MaruchanPark commited on
Commit
f43ca49
1 Parent(s): 283c4b3
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/KonanLLM-peft-train-serving/model/kylin-7b-chat-2406-v2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7c8c5689f6d0c54af75f69b7c7d4e70a1df14cf7d27b39fe30ce635c2a21a4d
3
+ size 6832728
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86052738ddbd1f67a03f20ed189ddb89f2b7ea19879f9fb7f429e298f92fbfeb
3
+ size 13738693
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ae2bc7c0ba6650d2e269643a01954663ce1d8e27edf4c2de2269f488c94882e
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e49e6c54a6616f96e8fa4a7eaf8c40cf787e5446bb7075cfc92fd89425df17b9
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": "<unk>"
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32000": {
30
+ "content": "<|tel|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "32001": {
38
+ "content": "<|rnn|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "32002": {
46
+ "content": "<|email|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "32003": {
54
+ "content": "<|crd|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "32004": {
62
+ "content": "<|acc|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "51510": {
70
+ "content": "<|im_start|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "51511": {
78
+ "content": "<|im_end|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ }
85
+ },
86
+ "bos_token": "<s>",
87
+ "chat_template": "{{('<|im_start|>assistant\n' + messages[0]['content'].strip() + '<|im_end|>' + '\n' if messages[0]['role'] == 'system' else '')}}{% for message in (messages[1:] if messages[0]['role'] == 'system' else messages) %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>' + '\n' + '<|im_start|>assistant\n'}}{% elif message['role'] == 'assistant' %}{{message['content']}}{% if loop.last %}{% if add_generation_prompt %}{{'<|im_end|>'}}{% endif %}{% else %}{{'<|im_end|>'}}{% endif %}{% endif %}{% endfor %}",
88
+ "clean_up_tokenization_spaces": true,
89
+ "eos_token": "</s>",
90
+ "legacy": true,
91
+ "model_max_length": 1000000000000000019884624838656,
92
+ "model_name": "kylin-7b",
93
+ "pad_token": "</s>",
94
+ "tokenizer_class": "LlamaTokenizer",
95
+ "unk_token": "<unk>",
96
+ "use_default_system_prompt": false
97
+ }
trainer_state.json ADDED
@@ -0,0 +1,1139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1580,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03164556962025317,
13
+ "grad_norm": 0.0072021484375,
14
+ "learning_rate": 0.0002,
15
+ "loss": 0.0019,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.06329113924050633,
20
+ "grad_norm": 0.01226806640625,
21
+ "learning_rate": 0.0002,
22
+ "loss": 0.0012,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.0949367088607595,
27
+ "grad_norm": 0.013427734375,
28
+ "learning_rate": 0.0002,
29
+ "loss": 0.0016,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.12658227848101267,
34
+ "grad_norm": 0.004791259765625,
35
+ "learning_rate": 0.0002,
36
+ "loss": 0.0037,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.15822784810126583,
41
+ "grad_norm": 0.00787353515625,
42
+ "learning_rate": 0.0002,
43
+ "loss": 0.0015,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.189873417721519,
48
+ "grad_norm": 0.0164794921875,
49
+ "learning_rate": 0.0002,
50
+ "loss": 0.0023,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.22151898734177214,
55
+ "grad_norm": 0.0019989013671875,
56
+ "learning_rate": 0.0002,
57
+ "loss": 0.0017,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.25316455696202533,
62
+ "grad_norm": 0.043701171875,
63
+ "learning_rate": 0.0002,
64
+ "loss": 0.0018,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.2848101265822785,
69
+ "grad_norm": 0.04150390625,
70
+ "learning_rate": 0.0002,
71
+ "loss": 0.0012,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.31645569620253167,
76
+ "grad_norm": 0.0126953125,
77
+ "learning_rate": 0.0002,
78
+ "loss": 0.0016,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.34810126582278483,
83
+ "grad_norm": 0.0299072265625,
84
+ "learning_rate": 0.0002,
