Hugging Face's logo

ganghyeon
/
NLP_HW_0

PEFT
Safetensors
Model card Files Community
ganghyeon commited on
Commit
5538283
•
1 Parent(s): e2393b2

Upload fine-tuned Llama model for order analysis

Browse files
Files changed (4) hide show
  1. optimizer.pt +3 -0
  2. rng_state.pth +3 -0
  3. scheduler.pt +3 -0
  4. trainer_state.json +229 -0
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fad6449d5850fc23d58409b38ae7dc42f3bd1ad94828621f7d88b3244f4d267
3
+ size 45276986
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f2ca99e2c5f8daa141e4bca82e3ff3f06813039feda2777d1c1eaa7b0d89f33
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20715e03e6f2f2744bc1fba8c744854dc7b82c89d8238b57676982792c428010
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,229 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 560,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03571428571428571,
13
+ "grad_norm": 1.8447134494781494,
14
+ "learning_rate": 3.571428571428572e-05,
15
+ "loss": 2.5344,
16
+ "step": 20
17
+ },
18
+ {
19
+ "epoch": 0.07142857142857142,
20
+ "grad_norm": 1.3903896808624268,
21
+ "learning_rate": 7.142857142857143e-05,
22
+ "loss": 1.8578,
23
+ "step": 40
24
+ },
25
+ {
26
+ "epoch": 0.10714285714285714,
27
+ "grad_norm": 0.9996151328086853,
28
+ "learning_rate": 9.920634920634922e-05,
29
+ "loss": 1.161,
30
+ "step": 60
31
+ },
32
+ {
33
+ "epoch": 0.14285714285714285,
34
+ "grad_norm": 0.7677631974220276,
35
+ "learning_rate": 9.523809523809524e-05,
36
+ "loss": 0.9116,
37
+ "step": 80
38
+ },
39
+ {
40
+ "epoch": 0.17857142857142858,
41
+ "grad_norm": 1.040696144104004,
42
+ "learning_rate": 9.126984126984128e-05,
43
+ "loss": 0.8243,
44
+ "step": 100
45
+ },
46
+ {
47
+ "epoch": 0.21428571428571427,
48
+ "grad_norm": 0.970762312412262,
49
+ "learning_rate": 8.730158730158731e-05,
50
+ "loss": 0.7555,
51
+ "step": 120
52
+ },
53
+ {
54
+ "epoch": 0.25,
55
+ "grad_norm": 1.0803948640823364,
56
+ "learning_rate": 8.333333333333334e-05,
57
+ "loss": 0.6679,
58
+ "step": 140
59
+ },
60
+ {
61
+ "epoch": 0.2857142857142857,
62
+ "grad_norm": 1.0338200330734253,
63
+ "learning_rate": 7.936507936507937e-05,
64
+ "loss": 0.6522,
65
+ "step": 160
66
+ },
67
+ {
68
+ "epoch": 0.32142857142857145,
69
+ "grad_norm": 0.8714532256126404,
70
+ "learning_rate": 7.53968253968254e-05,
71
+ "loss": 0.6209,
72
+ "step": 180
73
+ },
74
+ {
75
+ "epoch": 0.35714285714285715,
76
+ "grad_norm": 0.9677976965904236,
77
+ "learning_rate": 7.142857142857143e-05,
78
+ "loss": 0.6242,
79
+ "step": 200
80
+ },
81
+ {
82
+ "epoch": 0.39285714285714285,
83
+ "grad_norm": 0.962899386882782,
84
+ "learning_rate": 6.746031746031747e-05,
85
+ "loss": 0.5844,
86
+ "step": 220
87
+ },
88
+ {
89
+ "epoch": 0.42857142857142855,
90
+ "grad_norm": 1.0176018476486206,
91
+ "learning_rate": 6.349206349206349e-05,
92
+ "loss": 0.5915,
93
+ "step": 240
94
+ },
95
+ {
96
+ "epoch": 0.4642857142857143,
97
+ "grad_norm": 0.9592286348342896,
98
+ "learning_rate": 5.9523809523809524e-05,
99
+ "loss": 0.5948,
100
+ "step": 260
101
+ },
102
+ {
103
+ "epoch": 0.5,
104
