate": 0.0028910714285714286,
374
+ "loss": 2.4449,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 1.77,
379
+ "learning_rate": 0.0028892857142857145,
380
+ "loss": 2.4984,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 1.8,
385
+ "learning_rate": 0.0028875000000000003,
386
+ "loss": 2.4493,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 1.83,
391
+ "learning_rate": 0.0028857142857142857,
392
+ "loss": 2.4187,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 1.86,
397
+ "learning_rate": 0.0028839285714285716,
398
+ "loss": 2.5019,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 1.89,
403
+ "learning_rate": 0.0028821428571428574,
404
+ "loss": 2.4274,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 1.91,
409
+ "learning_rate": 0.002880357142857143,
410
+ "loss": 2.4485,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 1.94,
415
+ "learning_rate": 0.0028785714285714287,
416
+ "loss": 2.5096,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 1.97,
421
+ "learning_rate": 0.0028767857142857145,
422
+ "loss": 2.4862,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 2.0,
427
+ "learning_rate": 0.0028750000000000004,
428
+ "loss": 2.469,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 2.03,
433
+ "learning_rate": 0.002873214285714286,
434
+ "loss": 2.1795,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 2.06,
439
+ "learning_rate": 0.0028714285714285716,
440
+ "loss": 2.1106,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 2.09,
445
+ "learning_rate": 0.0028696428571428575,
446
+ "loss": 2.0896,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 2.11,
451
+ "learning_rate": 0.002867857142857143,
452
+ "loss": 2.2018,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 2.14,
457
+ "learning_rate": 0.0028660714285714288,
458
+ "loss": 2.0803,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 2.17,
463
+ "learning_rate": 0.0028642857142857146,
464
+ "loss": 2.1395,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 2.2,
469
+ "learning_rate": 0.0028625,
470
+ "loss": 2.1019,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 2.23,
475
+ "learning_rate": 0.002860714285714286,
476
+ "loss": 2.1383,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 2.26,
481
+ "learning_rate": 0.0028589285714285713,
482
+ "loss": 2.1109,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 2.29,
487
+ "learning_rate": 0.002857142857142857,
488
+ "loss": 2.0854,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 2.31,
493
+ "learning_rate": 0.0028553571428571426,
494
+ "loss": 2.1667,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 2.34,
499
+ "learning_rate": 0.0028535714285714284,
500
+ "loss": 2.1111,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 2.37,
505
+ "learning_rate": 0.0028517857142857143,
506
+ "loss": 2.1032,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 2.4,
511
+ "learning_rate": 0.00285,
512
+ "loss": 2.1708,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 2.43,
517
+ "learning_rate": 0.0028482142857142855,
518
+ "loss": 2.1118,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 2.46,
523
+ "learning_rate": 0.0028464285714285714,
524
+ "loss": 2.1481,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 2.49,
529
+ "learning_rate": 0.002844642857142857,
530
+ "loss": 2.1538,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 2.51,
535
+ "learning_rate": 0.0028428571428571426,
536
+ "loss": 2.1843,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 2.54,
541
+ "learning_rate": 0.0028410714285714285,
542
+ "loss": 2.1828,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 2.57,
547
+ "learning_rate": 0.0028392857142857143,
548
+ "loss": 2.2151,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 2.6,
553
+ "learning_rate": 0.0028375,
554
+ "loss": 2.1969,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 2.63,
559
+ "learning_rate": 0.0028357142857142856,
560
+ "loss": 2.1509,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 2.66,
565
+ "learning_rate": 0.0028339285714285714,
566
+ "loss": 2.2636,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 2.69,
571
+ "learning_rate": 0.0028321428571428573,
572
+ "loss": 2.2809,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 2.71,
577
+ "learning_rate": 0.0028303571428571427,
578
+ "loss": 2.2044,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 2.74,
583
+ "learning_rate": 0.0028285714285714286,
584
+ "loss": 2.2064,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 2.77,
589
+ "learning_rate": 0.0028267857142857144,
590
+ "loss": 2.2408,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 2.8,
595
+ "learning_rate": 0.002825,
596
+ "loss": 2.2446,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 2.83,
601
+ "learning_rate": 0.0028232142857142857,
602
+ "loss": 2.1965,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 2.86,
607
+ "learning_rate": 0.0028214285714285715,
608
+ "loss": 2.3093,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 2.89,
613
+ "learning_rate": 0.0028196428571428574,
614
+ "loss": 2.2188,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 2.91,
619
+ "learning_rate": 0.0028178571428571428,
620
+ "loss": 2.3098,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 2.94,
625
+ "learning_rate": 0.0028160714285714286,
626
+ "loss": 2.2268,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 2.97,
631
+ "learning_rate": 0.0028142857142857145,
632
+ "loss": 2.2574,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 3.0,
637
+ "learning_rate": 0.0028125,
638
+ "loss": 2.2982,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 3.03,
643
+ "learning_rate": 0.0028107142857142857,
644
+ "loss": 1.879,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 3.06,
649
+ "learning_rate": 0.0028089285714285716,
650
+ "loss": 1.8074,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 3.09,
655
+ "learning_rate": 0.002807142857142857,
656
+ "loss": 1.8174,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 3.11,
661
+ "learning_rate": 0.002805357142857143,
662
+ "loss": 1.784,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 3.14,
667
+ "learning_rate": 0.0028035714285714287,
668
+ "loss": 1.8469,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 3.17,
673
+ "learning_rate": 0.0028017857142857146,
674
+ "loss": 1.8614,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 3.2,
679
+ "learning_rate": 0.0028,
680
+ "loss": 1.8648,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 3.23,
685
+ "learning_rate": 0.002798214285714286,
686
+ "loss": 1.8172,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 3.26,
691
+ "learning_rate": 0.0027964285714285717,
692
+ "loss": 1.8579,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 3.29,
697
+ "learning_rate": 0.002794642857142857,
698
+ "loss": 1.8261,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 3.31,
703
+ "learning_rate": 0.002792857142857143,
704
+ "loss": 1.8993,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 3.34,
709
+ "learning_rate": 0.0027910714285714288,
710
+ "loss": 1.8144,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 3.37,
715
+ "learning_rate": 0.0027892857142857146,
716
+ "loss": 1.8583,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 3.4,
721
+ "learning_rate": 0.0027875,
722
+ "loss": 1.8589,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 3.43,
727
+ "learning_rate": 0.002785714285714286,
728
+ "loss": 1.9069,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 3.46,
733
+ "learning_rate": 0.0027839285714285717,
734
+ "loss": 1.9004,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 3.49,
739
+ "learning_rate": 0.002782142857142857,
740
+ "loss": 1.9378,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 3.51,
745
+ "learning_rate": 0.002780357142857143,
746
+ "loss": 1.9161,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 3.54,
751
+ "learning_rate": 0.002778571428571429,
752
+ "loss": 1.9886,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 3.57,
757
+ "learning_rate": 0.0027767857142857143,
758
+ "loss": 1.8636,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 3.6,
763
+ "learning_rate": 0.002775,
764
+ "loss": 1.9642,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 3.63,
769
+ "learning_rate": 0.002773214285714286,
770
+ "loss": 1.959,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 3.66,
775
+ "learning_rate": 0.002771428571428572,
776
+ "loss": 1.9787,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 3.69,
781
+ "learning_rate": 0.0027696428571428572,
782
+ "loss": 2.0272,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 3.71,
787
+ "learning_rate": 0.002767857142857143,
788
+ "loss": 2.0362,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 3.74,
793
+ "learning_rate": 0.002766071428571429,
794
+ "loss": 2.0369,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 3.77,
799
+ "learning_rate": 0.0027642857142857143,
800
+ "loss": 2.0721,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 3.8,
805
+ "learning_rate": 0.0027624999999999998,
806
+ "loss": 1.9939,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 3.83,
811
+ "learning_rate": 0.0027607142857142856,
812
+ "loss": 2.0403,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 3.86,
817
+ "learning_rate": 0.0027589285714285715,
818
+ "loss": 2.1132,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 3.89,
823
+ "learning_rate": 0.002757142857142857,
824
+ "loss": 2.0741,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 3.91,
829
+ "learning_rate": 0.0027553571428571427,
830
+ "loss": 2.0754,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 3.94,
835
+ "learning_rate": 0.0027535714285714286,
836
+ "loss": 2.1321,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 3.97,
841
+ "learning_rate": 0.0027517857142857144,
842
+ "loss": 2.0665,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 4.0,
847
+ "learning_rate": 0.00275,
848
+ "loss": 2.1085,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 4.03,
853
+ "learning_rate": 0.0027482142857142857,
854
+ "loss": 1.653,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 4.06,
859
+ "learning_rate": 0.0027464285714285715,
860
+ "loss": 1.5934,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 4.09,
865
+ "learning_rate": 0.002744642857142857,
866
+ "loss": 1.6795,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 4.11,
871
+ "learning_rate": 0.002742857142857143,