85
+ "loss": 0.0017,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.379746835443038,
90
+ "grad_norm": 0.017333984375,
91
+ "learning_rate": 0.0002,
92
+ "loss": 0.0021,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.41139240506329117,
97
+ "grad_norm": 0.0284423828125,
98
+ "learning_rate": 0.0002,
99
+ "loss": 0.004,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.4430379746835443,
104
+ "grad_norm": 0.0228271484375,
105
+ "learning_rate": 0.0002,
106
+ "loss": 0.0015,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.47468354430379744,
111
+ "grad_norm": 0.0216064453125,
112
+ "learning_rate": 0.0002,
113
+ "loss": 0.0012,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.5063291139240507,
118
+ "grad_norm": 0.0079345703125,
119
+ "learning_rate": 0.0002,
120
+ "loss": 0.0017,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.5379746835443038,
125
+ "grad_norm": 0.03564453125,
126
+ "learning_rate": 0.0002,
127
+ "loss": 0.0007,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.569620253164557,
132
+ "grad_norm": 0.0859375,
133
+ "learning_rate": 0.0002,
134
+ "loss": 0.0016,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.6012658227848101,
139
+ "grad_norm": 0.0014801025390625,
140
+ "learning_rate": 0.0002,
141
+ "loss": 0.0013,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.6329113924050633,
146
+ "grad_norm": 0.02734375,
147
+ "learning_rate": 0.0002,
148
+ "loss": 0.0015,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.6645569620253164,
153
+ "grad_norm": 0.00836181640625,
154
+ "learning_rate": 0.0002,
155
+ "loss": 0.0012,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.6962025316455697,
160
+ "grad_norm": 0.0218505859375,
161
+ "learning_rate": 0.0002,
162
+ "loss": 0.0012,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.7278481012658228,
167
+ "grad_norm": 0.00799560546875,
168
+ "learning_rate": 0.0002,
169
+ "loss": 0.0013,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.759493670886076,
174
+ "grad_norm": 0.0478515625,
175
+ "learning_rate": 0.0002,
176
+ "loss": 0.003,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.7911392405063291,
181
+ "grad_norm": 0.091796875,
182
+ "learning_rate": 0.0002,
183
+ "loss": 0.0008,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.8227848101265823,
188
+ "grad_norm": 0.0218505859375,
189
+ "learning_rate": 0.0002,
190
+ "loss": 0.0008,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.8544303797468354,
195
+ "grad_norm": 0.006317138671875,
196
+ "learning_rate": 0.0002,
197
+ "loss": 0.0009,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.8860759493670886,
202
+ "grad_norm": 0.034912109375,
203
+ "learning_rate": 0.0002,
204
+ "loss": 0.0016,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.9177215189873418,
209
+ "grad_norm": 0.0115966796875,
210
+ "learning_rate": 0.0002,
211
+ "loss": 0.0005,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.9493670886075949,
216
+ "grad_norm": 0.04296875,
217
+ "learning_rate": 0.0002,
218
+ "loss": 0.0027,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.9810126582278481,
223
+ "grad_norm": 0.0277099609375,
224
+ "learning_rate": 0.0002,
225
+ "loss": 0.0008,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 1.0126582278481013,
230
+ "grad_norm": 0.0240478515625,
231
+ "learning_rate": 0.0002,
232
+ "loss": 0.001,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 1.0443037974683544,
237
+ "grad_norm": 0.0078125,
238
+ "learning_rate": 0.0002,
239
+ "loss": 0.0042,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 1.0759493670886076,
244
+ "grad_norm": 0.0047607421875,
245
+ "learning_rate": 0.0002,
246
+ "loss": 0.0006,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 1.1075949367088607,
251
+ "grad_norm": 0.007598876953125,
252
+ "learning_rate": 0.0002,
253
+ "loss": 0.0011,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 1.139240506329114,
258
+ "grad_norm": 0.00665283203125,
259
+ "learning_rate": 0.0002,
260
+ "loss": 0.0006,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 1.1708860759493671,
265
