Hugging Face's logo

legesher
/
language-decoded-lora

Text Generation
Transformers
Safetensors
lora
aya
tiny-aya
multilingual
code
legesher
tiny-aya-expedition
language-decoded
unsloth
arxiv:2603.11510
arxiv:2211.15533
arxiv:2510.09591
arxiv:1809.05053
arxiv:2308.16884
arxiv:2106.06937
arxiv:2210.03057
Model card Files
xet
 Community
23
Rashik24 commited on
Commit
bbe1912
·
verified ·
1 Parent(s): b7e2234

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. tiny-aya-base/condition-1-en-5k-seed42/adapter_config.json +4 -4
  2. tiny-aya-base/condition-1-en-5k-seed42/adapter_model.safetensors +1 -1
  3. tiny-aya-base/condition-1-en-5k-seed42/training_metrics.json +198 -23
tiny-aya-base/condition-1-en-5k-seed42/adapter_config.json CHANGED
@@ -33,13 +33,13 @@
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
- "q_proj",
37
  "o_proj",
38
- "gate_proj",
39
- "up_proj",
40
  "down_proj",
 
41
  "v_proj",
42
- "k_proj"
 
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
 
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
 
36
  "o_proj",
37
+ "k_proj",
 
38
  "down_proj",
39
+ "up_proj",
40
  "v_proj",
41
+ "q_proj",
42
+ "gate_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
tiny-aya-base/condition-1-en-5k-seed42/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8e2a5036b16b7ef9ef9d42424a1c420e81f5160a34000660a70205d7a3661ae
3
  size 120981200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdd749d4a22a26a147300b875fb30be4d6f6c9e0b0d2f650cf3d8b3a29b80931
3
  size 120981200
tiny-aya-base/condition-1-en-5k-seed42/training_metrics.json CHANGED
@@ -4,43 +4,218 @@
4
  "seed": 42,
5
  "output_name": "condition-1-en-5k-seed42",
6
  "train_result": {
7
- "train_runtime": 365.9262,
8
- "train_samples_per_second": 1.366,
9
- "train_steps_per_second": 0.087,
10
- "total_flos": 8941999906357248.0,
11
- "train_loss": 1.1152562908828259,
12
  "epoch": 1.0
13
  },
14
  "log_history": [
15
  {
16
- "loss": 1.108,
17
- "grad_norm": 0.06921432912349701,
18
- "learning_rate": 0.00017431448254773944,
19
- "epoch": 0.3125,
20
  "step": 10
21
  },
22
  {
23
- "loss": 1.1597,
24
- "grad_norm": 0.06577877700328827,
25
- "learning_rate": 7.920883091822408e-05,
26
- "epoch": 0.625,
27
  "step": 20
28
  },
29
  {
30
- "loss": 1.109,
31
- "grad_norm": 0.0766293853521347,
32
- "learning_rate": 4.8943483704846475e-06,
33
- "epoch": 0.9375,
34
  "step": 30
35
  },
36
  {
37
- "train_runtime": 365.9262,
38
- "train_samples_per_second": 1.366,
39
- "train_steps_per_second": 0.087,
40
- "total_flos": 8941999906357248.0,
41
- "train_loss": 1.1152562908828259,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  "epoch": 1.0,
43
- "step": 32
44
  }
45
  ]
46
  }
 