872
+ "loss": 1.6043,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 4.14,
877
+ "learning_rate": 0.0027410714285714287,
878
+ "loss": 1.586,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 4.17,
883
+ "learning_rate": 0.002739285714285714,
884
+ "loss": 1.6061,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 4.2,
889
+ "learning_rate": 0.0027375,
890
+ "loss": 1.6438,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 4.23,
895
+ "learning_rate": 0.0027357142857142858,
896
+ "loss": 1.6097,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 4.26,
901
+ "learning_rate": 0.0027339285714285716,
902
+ "loss": 1.7163,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 4.29,
907
+ "learning_rate": 0.002732142857142857,
908
+ "loss": 1.6485,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 4.31,
913
+ "learning_rate": 0.002730357142857143,
914
+ "loss": 1.6555,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 4.34,
919
+ "learning_rate": 0.0027285714285714287,
920
+ "loss": 1.689,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 4.37,
925
+ "learning_rate": 0.002726785714285714,
926
+ "loss": 1.7174,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 4.4,
931
+ "learning_rate": 0.002725,
932
+ "loss": 1.7205,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 4.43,
937
+ "learning_rate": 0.002723214285714286,
938
+ "loss": 1.7064,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 4.46,
943
+ "learning_rate": 0.0027214285714285717,
944
+ "loss": 1.7045,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 4.49,
949
+ "learning_rate": 0.002719642857142857,
950
+ "loss": 1.7749,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 4.51,
955
+ "learning_rate": 0.002717857142857143,
956
+ "loss": 1.7826,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 4.54,
961
+ "learning_rate": 0.002716071428571429,
962
+ "loss": 1.7882,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 4.57,
967
+ "learning_rate": 0.0027142857142857142,
968
+ "loss": 1.8073,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 4.6,
973
+ "learning_rate": 0.0027125,
974
+ "loss": 1.7931,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 4.63,
979
+ "learning_rate": 0.002710714285714286,
980
+ "loss": 1.8388,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 4.66,
985
+ "learning_rate": 0.0027089285714285713,
986
+ "loss": 1.8267,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 4.69,
991
+ "learning_rate": 0.002707142857142857,
992
+ "loss": 1.8208,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 4.71,
997
+ "learning_rate": 0.002705357142857143,
998
+ "loss": 1.8404,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 4.74,
1003
+ "learning_rate": 0.002703571428571429,
1004
+ "loss": 1.8375,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 4.77,
1009
+ "learning_rate": 0.0027017857142857143,
1010
+ "loss": 1.9444,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 4.8,
1015
+ "learning_rate": 0.0027,
1016
+ "loss": 1.8325,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 4.83,
1021
+ "learning_rate": 0.002698214285714286,
1022
+ "loss": 1.8705,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 4.86,
1027
+ "learning_rate": 0.0026964285714285714,
1028
+ "loss": 1.9368,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 4.89,
1033
+ "learning_rate": 0.0026946428571428573,
1034
+ "loss": 1.8758,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 4.91,
1039
+ "learning_rate": 0.002692857142857143,
1040
+ "loss": 1.999,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 4.94,
1045
+ "learning_rate": 0.0026910714285714285,
1046
+ "loss": 1.9547,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 4.97,
1051
+ "learning_rate": 0.0026892857142857144,
1052
+ "loss": 1.9332,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 5.0,
1057
+ "learning_rate": 0.0026875000000000002,
1058
+ "loss": 1.9704,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 5.03,
1063
+ "learning_rate": 0.002685714285714286,
1064
+ "loss": 1.4766,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 5.06,
1069
+ "learning_rate": 0.0026839285714285715,
1070
+ "loss": 1.4459,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 5.09,
1075
+ "learning_rate": 0.0026821428571428573,
1076
+ "loss": 1.4451,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 5.11,
1081
+ "learning_rate": 0.002680357142857143,
1082
+ "loss": 1.4761,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 5.14,
1087
+ "learning_rate": 0.0026785714285714286,
1088
+ "loss": 1.5092,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 5.17,
1093
+ "learning_rate": 0.0026767857142857144,
1094
+ "loss": 1.4439,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 5.2,
1099
+ "learning_rate": 0.0026750000000000003,
1100
+ "loss": 1.4539,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 5.23,
1105
+ "learning_rate": 0.002673214285714286,
1106
+ "loss": 1.4804,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 5.26,
1111
+ "learning_rate": 0.002671428571428571,
1112
+ "loss": 1.4958,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 5.29,
1117
+ "learning_rate": 0.002669642857142857,
1118
+ "loss": 1.5054,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 5.31,
1123
+ "learning_rate": 0.002667857142857143,
1124
+ "loss": 1.4673,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 5.34,
1129
+ "learning_rate": 0.0026660714285714287,
1130
+ "loss": 1.5703,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 5.37,
1135
+ "learning_rate": 0.002664285714285714,
1136
+ "loss": 1.5504,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 5.4,
1141
+ "learning_rate": 0.0026625,
1142
+ "loss": 1.6126,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 5.43,
1147
+ "learning_rate": 0.002660714285714286,
1148
+ "loss": 1.5777,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 5.46,
1153
+ "learning_rate": 0.002658928571428571,
1154
+ "loss": 1.5994,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 5.49,
1159
+ "learning_rate": 0.002657142857142857,
1160
+ "loss": 1.5939,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 5.51,
1165
+ "learning_rate": 0.002655357142857143,
1166
+ "loss": 1.6297,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 5.54,
1171
+ "learning_rate": 0.0026535714285714283,
1172
+ "loss": 1.6749,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 5.57,
1177
+ "learning_rate": 0.002651785714285714,
1178
+ "loss": 1.6525,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 5.6,
1183
+ "learning_rate": 0.00265,
1184
+ "loss": 1.657,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 5.63,
1189
+ "learning_rate": 0.002648214285714286,
1190
+ "loss": 1.6818,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 5.66,
1195
+ "learning_rate": 0.0026464285714285713,
1196
+ "loss": 1.6985,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 5.69,
1201
+ "learning_rate": 0.002644642857142857,
1202
+ "loss": 1.7456,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 5.71,
1207
+ "learning_rate": 0.002642857142857143,
1208
+ "loss": 1.678,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 5.74,
1213
+ "learning_rate": 0.0026410714285714284,
1214
+ "loss": 1.7613,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 5.77,
1219
+ "learning_rate": 0.0026392857142857142,
1220
+ "loss": 1.7541,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 5.8,
1225
+ "learning_rate": 0.0026375,
1226
+ "loss": 1.798,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 5.83,
1231
+ "learning_rate": 0.002635714285714286,
1232
+ "loss": 1.821,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 5.86,
1237
+ "learning_rate": 0.0026339285714285714,
1238
+ "loss": 1.8385,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 5.89,
1243
+ "learning_rate": 0.002632142857142857,
1244
+ "loss": 1.8613,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 5.91,
1249
+ "learning_rate": 0.002630357142857143,
1250
+ "loss": 1.902,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 5.94,
1255
+ "learning_rate": 0.0026285714285714285,
1256
+ "loss": 2.0848,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 5.97,
1261
+ "learning_rate": 0.0026267857142857143,
1262
+ "loss": 2.3277,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 6.0,
1267
+ "learning_rate": 0.002625,
1268
+ "loss": 2.8535,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 6.03,
1273
+ "learning_rate": 0.0026232142857142856,
1274
+ "loss": 6.2197,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 6.06,
1279
+ "learning_rate": 0.0026214285714285714,
1280
+ "loss": 10.2288,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 6.09,
1285
+ "learning_rate": 0.0026196428571428573,
1286
+ "loss": 12.5006,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 6.11,
1291
+ "learning_rate": 0.002617857142857143,
1292
+ "loss": 10.5184,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 6.14,
1297
+ "learning_rate": 0.0026160714285714285,
1298
+ "loss": 9.4834,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 6.17,
1303
+ "learning_rate": 0.0026142857142857144,
1304
+ "loss": 16.0513,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 6.2,
1309
+ "learning_rate": 0.0026125000000000002,
1310
+ "loss": 11.0576,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 6.23,
1315
+ "learning_rate": 0.0026107142857142857,
1316
+ "loss": 15.3574,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 6.26,
1321
+ "learning_rate": 0.0026089285714285715,
1322
+ "loss": 15.5239,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 6.29,
1327
+ "learning_rate": 0.0026071428571428574,
1328
+ "loss": 15.3973,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 6.31,
1333
+ "learning_rate": 0.0026053571428571428,
1334
+ "loss": 12.059,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 6.34,
1339
+ "learning_rate": 0.0026035714285714286,
1340
+ "loss": 10.8352,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 6.37,
1345
+ "learning_rate": 0.0026017857142857145,
1346
+ "loss": 10.1507,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 6.4,
1351
+ "learning_rate": 0.0026000000000000003,
1352
+ "loss": 10.651,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 6.43,
1357
+ "learning_rate": 0.0025982142857142857,
1358
+ "loss": 9.8363,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 6.46,
1363
+ "learning_rate": 0.0025964285714285716,
1364
