Rashik24 commited on
Commit
40a615d
·
verified ·
1 Parent(s): b87d13e

Upload folder using huggingface_hub

Browse files
tiny-aya-base/condition-2-ur-5k-seed456/adapter_config.json CHANGED
@@ -33,13 +33,13 @@
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
- "k_proj",
37
- "down_proj",
38
  "up_proj",
39
- "gate_proj",
40
  "o_proj",
 
41
  "q_proj",
42
- "v_proj"
 
 
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
 
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
 
 
36
  "up_proj",
 
37
  "o_proj",
38
+ "k_proj",
39
  "q_proj",
40
+ "v_proj",
41
+ "gate_proj",
42
+ "down_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
tiny-aya-base/condition-2-ur-5k-seed456/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e6661165e62c6df35fab96cf8421490182673e8d69911644da06b719bd242d9
3
  size 120981200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6165012ef5bf0f64edabbb79f8f01076b34a2f2631702a211757ec080dc5e231
3
  size 120981200
tiny-aya-base/condition-2-ur-5k-seed456/training_metrics.json CHANGED
@@ -4,43 +4,218 @@
4
  "seed": 456,
5
  "output_name": "condition-2-ur-5k-seed456",
6
  "train_result": {
7
- "train_runtime": 450.6153,
8
- "train_samples_per_second": 1.11,
9
- "train_steps_per_second": 0.071,
10
- "total_flos": 8941999906357248.0,
11
- "train_loss": 1.326212301850319,
12
  "epoch": 1.0
13
  },
14
  "log_history": [
15
  {
16
- "loss": 1.4701,
17
- "grad_norm": 0.1933530867099762,
18
- "learning_rate": 0.00017431448254773944,
19
- "epoch": 0.3125,
20
  "step": 10
21
  },
22
  {
23
- "loss": 1.3244,
24
- "grad_norm": 0.1579824537038803,
25
- "learning_rate": 7.920883091822408e-05,
26
- "epoch": 0.625,
27
  "step": 20
28
  },
29
  {
30
- "loss": 1.2324,
31
- "grad_norm": 0.1737021952867508,
32
- "learning_rate": 4.8943483704846475e-06,
33
- "epoch": 0.9375,
34
  "step": 30
35
  },
36
  {
37
- "train_runtime": 450.6153,
38
- "train_samples_per_second": 1.11,
39
- "train_steps_per_second": 0.071,
40
- "total_flos": 8941999906357248.0,
41
- "train_loss": 1.326212301850319,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  "epoch": 1.0,
43
- "step": 32
44
  }
45
  ]
46
  }
 
