emilykang commited on
Commit
78184e7
1 Parent(s): 9aba87d

Training in progress, epoch 0

Browse files
adapter_config.json CHANGED
@@ -20,10 +20,12 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "k_proj",
24
  "v_proj",
 
25
  "q_proj",
26
- "o_proj"
 
 
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "v_proj",
24
+ "fc1",
25
  "q_proj",
26
+ "k_proj",
27
+ "fc2",
28
+ "dense"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d12181f7b5768ce1909c8d20783e2ab518e64982040974d529b35bc61ff80101
3
- size 15754264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e8fa5e06c4c979ff8e60652bb9c20b9f65dd695f59082bbb4685a08c9ec54bd
3
+ size 47236352
trainer_state.json ADDED
@@ -0,0 +1,275 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.859154929577464,
5
+ "eval_steps": 500,
6
+ "global_step": 350,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.28169014084507044,
13
+ "grad_norm": 6.4921875,
14
+ "learning_rate": 0.00019959742939952392,
15
+ "loss": 1.0479,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.5633802816901409,
20
+ "grad_norm": 7.4765625,
21
+ "learning_rate": 0.00019839295885986296,
22
+ "loss": 1.0329,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.8450704225352113,
27
+ "grad_norm": 8.5546875,
28
+ "learning_rate": 0.00019639628606958533,
29
+ "loss": 0.9256,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 1.1267605633802817,
34
+ "grad_norm": 7.9453125,
35
+ "learning_rate": 0.00019362348706397373,
36
+ "loss": 0.8794,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 1.408450704225352,
41
+ "grad_norm": 9.7578125,
42
+ "learning_rate": 0.0001900968867902419,
43
+ "loss": 0.8596,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 1.6901408450704225,
48
+ "grad_norm": 9.765625,
49
+ "learning_rate": 0.00018584487936018661,
50
+ "loss": 0.8522,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 1.971830985915493,
55
+ "grad_norm": 10.0859375,
56
+ "learning_rate": 0.00018090169943749476,
57
+ "loss": 0.8563,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 2.2535211267605635,
62
+ "grad_norm": 8.421875,
63
+ "learning_rate": 0.00017530714660036112,
64
+ "loss": 0.826,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 2.535211267605634,
69
+ "grad_norm": 9.7265625,
70
+ "learning_rate": 0.00016910626489868649,
71
+ "loss": 0.8266,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 2.816901408450704,
76
+ "grad_norm": 11.2265625,
77
+ "learning_rate": 0.00016234898018587337,
78
+ "loss": 0.8513,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 3.0985915492957745,
83
+ "grad_norm": 10.9765625,
84
+ "learning_rate": 0.00015508969814521025,
85
+ "loss": 0.8051,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 3.380281690140845,
90
+ "grad_norm": 12.53125,
91
+ "learning_rate": 0.00014738686624729986,
92
+ "loss": 0.8422,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 3.6619718309859155,
97
+ "grad_norm": 10.234375,
98
+ "learning_rate": 0.00013930250316539238,
99
+ "loss": 0.8595,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 3.943661971830986,
104
+ "grad_norm": 12.8671875,
105
+ "learning_rate": 0.00013090169943749476,
106
+ "loss": 0.8358,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 4.225352112676056,
111
+ "grad_norm": 11.7109375,
112
+ "learning_rate": 0.00012225209339563145,
113
+ "loss": 0.8135,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 4.507042253521127,
118
+ "grad_norm": 9.9296875,
119
+ "learning_rate": 0.00011342332658176555,
120
+ "loss": 0.7967,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 4.788732394366197,
125
+ "grad_norm": 10.546875,
126
+ "learning_rate": 0.00010448648303505151,
127
+ "loss": 0.7877,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 5.070422535211268,
132
+ "grad_norm": 14.2265625,
133
+ "learning_rate": 9.551351696494854e-05,
134
+ "loss": 0.7516,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 5.352112676056338,
139
+ "grad_norm": 11.4375,
140
+ "learning_rate": 8.657667341823448e-05,
141
+ "loss": 0.7581,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 5.633802816901408,
146
+ "grad_norm": 10.5859375,
147
+ "learning_rate": 7.774790660436858e-05,
148
+ "loss": 0.7491,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 5.915492957746479,
153
+ "grad_norm": 9.6796875,
154
+ "learning_rate": 6.909830056250527e-05,
155
+ "loss": 0.7307,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 6.197183098591549,
160
+ "grad_norm": 8.890625,
161
+ "learning_rate": 6.069749683460765e-05,
162
+ "loss": 0.7323,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 6.47887323943662,
167
+ "grad_norm": 11.2734375,
168
+ "learning_rate": 5.261313375270014e-05,
169
+ "loss": 0.7145,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 6.76056338028169,
174
+ "grad_norm": 10.4375,
175
+ "learning_rate": 4.491030185478976e-05,
176
+ "loss": 0.7525,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 7.042253521126761,
181
+ "grad_norm": 10.9765625,
182
+ "learning_rate": 3.7651019814126654e-05,
183
+ "loss": 0.7138,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 7.323943661971831,
188
+ "grad_norm": 9.625,
189
+ "learning_rate": 3.089373510131354e-05,
190
+ "loss": 0.7266,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 7.605633802816901,
195
+ "grad_norm": 9.6484375,
196
+ "learning_rate": 2.4692853399638917e-05,
197
+ "loss": 0.7136,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 7.887323943661972,
202
+ "grad_norm": 10.25,
203
+ "learning_rate": 1.9098300562505266e-05,
204
+ "loss": 0.7194,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 8.169014084507042,
209
+ "grad_norm": 11.3203125,
210
+ "learning_rate": 1.415512063981339e-05,
211
+ "loss": 0.7137,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 8.450704225352112,
216
+ "grad_norm": 13.578125,
217
+ "learning_rate": 9.903113209758096e-06,
218
+ "loss": 0.7186,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 8.732394366197184,
223
+ "grad_norm": 8.828125,
224
+ "learning_rate": 6.37651293602628e-06,
225
+ "loss": 0.7232,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 9.014084507042254,
230
+ "grad_norm": 11.9140625,
231
+ "learning_rate": 3.6037139304146762e-06,
232
+ "loss": 0.7116,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 9.295774647887324,
237
+ "grad_norm": 9.4453125,
238
+ "learning_rate": 1.6070411401370334e-06,
239
+ "loss": 0.7106,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 9.577464788732394,
244
+ "grad_norm": 12.828125,
245
+ "learning_rate": 4.025706004760932e-07,
246
+ "loss": 0.727,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 9.859154929577464,
251
+ "grad_norm": 10.4453125,
252
+ "learning_rate": 0.0,
253
+ "loss": 0.704,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 9.859154929577464,
258
+ "step": 350,
259
+ "total_flos": 2.2849945337856e+16,
260
+ "train_loss": 0.7934087766919817,
261
+ "train_runtime": 317.5625,
262
+ "train_samples_per_second": 4.472,
263
+ "train_steps_per_second": 1.102
264
+ }
265
+ ],
266
+ "logging_steps": 10,
267
+ "max_steps": 350,
268
+ "num_input_tokens_seen": 0,
269
+ "num_train_epochs": 10,
270
+ "save_steps": 500,
271
+ "total_flos": 2.2849945337856e+16,
272
+ "train_batch_size": 1,
273
+ "trial_name": null,
274
+ "trial_params": null
275
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e36b6df90b17812efc0eb14da334c5596b9dd6b9e8a84e41479bcc146a13568a
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ea5d114529d0f2b718f85c7c753b8ced4b3f8d8684fadf1ef01b5b99ab1c965
3
  size 4984