+ "loss": 9.3673,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 6.49,
1369
+ "learning_rate": 0.0025946428571428574,
1370
+ "loss": 9.5433,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 6.51,
1375
+ "learning_rate": 0.002592857142857143,
1376
+ "loss": 9.9206,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 6.54,
1381
+ "learning_rate": 0.0025910714285714287,
1382
+ "loss": 9.5516,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 6.57,
1387
+ "learning_rate": 0.0025892857142857145,
1388
+ "loss": 9.2165,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 6.6,
1393
+ "learning_rate": 0.0025875000000000004,
1394
+ "loss": 9.0825,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 6.63,
1399
+ "learning_rate": 0.002585714285714286,
1400
+ "loss": 8.7437,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 6.66,
1405
+ "learning_rate": 0.0025839285714285717,
1406
+ "loss": 8.6366,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 6.69,
1411
+ "learning_rate": 0.0025821428571428575,
1412
+ "loss": 9.7431,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 6.71,
1417
+ "learning_rate": 0.002580357142857143,
1418
+ "loss": 8.1876,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 6.74,
1423
+ "learning_rate": 0.0025785714285714288,
1424
+ "loss": 8.4559,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 6.77,
1429
+ "learning_rate": 0.002576785714285714,
1430
+ "loss": 8.0092,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 6.8,
1435
+ "learning_rate": 0.002575,
1436
+ "loss": 8.028,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 6.83,
1441
+ "learning_rate": 0.0025732142857142854,
1442
+ "loss": 7.8379,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 6.86,
1447
+ "learning_rate": 0.0025714285714285713,
1448
+ "loss": 7.8127,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 6.89,
1453
+ "learning_rate": 0.002569642857142857,
1454
+ "loss": 7.8252,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 6.91,
1459
+ "learning_rate": 0.002567857142857143,
1460
+ "loss": 7.7094,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 6.94,
1465
+ "learning_rate": 0.0025660714285714284,
1466
+ "loss": 7.7962,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 6.97,
1471
+ "learning_rate": 0.0025642857142857143,
1472
+ "loss": 7.4966,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 7.0,
1477
+ "learning_rate": 0.0025625,
1478
+ "loss": 7.4851,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 7.03,
1483
+ "learning_rate": 0.0025607142857142855,
1484
+ "loss": 7.5188,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 7.06,
1489
+ "learning_rate": 0.0025589285714285714,
1490
+ "loss": 7.7866,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 7.09,
1495
+ "learning_rate": 0.0025571428571428572,
1496
+ "loss": 7.5743,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 7.11,
1501
+ "learning_rate": 0.0025553571428571426,
1502
+ "loss": 7.4608,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 7.14,
1507
+ "learning_rate": 0.0025535714285714285,
1508
+ "loss": 7.4655,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 7.17,
1513
+ "learning_rate": 0.0025517857142857143,
1514
+ "loss": 7.5474,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 7.2,
1519
+ "learning_rate": 0.00255,
1520
+ "loss": 7.6983,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 7.23,
1525
+ "learning_rate": 0.0025482142857142856,
1526
+ "loss": 7.4936,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 7.26,
1531
+ "learning_rate": 0.0025464285714285714,
1532
+ "loss": 7.6966,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 7.29,
1537
+ "learning_rate": 0.0025446428571428573,
1538
+ "loss": 7.4701,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 7.31,
1543
+ "learning_rate": 0.0025428571428571427,
1544
+ "loss": 7.511,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 7.34,
1549
+ "learning_rate": 0.0025410714285714286,
1550
+ "loss": 7.3709,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 7.37,
1555
+ "learning_rate": 0.0025392857142857144,
1556
+ "loss": 7.4582,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 7.4,
1561
+ "learning_rate": 0.0025375,
1562
+ "loss": 7.4263,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 7.43,
1567
+ "learning_rate": 0.0025357142857142857,
1568
+ "loss": 7.3134,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 7.46,
1573
+ "learning_rate": 0.0025339285714285715,
1574
+ "loss": 7.3849,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 7.49,
1579
+ "learning_rate": 0.0025321428571428574,
1580
+ "loss": 7.292,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 7.51,
1585
+ "learning_rate": 0.002530357142857143,
1586
+ "loss": 7.343,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 7.54,
1591
+ "learning_rate": 0.0025285714285714286,
1592
+ "loss": 7.3166,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 7.57,
1597
+ "learning_rate": 0.0025267857142857145,
1598
+ "loss": 7.2676,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 7.6,
1603
+ "learning_rate": 0.002525,
1604
+ "loss": 7.2955,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 7.63,
1609
+ "learning_rate": 0.0025232142857142857,
1610
+ "loss": 7.3386,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 7.66,
1615
+ "learning_rate": 0.0025214285714285716,
1616
+ "loss": 7.2682,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 7.69,
1621
+ "learning_rate": 0.0025196428571428574,
1622
+ "loss": 7.2359,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 7.71,
1627
+ "learning_rate": 0.002517857142857143,
1628
+ "loss": 7.1849,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 7.74,
1633
+ "learning_rate": 0.0025160714285714287,
1634
+ "loss": 7.2421,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 7.77,
1639
+ "learning_rate": 0.0025142857142857146,
1640
+ "loss": 7.2341,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 7.8,
1645
+ "learning_rate": 0.0025125,
1646
+ "loss": 7.2901,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 7.83,
1651
+ "learning_rate": 0.002510714285714286,
1652
+ "loss": 7.1931,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 7.86,
1657
+ "learning_rate": 0.0025089285714285717,
1658
+ "loss": 7.1907,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 7.89,
1663
+ "learning_rate": 0.002507142857142857,
1664
+ "loss": 7.2369,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 7.91,
1669
+ "learning_rate": 0.002505357142857143,
1670
+ "loss": 7.1764,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 7.94,
1675
+ "learning_rate": 0.002503571428571429,
1676
+ "loss": 7.1928,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 7.97,
1681
+ "learning_rate": 0.0025017857142857146,
1682
+ "loss": 7.2114,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 8.0,
1687
+ "learning_rate": 0.0025,
1688
+ "loss": 7.2307,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 8.03,
1693
+ "learning_rate": 0.002498214285714286,
1694
+ "loss": 7.2477,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 8.06,
1699
+ "learning_rate": 0.0024964285714285718,
1700
+ "loss": 7.2069,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 8.09,
1705
+ "learning_rate": 0.002494642857142857,
1706
+ "loss": 7.1484,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 8.11,
1711
+ "learning_rate": 0.002492857142857143,
1712
+ "loss": 7.1076,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 8.14,
1717
+ "learning_rate": 0.002491071428571429,
1718
+ "loss": 7.0819,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 8.17,
1723
+ "learning_rate": 0.0024892857142857143,
1724
+ "loss": 7.0708,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 8.2,
1729
+ "learning_rate": 0.0024875,
1730
+ "loss": 7.0763,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 8.23,
1735
+ "learning_rate": 0.002485714285714286,
1736
+ "loss": 7.0792,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 8.26,
1741
+ "learning_rate": 0.0024839285714285714,
1742
+ "loss": 7.1397,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 8.29,
1747
+ "learning_rate": 0.0024821428571428572,
1748
+ "loss": 7.0893,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 8.31,
1753
+ "learning_rate": 0.0024803571428571427,
1754
+ "loss": 7.1263,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 8.34,
1759
+ "learning_rate": 0.0024785714285714285,
1760
+ "loss": 7.0226,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 8.37,
1765
+ "learning_rate": 0.0024767857142857144,
1766
+ "loss": 7.1017,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 8.4,
1771
+ "learning_rate": 0.0024749999999999998,
1772
+ "loss": 7.0161,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 8.43,
1777
+ "learning_rate": 0.0024732142857142856,
1778
+ "loss": 7.117,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 8.46,
1783
+ "learning_rate": 0.0024714285714285715,
1784
+ "loss": 7.0234,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 8.49,
1789
+ "learning_rate": 0.002469642857142857,
1790
+ "loss": 7.0663,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 8.51,
1795
+ "learning_rate": 0.0024678571428571427,
1796
+ "loss": 7.1604,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 8.54,
1801
+ "learning_rate": 0.0024660714285714286,
1802
+ "loss": 7.0543,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 8.57,
1807
+ "learning_rate": 0.0024642857142857144,
1808
+ "loss": 7.0131,
1809
+ "step": 300
1810
+ }
1811
+ ],
1812
+ "logging_steps": 1,
1813
+ "max_steps": 1680,
1814
+ "num_train_epochs": 48,
1815
+ "save_steps": 100,
1816
+ "total_flos": 1.7318304645777408e+17,
1817
+ "trial_name": null,
1818
+ "trial_params": null
1819
+ }
checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8697dec26118787553757d80401d29ed990405410ca911afb8c282e3da6934e3
3
+ size 4091
checkpoint-400/README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: True
22
+ - load_in_4bit: False
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: fp4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float32
30
+ ### Framework versions
31
+
32
+ - PEFT 0.6.0.dev0
33
+
34
+ - PEFT 0.6.0.dev0
checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "bigscience/bloomz-3b",
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": 0.0,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "dense_4h_to_h",
18
+ "dense",
19
+ "dense_h_to_4h",
20