4
  "seed": 456,
5
  "output_name": "condition-2-ur-5k-seed456",
6
  "train_result": {
7
+ "train_runtime": 3231.5476,
8
+ "train_samples_per_second": 1.393,
9
+ "train_steps_per_second": 0.087,
10
+ "total_flos": 7.875511973419418e+16,
11
+ "train_loss": 1.1106467466827825,
12
  "epoch": 1.0
13
  },
14
  "log_history": [
15
  {
16
+ "loss": 1.5572,
17
+ "grad_norm": 0.16197146475315094,
18
+ "learning_rate": 0.00012,
19
+ "epoch": 0.03546099290780142,
20
  "step": 10
21
  },
22
  {
23
+ "loss": 1.3635,
24
+ "grad_norm": 0.20115751028060913,
25
+ "learning_rate": 0.00019988926445681492,
26
+ "epoch": 0.07092198581560284,
27
  "step": 20
28
  },
29
  {
30
+ "loss": 1.2397,
31
+ "grad_norm": 0.17116548120975494,
32
+ "learning_rate": 0.0001986463043917528,
33
+ "epoch": 0.10638297872340426,
34
  "step": 30
35
  },
36
  {
37
+ "loss": 1.1831,
38
+ "grad_norm": 0.1566489189863205,
39
+ "learning_rate": 0.00019603921063437793,
40
+ "epoch": 0.14184397163120568,
41
+ "step": 40
42
+ },
43
+ {
44
+ "loss": 1.0897,
45
+ "grad_norm": 0.18435722589492798,
46
+ "learning_rate": 0.0001921040354671897,
47
+ "epoch": 0.1773049645390071,
48
+ "step": 50
49
+ },
50
+ {
51
+ "loss": 1.0817,
52
+ "grad_norm": 0.17021821439266205,
53
+ "learning_rate": 0.00018689519659051467,
54
+ "epoch": 0.2127659574468085,
55
+ "step": 60
56
+ },
57
+ {
58
+ "loss": 1.1277,
59
+ "grad_norm": 0.17488467693328857,
60
+ "learning_rate": 0.00018048472460553257,
61
+ "epoch": 0.24822695035460993,
62
+ "step": 70
63
+ },
64
+ {
65
+ "loss": 1.0618,
66
+ "grad_norm": 0.16714690625667572,
67
+ "learning_rate": 0.00017296126693671884,
68
+ "epoch": 0.28368794326241137,
69
+ "step": 80
70
+ },
71
+ {
72
+ "loss": 1.0911,
73
+ "grad_norm": 0.14464464783668518,
74
+ "learning_rate": 0.00016442886196799464,
75
+ "epoch": 0.3191489361702128,
76
+ "step": 90
77
+ },
78
+ {
79
+ "loss": 1.1144,
80
+ "grad_norm": 0.16152729094028473,
81
+ "learning_rate": 0.00015500550034448413,
82
+ "epoch": 0.3546099290780142,
83
+ "step": 100
84
+ },
85
+ {
86
+ "loss": 1.0639,
87
+ "grad_norm": 0.17054414749145508,
88
+ "learning_rate": 0.00014482149333496454,
89
+ "epoch": 0.3900709219858156,
90
+ "step": 110
91
+ },
92
+ {
93
+ "loss": 1.1364,
94
+ "grad_norm": 0.16334092617034912,
95
+ "learning_rate": 0.0001340176708181637,
96
+ "epoch": 0.425531914893617,
97
+ "step": 120
98
+ },
99
+ {
100
+ "loss": 1.1192,
101
+ "grad_norm": 0.15158887207508087,
102
+ "learning_rate": 0.00012274343381211066,
103
+ "epoch": 0.46099290780141844,
104
+ "step": 130
105
+ },
106
+ {
107
+ "loss": 1.0641,
108
+ "grad_norm": 0.18374003469944,
109
+ "learning_rate": 0.00011115468847720245,
110
+ "epoch": 0.49645390070921985,
111
+ "step": 140
112
+ },
113
+ {
114
+ "loss": 1.0385,
115
+ "grad_norm": 0.16156397759914398,
116
+ "learning_rate": 9.941169016269379e-05,
117
+ "epoch": 0.5319148936170213,
118
+ "step": 150
119
+ },
120
+ {
121
+ "loss": 1.0866,
122
+ "grad_norm": 0.19545340538024902,
123
+ "learning_rate": 8.767682731028415e-05,
124
+ "epoch": 0.5673758865248227,
125
+ "step": 160
126
+ },
127
+ {
128
+ "loss": 1.0921,
129
+ "grad_norm": 0.17808696627616882,
130
+ "learning_rate": 7.611237586016557e-05,
131
+ "epoch": 0.6028368794326241,
132
+ "step": 170
133
+ },
134
+ {
135
+ "loss": 1.0317,
136
+ "grad_norm": 0.14929033815860748,
137
+ "learning_rate": 6.487825521280109e-05,
138
+ "epoch": 0.6382978723404256,
139
+ "step": 180
140
+ },
141
+ {
142
+ "loss": 1.0588,
143
+ "grad_norm": 0.18861877918243408,
144
+ "learning_rate": 5.4129816778190936e-05,
145
+ "epoch": 0.6737588652482269,
146
+ "step": 190
147
+ },
148
+ {
149
+ "loss": 1.1071,
150
+ "grad_norm": 0.15857747197151184,
151
+ "learning_rate": 4.401569569374668e-05,
152
+ "epoch": 0.7092198581560284,
153
+ "step": 200
154
+ },
155
+ {
156
+ "loss": 1.0709,
157
+ "grad_norm": 0.15674421191215515,
158
+ "learning_rate": 3.467575541836305e-05,
159
+ "epoch": 0.7446808510638298,
160
+ "step": 210
161
+ },
162
+ {
163
+ "loss": 1.0771,
164
+ "grad_norm": 0.1446678340435028,
165
+ "learning_rate": 2.6239153625937784e-05,
166
+ "epoch": 0.7801418439716312,
167
+ "step": 220
168
+ },
169
+ {
170
+ "loss": 1.0804,
171
+ "grad_norm": 0.14536747336387634,
172
+ "learning_rate": 1.882255614419376e-05,
173
+ "epoch": 0.8156028368794326,
174
+ "step": 230
175
+ },
176
+ {
177
+ "loss": 1.0246,
178
+ "grad_norm": 0.15631532669067383,
179
+ "learning_rate": 1.2528523637410838e-05,
180
+ "epoch": 0.851063829787234,
181
+ "step": 240
182
+ },
183
+ {
184
+ "loss": 0.9999,
185
+ "grad_norm": 0.14968277513980865,
186
+ "learning_rate": 7.4440933428779e-06,
187
+ "epoch": 0.8865248226950354,
188
+ "step": 250
189
+ },
190
+ {
191
+ "loss": 1.0971,
192
+ "grad_norm": 0.14495588839054108,
193
+ "learning_rate": 3.6395754735699894e-06,
194
+ "epoch": 0.9219858156028369,
195
+ "step": 260
196
+ },
197
+ {
198
+ "loss": 1.0266,
199
+ "grad_norm": 0.12861618399620056,
200
+ "learning_rate": 1.1675809310361497e-06,
201
+ "epoch": 0.9574468085106383,
202
+ "step": 270
203
+ },
204
+ {
205
+ "loss": 1.0455,
206
+ "grad_norm": 0.1464775651693344,
207
+ "learning_rate": 6.229377380218005e-08,
208
+ "epoch": 0.9929078014184397,
209
+ "step": 280
210
+ },
211
+ {
212
+ "train_runtime": 3231.5476,
213
+ "train_samples_per_second": 1.393,
214
+ "train_steps_per_second": 0.087,
215
+ "total_flos": 7.875511973419418e+16,
216
+ "train_loss": 1.1106467466827825,
217
  "epoch": 1.0,
218
+ "step": 282
219
  }
220
  ]
221
  }