+ "grad_norm": 0.9406882524490356,
105
+ "learning_rate": 5.555555555555556e-05,
106
+ "loss": 0.5557,
107
+ "step": 280
108
+ },
109
+ {
110
+ "epoch": 0.5357142857142857,
111
+ "grad_norm": 1.0566672086715698,
112
+ "learning_rate": 5.158730158730159e-05,
113
+ "loss": 0.5596,
114
+ "step": 300
115
+ },
116
+ {
117
+ "epoch": 0.5714285714285714,
118
+ "grad_norm": 1.0166610479354858,
119
+ "learning_rate": 4.761904761904762e-05,
120
+ "loss": 0.5514,
121
+ "step": 320
122
+ },
123
+ {
124
+ "epoch": 0.6071428571428571,
125
+ "grad_norm": 1.110986590385437,
126
+ "learning_rate": 4.3650793650793655e-05,
127
+ "loss": 0.5523,
128
+ "step": 340
129
+ },
130
+ {
131
+ "epoch": 0.6428571428571429,
132
+ "grad_norm": 1.1951007843017578,
133
+ "learning_rate": 3.968253968253968e-05,
134
+ "loss": 0.5395,
135
+ "step": 360
136
+ },
137
+ {
138
+ "epoch": 0.6785714285714286,
139
+ "grad_norm": 1.0911144018173218,
140
+ "learning_rate": 3.571428571428572e-05,
141
+ "loss": 0.548,
142
+ "step": 380
143
+ },
144
+ {
145
+ "epoch": 0.7142857142857143,
146
+ "grad_norm": 1.1718319654464722,
147
+ "learning_rate": 3.1746031746031745e-05,
148
+ "loss": 0.5188,
149
+ "step": 400
150
+ },
151
+ {
152
+ "epoch": 0.75,
153
+ "grad_norm": 0.9721041917800903,
154
+ "learning_rate": 2.777777777777778e-05,
155
+ "loss": 0.5081,
156
+ "step": 420
157
+ },
158
+ {
159
+ "epoch": 0.7857142857142857,
160
+ "grad_norm": 1.103784203529358,
161
+ "learning_rate": 2.380952380952381e-05,
162
+ "loss": 0.5183,
163
+ "step": 440
164
+ },
165
+ {
166
+ "epoch": 0.8214285714285714,
167
+ "grad_norm": 1.1778147220611572,
168
+ "learning_rate": 1.984126984126984e-05,
169
+ "loss": 0.5064,
170
+ "step": 460
171
+ },
172
+ {
173
+ "epoch": 0.8571428571428571,
174
+ "grad_norm": 1.0783812999725342,
175
+ "learning_rate": 1.5873015873015872e-05,
176
+ "loss": 0.527,
177
+ "step": 480
178
+ },
179
+ {
180
+ "epoch": 0.8928571428571429,
181
+ "grad_norm": 1.0787134170532227,
182
+ "learning_rate": 1.1904761904761905e-05,
183
+ "loss": 0.5132,
184
+ "step": 500
185
+ },
186
+ {
187
+ "epoch": 0.9285714285714286,
188
+ "grad_norm": 1.0964124202728271,
189
+ "learning_rate": 7.936507936507936e-06,
190
+ "loss": 0.4971,
191
+ "step": 520
192
+ },
193
+ {
194
+ "epoch": 0.9642857142857143,
195
+ "grad_norm": 1.1419587135314941,
196
+ "learning_rate": 3.968253968253968e-06,
197
+ "loss": 0.5368,
198
+ "step": 540
199
+ },
200
+ {
201
+ "epoch": 1.0,
202
+ "grad_norm": 1.0203648805618286,
203
+ "learning_rate": 0.0,
204
+ "loss": 0.501,
205
+ "step": 560
206
+ }
207
+ ],
208
+ "logging_steps": 20,
209
+ "max_steps": 560,
210
+ "num_input_tokens_seen": 0,
211
+ "num_train_epochs": 1,
212
+ "save_steps": 50,
213
+ "stateful_callbacks": {
214
+ "TrainerControl": {
215
+ "args": {
216
+ "should_epoch_stop": false,
217
+ "should_evaluate": false,
218
+ "should_log": false,
219
+ "should_save": true,
220
+ "should_training_stop": true
221
+ },
222
+ "attributes": {}
223
+ }
224
+ },
225
+ "total_flos": 8419093040332800.0,
226
+ "train_batch_size": 5,
227
+ "trial_name": null,
228
+ "trial_params": null
229
+ }