Yida commited on
Commit
8d46238
·
verified ·
1 Parent(s): 57cd3ef

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. head.pt +3 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +270 -0
  7. training_args.bin +3 -0
head.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5a0a8bb9cf2ee752d9170af4b86d2c2d763a659c0e7e6862cbe99c1a70a0efd
3
+ size 34182
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e733d6a0564c7b754ba39394b02755e8dac07c884cc6a65e75945e8f4feef1f7
3
+ size 15177759456
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd9ada6c4f72947060fa276813d168a860cccf3cc8cc591c20daef03bf554fde
3
+ size 335989656
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ad5de38127f4a19fb8dbaf81916557b7a1d548c8559dc72f0ee366ec2c1563
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c8d5b56fb7354e84bd343528e0612a2d3e81ab6cdf2990d2590a2a362b6ebef
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,270 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 15000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1,
13
+ "grad_norm": 31.439960479736328,
14
+ "learning_rate": 1.6666666666666667e-05,
15
+ "loss": 1.3922,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.2,
20
+ "grad_norm": 2.689053535461426,
21
+ "learning_rate": 3.3333333333333335e-05,
22
+ "loss": 0.6572,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.3,
27
+ "grad_norm": 9.427984237670898,
28
+ "learning_rate": 5e-05,
29
+ "loss": 0.5827,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.4,
34
+ "grad_norm": 12.102423667907715,
35
+ "learning_rate": 4.983095894354858e-05,
36
+ "loss": 0.5335,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.5,
41
+ "grad_norm": 13.714262008666992,
42
+ "learning_rate": 4.9326121764495596e-05,
43
+ "loss": 0.51,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.6,
48
+ "grad_norm": 13.829536437988281,
49
+ "learning_rate": 4.849231551964771e-05,
50
+ "loss": 0.4889,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.7,
55
+ "grad_norm": 18.672182083129883,
56
+ "learning_rate": 4.734081600808531e-05,
57
+ "loss": 0.4614,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.8,
62
+ "grad_norm": 16.94382667541504,
63
+ "learning_rate": 4.588719528532342e-05,
64
+ "loss": 0.4214,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.9,
69
+ "grad_norm": 13.588418960571289,
70
+ "learning_rate": 4.415111107797445e-05,
71
+ "loss": 0.4399,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 1.0,
76
+ "grad_norm": 12.39639949798584,
77
+ "learning_rate": 4.215604094671835e-05,
78
+ "loss": 0.4323,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 1.0,
83
+ "eval_accuracy": 0.83475,
84
+ "eval_loss": 0.4028127193450928,
85
+ "eval_runtime": 224.488,
86
+ "eval_samples_per_second": 17.818,
87
+ "eval_steps_per_second": 2.227,
88
+ "step": 5000
89
+ },
90
+ {
91
+ "epoch": 1.1,
92
+ "grad_norm": 19.143348693847656,
93
+ "learning_rate": 3.9928964792569655e-05,
94
+ "loss": 0.3163,
95
+ "step": 5500
96
+ },
97
+ {
98
+ "epoch": 1.2,
99
+ "grad_norm": 22.87167739868164,
100
+ "learning_rate": 3.7500000000000003e-05,
101
+ "loss": 0.333,
102
+ "step": 6000
103
+ },
104
+ {
105
+ "epoch": 1.3,
106
+ "grad_norm": 2.1354031562805176,
107
+ "learning_rate": 3.490199415097892e-05,
108
+ "loss": 0.3329,
109
+ "step": 6500
110
+ },
111
+ {
112
+ "epoch": 1.4,
113
+ "grad_norm": 21.64975357055664,
114
+ "learning_rate": 3.217008081777726e-05,
115
+ "loss": 0.327,
116
+ "step": 7000
117
+ },
118
+ {
119
+ "epoch": 1.5,
120
+ "grad_norm": 15.015271186828613,
121
+ "learning_rate": 2.9341204441673266e-05,
122
+ "loss": 0.307,
123