+ "grad_norm": 0.00445556640625,
266
+ "learning_rate": 0.0002,
267
+ "loss": 0.0005,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 1.2025316455696202,
272
+ "grad_norm": 0.004364013671875,
273
+ "learning_rate": 0.0002,
274
+ "loss": 0.0006,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 1.2341772151898733,
279
+ "grad_norm": 0.003662109375,
280
+ "learning_rate": 0.0002,
281
+ "loss": 0.0005,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 1.2658227848101267,
286
+ "grad_norm": 0.020263671875,
287
+ "learning_rate": 0.0002,
288
+ "loss": 0.0008,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 1.2974683544303798,
293
+ "grad_norm": 0.008544921875,
294
+ "learning_rate": 0.0002,
295
+ "loss": 0.0009,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 1.3291139240506329,
300
+ "grad_norm": 0.0140380859375,
301
+ "learning_rate": 0.0002,
302
+ "loss": 0.0015,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 1.360759493670886,
307
+ "grad_norm": 0.00616455078125,
308
+ "learning_rate": 0.0002,
309
+ "loss": 0.001,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 1.3924050632911391,
314
+ "grad_norm": 0.00506591796875,
315
+ "learning_rate": 0.0002,
316
+ "loss": 0.0004,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 1.4240506329113924,
321
+ "grad_norm": 0.041748046875,
322
+ "learning_rate": 0.0002,
323
+ "loss": 0.0008,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 1.4556962025316456,
328
+ "grad_norm": 0.0849609375,
329
+ "learning_rate": 0.0002,
330
+ "loss": 0.0011,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 1.4873417721518987,
335
+ "grad_norm": 0.01495361328125,
336
+ "learning_rate": 0.0002,
337
+ "loss": 0.001,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 1.518987341772152,
342
+ "grad_norm": 0.007110595703125,
343
+ "learning_rate": 0.0002,
344
+ "loss": 0.0006,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 1.5506329113924051,
349
+ "grad_norm": 0.005401611328125,
350
+ "learning_rate": 0.0002,
351
+ "loss": 0.0006,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 1.5822784810126582,
356
+ "grad_norm": 0.0084228515625,
357
+ "learning_rate": 0.0002,
358
+ "loss": 0.0006,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 1.6139240506329116,
363
+ "grad_norm": 0.01123046875,
364
+ "learning_rate": 0.0002,
365
+ "loss": 0.0006,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 1.6455696202531644,
370
+ "grad_norm": 0.00970458984375,
371
+ "learning_rate": 0.0002,
372
+ "loss": 0.0008,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 1.6772151898734178,
377
+ "grad_norm": 0.00665283203125,
378
+ "learning_rate": 0.0002,
379
+ "loss": 0.0005,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 1.7088607594936709,
384
+ "grad_norm": 0.00506591796875,
385
+ "learning_rate": 0.0002,
386
+ "loss": 0.001,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 1.740506329113924,
391
+ "grad_norm": 0.0205078125,
392
+ "learning_rate": 0.0002,
393
+ "loss": 0.0005,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 1.7721518987341773,
398
+ "grad_norm": 0.04052734375,
399
+ "learning_rate": 0.0002,
400
+ "loss": 0.0011,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 1.8037974683544302,
405
+ "grad_norm": 0.0179443359375,
406
+ "learning_rate": 0.0002,
407
+ "loss": 0.0007,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 1.8354430379746836,
412
+ "grad_norm": 0.0145263671875,
413
+ "learning_rate": 0.0002,
414
+ "loss": 0.0009,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 1.8670886075949367,
419
+ "grad_norm": 0.004913330078125,
420
+ "learning_rate": 0.0002,
421
+ "loss": 0.0004,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 1.8987341772151898,
426
+ "grad_norm": 0.014404296875,
427
+ "learning_rate": 0.0002,
428
+ "loss": 0.0007,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 1.9303797468354431,
433
+ "grad_norm": 0.005126953125,
434
+ "learning_rate": 0.0002,
435
+ "loss": 0.0005,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 1.9620253164556962,
440
+ "grad_norm": 0.00390625,
441
+ "learning_rate": 0.0002,
442
