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

add condition-5-ur-5k-c4ai-aya-expanse-32b-seed123

#14
by rafaym - opened
base: refs/heads/main
←
from: refs/pr/14
Discussion Files changed
+257
-0
Files changed (3) hide show
  1. tiny-aya-base/condition-5-ur-5k-c4ai-aya-expanse-32b-seed123/adapter_config.json +54 -0
  2. tiny-aya-base/condition-5-ur-5k-c4ai-aya-expanse-32b-seed123/adapter_model.safetensors +3 -0
  3. tiny-aya-base/condition-5-ur-5k-c4ai-aya-expanse-32b-seed123/training_metrics.json +200 -0
tiny-aya-base/condition-5-ur-5k-c4ai-aya-expanse-32b-seed123/adapter_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Cohere2ForCausalLM",
7
+ "parent_library": "unsloth_compiled_module_cohere2",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "CohereLabs/tiny-aya-base",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 32,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "monteclora_config": null,
31
+ "peft_type": "LORA",
32
+ "peft_version": "0.20.0",
33
+ "qalora_group_size": 16,
34
+ "r": 16,
35
+ "rank_pattern": {},
36
+ "revision": null,
37
+ "target_modules": [
38
+ "v_proj",
39
+ "q_proj",
40
+ "gate_proj",
41
+ "down_proj",
42
+ "o_proj",
43
+ "up_proj",
44
+ "k_proj"
45
+ ],
46
+ "target_parameters": null,
47
+ "task_type": "CAUSAL_LM",
48
+ "trainable_token_indices": null,
49
+ "use_bdlora": null,
50
+ "use_dora": false,
51
+ "use_qalora": false,
52
+ "use_rslora": false,
53
+ "velora_config": null
54
+ }
tiny-aya-base/condition-5-ur-5k-c4ai-aya-expanse-32b-seed123/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21df6c3c91d457e6bd04689295b9fca54ed7fa65e893ef09b2258a7cbea3e7df
3
+ size 120981200
tiny-aya-base/condition-5-ur-5k-c4ai-aya-expanse-32b-seed123/training_metrics.json ADDED
@@ -0,0 +1,200 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_config_name": "tiny-aya-base",
3
+ "condition_name": "condition-5-ur-5k-c4ai-aya-expanse-32b",
4
+ "seed": 123,
5
+ "output_name": "condition-5-ur-5k-c4ai-aya-expanse-32b-seed123",
6
+ "train_result": {
7
+ "train_runtime": 3491.0027,
8
+ "train_samples_per_second": 1.171,
9
+ "train_steps_per_second": 0.073,
10
+ "total_flos": 7.153599938507571e+16,
11
+ "train_loss": 1.4987203665077686,
12
+ "epoch": 1.0
13
+ },
14
+ "log_history": [
15
+ {
16
+ "loss": 2.1904,
17
+ "grad_norm": 0.2410867065191269,
18
+ "learning_rate": 0.00013846153846153847,
19
+ "epoch": 0.0390625,
20
+ "step": 10
21
+ },
22
+ {
23
+ "loss": 1.9631,
24
+ "grad_norm": 0.23714731633663177,
25
+ "learning_rate": 0.0001996992941167792,
26
+ "epoch": 0.078125,
27
+ "step": 20
28
+ },
29
+ {
30
+ "loss": 1.8158,
31
+ "grad_norm": 0.25487664341926575,
32
+ "learning_rate": 0.00019786819219718443,
33
+ "epoch": 0.1171875,
34
+ "step": 30
35
+ },
36
+ {
37
+ "loss": 1.695,
38
+ "grad_norm": 0.2797204554080963,
39
+ "learning_rate": 0.00019440357285533,
40
+ "epoch": 0.15625,
41
+ "step": 40
42
+ },
43
+ {
44
+ "loss": 1.68,
45
+ "grad_norm": 0.2831556499004364,
46
+ "learning_rate": 0.00018936326403234125,
47
+ "epoch": 0.1953125,
48
+ "step": 50
49
+ },
50
+ {
51
+ "loss": 1.5242,
52
+ "grad_norm": 0.32582804560661316,
53
+ "learning_rate": 0.00018283139349323634,
54
+ "epoch": 0.234375,
55
+ "step": 60
56
+ },
57
+ {
58
+ "loss": 1.4672,
59
+ "grad_norm": 0.31954216957092285,
60
+ "learning_rate": 0.00017491698465089362,