+ "step": 7500
124
+ },
125
+ {
126
+ "epoch": 1.6,
127
+ "grad_norm": 7.016956329345703,
128
+ "learning_rate": 2.6453620722761896e-05,
129
+ "loss": 0.3177,
130
+ "step": 8000
131
+ },
132
+ {
133
+ "epoch": 1.7,
134
+ "grad_norm": 7.591048240661621,
135
+ "learning_rate": 2.3546379277238107e-05,
136
+ "loss": 0.289,
137
+ "step": 8500
138
+ },
139
+ {
140
+ "epoch": 1.8,
141
+ "grad_norm": 89.22419738769531,
142
+ "learning_rate": 2.0658795558326743e-05,
143
+ "loss": 0.3074,
144
+ "step": 9000
145
+ },
146
+ {
147
+ "epoch": 1.9,
148
+ "grad_norm": 1.194404125213623,
149
+ "learning_rate": 1.7829919182222752e-05,
150
+ "loss": 0.2857,
151
+ "step": 9500
152
+ },
153
+ {
154
+ "epoch": 2.0,
155
+ "grad_norm": 6.9914679527282715,
156
+ "learning_rate": 1.509800584902108e-05,
157
+ "loss": 0.2904,
158
+ "step": 10000
159
+ },
160
+ {
161
+ "epoch": 2.0,
162
+ "eval_accuracy": 0.87,
163
+ "eval_loss": 0.534140408039093,
164
+ "eval_runtime": 224.6782,
165
+ "eval_samples_per_second": 17.803,
166
+ "eval_steps_per_second": 2.225,
167
+ "step": 10000
168
+ },
169
+ {
170
+ "epoch": 2.1,
171
+ "grad_norm": 95.4480972290039,
172
+ "learning_rate": 1.2500000000000006e-05,
173
+ "loss": 0.0852,
174
+ "step": 10500
175
+ },
176
+ {
177
+ "epoch": 2.2,
178
+ "grad_norm": 52.108890533447266,
179
+ "learning_rate": 1.0071035207430352e-05,
180
+ "loss": 0.1166,
181
+ "step": 11000
182
+ },
183
+ {
184
+ "epoch": 2.3,
185
+ "grad_norm": 0.004855601117014885,
186
+ "learning_rate": 7.843959053281663e-06,
187
+ "loss": 0.1055,
188
+ "step": 11500
189
+ },
190
+ {
191
+ "epoch": 2.4,
192
+ "grad_norm": 0.0002819446672219783,
193
+ "learning_rate": 5.848888922025553e-06,
194
+ "loss": 0.0829,
195
+ "step": 12000
196
+ },
197
+ {
198
+ "epoch": 2.5,
199
+ "grad_norm": 0.0005901407566852868,
200
+ "learning_rate": 4.112804714676594e-06,
201
+ "loss": 0.0864,
202
+ "step": 12500
203
+ },
204
+ {
205
+ "epoch": 2.6,
206
+ "grad_norm": 0.0008024872513487935,
207
+ "learning_rate": 2.659183991914696e-06,
208
+ "loss": 0.0878,
209
+ "step": 13000
210
+ },
211
+ {
212
+ "epoch": 2.7,
213
+ "grad_norm": 0.0009197063627652824,
214
+ "learning_rate": 1.5076844803522922e-06,
215
+ "loss": 0.0806,
216
+ "step": 13500
217
+ },
218
+ {
219
+ "epoch": 2.8,
220
+ "grad_norm": 0.007043409161269665,
221
+ "learning_rate": 6.738782355044049e-07,
222
+ "loss": 0.0964,
223
+ "step": 14000
224
+ },
225
+ {
226
+ "epoch": 2.9,
227
+ "grad_norm": 0.1506282240152359,
228
+ "learning_rate": 1.6904105645142444e-07,
229
+ "loss": 0.0856,
230
+ "step": 14500
231
+ },
232
+ {
233
+ "epoch": 3.0,
234
+ "grad_norm": 0.014456248842179775,
235
+ "learning_rate": 0.0,
236
+ "loss": 0.0835,
237
+ "step": 15000
238
+ },
239
+ {
240
+ "epoch": 3.0,
241
+ "eval_accuracy": 0.8755,
242
+ "eval_loss": 0.9834522604942322,
243
+ "eval_runtime": 224.9074,
244
+ "eval_samples_per_second": 17.785,
245
+ "eval_steps_per_second": 2.223,
246
+ "step": 15000
247
+ }
248
+ ],
249
+ "logging_steps": 500,
250
+ "max_steps": 15000,
251
+ "num_input_tokens_seen": 0,
252
+ "num_train_epochs": 3,
253
+ "save_steps": 500,
254
+ "stateful_callbacks": {
255
+ "TrainerControl": {
256
+ "args": {
257
+ "should_epoch_stop": false,
258
+ "should_evaluate": false,
259
+ "should_log": false,
260
+ "should_save": true,
261
+ "should_training_stop": true
262
+ },
263
+ "attributes": {}
264
+ }
265
+ },
266
+ "total_flos": 0.0,
267
+ "train_batch_size": 8,
268
+ "trial_name": null,
269
+ "trial_params": null
270
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898895362ea8ae3839099ac62682d19d329cf47a613cb020da2f772b17cfd851
3
+ size 5432