+ "query_key_value"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
checkpoint-400/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b7c71f5a48f92e6510bcb8484209f58b75e91833c9a1c22c3aac3c29d200327
3
+ size 39409357
checkpoint-400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3319acdf659478ae0888e0b42c35dd789fcd6f3cf90e0350a5faa31dda4e7fbb
3
+ size 78844421
checkpoint-400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:370c3a07f37a8aae6ea141b54ca992b21699546baf7407eb587b6056f787333b
3
+ size 14575
checkpoint-400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f71b8f28a925f4e713f8094eb164fc93a2eae54f8641cb0bc6cba1f8b907c73
3
+ size 627
checkpoint-400/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
checkpoint-400/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d81d9b2c9d9db79ea02c00d4c7e79bb77a718dc57ab01f5f3b1cd6649f08993
3
+ size 14500569
checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "tokenizer_class": "BloomTokenizer",
9
+ "unk_token": "<unk>"
10
+ }
checkpoint-400/trainer_state.json ADDED
@@ -0,0 +1,2419 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 11.428571428571429,
5
+ "eval_steps": 500,
6
+ "global_step": 400,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 0.002998214285714286,
14
+ "loss": 3.0944,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.06,
19
+ "learning_rate": 0.0029964285714285713,
20
+ "loss": 2.8734,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.09,
25
+ "learning_rate": 0.002994642857142857,
26
+ "loss": 8.7265,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.11,
31
+ "learning_rate": 0.002992857142857143,
32
+ "loss": 4.7587,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.14,
37
+ "learning_rate": 0.002991071428571429,
38
+ "loss": 4.3637,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.17,
43
+ "learning_rate": 0.0029892857142857143,
44
+ "loss": 3.315,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.2,
49
+ "learning_rate": 0.0029875,
50
+ "loss": 3.1726,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.23,
55
+ "learning_rate": 0.002985714285714286,
56
+ "loss": 2.9938,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.26,
61
+ "learning_rate": 0.0029839285714285714,
62
+ "loss": 3.0509,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.29,
67
+ "learning_rate": 0.0029821428571428573,
68
+ "loss": 2.93,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.31,
73
+ "learning_rate": 0.002980357142857143,
74
+ "loss": 2.8436,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.34,
79
+ "learning_rate": 0.0029785714285714285,
80
+ "loss": 2.8756,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.37,
85
+ "learning_rate": 0.0029767857142857144,
86
+ "loss": 2.8528,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.4,
91
+ "learning_rate": 0.002975,
92
+ "loss": 2.8405,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.43,
97
+ "learning_rate": 0.002973214285714286,
98
+ "loss": 2.8022,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.46,
103
+ "learning_rate": 0.0029714285714285715,
104
+ "loss": 2.8356,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.49,
109
+ "learning_rate": 0.0029696428571428573,
110
+ "loss": 2.7915,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.51,
115
+ "learning_rate": 0.002967857142857143,
116
+ "loss": 2.7848,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.54,
121
+ "learning_rate": 0.0029660714285714286,
122
+ "loss": 2.6604,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.57,
127
+ "learning_rate": 0.0029642857142857144,
128
+ "loss": 2.736,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.6,
133
+ "learning_rate": 0.0029625000000000003,
134
+ "loss": 2.7747,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.63,
139
+ "learning_rate": 0.0029607142857142857,
140
+ "loss": 2.6958,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.66,
145
+ "learning_rate": 0.0029589285714285716,
146
+ "loss": 2.7309,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.69,
151
+ "learning_rate": 0.0029571428571428574,
152
+ "loss": 2.7294,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.71,
157
+ "learning_rate": 0.0029553571428571433,
158
+ "loss": 2.7493,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.74,
163
+ "learning_rate": 0.0029535714285714287,
164
+ "loss": 2.7351,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.77,
169
+ "learning_rate": 0.002951785714285714,
170
+ "loss": 2.6825,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.8,
175
+ "learning_rate": 0.00295,
176
+ "loss": 2.6658,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.83,
181
+ "learning_rate": 0.0029482142857142858,
182
+ "loss": 2.6127,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.86,
187
+ "learning_rate": 0.002946428571428571,
188
+ "loss": 2.6338,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.89,
193
+ "learning_rate": 0.002944642857142857,
194
+ "loss": 2.7094,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.91,
199
+ "learning_rate": 0.002942857142857143,
200
+ "loss": 2.6943,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.94,
205
+ "learning_rate": 0.0029410714285714283,
206
+ "loss": 2.7222,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.97,
211
+ "learning_rate": 0.002939285714285714,
212
+ "loss": 2.6541,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 1.0,
217
+ "learning_rate": 0.0029375,
218
+ "loss": 2.7111,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 1.03,
223
+ "learning_rate": 0.002935714285714286,
224
+ "loss": 2.5123,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 1.06,
229
+ "learning_rate": 0.0029339285714285713,
230
+ "loss": 2.493,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 1.09,
235
+ "learning_rate": 0.002932142857142857,
236
+ "loss": 2.4434,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 1.11,
241
+ "learning_rate": 0.002930357142857143,
242
+ "loss": 2.4883,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 1.14,
247
+ "learning_rate": 0.0029285714285714284,
248
+ "loss": 2.5004,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 1.17,
253
+ "learning_rate": 0.0029267857142857142,
254
+ "loss": 2.4667,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 1.2,
259
+ "learning_rate": 0.002925,
260
+ "loss": 2.4461,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 1.23,
265
+ "learning_rate": 0.002923214285714286,
266
+ "loss": 2.5361,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 1.26,
271
+ "learning_rate": 0.0029214285714285713,
272
+ "loss": 2.4597,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 1.29,
277
+ "learning_rate": 0.002919642857142857,
278
+ "loss": 2.4006,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 1.31,
283
+ "learning_rate": 0.002917857142857143,
284
+ "loss": 2.5019,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 1.34,
289
+ "learning_rate": 0.0029160714285714285,
290
+ "loss": 2.5209,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 1.37,
295
+ "learning_rate": 0.0029142857142857143,
296
+ "loss": 2.4753,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 1.4,
301
+ "learning_rate": 0.0029125,
302
+ "loss": 2.4104,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 1.43,
307
+ "learning_rate": 0.0029107142857142856,
308
+ "loss": 2.3938,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 1.46,
313
+ "learning_rate": 0.0029089285714285714,
314
+ "loss": 2.4999,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 1.49,
319
+ "learning_rate": 0.0029071428571428573,
320
+ "loss": 2.4292,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 1.51,
325
+ "learning_rate": 0.002905357142857143,
326
+ "loss": 2.4636,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 1.54,
331
+ "learning_rate": 0.0029035714285714285,
332
+ "loss": 2.5163,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 1.57,
337
+ "learning_rate": 0.0029017857142857144,
338
+ "loss": 2.5098,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 1.6,
343
+ "learning_rate": 0.0029000000000000002,
344
+ "loss": 2.447,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 1.63,
349
+ "learning_rate": 0.0028982142857142856,
350
+ "loss": 2.4262,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 1.66,
355
+ "learning_rate": 0.0028964285714285715,
356
+ "loss": 2.5146,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 1.69,
361
+ "learning_rate": 0.0028946428571428573,
362
+ "loss": 2.4225,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 1.71,
367
+ "learning_rate": 0.0028928571428571428,
368
+ "loss": 2.452,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 1.74,
373
+ "learning_rate": 0.0028910714285714286,
374
+ "loss": 2.4449,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 1.77,
379
+ "learning_rate": 0.0028892857142857145,
380
+ "loss": 2.4984,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 1.8,
385
+ "learning_rate": 0.0028875000000000003,
386
+ "loss": 2.4493,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 1.83,
391
+ "learning_rate": 0.0028857142857142857,
392
+ "loss": 2.4187,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 1.86,
397
+ "learning_rate": 0.0028839285714285716,
398
+ "loss": 2.5019,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 1.89,
403
+ "learning_rate": 0.0028821428571428574,
404
+ "loss": 2.4274,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 1.91,
409
+ "learning_rate": 0.002880357142857143,
410
+ "loss": 2.4485,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 1.94,
415
+ "learning_rate": 0.0028785714285714287,
416
+ "loss": 2.5096,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 1.97,
421
+ "learning_rate": 0.0028767857142857145,
422
+ "loss": 2.4862,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 2.0,
427
+ "learning_rate": 0.0028750000000000004,
428
+ "loss": 2.469,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 2.03,
433
+ "learning_rate": 0.002873214285714286,
434
+ "loss": 2.1795,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 2.06,
439
+ "learning_rate": 0.0028714285714285716,
440
+ "loss": 2.1106,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 2.09,
445
+ "learning_rate": 0.0028696428571428575,
446
+ "loss": 2.0896,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 2.11,
451
+ "learning_rate": 0.002867857142857143,
452
+ "loss": 2.2018,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 2.14,
457