+ "loss": 0.001,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 1.9936708860759493,
447
+ "grad_norm": 0.0020904541015625,
448
+ "learning_rate": 0.0002,
449
+ "loss": 0.0006,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 2.0253164556962027,
454
+ "grad_norm": 0.00102996826171875,
455
+ "learning_rate": 0.0002,
456
+ "loss": 0.0006,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 2.0569620253164556,
461
+ "grad_norm": 0.0079345703125,
462
+ "learning_rate": 0.0002,
463
+ "loss": 0.0005,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 2.088607594936709,
468
+ "grad_norm": 0.004058837890625,
469
+ "learning_rate": 0.0002,
470
+ "loss": 0.0004,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 2.1202531645569622,
475
+ "grad_norm": 0.006683349609375,
476
+ "learning_rate": 0.0002,
477
+ "loss": 0.0004,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 2.151898734177215,
482
+ "grad_norm": 0.00799560546875,
483
+ "learning_rate": 0.0002,
484
+ "loss": 0.0007,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 2.1835443037974684,
489
+ "grad_norm": 0.01416015625,
490
+ "learning_rate": 0.0002,
491
+ "loss": 0.0008,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 2.2151898734177213,
496
+ "grad_norm": 0.005523681640625,
497
+ "learning_rate": 0.0002,
498
+ "loss": 0.0005,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 2.2468354430379747,
503
+ "grad_norm": 0.003692626953125,
504
+ "learning_rate": 0.0002,
505
+ "loss": 0.0006,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 2.278481012658228,
510
+ "grad_norm": 0.01287841796875,
511
+ "learning_rate": 0.0002,
512
+ "loss": 0.0004,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 2.310126582278481,
517
+ "grad_norm": 0.0101318359375,
518
+ "learning_rate": 0.0002,
519
+ "loss": 0.0004,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 2.3417721518987342,
524
+ "grad_norm": 0.006866455078125,
525
+ "learning_rate": 0.0002,
526
+ "loss": 0.0005,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 2.3734177215189876,
531
+ "grad_norm": 0.00921630859375,
532
+ "learning_rate": 0.0002,
533
+ "loss": 0.0004,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 2.4050632911392404,
538
+ "grad_norm": 0.0072021484375,
539
+ "learning_rate": 0.0002,
540
+ "loss": 0.0003,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 2.4367088607594938,
545
+ "grad_norm": 0.00921630859375,
546
+ "learning_rate": 0.0002,
547
+ "loss": 0.0003,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 2.4683544303797467,
552
+ "grad_norm": 0.01239013671875,
553
+ "learning_rate": 0.0002,
554
+ "loss": 0.0004,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 2.5,
559
+ "grad_norm": 0.01226806640625,
560
+ "learning_rate": 0.0002,
561
+ "loss": 0.0004,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 2.5316455696202533,
566
+ "grad_norm": 0.00872802734375,
567
+ "learning_rate": 0.0002,
568
+ "loss": 0.0004,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 2.5632911392405062,
573
+ "grad_norm": 0.007781982421875,
574
+ "learning_rate": 0.0002,
575
+ "loss": 0.0008,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 2.5949367088607596,
580
+ "grad_norm": 0.005767822265625,
581
+ "learning_rate": 0.0002,
582
+ "loss": 0.0004,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 2.6265822784810124,
587
+ "grad_norm": 0.0111083984375,
588
+ "learning_rate": 0.0002,
589
+ "loss": 0.0004,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 2.6582278481012658,
594
+ "grad_norm": 0.0157470703125,
595
+ "learning_rate": 0.0002,
596
+ "loss": 0.0007,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 2.689873417721519,
601
+ "grad_norm": 0.0111083984375,
602
+ "learning_rate": 0.0002,
603
+ "loss": 0.0008,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 2.721518987341772,
608
+ "grad_norm": 0.009521484375,
609
+ "learning_rate": 0.0002,
610
+ "loss": 0.0006,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 2.7531645569620253,
615
+ "grad_norm": 0.0018463134765625,
616
+ "learning_rate": 0.0002,
617
