Hugging Face's logo

CreatorPhan
/
Bloomz_lora_answer_v2

PEFT
Model card Files Community
4
CreatorPhan commited on
Commit
3540d17
•
1 Parent(s): eafb612

Upload folder using huggingface_hub (#1)

Browse files

- Upload folder using huggingface_hub (77649d63f4dec929b56f2c1284a783189e9477fc)

Files changed (12) hide show
  1. .gitattributes +1 -0
  2. README.md +60 -0
  3. adapter_config.json +25 -0
  4. adapter_model.bin +3 -0
  5. optimizer.pt +3 -0
  6. rng_state.pth +3 -0
  7. scheduler.pt +3 -0
  8. special_tokens_map.json +6 -0
  9. tokenizer.json +3 -0
  10. tokenizer_config.json +10 -0
  11. trainer_state.json +1219 -0
  12. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+
31
+ The following `bitsandbytes` quantization config was used during training:
32
+ - quant_method: bitsandbytes
33
+ - load_in_8bit: True
34
+ - load_in_4bit: False
35
+ - llm_int8_threshold: 6.0
36
+ - llm_int8_skip_modules: None
37
+ - llm_int8_enable_fp32_cpu_offload: False
38
+ - llm_int8_has_fp16_weight: False
39
+ - bnb_4bit_quant_type: fp4
40
+ - bnb_4bit_use_double_quant: False
41
+ - bnb_4bit_compute_dtype: float32
42
+
43
+ The following `bitsandbytes` quantization config was used during training:
44
+ - quant_method: bitsandbytes
45
+ - load_in_8bit: True
46
+ - load_in_4bit: False
47
+ - llm_int8_threshold: 6.0
48
+ - llm_int8_skip_modules: None
49
+ - llm_int8_enable_fp32_cpu_offload: False
50
+ - llm_int8_has_fp16_weight: False
51
+ - bnb_4bit_quant_type: fp4
52
+ - bnb_4bit_use_double_quant: False
53
+ - bnb_4bit_compute_dtype: float32
54
+ ### Framework versions
55
+
56
+ - PEFT 0.6.0.dev0
57
+ - PEFT 0.6.0.dev0
58
+ - PEFT 0.6.0.dev0
59
+
60
+ - PEFT 0.6.0.dev0
adapter_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "bigscience/bloomz-3b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.0,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 8,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "dense_4h_to_h",
20
+ "dense",
21
+ "dense_h_to_4h",
22
+ "query_key_value"
23
+ ],
24
+ "task_type": "CAUSAL_LM"
25
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5d07783590970cc01440af02efb30baf84be013f42d6e324dbec3f1211d5743
3
+ size 39409357
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bb4e74f21744cbd194fc93b7a41891675165b22a0068ad1db19aeac49015587
3
+ size 78844421
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972139d83957a9cf2600cb6eeca17287d7a5377c33a53500ae7e13fe830ad36b
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d3e390b4500e3448050a2123ac7e837c199dcd6015f166fda34e0372e32849
3
+ size 627
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
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
3
+ size 14500570
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
+ }
trainer_state.json ADDED
@@ -0,0 +1,1219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.1173184357541899,
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": 0.01,
13
+ "learning_rate": 0.00019972067039106145,
14
+ "loss": 2.6443,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.00019944134078212292,
20
+ "loss": 2.4104,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 0.00019916201117318435,
26
+ "loss": 2.4975,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 0.00019888268156424582,
32
+ "loss": 2.3513,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 0.0001986033519553073,
38
+ "loss": 2.4274,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.03,
43
+ "learning_rate": 0.00019832402234636873,
44
+ "loss": 2.3628,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 0.0001980446927374302,
50
+ "loss": 2.3567,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "learning_rate": 0.00019776536312849163,
56
+ "loss": 2.4121,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.05,
61
+ "learning_rate": 0.00019748603351955307,
62
+ "loss": 2.4033,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 0.00019720670391061454,
68
+ "loss": 2.2805,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.06,
73
+ "learning_rate": 0.00019692737430167598,
74
+ "loss": 2.2639,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.07,
79
+ "learning_rate": 0.00019664804469273744,
80
+ "loss": 2.2724,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.07,
85
+ "learning_rate": 0.00019636871508379888,
86
+ "loss": 2.332,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.08,
91
+ "learning_rate": 0.00019608938547486035,
92
+ "loss": 2.2261,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.08,
97
+ "learning_rate": 0.00019581005586592182,
98
+ "loss": 2.2208,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.09,
103
+ "learning_rate": 0.00019553072625698326,
104
+ "loss": 2.3351,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.09,
