Hugging Face's logo

gitpullpull
/
nahida_lora_jp

Model card Files
xet
Community
gitpullpull commited on
Commit
cc49b6f
·
verified ·
1 Parent(s): 3f320e6

I trained with Nahida's dataset using qlora.

Browse files
Files changed (14) hide show
  1. README.md +20 -0
  2. adapter_config.json +26 -0
  3. adapter_model.bin +3 -0
  4. adapter_model/README.md +32 -0
  5. adapter_model/adapter_config.json +26 -0
  6. adapter_model/adapter_model.bin +3 -0
  7. optimizer.pt +3 -0
  8. rng_state.pth +3 -0
  9. scheduler.pt +3 -0
  10. special_tokens_map.json +12 -0
  11. tokenizer.model +3 -0
  12. tokenizer_config.json +71 -0
  13. trainer_state.json +616 -0
  14. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: True
16
+ - bnb_4bit_compute_dtype: bfloat16
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.4.0
adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "D:\\free_soft\\LLM\\ELYZA\\ELYZA-japanese-Llama-2-13b-instruct",
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": 16.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "v_proj",
18
+ "up_proj",
19
+ "k_proj",
20
+ "down_proj",
21
+ "q_proj",
22
+ "o_proj",
23
+ "gate_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed3a783bef4c5e78d3d11e3616ada4de4c16c8836fafe7c7407695ac6e4a903c
3
+ size 500897546
adapter_model/README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: True
16
+ - bnb_4bit_compute_dtype: bfloat16
17
+
18
+ The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: False
20
+ - load_in_4bit: True
21
+ - llm_int8_threshold: 6.0
22
+ - llm_int8_skip_modules: None
23
+ - llm_int8_enable_fp32_cpu_offload: False
24
+ - llm_int8_has_fp16_weight: False
25
+ - bnb_4bit_quant_type: nf4
26
+ - bnb_4bit_use_double_quant: True
27
+ - bnb_4bit_compute_dtype: bfloat16
28
+ ### Framework versions
29
+
30
+ - PEFT 0.4.0
31
+
32
+ - PEFT 0.4.0
adapter_model/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "D:\\free_soft\\LLM\\ELYZA\\ELYZA-japanese-Llama-2-13b-instruct",
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": 16.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "v_proj",
18
+ "up_proj",
19
+ "k_proj",
20
+ "down_proj",
21
+ "q_proj",
22
+ "o_proj",
23
+ "gate_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
adapter_model/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed3a783bef4c5e78d3d11e3616ada4de4c16c8836fafe7c7407695ac6e4a903c
3
+ size 500897546
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5ce89aaceab50163ecfc67d150eccebfe2df57f484a888efc46b8ab502e512c
3
+ size 2003127538
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8b8a4d5b07284a0dc7be940abae6a68571c541c756893a4ac3d8def8a82afa9
3
+ size 14180
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5db97ab97d238e7b777a7227775dfbd5343f9e53dfb4d1e78985309a0b24731
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": {
5
+ "content": "</s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "unk_token": "</s>"
12
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": {
32
+ "__type": "AddedToken",
33
+ "content": "<s>",
34
+ "lstrip": false,