+ "loss": 0.0002,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 2.7848101265822782,
622
+ "grad_norm": 0.00168609619140625,
623
+ "learning_rate": 0.0002,
624
+ "loss": 0.0006,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 2.8164556962025316,
629
+ "grad_norm": 0.01470947265625,
630
+ "learning_rate": 0.0002,
631
+ "loss": 0.0004,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 2.848101265822785,
636
+ "grad_norm": 0.0211181640625,
637
+ "learning_rate": 0.0002,
638
+ "loss": 0.0004,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 2.879746835443038,
643
+ "grad_norm": 0.0057373046875,
644
+ "learning_rate": 0.0002,
645
+ "loss": 0.0017,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 2.911392405063291,
650
+ "grad_norm": 0.00469970703125,
651
+ "learning_rate": 0.0002,
652
+ "loss": 0.0022,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 2.9430379746835444,
657
+ "grad_norm": 0.00982666015625,
658
+ "learning_rate": 0.0002,
659
+ "loss": 0.0006,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 2.9746835443037973,
664
+ "grad_norm": 0.0087890625,
665
+ "learning_rate": 0.0002,
666
+ "loss": 0.0003,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 3.0063291139240507,
671
+ "grad_norm": 0.0098876953125,
672
+ "learning_rate": 0.0002,
673
+ "loss": 0.0004,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 3.037974683544304,
678
+ "grad_norm": 0.00360107421875,
679
+ "learning_rate": 0.0002,
680
+ "loss": 0.0004,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 3.069620253164557,
685
+ "grad_norm": 0.0150146484375,
686
+ "learning_rate": 0.0002,
687
+ "loss": 0.0007,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 3.1012658227848102,
692
+ "grad_norm": 0.005828857421875,
693
+ "learning_rate": 0.0002,
694
+ "loss": 0.0004,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 3.132911392405063,
699
+ "grad_norm": 0.00665283203125,
700
+ "learning_rate": 0.0002,
701
+ "loss": 0.0004,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 3.1645569620253164,
706
+ "grad_norm": 0.005401611328125,
707
+ "learning_rate": 0.0002,
708
+ "loss": 0.0003,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 3.1962025316455698,
713
+ "grad_norm": 0.0216064453125,
714
+ "learning_rate": 0.0002,
715
+ "loss": 0.0006,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 3.2278481012658227,
720
+ "grad_norm": 0.0152587890625,
721
+ "learning_rate": 0.0002,
722
+ "loss": 0.0006,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 3.259493670886076,
727
+ "grad_norm": 0.0096435546875,
728
+ "learning_rate": 0.0002,
729
+ "loss": 0.0003,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 3.291139240506329,
734
+ "grad_norm": 0.007232666015625,
735
+ "learning_rate": 0.0002,
736
+ "loss": 0.0003,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 3.3227848101265822,
741
+ "grad_norm": 0.006439208984375,
742
+ "learning_rate": 0.0002,
743
+ "loss": 0.0003,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 3.3544303797468356,
748
+ "grad_norm": 0.003692626953125,
749
+ "learning_rate": 0.0002,
750
+ "loss": 0.0005,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 3.3860759493670884,
755
+ "grad_norm": 0.0028839111328125,
756
+ "learning_rate": 0.0002,
757
+ "loss": 0.0004,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 3.4177215189873418,
762
+ "grad_norm": 0.005859375,
763
+ "learning_rate": 0.0002,
764
+ "loss": 0.0003,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 3.449367088607595,
769
+ "grad_norm": 0.0067138671875,
770
+ "learning_rate": 0.0002,
771
+ "loss": 0.0004,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 3.481012658227848,
776
+ "grad_norm": 0.007171630859375,
777
+ "learning_rate": 0.0002,
778
+ "loss": 0.0003,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 3.5126582278481013,
783
+ "grad_norm": 0.00537109375,
784
+ "learning_rate": 0.0002,
785
+ "loss": 0.0003,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 3.5443037974683547,
790
+ "grad_norm": 0.00775146484375,
791
+ "learning_rate": 0.0002,
792
+ "loss": 0.0004,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 3.5759493670886076,