109
+ "learning_rate": 0.0001952513966480447,
110
+ "loss": 2.2475,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.1,
115
+ "learning_rate": 0.00019497206703910616,
116
+ "loss": 2.3283,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.11,
121
+ "learning_rate": 0.0001946927374301676,
122
+ "loss": 2.1346,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.11,
127
+ "learning_rate": 0.00019441340782122907,
128
+ "loss": 2.131,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.12,
133
+ "learning_rate": 0.0001941340782122905,
134
+ "loss": 2.1718,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.12,
139
+ "learning_rate": 0.00019385474860335195,
140
+ "loss": 2.2446,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.13,
145
+ "learning_rate": 0.0001935754189944134,
146
+ "loss": 2.306,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.13,
151
+ "learning_rate": 0.00019329608938547488,
152
+ "loss": 2.1908,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.14,
157
+ "learning_rate": 0.00019301675977653632,
158
+ "loss": 2.2844,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.15,
163
+ "learning_rate": 0.00019273743016759779,
164
+ "loss": 2.2235,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.15,
169
+ "learning_rate": 0.00019245810055865922,
170
+ "loss": 2.1842,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.16,
175
+ "learning_rate": 0.00019217877094972066,
176
+ "loss": 2.2675,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.16,
181
+ "learning_rate": 0.00019189944134078213,
182
+ "loss": 2.2532,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.17,
187
+ "learning_rate": 0.00019162011173184357,
188
+ "loss": 2.1788,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.17,
193
+ "learning_rate": 0.00019134078212290504,
194
+ "loss": 2.2494,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.18,
199
+ "learning_rate": 0.0001910614525139665,
200
+ "loss": 2.1995,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.18,
205
+ "learning_rate": 0.00019078212290502794,
206
+ "loss": 2.1451,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.19,
211
+ "learning_rate": 0.0001905027932960894,
212
+ "loss": 2.223,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.2,
217
+ "learning_rate": 0.00019022346368715085,
218
+ "loss": 2.2854,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.2,
223
+ "learning_rate": 0.0001899441340782123,
224
+ "loss": 2.2265,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.21,
229
+ "learning_rate": 0.00018966480446927375,
230
+ "loss": 2.1214,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.21,
235
+ "learning_rate": 0.0001893854748603352,
236
+ "loss": 2.1898,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.22,
241
+ "learning_rate": 0.00018910614525139666,
242
+ "loss": 2.1974,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.22,
247
+ "learning_rate": 0.0001888268156424581,
248
+ "loss": 2.2259,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.23,
253
+ "learning_rate": 0.00018854748603351957,
254
+ "loss": 2.2094,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.23,
259
+ "learning_rate": 0.00018826815642458103,
260
+ "loss": 2.1731,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.24,
265
+ "learning_rate": 0.00018798882681564247,
266
+ "loss": 2.2373,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.25,
271
+ "learning_rate": 0.0001877094972067039,
272
+ "loss": 2.2295,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.25,
277
+ "learning_rate": 0.00018743016759776538,
278
+ "loss": 2.1947,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.26,
283
+ "learning_rate": 0.00018715083798882682,
284
+ "loss": 2.2115,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.26,
289
+ "learning_rate": 0.00018687150837988828,
290
+ "loss": 2.1224,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.27,
295
+ "learning_rate": 0.00018659217877094972,
296
+ "loss": 2.2137,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.27,
301
+ "learning_rate": 0.00018631284916201116,
302
+ "loss": 2.2338,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.28,
307
+ "learning_rate": 0.00018603351955307266,
308
+ "loss": 2.1298,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.28,
313
+ "learning_rate": 0.0001857541899441341,
314
+ "loss": 2.0883,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.29,
319
+ "learning_rate": 0.00018547486033519553,
320
+ "loss": 2.1216,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.3,
325
+ "learning_rate": 0.000185195530726257,
326
+ "loss": 2.2112,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.3,
331
+ "learning_rate": 0.00018491620111731844,