35
+ "normalized": true,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": {
41
+ "__type": "AddedToken",
42
+ "content": "</s>",
43
+ "lstrip": false,
44
+ "normalized": true,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "legacy": false,
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": {
51
+ "__type": "AddedToken",
52
+ "content": "</s>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false
57
+ },
58
+ "padding_side": "right",
59
+ "sp_model_kwargs": {},
60
+ "spaces_between_special_tokens": false,
61
+ "tokenizer_class": "LlamaTokenizer",
62
+ "unk_token": {
63
+ "__type": "AddedToken",
64
+ "content": "<unk>",
65
+ "lstrip": false,
66
+ "normalized": true,
67
+ "rstrip": false,
68
+ "single_word": false
69
+ },
70
+ "use_default_system_prompt": true
71
+ }
trainer_state.json ADDED
@@ -0,0 +1,616 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 35.08771929824562,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.35,
12
+ "learning_rate": 0.0002,
13
+ "loss": 2.0495,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.7,
18
+ "learning_rate": 0.0002,
19
+ "loss": 1.9419,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 1.05,
24
+ "learning_rate": 0.0002,
25
+ "loss": 1.6328,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 1.4,
30
+ "learning_rate": 0.0002,
31
+ "loss": 1.2627,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 1.75,
36
+ "learning_rate": 0.0002,
37
+ "loss": 1.1166,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 2.11,
42
+ "learning_rate": 0.0002,
43
+ "loss": 0.9466,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 2.46,
48
+ "learning_rate": 0.0002,
49
+ "loss": 0.4556,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 2.81,
54
+ "learning_rate": 0.0002,
55
+ "loss": 0.4507,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 3.16,
60
+ "learning_rate": 0.0002,
61
+ "loss": 0.3553,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 3.51,
66
+ "learning_rate": 0.0002,
67
+ "loss": 0.1801,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 3.86,
72
+ "learning_rate": 0.0002,
73
+ "loss": 0.2521,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 4.21,
78
+ "learning_rate": 0.0002,
79
+ "loss": 0.1021,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 4.56,
84
+ "learning_rate": 0.0002,
85
+ "loss": 0.0998,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 4.91,
90
+ "learning_rate": 0.0002,
91
+ "loss": 0.0726,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 5.26,
96
+ "learning_rate": 0.0002,
97
+ "loss": 0.0708,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 5.61,
102
+ "learning_rate": 0.0002,
103
+ "loss": 0.0327,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 5.96,
108
+ "learning_rate": 0.0002,
109
+ "loss": 0.0662,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 6.32,
114
+ "learning_rate": 0.0002,
115
+ "loss": 0.0258,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 6.67,
120
+ "learning_rate": 0.0002,
121
+ "loss": 0.0301,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 7.02,