797
+ "grad_norm": 0.0030517578125,
798
+ "learning_rate": 0.0002,
799
+ "loss": 0.0003,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 3.607594936708861,
804
+ "grad_norm": 0.00823974609375,
805
+ "learning_rate": 0.0002,
806
+ "loss": 0.0004,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 3.6392405063291138,
811
+ "grad_norm": 0.005157470703125,
812
+ "learning_rate": 0.0002,
813
+ "loss": 0.0003,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 3.670886075949367,
818
+ "grad_norm": 0.01202392578125,
819
+ "learning_rate": 0.0002,
820
+ "loss": 0.0009,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 3.7025316455696204,
825
+ "grad_norm": 0.0233154296875,
826
+ "learning_rate": 0.0002,
827
+ "loss": 0.0004,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 3.7341772151898733,
832
+ "grad_norm": 0.005218505859375,
833
+ "learning_rate": 0.0002,
834
+ "loss": 0.0004,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 3.7658227848101267,
839
+ "grad_norm": 0.0108642578125,
840
+ "learning_rate": 0.0002,
841
+ "loss": 0.0004,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 3.7974683544303796,
846
+ "grad_norm": 0.0086669921875,
847
+ "learning_rate": 0.0002,
848
+ "loss": 0.0006,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 3.829113924050633,
853
+ "grad_norm": 0.002685546875,
854
+ "learning_rate": 0.0002,
855
+ "loss": 0.0003,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 3.8607594936708862,
860
+ "grad_norm": 0.0019683837890625,
861
+ "learning_rate": 0.0002,
862
+ "loss": 0.0002,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 3.892405063291139,
867
+ "grad_norm": 0.0020294189453125,
868
+ "learning_rate": 0.0002,
869
+ "loss": 0.0005,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 3.9240506329113924,
874
+ "grad_norm": 0.003509521484375,
875
+ "learning_rate": 0.0002,
876
+ "loss": 0.0002,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 3.9556962025316453,
881
+ "grad_norm": 0.004486083984375,
882
+ "learning_rate": 0.0002,
883
+ "loss": 0.0003,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 3.9873417721518987,
888
+ "grad_norm": 0.0034637451171875,
889
+ "learning_rate": 0.0002,
890
+ "loss": 0.0003,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 4.018987341772152,
895
+ "grad_norm": 0.0031890869140625,
896
+ "learning_rate": 0.0002,
897
+ "loss": 0.0002,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 4.050632911392405,
902
+ "grad_norm": 0.0036163330078125,
903
+ "learning_rate": 0.0002,
904
+ "loss": 0.0003,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 4.082278481012658,
909
+ "grad_norm": 0.01055908203125,
910
+ "learning_rate": 0.0002,
911
+ "loss": 0.0003,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 4.113924050632911,
916
+ "grad_norm": 0.00188446044921875,
917
+ "learning_rate": 0.0002,
918
+ "loss": 0.0002,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 4.1455696202531644,
923
+ "grad_norm": 0.0029296875,
924
+ "learning_rate": 0.0002,
925
+ "loss": 0.0004,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 4.177215189873418,
930
+ "grad_norm": 0.00167083740234375,
931
+ "learning_rate": 0.0002,
932
+ "loss": 0.0004,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 4.208860759493671,
937
+ "grad_norm": 0.005584716796875,
938
+ "learning_rate": 0.0002,
939
+ "loss": 0.0004,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 4.2405063291139244,
944
+ "grad_norm": 0.007171630859375,
945
+ "learning_rate": 0.0002,
946
+ "loss": 0.0002,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 4.272151898734177,
951
+ "grad_norm": 0.004119873046875,
952
+ "learning_rate": 0.0002,
953
+ "loss": 0.0002,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 4.30379746835443,
958
+ "grad_norm": 0.00543212890625,
959
+ "learning_rate": 0.0002,
960
+ "loss": 0.0003,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 4.3354430379746836,
965
+ "grad_norm": 0.00860595703125,
966
+ "learning_rate": 0.0002,
967
+ "loss": 0.0004,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 4.367088607594937,
972