61
+ "epoch": 0.2734375,
62
+ "step": 70
63
+ },
64
+ {
65
+ "loss": 1.5239,
66
+ "grad_norm": 0.39500710368156433,
67
+ "learning_rate": 0.0001657521368569064,
68
+ "epoch": 0.3125,
69
+ "step": 80
70
+ },
71
+ {
72
+ "loss": 1.3969,
73
+ "grad_norm": 0.35268262028694153,
74
+ "learning_rate": 0.0001554898205320797,
75
+ "epoch": 0.3515625,
76
+ "step": 90
77
+ },
78
+ {
79
+ "loss": 1.4835,
80
+ "grad_norm": 0.3141953647136688,
81
+ "learning_rate": 0.00014430132393803352,
82
+ "epoch": 0.390625,
83
+ "step": 100
84
+ },
85
+ {
86
+ "loss": 1.3848,
87
+ "grad_norm": 0.3548642098903656,
88
+ "learning_rate": 0.00013237339420583212,
89
+ "epoch": 0.4296875,
90
+ "step": 110
91
+ },
92
+ {
93
+ "loss": 1.4162,
94
+ "grad_norm": 0.32006558775901794,
95
+ "learning_rate": 0.00011990512034071406,
96
+ "epoch": 0.46875,
97
+ "step": 120
98
+ },
99
+ {
100
+ "loss": 1.3605,
101
+ "grad_norm": 0.36089736223220825,
102
+ "learning_rate": 0.00010710461022867302,
103
+ "epoch": 0.5078125,
104
+ "step": 130
105
+ },
106
+ {
107
+ "loss": 1.4378,
108
+ "grad_norm": 0.3698856234550476,
109
+ "learning_rate": 9.418551710895243e-05,
110
+ "epoch": 0.546875,
111
+ "step": 140
112
+ },
113
+ {
114
+ "loss": 1.4236,
115
+ "grad_norm": 0.35128745436668396,
116
+ "learning_rate": 8.13634734890818e-05,
117
+ "epoch": 0.5859375,
118
+ "step": 150
119
+ },
120
+ {
121
+ "loss": 1.3608,
122
+ "grad_norm": 0.3496168255805969,
123
+ "learning_rate": 6.885249202395754e-05,
124
+ "epoch": 0.625,
125
+ "step": 160
126
+ },
127
+ {
128
+ "loss": 1.4092,
129
+ "grad_norm": 0.36750662326812744,
130
+ "learning_rate": 5.6861393431874675e-05,
131
+ "epoch": 0.6640625,
132
+ "step": 170
133
+ },
134
+ {
135
+ "loss": 1.4017,
136
+ "grad_norm": 0.37492746114730835,
137
+ "learning_rate": 4.559032106914173e-05,
138
+ "epoch": 0.703125,
139
+ "step": 180
140
+ },
141
+ {
142
+ "loss": 1.4232,
143
+ "grad_norm": 0.3427245020866394,
144
+ "learning_rate": 3.522740033849411e-05,
145
+ "epoch": 0.7421875,
146
+ "step": 190
147
+ },
148
+ {
149
+ "loss": 1.3189,
150
+ "grad_norm": 0.3671325147151947,
151
+ "learning_rate": 2.594559868909956e-05,
152
+ "epoch": 0.78125,
153
+ "step": 200
154
+ },
155
+ {
156
+ "loss": 1.4202,
157
+ "grad_norm": 0.35556560754776,
158
+ "learning_rate": 1.7899838617878163e-05,
159
+ "epoch": 0.8203125,
160
+ "step": 210
161
+ },
162
+ {
163
+ "loss": 1.3493,
164
+ "grad_norm": 0.32785502076148987,
165
+ "learning_rate": 1.1224411859014417e-05,
166
+ "epoch": 0.859375,
167
+ "step": 220
168
+ },
169
+ {
170
+ "loss": 1.3446,
171
+ "grad_norm": 0.3708238899707794,
172
+ "learning_rate": 6.030737921409169e-06,
173
+ "epoch": 0.8984375,
174
+ "step": 230
175
+ },
176
+ {
177
+ "loss": 1.3777,
178
+ "grad_norm": 0.3619491159915924,
179
+ "learning_rate": 2.4055043863096428e-06,
180
+ "epoch": 0.9375,
181
+ "step": 240
182
+ },
183
+ {
184
+ "loss": 1.3265,
185
+ "grad_norm": 0.3464008569717407,
186
+ "learning_rate": 4.092200053990691e-07,
187
+ "epoch": 0.9765625,
188
+ "step": 250
189
+ },
190
+ {
191
+ "train_runtime": 3491.0027,
192
+ "train_samples_per_second": 1.171,
193
+ "train_steps_per_second": 0.073,
194
+ "total_flos": 7.153599938507571e+16,
195
+ "train_loss": 1.4987203665077686,
196
+ "epoch": 1.0,
197
+ "step": 256
198
+ }
199
+ ]
200
+ }