+ "learning_rate": 0.0028660714285714288,
458
+ "loss": 2.0803,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 2.17,
463
+ "learning_rate": 0.0028642857142857146,
464
+ "loss": 2.1395,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 2.2,
469
+ "learning_rate": 0.0028625,
470
+ "loss": 2.1019,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 2.23,
475
+ "learning_rate": 0.002860714285714286,
476
+ "loss": 2.1383,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 2.26,
481
+ "learning_rate": 0.0028589285714285713,
482
+ "loss": 2.1109,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 2.29,
487
+ "learning_rate": 0.002857142857142857,
488
+ "loss": 2.0854,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 2.31,
493
+ "learning_rate": 0.0028553571428571426,
494
+ "loss": 2.1667,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 2.34,
499
+ "learning_rate": 0.0028535714285714284,
500
+ "loss": 2.1111,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 2.37,
505
+ "learning_rate": 0.0028517857142857143,
506
+ "loss": 2.1032,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 2.4,
511
+ "learning_rate": 0.00285,
512
+ "loss": 2.1708,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 2.43,
517
+ "learning_rate": 0.0028482142857142855,
518
+ "loss": 2.1118,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 2.46,
523
+ "learning_rate": 0.0028464285714285714,
524
+ "loss": 2.1481,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 2.49,
529
+ "learning_rate": 0.002844642857142857,
530
+ "loss": 2.1538,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 2.51,
535
+ "learning_rate": 0.0028428571428571426,
536
+ "loss": 2.1843,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 2.54,
541
+ "learning_rate": 0.0028410714285714285,
542
+ "loss": 2.1828,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 2.57,
547
+ "learning_rate": 0.0028392857142857143,
548
+ "loss": 2.2151,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 2.6,
553
+ "learning_rate": 0.0028375,
554
+ "loss": 2.1969,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 2.63,
559
+ "learning_rate": 0.0028357142857142856,
560
+ "loss": 2.1509,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 2.66,
565
+ "learning_rate": 0.0028339285714285714,
566
+ "loss": 2.2636,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 2.69,
571
+ "learning_rate": 0.0028321428571428573,
572
+ "loss": 2.2809,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 2.71,
577
+ "learning_rate": 0.0028303571428571427,
578
+ "loss": 2.2044,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 2.74,
583
+ "learning_rate": 0.0028285714285714286,
584
+ "loss": 2.2064,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 2.77,
589
+ "learning_rate": 0.0028267857142857144,
590
+ "loss": 2.2408,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 2.8,
595
+ "learning_rate": 0.002825,
596
+ "loss": 2.2446,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 2.83,
601
+ "learning_rate": 0.0028232142857142857,
602
+ "loss": 2.1965,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 2.86,
607
+ "learning_rate": 0.0028214285714285715,
608
+ "loss": 2.3093,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 2.89,
613
+ "learning_rate": 0.0028196428571428574,
614
+ "loss": 2.2188,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 2.91,
619
+ "learning_rate": 0.0028178571428571428,
620
+ "loss": 2.3098,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 2.94,
625
+ "learning_rate": 0.0028160714285714286,
626
+ "loss": 2.2268,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 2.97,
631
+ "learning_rate": 0.0028142857142857145,
632
+ "loss": 2.2574,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 3.0,
637
+ "learning_rate": 0.0028125,
638
+ "loss": 2.2982,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 3.03,
643
+ "learning_rate": 0.0028107142857142857,
644
+ "loss": 1.879,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 3.06,
649
+ "learning_rate": 0.0028089285714285716,
650
+ "loss": 1.8074,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 3.09,
655
+ "learning_rate": 0.002807142857142857,
656
+ "loss": 1.8174,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 3.11,
661
+ "learning_rate": 0.002805357142857143,
662
+ "loss": 1.784,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 3.14,
667
+ "learning_rate": 0.0028035714285714287,
668
+ "loss": 1.8469,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 3.17,
673
+ "learning_rate": 0.0028017857142857146,
674
+ "loss": 1.8614,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 3.2,
679
+ "learning_rate": 0.0028,
680
+ "loss": 1.8648,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 3.23,
685
+ "learning_rate": 0.002798214285714286,
686
+ "loss": 1.8172,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 3.26,
691
+ "learning_rate": 0.0027964285714285717,
692
+ "loss": 1.8579,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 3.29,
697
+ "learning_rate": 0.002794642857142857,
698
+ "loss": 1.8261,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 3.31,
703
+ "learning_rate": 0.002792857142857143,
704
+ "loss": 1.8993,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 3.34,
709
+ "learning_rate": 0.0027910714285714288,
710
+ "loss": 1.8144,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 3.37,
715
+ "learning_rate": 0.0027892857142857146,
716
+ "loss": 1.8583,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 3.4,
721
+ "learning_rate": 0.0027875,
722
+ "loss": 1.8589,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 3.43,
727
+ "learning_rate": 0.002785714285714286,
728
+ "loss": 1.9069,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 3.46,
733
+ "learning_rate": 0.0027839285714285717,
734
+ "loss": 1.9004,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 3.49,
739
+ "learning_rate": 0.002782142857142857,
740
+ "loss": 1.9378,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 3.51,
745
+ "learning_rate": 0.002780357142857143,
746
+ "loss": 1.9161,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 3.54,
751
+ "learning_rate": 0.002778571428571429,
752
+ "loss": 1.9886,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 3.57,
757
+ "learning_rate": 0.0027767857142857143,
758
+ "loss": 1.8636,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 3.6,
763
+ "learning_rate": 0.002775,
764
+ "loss": 1.9642,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 3.63,
769
+ "learning_rate": 0.002773214285714286,
770
+ "loss": 1.959,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 3.66,
775
+ "learning_rate": 0.002771428571428572,
776
+ "loss": 1.9787,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 3.69,
781
+ "learning_rate": 0.0027696428571428572,
782
+ "loss": 2.0272,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 3.71,
787
+ "learning_rate": 0.002767857142857143,
788
+ "loss": 2.0362,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 3.74,
793
+ "learning_rate": 0.002766071428571429,
794
+ "loss": 2.0369,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 3.77,
799
+ "learning_rate": 0.0027642857142857143,
800
+ "loss": 2.0721,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 3.8,
805
+ "learning_rate": 0.0027624999999999998,
806
+ "loss": 1.9939,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 3.83,
811
+ "learning_rate": 0.0027607142857142856,
812
+ "loss": 2.0403,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 3.86,
817
+ "learning_rate": 0.0027589285714285715,
818
+ "loss": 2.1132,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 3.89,
823
+ "learning_rate": 0.002757142857142857,
824
+ "loss": 2.0741,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 3.91,
829
+ "learning_rate": 0.0027553571428571427,
830
+ "loss": 2.0754,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 3.94,
835
+ "learning_rate": 0.0027535714285714286,
836
+ "loss": 2.1321,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 3.97,
841
+ "learning_rate": 0.0027517857142857144,
842
+ "loss": 2.0665,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 4.0,
847
+ "learning_rate": 0.00275,
848
+ "loss": 2.1085,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 4.03,
853
+ "learning_rate": 0.0027482142857142857,
854
+ "loss": 1.653,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 4.06,
859
+ "learning_rate": 0.0027464285714285715,
860
+ "loss": 1.5934,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 4.09,
865
+ "learning_rate": 0.002744642857142857,
866
+ "loss": 1.6795,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 4.11,
871
+ "learning_rate": 0.002742857142857143,
872
+ "loss": 1.6043,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 4.14,
877
+ "learning_rate": 0.0027410714285714287,
878
+ "loss": 1.586,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 4.17,
883
+ "learning_rate": 0.002739285714285714,
884
+ "loss": 1.6061,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 4.2,
889
+ "learning_rate": 0.0027375,
890
+ "loss": 1.6438,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 4.23,
895
+ "learning_rate": 0.0027357142857142858,
896
+ "loss": 1.6097,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 4.26,
901
+ "learning_rate": 0.0027339285714285716,
902
+ "loss": 1.7163,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 4.29,
907
+ "learning_rate": 0.002732142857142857,
908
+ "loss": 1.6485,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 4.31,
913
+ "learning_rate": 0.002730357142857143,
914
+ "loss": 1.6555,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 4.34,
919
+ "learning_rate": 0.0027285714285714287,
920
+ "loss": 1.689,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 4.37,
925
+ "learning_rate": 0.002726785714285714,
926
+ "loss": 1.7174,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 4.4,
931
+ "learning_rate": 0.002725,
932
+ "loss": 1.7205,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 4.43,
937
+ "learning_rate": 0.002723214285714286,
938
+ "loss": 1.7064,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 4.46,
943
+ "learning_rate": 0.0027214285714285717,
944
+ "loss": 1.7045,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 4.49,
949
+ "learning_rate": 0.002719642857142857,
950
+ "loss": 1.7749,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 4.51,
955
+ "learning_rate": 0.002717857142857143,
956