332
+ "loss": 2.1224,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.31,
337
+ "learning_rate": 0.0001846368715083799,
338
+ "loss": 2.2375,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.31,
343
+ "learning_rate": 0.00018435754189944135,
344
+ "loss": 2.2235,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.32,
349
+ "learning_rate": 0.00018407821229050279,
350
+ "loss": 2.1682,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.32,
355
+ "learning_rate": 0.00018379888268156425,
356
+ "loss": 2.2077,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.33,
361
+ "learning_rate": 0.00018351955307262572,
362
+ "loss": 2.1596,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.34,
367
+ "learning_rate": 0.00018324022346368716,
368
+ "loss": 2.1311,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.34,
373
+ "learning_rate": 0.00018296089385474862,
374
+ "loss": 2.1333,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.35,
379
+ "learning_rate": 0.00018268156424581006,
380
+ "loss": 2.0901,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.35,
385
+ "learning_rate": 0.00018240223463687153,
386
+ "loss": 2.1971,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.36,
391
+ "learning_rate": 0.00018212290502793297,
392
+ "loss": 2.2602,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.36,
397
+ "learning_rate": 0.0001818435754189944,
398
+ "loss": 2.2194,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.37,
403
+ "learning_rate": 0.00018156424581005588,
404
+ "loss": 2.1218,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.37,
409
+ "learning_rate": 0.00018128491620111731,
410
+ "loss": 2.2049,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.38,
415
+ "learning_rate": 0.00018100558659217878,
416
+ "loss": 2.1521,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.39,
421
+ "learning_rate": 0.00018072625698324025,
422
+ "loss": 2.112,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.39,
427
+ "learning_rate": 0.0001804469273743017,
428
+ "loss": 2.1906,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.4,
433
+ "learning_rate": 0.00018016759776536313,
434
+ "loss": 2.1717,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.4,
439
+ "learning_rate": 0.0001798882681564246,
440
+ "loss": 2.0712,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.41,
445
+ "learning_rate": 0.00017960893854748603,
446
+ "loss": 2.141,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.41,
451
+ "learning_rate": 0.0001793296089385475,
452
+ "loss": 2.0656,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.42,
457
+ "learning_rate": 0.00017905027932960894,
458
+ "loss": 2.1125,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.42,
463
+ "learning_rate": 0.00017877094972067038,
464
+ "loss": 2.0869,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.43,
469
+ "learning_rate": 0.00017849162011173187,
470
+ "loss": 2.2478,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.44,
475
+ "learning_rate": 0.0001782122905027933,
476
+ "loss": 2.1535,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.44,
481
+ "learning_rate": 0.00017793296089385475,
482
+ "loss": 2.1927,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.45,
487
+ "learning_rate": 0.00017765363128491622,
488
+ "loss": 2.1213,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.45,
493
+ "learning_rate": 0.00017737430167597766,
494
+ "loss": 2.0981,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.46,
499
+ "learning_rate": 0.00017709497206703912,
500
+ "loss": 2.1828,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.46,
505
+ "learning_rate": 0.00017681564245810056,
506
+ "loss": 2.0562,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.47,
511
+ "learning_rate": 0.000176536312849162,
512
+ "loss": 2.1334,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.47,
517
+ "learning_rate": 0.00017625698324022347,
518
+ "loss": 2.1225,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.48,
523
+ "learning_rate": 0.00017597765363128493,
524
+ "loss": 2.2098,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.49,
529
+ "learning_rate": 0.00017569832402234637,
530
+ "loss": 2.1519,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.49,
535
+ "learning_rate": 0.00017541899441340784,
536
+ "loss": 2.1132,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.5,
541
+ "learning_rate": 0.00017513966480446928,
542
+ "loss": 2.0333,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.5,
547
+ "learning_rate": 0.00017486033519553075,
548
+ "loss": 2.2764,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.51,
553
+ "learning_rate": 0.00017458100558659218,
554
+ "loss": 2.1838,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.51,