126
+ "learning_rate": 0.0002,
127
+ "loss": 0.0412,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 7.37,
132
+ "learning_rate": 0.0002,
133
+ "loss": 0.0396,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 7.72,
138
+ "learning_rate": 0.0002,
139
+ "loss": 0.0155,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 8.07,
144
+ "learning_rate": 0.0002,
145
+ "loss": 0.0295,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 8.42,
150
+ "learning_rate": 0.0002,
151
+ "loss": 0.01,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 8.77,
156
+ "learning_rate": 0.0002,
157
+ "loss": 0.0247,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 9.12,
162
+ "learning_rate": 0.0002,
163
+ "loss": 0.0183,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 9.47,
168
+ "learning_rate": 0.0002,
169
+ "loss": 0.0018,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 9.82,
174
+ "learning_rate": 0.0002,
175
+ "loss": 0.0053,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 10.18,
180
+ "learning_rate": 0.0002,
181
+ "loss": 0.0161,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 10.53,
186
+ "learning_rate": 0.0002,
187
+ "loss": 0.0122,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 10.88,
192
+ "learning_rate": 0.0002,
193
+ "loss": 0.0126,
194
+ "step": 310
195
+ },
196
+ {
197
+ "epoch": 11.23,
198
+ "learning_rate": 0.0002,
199
+ "loss": 0.0135,
200
+ "step": 320
201
+ },
202
+ {
203
+ "epoch": 11.58,
204
+ "learning_rate": 0.0002,
205
+ "loss": 0.0196,
206
+ "step": 330
207
+ },
208
+ {
209
+ "epoch": 11.93,
210
+ "learning_rate": 0.0002,
211
+ "loss": 0.014,
212
+ "step": 340
213
+ },
214
+ {
215
+ "epoch": 12.28,
216
+ "learning_rate": 0.0002,
217
+ "loss": 0.0056,
218
+ "step": 350
219
+ },
220
+ {
221
+ "epoch": 12.63,
222
+ "learning_rate": 0.0002,
223
+ "loss": 0.0078,
224
+ "step": 360
225
+ },
226
+ {
227
+ "epoch": 12.98,
228
+ "learning_rate": 0.0002,
229
+ "loss": 0.0151,
230
+ "step": 370
231
+ },
232
+ {
233
+ "epoch": 13.33,
234
+ "learning_rate": 0.0002,
235
+ "loss": 0.0155,
236
+ "step": 380
237
+ },
238
+ {
239
+ "epoch": 13.68,
240
+ "learning_rate": 0.0002,
241
+ "loss": 0.0019,
242
+ "step": 390
243
+ },
244
+ {
245
+ "epoch": 14.04,
246
+ "learning_rate": 0.0002,
247
+ "loss": 0.0396,
248
+ "step": 400
249
+ },
250
+ {
251
+ "epoch": 14.39,
252
+ "learning_rate": 0.0002,
253
+ "loss": 0.0262,
254
+ "step": 410
255
+ },
256
+ {
257
+ "epoch": 14.74,
258
+ "learning_rate": 0.0002,
259
+ "loss": 0.0209,
260
+ "step": 420
261
+ },
262
+ {
263
+ "epoch": 15.09,
264
+ "learning_rate": 0.0002,
265
+ "loss": 0.0094,
266
+ "step": 430
267
+ },
268
+ {
269
+ "epoch": 15.44,
270
+ "learning_rate": 0.0002,
271
+ "loss": 0.0126,
272
+ "step": 440
273
+ },
274
+ {
275
+ "epoch": 15.79,
276
+ "learning_rate": 0.0002,
277
+ "loss": 0.0118,
278
+ "step": 450
279
+ },
280
+ {
281
+ "epoch": 16.14,
282
+ "learning_rate": 0.0002,
283
+ "loss": 0.0049,
284
+ "step": 460
285
+ },
286
+ {
287
+ "epoch": 16.49,
288
+ "learning_rate": 0.0002,
289
+ "loss": 0.0018,
290
+ "step": 470