+ "loss": 1.7826,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 4.54,
961
+ "learning_rate": 0.002716071428571429,
962
+ "loss": 1.7882,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 4.57,
967
+ "learning_rate": 0.0027142857142857142,
968
+ "loss": 1.8073,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 4.6,
973
+ "learning_rate": 0.0027125,
974
+ "loss": 1.7931,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 4.63,
979
+ "learning_rate": 0.002710714285714286,
980
+ "loss": 1.8388,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 4.66,
985
+ "learning_rate": 0.0027089285714285713,
986
+ "loss": 1.8267,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 4.69,
991
+ "learning_rate": 0.002707142857142857,
992
+ "loss": 1.8208,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 4.71,
997
+ "learning_rate": 0.002705357142857143,
998
+ "loss": 1.8404,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 4.74,
1003
+ "learning_rate": 0.002703571428571429,
1004
+ "loss": 1.8375,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 4.77,
1009
+ "learning_rate": 0.0027017857142857143,
1010
+ "loss": 1.9444,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 4.8,
1015
+ "learning_rate": 0.0027,
1016
+ "loss": 1.8325,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 4.83,
1021
+ "learning_rate": 0.002698214285714286,
1022
+ "loss": 1.8705,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 4.86,
1027
+ "learning_rate": 0.0026964285714285714,
1028
+ "loss": 1.9368,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 4.89,
1033
+ "learning_rate": 0.0026946428571428573,
1034
+ "loss": 1.8758,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 4.91,
1039
+ "learning_rate": 0.002692857142857143,
1040
+ "loss": 1.999,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 4.94,
1045
+ "learning_rate": 0.0026910714285714285,
1046
+ "loss": 1.9547,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 4.97,
1051
+ "learning_rate": 0.0026892857142857144,
1052
+ "loss": 1.9332,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 5.0,
1057
+ "learning_rate": 0.0026875000000000002,
1058
+ "loss": 1.9704,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 5.03,
1063
+ "learning_rate": 0.002685714285714286,
1064
+ "loss": 1.4766,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 5.06,
1069
+ "learning_rate": 0.0026839285714285715,
1070
+ "loss": 1.4459,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 5.09,
1075
+ "learning_rate": 0.0026821428571428573,
1076
+ "loss": 1.4451,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 5.11,
1081
+ "learning_rate": 0.002680357142857143,
1082
+ "loss": 1.4761,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 5.14,
1087
+ "learning_rate": 0.0026785714285714286,
1088
+ "loss": 1.5092,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 5.17,
1093
+ "learning_rate": 0.0026767857142857144,
1094
+ "loss": 1.4439,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 5.2,
1099
+ "learning_rate": 0.0026750000000000003,
1100
+ "loss": 1.4539,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 5.23,
1105
+ "learning_rate": 0.002673214285714286,
1106
+ "loss": 1.4804,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 5.26,
1111
+ "learning_rate": 0.002671428571428571,
1112
+ "loss": 1.4958,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 5.29,
1117
+ "learning_rate": 0.002669642857142857,
1118
+ "loss": 1.5054,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 5.31,
1123
+ "learning_rate": 0.002667857142857143,
1124
+ "loss": 1.4673,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 5.34,
1129
+ "learning_rate": 0.0026660714285714287,
1130
+ "loss": 1.5703,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 5.37,
1135
+ "learning_rate": 0.002664285714285714,
1136
+ "loss": 1.5504,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 5.4,
1141
+ "learning_rate": 0.0026625,
1142
+ "loss": 1.6126,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 5.43,
1147
+ "learning_rate": 0.002660714285714286,
1148
+ "loss": 1.5777,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 5.46,
1153
+ "learning_rate": 0.002658928571428571,
1154
+ "loss": 1.5994,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 5.49,
1159
+ "learning_rate": 0.002657142857142857,
1160
+ "loss": 1.5939,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 5.51,
1165
+ "learning_rate": 0.002655357142857143,
1166
+ "loss": 1.6297,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 5.54,
1171
+ "learning_rate": 0.0026535714285714283,
1172
+ "loss": 1.6749,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 5.57,
1177
+ "learning_rate": 0.002651785714285714,
1178
+ "loss": 1.6525,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 5.6,
1183
+ "learning_rate": 0.00265,
1184
+ "loss": 1.657,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 5.63,
1189
+ "learning_rate": 0.002648214285714286,
1190
+ "loss": 1.6818,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 5.66,
1195
+ "learning_rate": 0.0026464285714285713,
1196
+ "loss": 1.6985,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 5.69,
1201
+ "learning_rate": 0.002644642857142857,
1202
+ "loss": 1.7456,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 5.71,
1207
+ "learning_rate": 0.002642857142857143,
1208
+ "loss": 1.678,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 5.74,
1213
+ "learning_rate": 0.0026410714285714284,
1214
+ "loss": 1.7613,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 5.77,
1219
+ "learning_rate": 0.0026392857142857142,
1220
+ "loss": 1.7541,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 5.8,
1225
+ "learning_rate": 0.0026375,
1226
+ "loss": 1.798,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 5.83,
1231
+ "learning_rate": 0.002635714285714286,
1232
+ "loss": 1.821,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 5.86,
1237
+ "learning_rate": 0.0026339285714285714,
1238
+ "loss": 1.8385,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 5.89,
1243
+ "learning_rate": 0.002632142857142857,
1244
+ "loss": 1.8613,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 5.91,
1249
+ "learning_rate": 0.002630357142857143,
1250
+ "loss": 1.902,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 5.94,
1255
+ "learning_rate": 0.0026285714285714285,
1256
+ "loss": 2.0848,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 5.97,
1261
+ "learning_rate": 0.0026267857142857143,
1262
+ "loss": 2.3277,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 6.0,
1267
+ "learning_rate": 0.002625,
1268
+ "loss": 2.8535,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 6.03,
1273
+ "learning_rate": 0.0026232142857142856,
1274
+ "loss": 6.2197,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 6.06,
1279
+ "learning_rate": 0.0026214285714285714,
1280
+ "loss": 10.2288,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 6.09,
1285
+ "learning_rate": 0.0026196428571428573,
1286
+ "loss": 12.5006,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 6.11,
1291
+ "learning_rate": 0.002617857142857143,
1292
+ "loss": 10.5184,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 6.14,
1297
+ "learning_rate": 0.0026160714285714285,
1298
+ "loss": 9.4834,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 6.17,
1303
+ "learning_rate": 0.0026142857142857144,
1304
+ "loss": 16.0513,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 6.2,
1309
+ "learning_rate": 0.0026125000000000002,
1310
+ "loss": 11.0576,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 6.23,
1315
+ "learning_rate": 0.0026107142857142857,
1316
+ "loss": 15.3574,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 6.26,
1321
+ "learning_rate": 0.0026089285714285715,
1322
+ "loss": 15.5239,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 6.29,
1327
+ "learning_rate": 0.0026071428571428574,
1328
+ "loss": 15.3973,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 6.31,
1333
+ "learning_rate": 0.0026053571428571428,
1334
+ "loss": 12.059,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 6.34,
1339
+ "learning_rate": 0.0026035714285714286,
1340
+ "loss": 10.8352,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 6.37,
1345
+ "learning_rate": 0.0026017857142857145,
1346
+ "loss": 10.1507,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 6.4,
1351
+ "learning_rate": 0.0026000000000000003,
1352
+ "loss": 10.651,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 6.43,
1357
+ "learning_rate": 0.0025982142857142857,
1358
+ "loss": 9.8363,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 6.46,
1363
+ "learning_rate": 0.0025964285714285716,
1364
+ "loss": 9.3673,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 6.49,
1369
+ "learning_rate": 0.0025946428571428574,
1370
+ "loss": 9.5433,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 6.51,
1375
+ "learning_rate": 0.002592857142857143,
1376
+ "loss": 9.9206,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 6.54,
1381
+ "learning_rate": 0.0025910714285714287,
1382
+ "loss": 9.5516,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 6.57,
1387
+ "learning_rate": 0.0025892857142857145,
1388
+ "loss": 9.2165,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 6.6,
1393
+ "learning_rate": 0.0025875000000000004,
1394
+ "loss": 9.0825,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 6.63,
1399
+ "learning_rate": 0.002585714285714286,
1400
+ "loss": 8.7437,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 6.66,
1405
+ "learning_rate": 0.0025839285714285717,
1406
+ "loss": 8.6366,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 6.69,
1411
+ "learning_rate": 0.0025821428571428575,
1412
+ "loss": 9.7431,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 6.71,
1417
+ "learning_rate": 0.002580357142857143,
1418
+ "loss": 8.1876,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 6.74,
1423
+ "learning_rate": 0.0025785714285714288,
1424
+ "loss": 8.4559,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 6.77,
1429
+ "learning_rate": 0.002576785714285714,
1430
+ "loss": 8.0092,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 6.8,
1435
+ "learning_rate": 0.002575,
1436
+ "loss": 8.028,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 6.83,
1441
+ "learning_rate": 0.0025732142857142854,
1442
+ "loss": 7.8379,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 6.86,
1447
+ "learning_rate": 0.0025714285714285713,