559
+ "learning_rate": 0.00017430167597765362,
560
+ "loss": 2.1386,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.52,
565
+ "learning_rate": 0.0001740223463687151,
566
+ "loss": 2.1034,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.53,
571
+ "learning_rate": 0.00017374301675977656,
572
+ "loss": 2.0346,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.53,
577
+ "learning_rate": 0.000173463687150838,
578
+ "loss": 2.0274,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.54,
583
+ "learning_rate": 0.00017318435754189946,
584
+ "loss": 2.1036,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.54,
589
+ "learning_rate": 0.0001729050279329609,
590
+ "loss": 2.1208,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.55,
595
+ "learning_rate": 0.00017262569832402237,
596
+ "loss": 2.0572,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.55,
601
+ "learning_rate": 0.0001723463687150838,
602
+ "loss": 2.1702,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.56,
607
+ "learning_rate": 0.00017206703910614525,
608
+ "loss": 2.1302,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.56,
613
+ "learning_rate": 0.0001717877094972067,
614
+ "loss": 2.0175,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.57,
619
+ "learning_rate": 0.00017150837988826815,
620
+ "loss": 2.1006,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.58,
625
+ "learning_rate": 0.00017122905027932962,
626
+ "loss": 2.0662,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.58,
631
+ "learning_rate": 0.00017094972067039109,
632
+ "loss": 1.988,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.59,
637
+ "learning_rate": 0.00017067039106145253,
638
+ "loss": 2.1008,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.59,
643
+ "learning_rate": 0.00017039106145251396,
644
+ "loss": 2.1482,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.6,
649
+ "learning_rate": 0.00017011173184357543,
650
+ "loss": 2.1052,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.6,
655
+ "learning_rate": 0.00016983240223463687,
656
+ "loss": 2.0978,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.61,
661
+ "learning_rate": 0.00016955307262569834,
662
+ "loss": 2.1303,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.61,
667
+ "learning_rate": 0.00016927374301675978,
668
+ "loss": 2.0794,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.62,
673
+ "learning_rate": 0.00016899441340782122,
674
+ "loss": 2.1059,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.63,
679
+ "learning_rate": 0.0001687150837988827,
680
+ "loss": 1.9642,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.63,
685
+ "learning_rate": 0.00016843575418994415,
686
+ "loss": 2.0415,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.64,
691
+ "learning_rate": 0.0001681564245810056,
692
+ "loss": 2.0795,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.64,
697
+ "learning_rate": 0.00016787709497206705,
698
+ "loss": 2.0238,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.65,
703
+ "learning_rate": 0.0001675977653631285,
704
+ "loss": 2.078,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.65,
709
+ "learning_rate": 0.00016731843575418996,
710
+ "loss": 2.1362,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.66,
715
+ "learning_rate": 0.0001670391061452514,
716
+ "loss": 2.0552,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.66,
721
+ "learning_rate": 0.00016675977653631284,
722
+ "loss": 2.213,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.67,
727
+ "learning_rate": 0.0001664804469273743,
728
+ "loss": 1.9999,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.68,
733
+ "learning_rate": 0.00016620111731843577,
734
+ "loss": 2.06,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.68,
739
+ "learning_rate": 0.0001659217877094972,
740
+ "loss": 2.0177,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.69,
745
+ "learning_rate": 0.00016564245810055868,
746
+ "loss": 2.0504,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.69,
751
+ "learning_rate": 0.00016536312849162012,
752
+ "loss": 2.0585,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.7,
757
+ "learning_rate": 0.00016508379888268158,
758
+ "loss": 2.0273,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.7,
763
+ "learning_rate": 0.00016480446927374302,
764
+ "loss": 2.0549,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.71,
769
+ "learning_rate": 0.00016452513966480446,
770
+ "loss": 2.044,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.72,
775
+ "learning_rate": 0.00016424581005586593,
776
+ "loss": 2.0731,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.72,
781
+ "learning_rate": 0.00016396648044692737,
782
