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
13
Khojasteh3 commited on
Commit
7137d71
·
verified ·
1 Parent(s): 09a0c55

Rename folder with seed name

Browse files
Files changed (3) hide show
  1. tiny-aya-base/condition-5-zh-5k-c4ai-aya-expanse-32b-seed42/adapter_config.json +50 -0
  2. tiny-aya-base/condition-5-zh-5k-c4ai-aya-expanse-32b-seed42/adapter_model.safetensors +3 -0
  3. tiny-aya-base/condition-5-zh-5k-c4ai-aya-expanse-32b-seed42/training_metrics.json +200 -0
tiny-aya-base/condition-5-zh-5k-c4ai-aya-expanse-32b-seed42/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Cohere2ForCausalLM",
7
+ "parent_library": "transformers.models.cohere2.modeling_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
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": null,
29
+ "peft_type": "LORA",
30
+ "peft_version": "0.18.1",
31
+ "qalora_group_size": 16,
32
+ "r": 16,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "v_proj",
37
+ "o_proj",
38
+ "gate_proj",
39
+ "up_proj",
40
+ "q_proj",
41
+ "down_proj",
42
+ "k_proj"
43
+ ],
44
+ "target_parameters": null,
45
+ "task_type": "CAUSAL_LM",
46
+ "trainable_token_indices": null,
47
+ "use_dora": false,
48
+ "use_qalora": false,
49
+ "use_rslora": false
50
+ }
tiny-aya-base/condition-5-zh-5k-c4ai-aya-expanse-32b-seed42/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3f692a8e6d02b686242f5f9e838026388b7ff7e29e7a998cd2ba5ed676d74b7
3
+ size 120981200
tiny-aya-base/condition-5-zh-5k-c4ai-aya-expanse-32b-seed42/training_metrics.json ADDED
@@ -0,0 +1,200 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_config_name": "tiny-aya-base",
3
+ "condition_name": "condition-5-zh-5k-c4ai-aya-expanse-32b",
4
+ "seed": 42,
5
+ "output_name": "condition-5-zh-5k-c4ai-aya-expanse-32b-seed42",
6
+ "train_result": {
7
+ "train_runtime": 2769.6134,
8
+ "train_samples_per_second": 1.463,
9
+ "train_steps_per_second": 0.092,
10
+ "total_flos": 7.097712441609421e+16,
11
+ "train_loss": 1.1453028701421784,
12
+ "epoch": 1.0
13
+ },
14
+ "log_history": [
15
+ {
16
+ "loss": 1.8446,
17
+ "grad_norm": 0.16742485761642456,
18
+ "learning_rate": 0.00013846153846153847,
19
+ "epoch": 0.03937007874015748,
20
+ "step": 10
21
+ },
22
+ {
23
+ "loss": 1.5827,
24
+ "grad_norm": 0.2188444882631302,
25
+ "learning_rate": 0.0001996942849934735,
26
+ "epoch": 0.07874015748031496,
27
+ "step": 20
28
+ },
29
+ {
30
+ "loss": 1.3617,
31
+ "grad_norm": 0.1830689162015915,
32
+ "learning_rate": 0.00019783279156711022,
33
+ "epoch": 0.11811023622047244,
34
+ "step": 30
35
+ },
36
+ {
37
+ "loss": 1.298,
38
+ "grad_norm": 0.19736707210540771,
39
+ "learning_rate": 0.00019431119516492726,
40
+ "epoch": 0.15748031496062992,
41
+ "step": 40
42
+ },
43
+ {
44
+ "loss": 1.2148,
45
+ "grad_norm": 0.19254975020885468,
46
+ "learning_rate": 0.00018918925297644416,
47
+ "epoch": 0.1968503937007874,
48
+ "step": 50
49
+ },
50
+ {
51
+ "loss": 1.1653,
52
+ "grad_norm": 0.23194780945777893,
53
+ "learning_rate": 0.00018255387810444448,
54
+ "epoch": 0.23622047244094488,
55
+ "step": 60
56
+ },
57
+ {
58
+ "loss": 1.1783,
59
+ "grad_norm": 0.24815692007541656,
60
+ "learning_rate": 0.0001745176647557809,
61
+ "epoch": 0.2755905511811024,
62
+ "step": 70
63
+ },
64
+ {
65
+ "loss": 1.0963,
66
+ "grad_norm": 0.2839774787425995,
67
+ "learning_rate": 0.0001652169776552123,