291
+ },
292
+ {
293
+ "epoch": 16.84,
294
+ "learning_rate": 0.0002,
295
+ "loss": 0.0097,
296
+ "step": 480
297
+ },
298
+ {
299
+ "epoch": 17.19,
300
+ "learning_rate": 0.0002,
301
+ "loss": 0.0115,
302
+ "step": 490
303
+ },
304
+ {
305
+ "epoch": 17.54,
306
+ "learning_rate": 0.0002,
307
+ "loss": 0.0033,
308
+ "step": 500
309
+ },
310
+ {
311
+ "epoch": 17.89,
312
+ "learning_rate": 0.0002,
313
+ "loss": 0.0122,
314
+ "step": 510
315
+ },
316
+ {
317
+ "epoch": 18.25,
318
+ "learning_rate": 0.0002,
319
+ "loss": 0.0083,
320
+ "step": 520
321
+ },
322
+ {
323
+ "epoch": 18.6,
324
+ "learning_rate": 0.0002,
325
+ "loss": 0.002,
326
+ "step": 530
327
+ },
328
+ {
329
+ "epoch": 18.95,
330
+ "learning_rate": 0.0002,
331
+ "loss": 0.0136,
332
+ "step": 540
333
+ },
334
+ {
335
+ "epoch": 19.3,
336
+ "learning_rate": 0.0002,
337
+ "loss": 0.0127,
338
+ "step": 550
339
+ },
340
+ {
341
+ "epoch": 19.65,
342
+ "learning_rate": 0.0002,
343
+ "loss": 0.004,
344
+ "step": 560
345
+ },
346
+ {
347
+ "epoch": 20.0,
348
+ "learning_rate": 0.0002,
349
+ "loss": 0.0082,
350
+ "step": 570
351
+ },
352
+ {
353
+ "epoch": 20.35,
354
+ "learning_rate": 0.0002,
355
+ "loss": 0.0147,
356
+ "step": 580
357
+ },
358
+ {
359
+ "epoch": 20.7,
360
+ "learning_rate": 0.0002,
361
+ "loss": 0.0206,
362
+ "step": 590
363
+ },
364
+ {
365
+ "epoch": 21.05,
366
+ "learning_rate": 0.0002,
367
+ "loss": 0.0238,
368
+ "step": 600
369
+ },
370
+ {
371
+ "epoch": 21.4,
372
+ "learning_rate": 0.0002,
373
+ "loss": 0.0286,
374
+ "step": 610
375
+ },
376
+ {
377
+ "epoch": 21.75,
378
+ "learning_rate": 0.0002,
379
+ "loss": 0.0484,
380
+ "step": 620
381
+ },
382
+ {
383
+ "epoch": 22.11,
384
+ "learning_rate": 0.0002,
385
+ "loss": 0.0251,
386
+ "step": 630
387
+ },
388
+ {
389
+ "epoch": 22.46,
390
+ "learning_rate": 0.0002,
391
+ "loss": 0.0324,
392
+ "step": 640
393
+ },
394
+ {
395
+ "epoch": 22.81,
396
+ "learning_rate": 0.0002,
397
+ "loss": 0.024,
398
+ "step": 650
399
+ },
400
+ {
401
+ "epoch": 23.16,
402
+ "learning_rate": 0.0002,
403
+ "loss": 0.0166,
404
+ "step": 660
405
+ },
406
+ {
407
+ "epoch": 23.51,
408
+ "learning_rate": 0.0002,
409
+ "loss": 0.0298,
410
+ "step": 670
411
+ },
412
+ {
413
+ "epoch": 23.86,
414
+ "learning_rate": 0.0002,
415
+ "loss": 0.0383,
416
+ "step": 680
417
+ },
418
+ {
419
+ "epoch": 24.21,
420
+ "learning_rate": 0.0002,
421
+ "loss": 0.0309,
422
+ "step": 690
423
+ },
424
+ {
425
+ "epoch": 24.56,
426
+ "learning_rate": 0.0002,
427
+ "loss": 0.0164,
428
+ "step": 700
429
+ },
430
+ {
431
+ "epoch": 24.91,
432
+ "learning_rate": 0.0002,
433
+ "loss": 0.0281,
434
+ "step": 710
435
+ },
436
+ {
437
+ "epoch": 25.26,
438
+ "learning_rate": 0.0002,
439
+ "loss": 0.0146,
440
+ "step": 720
441
+ },
442
+ {
443
+ "epoch": 25.61,
444
+ "learning_rate": 0.0002,
445
+ "loss": 0.0433,
446
+ "step": 730
447
+ },
448
+ {
449
+ "epoch": 25.96,
450
+ "learning_rate": 0.0002,
451
+ "loss": 0.0543,
452
+ "step": 740
453
+ },
454
+ {
455
+ "epoch": 26.32,
456
+ "learning_rate": 0.0002,
457
+ "loss": 0.0786,
458