+ "loss": 2.0568,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.73,
787
+ "learning_rate": 0.00016368715083798883,
788
+ "loss": 2.007,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.73,
793
+ "learning_rate": 0.0001634078212290503,
794
+ "loss": 2.0707,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.74,
799
+ "learning_rate": 0.00016312849162011174,
800
+ "loss": 1.9793,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.74,
805
+ "learning_rate": 0.0001628491620111732,
806
+ "loss": 2.1311,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.75,
811
+ "learning_rate": 0.00016256983240223465,
812
+ "loss": 2.0016,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.75,
817
+ "learning_rate": 0.00016229050279329609,
818
+ "loss": 1.9945,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.76,
823
+ "learning_rate": 0.00016201117318435755,
824
+ "loss": 2.0186,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.77,
829
+ "learning_rate": 0.000161731843575419,
830
+ "loss": 2.0971,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.77,
835
+ "learning_rate": 0.00016145251396648046,
836
+ "loss": 2.0883,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.78,
841
+ "learning_rate": 0.00016117318435754192,
842
+ "loss": 2.0803,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.78,
847
+ "learning_rate": 0.00016089385474860336,
848
+ "loss": 2.0617,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.79,
853
+ "learning_rate": 0.00016061452513966483,
854
+ "loss": 2.1265,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.79,
859
+ "learning_rate": 0.00016033519553072627,
860
+ "loss": 2.0151,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.8,
865
+ "learning_rate": 0.0001600558659217877,
866
+ "loss": 1.996,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.8,
871
+ "learning_rate": 0.00015977653631284918,
872
+ "loss": 2.0164,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.81,
877
+ "learning_rate": 0.00015949720670391061,
878
+ "loss": 2.0314,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.82,
883
+ "learning_rate": 0.00015921787709497208,
884
+ "loss": 1.9501,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.82,
889
+ "learning_rate": 0.00015893854748603352,
890
+ "loss": 2.087,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.83,
895
+ "learning_rate": 0.000158659217877095,
896
+ "loss": 2.0262,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.83,
901
+ "learning_rate": 0.00015837988826815643,
902
+ "loss": 2.0765,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.84,
907
+ "learning_rate": 0.0001581005586592179,
908
+ "loss": 2.105,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.84,
913
+ "learning_rate": 0.00015782122905027933,
914
+ "loss": 1.9863,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.85,
919
+ "learning_rate": 0.0001575418994413408,
920
+ "loss": 1.9873,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.85,
925
+ "learning_rate": 0.00015726256983240224,
926
+ "loss": 2.0094,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.86,
931
+ "learning_rate": 0.00015698324022346368,
932
+ "loss": 1.9141,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.87,
937
+ "learning_rate": 0.00015670391061452514,
938
+ "loss": 1.917,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.87,
943
+ "learning_rate": 0.00015642458100558658,
944
+ "loss": 2.109,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.88,
949
+ "learning_rate": 0.00015614525139664805,
950
+ "loss": 1.9799,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.88,
955
+ "learning_rate": 0.00015586592178770952,
956
+ "loss": 1.9571,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.89,
961
+ "learning_rate": 0.00015558659217877096,
962
+ "loss": 1.9931,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.89,
967
+ "learning_rate": 0.00015530726256983242,
968
+ "loss": 2.1004,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.9,
973
+ "learning_rate": 0.00015502793296089386,
974
+ "loss": 2.0385,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.91,
979
+ "learning_rate": 0.0001547486033519553,
980
+ "loss": 1.9751,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.91,
985
+ "learning_rate": 0.00015446927374301677,
986
+ "loss": 2.0544,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.92,
991
+ "learning_rate": 0.0001541899441340782,
992
+ "loss": 2.0069,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.92,
997
+ "learning_rate": 0.00015391061452513967,
998
+ "loss": 1.9576,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.93,
1003
+ "learning_rate": 0.00015363128491620114,
1004
+ "loss": 1.8991,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.93,