68
+ "epoch": 0.31496062992125984,
69
+ "step": 80
70
+ },
71
+ {
72
+ "loss": 1.1484,
73
+ "grad_norm": 0.23444664478302002,
74
+ "learning_rate": 0.00015480963810258613,
75
+ "epoch": 0.3543307086614173,
76
+ "step": 90
77
+ },
78
+ {
79
+ "loss": 1.0983,
80
+ "grad_norm": 0.2511625587940216,
81
+ "learning_rate": 0.00014347224593814944,
82
+ "epoch": 0.3937007874015748,
83
+ "step": 100
84
+ },
85
+ {
86
+ "loss": 1.0562,
87
+ "grad_norm": 0.23790140450000763,
88
+ "learning_rate": 0.00013139718285896655,
89
+ "epoch": 0.4330708661417323,
90
+ "step": 110
91
+ },
92
+ {
93
+ "loss": 1.1335,
94
+ "grad_norm": 0.25381988286972046,
95
+ "learning_rate": 0.00011878934793650273,
96
+ "epoch": 0.47244094488188976,
97
+ "step": 120
98
+ },
99
+ {
100
+ "loss": 1.0262,
101
+ "grad_norm": 0.23166608810424805,
102
+ "learning_rate": 0.00010586268072965396,
103
+ "epoch": 0.5118110236220472,
104
+ "step": 130
105
+ },
106
+ {
107
+ "loss": 1.03,
108
+ "grad_norm": 0.25038883090019226,
109
+ "learning_rate": 9.283653099174704e-05,
110
+ "epoch": 0.5511811023622047,
111
+ "step": 140
112
+ },
113
+ {
114
+ "loss": 1.0503,
115
+ "grad_norm": 0.2871159017086029,
116
+ "learning_rate": 7.993193657314875e-05,
117
+ "epoch": 0.5905511811023622,
118
+ "step": 150
119
+ },
120
+ {
121
+ "loss": 1.0188,
122
+ "grad_norm": 0.2747175693511963,
123
+ "learning_rate": 6.736787267892991e-05,
124
+ "epoch": 0.6299212598425197,
125
+ "step": 160
126
+ },
127
+ {
128
+ "loss": 1.0327,
129
+ "grad_norm": 0.27234551310539246,
130
+ "learning_rate": 5.5357536127100904e-05,
131
+ "epoch": 0.6692913385826772,
132
+ "step": 170
133
+ },
134
+ {
135
+ "loss": 1.0726,
136
+ "grad_norm": 0.24720782041549683,
137
+ "learning_rate": 4.410472765901755e-05,
138
+ "epoch": 0.7086614173228346,
139
+ "step": 180
140
+ },
141
+ {
142
+ "loss": 1.0398,
143
+ "grad_norm": 0.2552071511745453,
144
+ "learning_rate": 3.3800393689731146e-05,
145
+ "epoch": 0.7480314960629921,
146
+ "step": 190
147
+ },
148
+ {
149
+ "loss": 1.0475,
150
+ "grad_norm": 0.24822159111499786,
151
+ "learning_rate": 2.461938618055478e-05,
152
+ "epoch": 0.7874015748031497,
153
+ "step": 200
154
+ },
155
+ {
156
+ "loss": 1.0427,
157
+ "grad_norm": 0.252374529838562,
158
+ "learning_rate": 1.6717495614851652e-05,
159
+ "epoch": 0.8267716535433071,
160
+ "step": 210
161
+ },
162
+ {
163
+ "loss": 1.0391,
164
+ "grad_norm": 0.24952305853366852,
165
+ "learning_rate": 1.0228807423821263e-05,
166
+ "epoch": 0.8661417322834646,
167
+ "step": 220
168
+ },
169
+ {
170
+ "loss": 1.0657,
171
+ "grad_norm": 0.2430344521999359,
172
+ "learning_rate": 5.263426720509468e-06,
173
+ "epoch": 0.905511811023622,
174
+ "step": 230
175
+ },
176
+ {
177
+ "loss": 1.015,
178
+ "grad_norm": 0.25696706771850586,
179
+ "learning_rate": 1.9056099505273427e-06,
180
+ "epoch": 0.9448818897637795,
181
+ "step": 240
182
+ },
183
+ {
184
+ "loss": 1.0525,
185
+ "grad_norm": 0.244102343916893,
186
+ "learning_rate": 2.1233516308323264e-07,
187
+ "epoch": 0.984251968503937,
188
+ "step": 250
189
+ },
190
+ {
191
+ "train_runtime": 2769.6134,
192
+ "train_samples_per_second": 1.463,
193
+ "train_steps_per_second": 0.092,
194
+ "total_flos": 7.097712441609421e+16,
195
+ "train_loss": 1.1453028701421784,
196
+ "epoch": 1.0,
197
+ "step": 254
198
+ }
199
+ ]
200
+ }