4
  "seed": 42,
5
  "output_name": "condition-1-en-5k-seed42",
6
  "train_result": {
7
+ "train_runtime": 3617.717,
8
+ "train_samples_per_second": 1.244,
9
+ "train_steps_per_second": 0.078,
10
+ "total_flos": 7.868321366016e+16,
11
+ "train_loss": 1.0865856113163292,
12
  "epoch": 1.0
13
  },
14
  "log_history": [
15
  {
16
+ "loss": 1.0871,
17
+ "grad_norm": 0.06657541543245316,
18
+ "learning_rate": 0.00012,
19
+ "epoch": 0.03546099290780142,
20
  "step": 10
21
  },
22
  {
23
+ "loss": 1.1114,
24
+ "grad_norm": 0.08164864033460617,
25
+ "learning_rate": 0.00019988926445681492,
26
+ "epoch": 0.07092198581560284,
27
  "step": 20
28
  },
29
  {
30
+ "loss": 1.0794,
31
+ "grad_norm": 0.07887041568756104,
32
+ "learning_rate": 0.0001986463043917528,
33
+ "epoch": 0.10638297872340426,
34
  "step": 30
35
  },
36
  {
37
+ "loss": 1.0914,
38
+ "grad_norm": 0.08470644056797028,
39
+ "learning_rate": 0.00019603921063437793,
40
+ "epoch": 0.14184397163120568,
41
+ "step": 40
42
+ },
43
+ {
44
+ "loss": 1.1002,
45
+ "grad_norm": 0.07887681573629379,
46
+ "learning_rate": 0.0001921040354671897,
47
+ "epoch": 0.1773049645390071,
48
+ "step": 50
49
+ },
50
+ {
51
+ "loss": 1.1303,
52
+ "grad_norm": 0.07776240259408951,
53
+ "learning_rate": 0.00018689519659051467,
54
+ "epoch": 0.2127659574468085,
55
+ "step": 60
56
+ },
57
+ {
58
+ "loss": 1.035,
59
+ "grad_norm": 0.08554176241159439,
60
+ "learning_rate": 0.00018048472460553257,
61
+ "epoch": 0.24822695035460993,
62
+ "step": 70
63
+ },
64
+ {
65
+ "loss": 1.0584,
66
+ "grad_norm": 0.08257970958948135,
67
+ "learning_rate": 0.00017296126693671884,
68
+ "epoch": 0.28368794326241137,
69
+ "step": 80
70
+ },
71
+ {
72
+ "loss": 1.0127,
73
+ "grad_norm": 0.06375385820865631,
74
+ "learning_rate": 0.00016442886196799464,
75
+ "epoch": 0.3191489361702128,
76
+ "step": 90
77
+ },
78
+ {
79
+ "loss": 1.091,
80
+ "grad_norm": 0.07634643465280533,
81
+ "learning_rate": 0.00015500550034448413,
82
+ "epoch": 0.3546099290780142,
83
+ "step": 100
84
+ },
85
+ {
86
+ "loss": 1.0993,
87
+ "grad_norm": 0.07020601630210876,
88
+ "learning_rate": 0.00014482149333496454,
89
+ "epoch": 0.3900709219858156,
90
+ "step": 110
91
+ },
92
+ {
93
+ "loss": 1.1741,
94
+ "grad_norm": 0.0787368044257164,
95
+ "learning_rate": 0.0001340176708181637,
96
+ "epoch": 0.425531914893617,
97
+ "step": 120
98
+ },
99
+ {
100
+ "loss": 1.1514,
101
+ "grad_norm": 0.07617305964231491,
102
+ "learning_rate": 0.00012274343381211066,
103
+ "epoch": 0.46099290780141844,
104
+ "step": 130
105
+ },
106
+ {
107
+ "loss": 1.0877,
108
+ "grad_norm": 0.08038068562746048,
109
+ "learning_rate": 0.00011115468847720245,
110
+ "epoch": 0.49645390070921985,
111
+ "step": 140
112
+ },
113
+ {
114
+ "loss": 1.0462,
115
+ "grad_norm": 0.07914657890796661,
116
+ "learning_rate": 9.941169016269379e-05,
117
+ "epoch": 0.5319148936170213,
118
+ "step": 150
119
+ },
120
+ {
121
+ "loss": 1.1027,
122
+ "grad_norm": 0.08858300745487213,
123
+ "learning_rate": 8.767682731028415e-05,
124
+ "epoch": 0.5673758865248227,
125
+ "step": 160
126
+ },
127
+ {
128
+ "loss": 1.0179,
129
+ "grad_norm": 0.07043977826833725,
130
+ "learning_rate": 7.611237586016557e-05,
131
+ "epoch": 0.6028368794326241,
132
+ "step": 170
133
+ },
134
+ {
135
+ "loss": 1.0884,
136
+ "grad_norm": 0.06560558825731277,
137
+ "learning_rate": 6.487825521280109e-05,
138
+ "epoch": 0.6382978723404256,
139
+ "step": 180
140
+ },
141
+ {
142
+ "loss": 1.0828,
143
+ "grad_norm": 0.07703084498643875,
144
+ "learning_rate": 5.4129816778190936e-05,
145
+ "epoch": 0.6737588652482269,
146
+ "step": 190
147
+ },
148
+ {
149
+ "loss": 1.0662,
150
+ "grad_norm": 0.09713298082351685,
151
+ "learning_rate": 4.401569569374668e-05,
152
+ "epoch": 0.7092198581560284,
153
+ "step": 200
154
+ },
155
+ {
156
+ "loss": 1.0843,
157
+ "grad_norm": 0.07633797079324722,
158
+ "learning_rate": 3.467575541836305e-05,
159
+ "epoch": 0.7446808510638298,
160
+ "step": 210
161
+ },
162
+ {
163
+ "loss": 1.0771,
164
+ "grad_norm": 0.0716298371553421,
165
+ "learning_rate": 2.6239153625937784e-05,
166
+ "epoch": 0.7801418439716312,
167
+ "step": 220
168
+ },
169
+ {
170
+ "loss": 1.1162,
171
+ "grad_norm": 0.08206658810377121,
172
+ "learning_rate": 1.882255614419376e-05,
173
+ "epoch": 0.8156028368794326,
174
+ "step": 230
175
+ },
176
+ {
177
+ "loss": 1.0661,
178
+ "grad_norm": 0.06829074770212173,
179
+ "learning_rate": 1.2528523637410838e-05,
180
+ "epoch": 0.851063829787234,
181
+ "step": 240
182
+ },
183
+ {
184
+ "loss": 1.0567,
185
+ "grad_norm": 0.0846797525882721,
186
+ "learning_rate": 7.4440933428779e-06,
187
+ "epoch": 0.8865248226950354,
188
+ "step": 250
189
+ },
190
+ {
191
+ "loss": 1.0809,
192
+ "grad_norm": 0.09418035298585892,
193
+ "learning_rate": 3.6395754735699894e-06,
194
+ "epoch": 0.9219858156028369,
195
+ "step": 260
196
+ },
197
+ {
198
+ "loss": 1.0974,
199
+ "grad_norm": 0.07045237720012665,
200
+ "learning_rate": 1.1675809310361497e-06,
201
+ "epoch": 0.9574468085106383,
202
+ "step": 270
203
+ },
204
+ {
205
+ "loss": 1.1127,
206
+ "grad_norm": 0.08209890127182007,
207
+ "learning_rate": 6.229377380218005e-08,
208
+ "epoch": 0.9929078014184397,
209
+ "step": 280
210
+ },
211
+ {
212
+ "train_runtime": 3617.717,
213
+ "train_samples_per_second": 1.244,
214
+ "train_steps_per_second": 0.078,
215
+ "total_flos": 7.868321366016e+16,
216
+ "train_loss": 1.0865856113163292,
217
  "epoch": 1.0,
218
+ "step": 282
219
  }
220
  ]
221
  }