1448
+ "loss": 7.8127,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 6.89,
1453
+ "learning_rate": 0.002569642857142857,
1454
+ "loss": 7.8252,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 6.91,
1459
+ "learning_rate": 0.002567857142857143,
1460
+ "loss": 7.7094,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 6.94,
1465
+ "learning_rate": 0.0025660714285714284,
1466
+ "loss": 7.7962,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 6.97,
1471
+ "learning_rate": 0.0025642857142857143,
1472
+ "loss": 7.4966,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 7.0,
1477
+ "learning_rate": 0.0025625,
1478
+ "loss": 7.4851,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 7.03,
1483
+ "learning_rate": 0.0025607142857142855,
1484
+ "loss": 7.5188,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 7.06,
1489
+ "learning_rate": 0.0025589285714285714,
1490
+ "loss": 7.7866,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 7.09,
1495
+ "learning_rate": 0.0025571428571428572,
1496
+ "loss": 7.5743,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 7.11,
1501
+ "learning_rate": 0.0025553571428571426,
1502
+ "loss": 7.4608,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 7.14,
1507
+ "learning_rate": 0.0025535714285714285,
1508
+ "loss": 7.4655,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 7.17,
1513
+ "learning_rate": 0.0025517857142857143,
1514
+ "loss": 7.5474,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 7.2,
1519
+ "learning_rate": 0.00255,
1520
+ "loss": 7.6983,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 7.23,
1525
+ "learning_rate": 0.0025482142857142856,
1526
+ "loss": 7.4936,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 7.26,
1531
+ "learning_rate": 0.0025464285714285714,
1532
+ "loss": 7.6966,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 7.29,
1537
+ "learning_rate": 0.0025446428571428573,
1538
+ "loss": 7.4701,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 7.31,
1543
+ "learning_rate": 0.0025428571428571427,
1544
+ "loss": 7.511,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 7.34,
1549
+ "learning_rate": 0.0025410714285714286,
1550
+ "loss": 7.3709,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 7.37,
1555
+ "learning_rate": 0.0025392857142857144,
1556
+ "loss": 7.4582,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 7.4,
1561
+ "learning_rate": 0.0025375,
1562
+ "loss": 7.4263,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 7.43,
1567
+ "learning_rate": 0.0025357142857142857,
1568
+ "loss": 7.3134,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 7.46,
1573
+ "learning_rate": 0.0025339285714285715,
1574
+ "loss": 7.3849,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 7.49,
1579
+ "learning_rate": 0.0025321428571428574,
1580
+ "loss": 7.292,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 7.51,
1585
+ "learning_rate": 0.002530357142857143,
1586
+ "loss": 7.343,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 7.54,
1591
+ "learning_rate": 0.0025285714285714286,
1592
+ "loss": 7.3166,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 7.57,
1597
+ "learning_rate": 0.0025267857142857145,
1598
+ "loss": 7.2676,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 7.6,
1603
+ "learning_rate": 0.002525,
1604
+ "loss": 7.2955,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 7.63,
1609
+ "learning_rate": 0.0025232142857142857,
1610
+ "loss": 7.3386,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 7.66,
1615
+ "learning_rate": 0.0025214285714285716,
1616
+ "loss": 7.2682,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 7.69,
1621
+ "learning_rate": 0.0025196428571428574,
1622
+ "loss": 7.2359,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 7.71,
1627
+ "learning_rate": 0.002517857142857143,
1628
+ "loss": 7.1849,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 7.74,
1633
+ "learning_rate": 0.0025160714285714287,
1634
+ "loss": 7.2421,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 7.77,
1639
+ "learning_rate": 0.0025142857142857146,
1640
+ "loss": 7.2341,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 7.8,
1645
+ "learning_rate": 0.0025125,
1646
+ "loss": 7.2901,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 7.83,
1651
+ "learning_rate": 0.002510714285714286,
1652
+ "loss": 7.1931,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 7.86,
1657
+ "learning_rate": 0.0025089285714285717,
1658
+ "loss": 7.1907,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 7.89,
1663
+ "learning_rate": 0.002507142857142857,
1664
+ "loss": 7.2369,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 7.91,
1669
+ "learning_rate": 0.002505357142857143,
1670
+ "loss": 7.1764,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 7.94,
1675
+ "learning_rate": 0.002503571428571429,
1676
+ "loss": 7.1928,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 7.97,
1681
+ "learning_rate": 0.0025017857142857146,
1682
+ "loss": 7.2114,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 8.0,
1687
+ "learning_rate": 0.0025,
1688
+ "loss": 7.2307,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 8.03,
1693
+ "learning_rate": 0.002498214285714286,
1694
+ "loss": 7.2477,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 8.06,
1699
+ "learning_rate": 0.0024964285714285718,
1700
+ "loss": 7.2069,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 8.09,
1705
+ "learning_rate": 0.002494642857142857,
1706
+ "loss": 7.1484,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 8.11,
1711
+ "learning_rate": 0.002492857142857143,
1712
+ "loss": 7.1076,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 8.14,
1717
+ "learning_rate": 0.002491071428571429,
1718
+ "loss": 7.0819,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 8.17,
1723
+ "learning_rate": 0.0024892857142857143,
1724
+ "loss": 7.0708,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 8.2,
1729
+ "learning_rate": 0.0024875,
1730
+ "loss": 7.0763,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 8.23,
1735
+ "learning_rate": 0.002485714285714286,
1736
+ "loss": 7.0792,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 8.26,
1741
+ "learning_rate": 0.0024839285714285714,
1742
+ "loss": 7.1397,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 8.29,
1747
+ "learning_rate": 0.0024821428571428572,
1748
+ "loss": 7.0893,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 8.31,
1753
+ "learning_rate": 0.0024803571428571427,
1754
+ "loss": 7.1263,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 8.34,
1759
+ "learning_rate": 0.0024785714285714285,
1760
+ "loss": 7.0226,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 8.37,
1765
+ "learning_rate": 0.0024767857142857144,
1766
+ "loss": 7.1017,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 8.4,
1771
+ "learning_rate": 0.0024749999999999998,
1772
+ "loss": 7.0161,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 8.43,
1777
+ "learning_rate": 0.0024732142857142856,
1778
+ "loss": 7.117,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 8.46,
1783
+ "learning_rate": 0.0024714285714285715,
1784
+ "loss": 7.0234,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 8.49,
1789
+ "learning_rate": 0.002469642857142857,
1790
+ "loss": 7.0663,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 8.51,
1795
+ "learning_rate": 0.0024678571428571427,
1796
+ "loss": 7.1604,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 8.54,
1801
+ "learning_rate": 0.0024660714285714286,
1802
+ "loss": 7.0543,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 8.57,
1807
+ "learning_rate": 0.0024642857142857144,
1808
+ "loss": 7.0131,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 8.6,
1813
+ "learning_rate": 0.0024625,
1814
+ "loss": 7.0294,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 8.63,
1819
+ "learning_rate": 0.0024607142857142857,
1820
+ "loss": 7.0273,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 8.66,
1825
+ "learning_rate": 0.0024589285714285715,
1826
+ "loss": 7.0074,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 8.69,
1831
+ "learning_rate": 0.002457142857142857,
1832
+ "loss": 6.9747,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 8.71,
1837
+ "learning_rate": 0.002455357142857143,
1838
+ "loss": 7.0617,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 8.74,
1843
+ "learning_rate": 0.0024535714285714287,
1844
+ "loss": 7.0907,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 8.77,
1849
+ "learning_rate": 0.002451785714285714,
1850
+ "loss": 7.0037,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 8.8,
1855
+ "learning_rate": 0.00245,
1856
+ "loss": 6.969,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 8.83,
1861
+ "learning_rate": 0.0024482142857142858,
1862
+ "loss": 7.0575,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 8.86,
1867
+ "learning_rate": 0.0024464285714285716,
1868
+ "loss": 6.9494,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 8.89,
1873
+ "learning_rate": 0.002444642857142857,
1874
+ "loss": 6.969,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 8.91,
1879
+ "learning_rate": 0.002442857142857143,
1880
+ "loss": 6.8827,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 8.94,
1885
+ "learning_rate": 0.0024410714285714287,
1886
+ "loss": 6.9058,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 8.97,
1891
+ "learning_rate": 0.002439285714285714,
1892
+ "loss": 6.8808,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 9.0,
1897
+ "learning_rate": 0.0024375,
1898
+ "loss": 6.9516,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 9.03,
1903
+ "learning_rate": 0.002435714285714286,
1904
+ "loss": 6.9132,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 9.06,
1909
+ "learning_rate": 0.0024339285714285717,
1910
+ "loss": 6.9058,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 9.09,
1915
+ "learning_rate": 0.002432142857142857,
1916
+ "loss": 6.9332,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 9.11,
1921
+ "learning_rate": 0.002430357142857143,
1922
+ "loss": 6.9757,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 9.14,
1927
+ "learning_rate": 0.002428571428571429,
1928
+ "loss": 6.8261,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 9.17,
1933
+ "learning_rate": 0.0024267857142857142,
1934
+ "loss": 6.8571,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 9.2,
1939
+ "learning_rate": 0.002425,
1940