+ "grad_norm": 0.0130615234375,
973
+ "learning_rate": 0.0002,
974
+ "loss": 0.0003,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 4.39873417721519,
979
+ "grad_norm": 0.0074462890625,
980
+ "learning_rate": 0.0002,
981
+ "loss": 0.0002,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 4.430379746835443,
986
+ "grad_norm": 0.00384521484375,
987
+ "learning_rate": 0.0002,
988
+ "loss": 0.0003,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 4.462025316455696,
993
+ "grad_norm": 0.0106201171875,
994
+ "learning_rate": 0.0002,
995
+ "loss": 0.0004,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 4.493670886075949,
1000
+ "grad_norm": 0.0027618408203125,
1001
+ "learning_rate": 0.0002,
1002
+ "loss": 0.0002,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 4.525316455696203,
1007
+ "grad_norm": 0.00555419921875,
1008
+ "learning_rate": 0.0002,
1009
+ "loss": 0.0002,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 4.556962025316456,
1014
+ "grad_norm": 0.006011962890625,
1015
+ "learning_rate": 0.0002,
1016
+ "loss": 0.0003,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 4.588607594936709,
1021
+ "grad_norm": 0.006256103515625,
1022
+ "learning_rate": 0.0002,
1023
+ "loss": 0.0002,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 4.620253164556962,
1028
+ "grad_norm": 0.003997802734375,
1029
+ "learning_rate": 0.0002,
1030
+ "loss": 0.0003,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 4.651898734177215,
1035
+ "grad_norm": 0.006744384765625,
1036
+ "learning_rate": 0.0002,
1037
+ "loss": 0.0003,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 4.6835443037974684,
1042
+ "grad_norm": 0.00836181640625,
1043
+ "learning_rate": 0.0002,
1044
+ "loss": 0.0005,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 4.715189873417722,
1049
+ "grad_norm": 0.0076904296875,
1050
+ "learning_rate": 0.0002,
1051
+ "loss": 0.0003,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 4.746835443037975,
1056
+ "grad_norm": 0.01239013671875,
1057
+ "learning_rate": 0.0002,
1058
+ "loss": 0.0003,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 4.7784810126582276,
1063
+ "grad_norm": 0.00146484375,
1064
+ "learning_rate": 0.0002,
1065
+ "loss": 0.0007,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 4.810126582278481,
1070
+ "grad_norm": 0.00909423828125,
1071
+ "learning_rate": 0.0002,
1072
+ "loss": 0.0003,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 4.841772151898734,
1077
+ "grad_norm": 0.0133056640625,
1078
+ "learning_rate": 0.0002,
1079
+ "loss": 0.0003,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 4.8734177215189876,
1084
+ "grad_norm": 0.00360107421875,
1085
+ "learning_rate": 0.0002,
1086
+ "loss": 0.0003,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 4.905063291139241,
1091
+ "grad_norm": 0.00799560546875,
1092
+ "learning_rate": 0.0002,
1093
+ "loss": 0.0003,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 4.936708860759493,
1098
+ "grad_norm": 0.0047607421875,
1099
+ "learning_rate": 0.0002,
1100
+ "loss": 0.0003,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 4.968354430379747,
1105
+ "grad_norm": 0.00157928466796875,
1106
+ "learning_rate": 0.0002,
1107
+ "loss": 0.0003,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 5.0,
1112
+ "grad_norm": 0.0101318359375,
1113
+ "learning_rate": 0.0002,
1114
+ "loss": 0.0003,
1115
+ "step": 1580
1116
+ }
1117
+ ],
1118
+ "logging_steps": 10,
1119
+ "max_steps": 1580,
1120
+ "num_input_tokens_seen": 0,
1121
+ "num_train_epochs": 5,
1122
+ "save_steps": 500,
1123
+ "stateful_callbacks": {
1124
+ "TrainerControl": {
1125
+ "args": {
1126
+ "should_epoch_stop": false,
1127
+ "should_evaluate": false,
1128
+ "should_log": false,
1129
+ "should_save": true,
1130
+ "should_training_stop": true
1131
+ },
1132
+ "attributes": {}
1133
+ }
1134
+ },
1135
+ "total_flos": 3.151495561120973e+17,
1136
+ "train_batch_size": 4,
1137
+ "trial_name": null,
1138
+ "trial_params": null
1139
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b416a7cdaae4669e6b55c4b65a6c90fe81e4ebe506af5ef36ed892b2ba782ab7
3
+ size 4987