+ "step": 750
459
+ },
460
+ {
461
+ "epoch": 26.67,
462
+ "learning_rate": 0.0002,
463
+ "loss": 0.0248,
464
+ "step": 760
465
+ },
466
+ {
467
+ "epoch": 27.02,
468
+ "learning_rate": 0.0002,
469
+ "loss": 0.0249,
470
+ "step": 770
471
+ },
472
+ {
473
+ "epoch": 27.37,
474
+ "learning_rate": 0.0002,
475
+ "loss": 0.0253,
476
+ "step": 780
477
+ },
478
+ {
479
+ "epoch": 27.72,
480
+ "learning_rate": 0.0002,
481
+ "loss": 0.0111,
482
+ "step": 790
483
+ },
484
+ {
485
+ "epoch": 28.07,
486
+ "learning_rate": 0.0002,
487
+ "loss": 0.0356,
488
+ "step": 800
489
+ },
490
+ {
491
+ "epoch": 28.42,
492
+ "learning_rate": 0.0002,
493
+ "loss": 0.0597,
494
+ "step": 810
495
+ },
496
+ {
497
+ "epoch": 28.77,
498
+ "learning_rate": 0.0002,
499
+ "loss": 0.0473,
500
+ "step": 820
501
+ },
502
+ {
503
+ "epoch": 29.12,
504
+ "learning_rate": 0.0002,
505
+ "loss": 0.0233,
506
+ "step": 830
507
+ },
508
+ {
509
+ "epoch": 29.47,
510
+ "learning_rate": 0.0002,
511
+ "loss": 0.0085,
512
+ "step": 840
513
+ },
514
+ {
515
+ "epoch": 29.82,
516
+ "learning_rate": 0.0002,
517
+ "loss": 0.0114,
518
+ "step": 850
519
+ },
520
+ {
521
+ "epoch": 30.18,
522
+ "learning_rate": 0.0002,
523
+ "loss": 0.035,
524
+ "step": 860
525
+ },
526
+ {
527
+ "epoch": 30.53,
528
+ "learning_rate": 0.0002,
529
+ "loss": 0.017,
530
+ "step": 870
531
+ },
532
+ {
533
+ "epoch": 30.88,
534
+ "learning_rate": 0.0002,
535
+ "loss": 0.0398,
536
+ "step": 880
537
+ },
538
+ {
539
+ "epoch": 31.23,
540
+ "learning_rate": 0.0002,
541
+ "loss": 0.0101,
542
+ "step": 890
543
+ },
544
+ {
545
+ "epoch": 31.58,
546
+ "learning_rate": 0.0002,
547
+ "loss": 0.0163,
548
+ "step": 900
549
+ },
550
+ {
551
+ "epoch": 31.93,
552
+ "learning_rate": 0.0002,
553
+ "loss": 0.0425,
554
+ "step": 910
555
+ },
556
+ {
557
+ "epoch": 32.28,
558
+ "learning_rate": 0.0002,
559
+ "loss": 0.0319,
560
+ "step": 920
561
+ },
562
+ {
563
+ "epoch": 32.63,
564
+ "learning_rate": 0.0002,
565
+ "loss": 0.0163,
566
+ "step": 930
567
+ },
568
+ {
569
+ "epoch": 32.98,
570
+ "learning_rate": 0.0002,
571
+ "loss": 0.0236,
572
+ "step": 940
573
+ },
574
+ {
575
+ "epoch": 33.33,
576
+ "learning_rate": 0.0002,
577
+ "loss": 0.0255,
578
+ "step": 950
579
+ },
580
+ {
581
+ "epoch": 33.68,
582
+ "learning_rate": 0.0002,
583
+ "loss": 0.0261,
584
+ "step": 960
585
+ },
586
+ {
587
+ "epoch": 34.04,
588
+ "learning_rate": 0.0002,
589
+ "loss": 0.0197,
590
+ "step": 970
591
+ },
592
+ {
593
+ "epoch": 34.39,
594
+ "learning_rate": 0.0002,
595
+ "loss": 0.0323,
596
+ "step": 980
597
+ },
598
+ {
599
+ "epoch": 34.74,
600
+ "learning_rate": 0.0002,
601
+ "loss": 0.0456,
602
+ "step": 990
603
+ },
604
+ {
605
+ "epoch": 35.09,
606
+ "learning_rate": 0.0002,
607
+ "loss": 0.0149,
608
+ "step": 1000
609
+ }
610
+ ],
611
+ "max_steps": 1000,
612
+ "num_train_epochs": 36,
613
+ "total_flos": 8864472152586240.0,
614
+ "trial_name": null,
615
+ "trial_params": null
616
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14508fab61f07162ea1d5164d07e384c785b2aa65470f433e70a0ed93125eb94
3
+ size 6200