+ "loss": 6.8435,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 9.23,
1945
+ "learning_rate": 0.002423214285714286,
1946
+ "loss": 6.9033,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 9.26,
1951
+ "learning_rate": 0.0024214285714285713,
1952
+ "loss": 6.8042,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 9.29,
1957
+ "learning_rate": 0.002419642857142857,
1958
+ "loss": 6.8732,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 9.31,
1963
+ "learning_rate": 0.002417857142857143,
1964
+ "loss": 6.752,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 9.34,
1969
+ "learning_rate": 0.002416071428571429,
1970
+ "loss": 6.8016,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 9.37,
1975
+ "learning_rate": 0.0024142857142857143,
1976
+ "loss": 6.8879,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 9.4,
1981
+ "learning_rate": 0.0024125,
1982
+ "loss": 6.7643,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 9.43,
1987
+ "learning_rate": 0.002410714285714286,
1988
+ "loss": 6.7084,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 9.46,
1993
+ "learning_rate": 0.0024089285714285714,
1994
+ "loss": 6.8049,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 9.49,
1999
+ "learning_rate": 0.0024071428571428573,
2000
+ "loss": 6.7925,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 9.51,
2005
+ "learning_rate": 0.002405357142857143,
2006
+ "loss": 6.7289,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 9.54,
2011
+ "learning_rate": 0.0024035714285714285,
2012
+ "loss": 6.7439,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 9.57,
2017
+ "learning_rate": 0.0024017857142857144,
2018
+ "loss": 6.7119,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 9.6,
2023
+ "learning_rate": 0.0024000000000000002,
2024
+ "loss": 6.7251,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 9.63,
2029
+ "learning_rate": 0.002398214285714286,
2030
+ "loss": 6.6659,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 9.66,
2035
+ "learning_rate": 0.0023964285714285715,
2036
+ "loss": 6.7422,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 9.69,
2041
+ "learning_rate": 0.0023946428571428573,
2042
+ "loss": 6.7852,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 9.71,
2047
+ "learning_rate": 0.002392857142857143,
2048
+ "loss": 6.6828,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 9.74,
2053
+ "learning_rate": 0.0023910714285714286,
2054
+ "loss": 6.686,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 9.77,
2059
+ "learning_rate": 0.002389285714285714,
2060
+ "loss": 6.7326,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 9.8,
2065
+ "learning_rate": 0.0023875,
2066
+ "loss": 6.5601,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 9.83,
2071
+ "learning_rate": 0.0023857142857142857,
2072
+ "loss": 6.6646,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 9.86,
2077
+ "learning_rate": 0.002383928571428571,
2078
+ "loss": 6.5673,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 9.89,
2083
+ "learning_rate": 0.002382142857142857,
2084
+ "loss": 6.6227,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 9.91,
2089
+ "learning_rate": 0.002380357142857143,
2090
+ "loss": 6.5526,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 9.94,
2095
+ "learning_rate": 0.0023785714285714287,
2096
+ "loss": 6.6842,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 9.97,
2101
+ "learning_rate": 0.002376785714285714,
2102
+ "loss": 6.6211,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 10.0,
2107
+ "learning_rate": 0.002375,
2108
+ "loss": 6.6952,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 10.03,
2113
+ "learning_rate": 0.002373214285714286,
2114
+ "loss": 6.5324,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 10.06,
2119
+ "learning_rate": 0.002371428571428571,
2120
+ "loss": 6.5792,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 10.09,
2125
+ "learning_rate": 0.002369642857142857,
2126
+ "loss": 6.5276,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 10.11,
2131
+ "learning_rate": 0.002367857142857143,
2132
+ "loss": 6.5634,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 10.14,
2137
+ "learning_rate": 0.0023660714285714288,
2138
+ "loss": 6.5385,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 10.17,
2143
+ "learning_rate": 0.002364285714285714,
2144
+ "loss": 6.4516,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 10.2,
2149
+ "learning_rate": 0.0023625,
2150
+ "loss": 6.5641,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 10.23,
2155
+ "learning_rate": 0.002360714285714286,
2156
+ "loss": 6.5001,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 10.26,
2161
+ "learning_rate": 0.0023589285714285713,
2162
+ "loss": 6.4846,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 10.29,
2167
+ "learning_rate": 0.002357142857142857,
2168
+ "loss": 6.4638,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 10.31,
2173
+ "learning_rate": 0.002355357142857143,
2174
+ "loss": 6.5217,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 10.34,
2179
+ "learning_rate": 0.0023535714285714284,
2180
+ "loss": 6.5444,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 10.37,
2185
+ "learning_rate": 0.0023517857142857142,
2186
+ "loss": 6.496,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 10.4,
2191
+ "learning_rate": 0.00235,
2192
+ "loss": 6.5345,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 10.43,
2197
+ "learning_rate": 0.002348214285714286,
2198
+ "loss": 6.4732,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 10.46,
2203
+ "learning_rate": 0.0023464285714285714,
2204
+ "loss": 6.4765,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 10.49,
2209
+ "learning_rate": 0.002344642857142857,
2210
+ "loss": 6.3881,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 10.51,
2215
+ "learning_rate": 0.002342857142857143,
2216
+ "loss": 6.4908,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 10.54,
2221
+ "learning_rate": 0.0023410714285714285,
2222
+ "loss": 6.4593,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 10.57,
2227
+ "learning_rate": 0.0023392857142857143,
2228
+ "loss": 6.5006,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 10.6,
2233
+ "learning_rate": 0.0023375,
2234
+ "loss": 6.4495,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 10.63,
2239
+ "learning_rate": 0.0023357142857142856,
2240
+ "loss": 6.3569,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 10.66,
2245
+ "learning_rate": 0.0023339285714285714,
2246
+ "loss": 6.3592,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 10.69,
2251
+ "learning_rate": 0.0023321428571428573,
2252
+ "loss": 6.3258,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 10.71,
2257
+ "learning_rate": 0.002330357142857143,
2258
+ "loss": 6.3216,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 10.74,
2263
+ "learning_rate": 0.0023285714285714285,
2264
+ "loss": 6.4878,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 10.77,
2269
+ "learning_rate": 0.0023267857142857144,
2270
+ "loss": 6.3412,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 10.8,
2275
+ "learning_rate": 0.0023250000000000002,
2276
+ "loss": 6.3925,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 10.83,
2281
+ "learning_rate": 0.0023232142857142857,
2282
+ "loss": 6.275,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 10.86,
2287
+ "learning_rate": 0.0023214285714285715,
2288
+ "loss": 6.3575,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 10.89,
2293
+ "learning_rate": 0.0023196428571428574,
2294
+ "loss": 6.3259,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 10.91,
2299
+ "learning_rate": 0.002317857142857143,
2300
+ "loss": 6.315,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 10.94,
2305
+ "learning_rate": 0.0023160714285714286,
2306
+ "loss": 6.277,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 10.97,
2311
+ "learning_rate": 0.0023142857142857145,
2312
+ "loss": 6.3259,
2313
+ "step": 384
2314
+ },
2315
+ {
2316
+ "epoch": 11.0,
2317
+ "learning_rate": 0.0023125000000000003,
2318
+ "loss": 6.3747,
2319
+ "step": 385
2320
+ },
2321
+ {
2322
+ "epoch": 11.03,
2323
+ "learning_rate": 0.0023107142857142857,
2324
+ "loss": 6.3646,
2325
+ "step": 386
2326
+ },
2327
+ {
2328
+ "epoch": 11.06,
2329
+ "learning_rate": 0.0023089285714285716,
2330
+ "loss": 6.3687,
2331
+ "step": 387
2332
+ },
2333
+ {
2334
+ "epoch": 11.09,
2335
+ "learning_rate": 0.0023071428571428574,
2336
+ "loss": 6.3374,
2337
+ "step": 388
2338
+ },
2339
+ {
2340
+ "epoch": 11.11,
2341
+ "learning_rate": 0.002305357142857143,
2342
+ "loss": 6.3129,
2343
+ "step": 389
2344
+ },
2345
+ {
2346
+ "epoch": 11.14,
2347
+ "learning_rate": 0.0023035714285714287,
2348
+ "loss": 6.3425,
2349
+ "step": 390
2350
+ },
2351
+ {
2352
+ "epoch": 11.17,
2353
+ "learning_rate": 0.0023017857142857145,
2354
+ "loss": 6.2122,
2355
+ "step": 391
2356
+ },
2357
+ {
2358
+ "epoch": 11.2,
2359
+ "learning_rate": 0.0023000000000000004,
2360
+ "loss": 6.2768,
2361
+ "step": 392
2362
+ },
2363
+ {
2364
+ "epoch": 11.23,
2365
+ "learning_rate": 0.002298214285714286,
2366
+ "loss": 6.2853,
2367
+ "step": 393
2368
+ },
2369
+ {
2370
+ "epoch": 11.26,
2371
+ "learning_rate": 0.0022964285714285712,
2372
+ "loss": 6.3215,
2373
+ "step": 394
2374
+ },
2375
+ {
2376
+ "epoch": 11.29,
2377
+ "learning_rate": 0.002294642857142857,
2378
+ "loss": 6.3244,
2379
+ "step": 395
2380
+ },
2381
+ {
2382
+ "epoch": 11.31,
2383
+ "learning_rate": 0.002292857142857143,
2384
+ "loss": 6.2399,
2385
+ "step": 396
2386
+ },
2387
+ {
2388
+ "epoch": 11.34,
2389
+ "learning_rate": 0.0022910714285714283,
2390
+ "loss": 6.2457,
2391
+ "step": 397
2392
+ },
2393
+ {
2394
+ "epoch": 11.37,
2395
+ "learning_rate": 0.002289285714285714,
2396
+ "loss": 6.2018,
2397
+ "step": 398
2398
+ },
2399
+ {
2400
+ "epoch": 11.4,
2401
+ "learning_rate": 0.0022875,
2402
+ "loss": 6.2101,
2403
+ "step": 399
2404
+ },
2405
+ {
2406
+ "epoch": 11.43,
2407
+ "learning_rate": 0.0022857142857142855,
2408
+ "loss": 6.2257,
2409
+ "step": 400
2410
+ }
2411
+ ],
2412
+ "logging_steps": 1,
2413
+ "max_steps": 1680,
2414
+ "num_train_epochs": 48,
2415
+ "save_steps": 100,
2416
+ "total_flos": 2.3080655169481728e+17,
2417
+ "trial_name": null,
2418
+ "trial_params": null
2419
+ }
checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8697dec26118787553757d80401d29ed990405410ca911afb8c282e3da6934e3
3
+ size 4091