1009
+ "learning_rate": 0.00015335195530726258,
1010
+ "loss": 1.9336,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.94,
1015
+ "learning_rate": 0.00015307262569832405,
1016
+ "loss": 1.9736,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.94,
1021
+ "learning_rate": 0.00015279329608938548,
1022
+ "loss": 1.9702,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.95,
1027
+ "learning_rate": 0.00015251396648044692,
1028
+ "loss": 1.9055,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.96,
1033
+ "learning_rate": 0.0001522346368715084,
1034
+ "loss": 2.0503,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.96,
1039
+ "learning_rate": 0.00015195530726256983,
1040
+ "loss": 2.0039,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.97,
1045
+ "learning_rate": 0.0001516759776536313,
1046
+ "loss": 1.9406,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.97,
1051
+ "learning_rate": 0.00015139664804469274,
1052
+ "loss": 2.0525,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.98,
1057
+ "learning_rate": 0.0001511173184357542,
1058
+ "loss": 1.9234,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.98,
1063
+ "learning_rate": 0.00015083798882681567,
1064
+ "loss": 1.8614,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.99,
1069
+ "learning_rate": 0.0001505586592178771,
1070
+ "loss": 1.9616,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.99,
1075
+ "learning_rate": 0.00015027932960893855,
1076
+ "loss": 1.9509,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 1.0,
1081
+ "learning_rate": 0.00015000000000000001,
1082
+ "loss": 1.9592,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 1.01,
1087
+ "learning_rate": 0.00014972067039106145,
1088
+ "loss": 1.8991,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 1.01,
1093
+ "learning_rate": 0.00014944134078212292,
1094
+ "loss": 1.9127,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 1.02,
1099
+ "learning_rate": 0.00014916201117318436,
1100
+ "loss": 1.8982,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 1.02,
1105
+ "learning_rate": 0.0001488826815642458,
1106
+ "loss": 1.9534,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 1.03,
1111
+ "learning_rate": 0.0001486033519553073,
1112
+ "loss": 1.7794,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 1.03,
1117
+ "learning_rate": 0.00014832402234636873,
1118
+ "loss": 1.7958,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 1.04,
1123
+ "learning_rate": 0.00014804469273743017,
1124
+ "loss": 1.8282,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 1.04,
1129
+ "learning_rate": 0.00014776536312849164,
1130
+ "loss": 2.0423,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 1.05,
1135
+ "learning_rate": 0.00014748603351955308,
1136
+ "loss": 1.9282,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 1.06,
1141
+ "learning_rate": 0.00014720670391061454,
1142
+ "loss": 1.9072,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 1.06,
1147
+ "learning_rate": 0.00014692737430167598,
1148
+ "loss": 1.8665,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 1.07,
1153
+ "learning_rate": 0.00014664804469273742,
1154
+ "loss": 1.9021,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 1.07,
1159
+ "learning_rate": 0.0001463687150837989,
1160
+ "loss": 1.7308,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 1.08,
1165
+ "learning_rate": 0.00014608938547486035,
1166
+ "loss": 1.9165,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 1.08,
1171
+ "learning_rate": 0.0001458100558659218,
1172
+ "loss": 1.842,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 1.09,
1177
+ "learning_rate": 0.00014553072625698326,
1178
+ "loss": 1.9128,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 1.09,
1183
+ "learning_rate": 0.0001452513966480447,
1184
+ "loss": 1.8005,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 1.1,
1189
+ "learning_rate": 0.00014497206703910614,
1190
+ "loss": 1.8547,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 1.11,
1195
+ "learning_rate": 0.0001446927374301676,
1196
+ "loss": 1.9042,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 1.11,
1201
+ "learning_rate": 0.00014441340782122905,
1202
+ "loss": 1.8609,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 1.12,
1207
+ "learning_rate": 0.0001441340782122905,
1208
+ "loss": 1.9591,
1209
+ "step": 200
1210
+ }
1211
+ ],
1212
+ "logging_steps": 1,
1213
+ "max_steps": 716,
1214
+ "num_train_epochs": 4,
1215
+ "save_steps": 100,
1216
+ "total_flos": 1.0290223796256768e+17,
1217
+ "trial_name": null,
1218
+ "trial_params": null
1219
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:188ae1c421cc0c6435d1f71d8d3423ac4abc7dba0e6fc2efcbc4dbe77c741317
3
+ size 4027