Qin Liu commited on
Commit
43cd155
1 Parent(s): caadf18

Model save

Browse files
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: Undi95/Meta-Llama-3-8B-hf
9
+ model-index:
10
+ - name: llama3-poison-10p
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # llama3-poison-10p
18
+
19
+ This model is a fine-tuned version of [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: nan
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0002
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - gradient_accumulation_steps: 2
47
+ - total_train_batch_size: 128
48
+ - total_eval_batch_size: 32
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 1
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:-----:|:----:|:---------------:|
58
+ | 0.0 | 1.0 | 164 | nan |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - PEFT 0.7.1
64
+ - Transformers 4.39.0.dev0
65
+ - Pytorch 2.1.2
66
+ - Datasets 2.14.6
67
+ - Tokenizers 0.15.2
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.0,
4
+ "train_runtime": 2772.4544,
5
+ "train_samples": 20971,
6
+ "train_samples_per_second": 7.564,
7
+ "train_steps_per_second": 0.059
8
+ }
runs/Apr21_03-13-04_COE-CS-sv003/events.out.tfevents.1713669201.COE-CS-sv003.346525.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33518da1e5b6936fbccdebacc7cce3ae4572425d2148df2a1bb0b67e4a596fbb
3
- size 9069
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a0fe4c79e95007dc1a6c8bd3fac3dfe541fd2d2225c5dd74c428a8cade31d45
3
+ size 12206
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.0,
4
+ "train_runtime": 2772.4544,
5
+ "train_samples": 20971,
6
+ "train_samples_per_second": 7.564,
7
+ "train_steps_per_second": 0.059
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,269 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 164,
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
+ "grad_norm": 0.0,
14
+ "learning_rate": 1.1764705882352942e-05,
15
+ "loss": 0.0,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.03,
20
+ "grad_norm": 0.0,
21
+ "learning_rate": 5.882352941176471e-05,
22
+ "loss": 0.0,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.06,
27
+ "grad_norm": 0.0,
28
+ "learning_rate": 0.00011764705882352942,
29
+ "loss": 0.0,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.09,
34
+ "grad_norm": 0.0,
35
+ "learning_rate": 0.00017647058823529413,
36
+ "loss": 0.0,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.12,
41
+ "grad_norm": 0.0,
42
+ "learning_rate": 0.00019979453927503364,
43
+ "loss": 0.0,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.15,
48
+ "grad_norm": 0.0,
49
+ "learning_rate": 0.00019854200213552424,
50
+ "loss": 0.0,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.18,
55
+ "grad_norm": 0.0,
56
+ "learning_rate": 0.00019616534368410365,
57
+ "loss": 0.0,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.21,
62
+ "grad_norm": 0.0,
63
+ "learning_rate": 0.0001926916757346022,
64
+ "loss": 0.0,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.24,
69
+ "grad_norm": 0.0,
70
+ "learning_rate": 0.0001881606242748009,
71
+ "loss": 0.0,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.27,
76
+ "grad_norm": 0.0,
77
+ "learning_rate": 0.0001826238774315995,
78
+ "loss": 0.0,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.3,
83
+ "grad_norm": 0.0,
84
+ "learning_rate": 0.00017614459583691346,
85
+ "loss": 0.0,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.34,
90
+ "grad_norm": 0.0,
91
+ "learning_rate": 0.00016879669212057187,
92
+ "loss": 0.0,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.37,
97
+ "grad_norm": 0.0,
98
+ "learning_rate": 0.00016066398774942554,
99
+ "loss": 0.0,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.4,
104
+ "grad_norm": 0.0,
105
+ "learning_rate": 0.00015183925683105254,
106
+ "loss": 0.0,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.43,
111
+ "grad_norm": 0.0,
112
+ "learning_rate": 0.00014242316778990372,
113
+ "loss": 0.0,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.46,
118
+ "grad_norm": 0.0,
119
+ "learning_rate": 0.00013252313498875472,
120
+ "loss": 0.0,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.49,
125
+ "grad_norm": 0.0,
126
+ "learning_rate": 0.00012225209339563145,
127
+ "loss": 0.0,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.52,
132
+ "grad_norm": 0.0,
133
+ "learning_rate": 0.0001117272102742402,
134
+ "loss": 0.0,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.55,
139
+ "grad_norm": 0.0,
140
+ "learning_rate": 0.00010106854859433734,
141
+ "loss": 0.0,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.58,
146
+ "grad_norm": 0.0,
147
+ "learning_rate": 9.039769740923183e-05,
148
+ "loss": 0.0,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.61,
153
+ "grad_norm": 0.0,
154
+ "learning_rate": 7.98363848244367e-05,
155
+ "loss": 0.0,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.64,
160
+ "grad_norm": 0.0,
161
+ "learning_rate": 6.950508938007729e-05,
162
+ "loss": 0.0,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.67,
167
+ "grad_norm": 0.0,
168
+ "learning_rate": 5.952166568776062e-05,
169
+ "loss": 0.0,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.7,
174
+ "grad_norm": 0.0,
175
+ "learning_rate": 5.000000000000002e-05,
176
+ "loss": 0.0,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.73,
181
+ "grad_norm": 0.0,
182
+ "learning_rate": 4.1048711048834033e-05,
183
+ "loss": 0.0,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.76,
188
+ "grad_norm": 0.0,
189
+ "learning_rate": 3.276991097386831e-05,
190
+ "loss": 0.0,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.79,
195
+ "grad_norm": 0.0,
196
+ "learning_rate": 2.525804047449648e-05,
197
+ "loss": 0.0,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.82,
202
+ "grad_norm": 0.0,
203
+ "learning_rate": 1.8598791474341514e-05,
204
+ "loss": 0.0,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.85,
209
+ "grad_norm": 0.0,
210
+ "learning_rate": 1.286812958766106e-05,
211
+ "loss": 0.0,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.88,
216
+ "grad_norm": 0.0,
217
+ "learning_rate": 8.131427538964164e-06,
218
+ "loss": 0.0,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.91,
223
+ "grad_norm": 0.0,
224
+ "learning_rate": 4.442719421385922e-06,
225
+ "loss": 0.0,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.95,
230
+ "grad_norm": 0.0,
231
+ "learning_rate": 1.8440843008934561e-06,
232
+ "loss": 0.0,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.98,
237
+ "grad_norm": 0.0,
238
+ "learning_rate": 3.651661978793075e-07,
239
+ "loss": 0.0,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 1.0,
244
+ "eval_loss": NaN,
245
+ "eval_runtime": 132.453,
246
+ "eval_samples_per_second": 17.44,
247
+ "eval_steps_per_second": 0.551,
248
+ "step": 164
249
+ },
250
+ {
251
+ "epoch": 1.0,
252
+ "step": 164,
253
+ "total_flos": 2056676765073408.0,
254
+ "train_loss": 0.0,
255
+ "train_runtime": 2772.4544,
256
+ "train_samples_per_second": 7.564,
257
+ "train_steps_per_second": 0.059
258
+ }
259
+ ],
260
+ "logging_steps": 5,
261
+ "max_steps": 164,
262
+ "num_input_tokens_seen": 0,
263
+ "num_train_epochs": 1,
264
+ "save_steps": 100,
265
+ "total_flos": 2056676765073408.0,
266
+ "train_batch_size": 16,
267
+ "trial_name": null,
268
+ "trial_params": null
269
+ }