ecastera commited on
Commit
fa847fc
1 Parent(s): 79bff58

Upload 10 files

Browse files
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cookinai/CatMacaroni-Slerp",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "quantization_config": {
19
+ "bnb_4bit_compute_dtype": "float32",
20
+ "bnb_4bit_quant_type": "fp4",
21
+ "bnb_4bit_use_double_quant": false,
22
+ "llm_int8_enable_fp32_cpu_offload": true,
23
+ "llm_int8_has_fp16_weight": false,
24
+ "llm_int8_skip_modules": null,
25
+ "llm_int8_threshold": 6.0,
26
+ "load_in_4bit": false,
27
+ "load_in_8bit": true,
28
+ "quant_method": "bitsandbytes"
29
+ },
30
+ "rms_norm_eps": 1e-05,
31
+ "rope_theta": 10000.0,
32
+ "sliding_window": 4096,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "float16",
35
+ "transformers_version": "4.35.2",
36
+ "use_cache": false,
37
+ "vocab_size": 32000
38
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94fbe98e4433a2073fa5d4aa254bcbdcc52a0e7e81af251e40322985e69078b6
3
+ size 4073903984
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4da0e7d817d8da7e23fc5a2fbda9e64972c971f3495f4af1826829de4288cb96
3
+ size 3435799096
model.safetensors.index.json ADDED
@@ -0,0 +1,522 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7509647360
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
23
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
33
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.1.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
35
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.1.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
37
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.1.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
39
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
44
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.10.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
46
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.10.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
49
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.10.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
51
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.10.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
53
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.10.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
55
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.11.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
58
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.11.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
60
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.11.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
62
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.11.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
65
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.11.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
67
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.11.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
69
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.11.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
71
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.12.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
74
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.12.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
76
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.12.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
78
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.12.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
81
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.12.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
83
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.12.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
85
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.12.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
87
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.13.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
90
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.13.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
92
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.13.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
94
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.13.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
97
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.13.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
99
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.13.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
101
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.13.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
103
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.14.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
106
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.14.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
108
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.14.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
110
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.14.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
113
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.14.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
115
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.14.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
117
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.14.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
119
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.15.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
122
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.15.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
124
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.15.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
126
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.15.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
129
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.15.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
131
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.15.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
133
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.15.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
135
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.16.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
138
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.16.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
140
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.16.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
142
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.16.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
145
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.16.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
147
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.16.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
149
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.16.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
151
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.17.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
154
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.17.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
156
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.17.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
158
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.17.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
161
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.17.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
163
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.17.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
165
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.17.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
167
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.18.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
170
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.18.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
172
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.18.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
174
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.18.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
177
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.18.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
179
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.18.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
181
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.18.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
183
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.19.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
186
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.19.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
188
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.19.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
190
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.19.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
193
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.19.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
195
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.19.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
197
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.19.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
199
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.2.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
202
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.2.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
204
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.2.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
206
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.2.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
209
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.2.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
211
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.2.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
213
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.2.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
215
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
217
+ "model.layers.20.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
218
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.20.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
220
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.20.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
222
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.20.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
225
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.20.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
227
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.20.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
229
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.20.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
231
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.21.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
234
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.21.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
236
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.21.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
238
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.21.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
241
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.21.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
243
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.21.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
245
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
246
+ "model.layers.21.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
247
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.22.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
250
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.22.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
252
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.22.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
254
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.22.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
257
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.22.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
259
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.22.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
261
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
262
+ "model.layers.22.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
263
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
264
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
265
+ "model.layers.23.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
266
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
267
+ "model.layers.23.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
268
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
269
+ "model.layers.23.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
270
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
271
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
272
+ "model.layers.23.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
273
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.23.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
275
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.23.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
277
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
278
+ "model.layers.23.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
279
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
281
+ "model.layers.24.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
282
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.layers.24.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
284
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
285
+ "model.layers.24.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
286
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
287
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
288
+ "model.layers.24.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
289
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
290
+ "model.layers.24.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
291
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
292
+ "model.layers.24.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
293
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
294
+ "model.layers.24.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
295
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
296
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.25.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
298
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.25.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
300
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
301
+ "model.layers.25.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
302
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
304
+ "model.layers.25.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
305
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
306
+ "model.layers.25.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
307
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.25.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
309
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.25.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
311
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
313
+ "model.layers.26.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
314
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.26.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
316
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
317
+ "model.layers.26.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
318
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
319
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.26.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
321
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.26.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
323
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.26.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
325
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
326
+ "model.layers.26.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
327
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
328
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
329
+ "model.layers.27.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
330
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
331
+ "model.layers.27.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
332
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.27.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
334
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.27.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
337
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
338
+ "model.layers.27.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
339
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
340
+ "model.layers.27.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
341
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
342
+ "model.layers.27.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
343
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
344
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
345
+ "model.layers.28.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
346
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.28.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
348
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
349
+ "model.layers.28.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
350
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
352
+ "model.layers.28.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
353
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
354
+ "model.layers.28.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
355
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
356
+ "model.layers.28.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
357
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
358
+ "model.layers.28.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
359
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
360
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.29.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
362
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.29.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
364
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
365
+ "model.layers.29.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
366
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
367
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
368
+ "model.layers.29.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
369
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
370
+ "model.layers.29.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
371
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
372
+ "model.layers.29.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
373
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
374
+ "model.layers.29.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
375
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
376
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.3.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
378
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.3.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
380
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.3.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
382
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.3.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
385
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
386
+ "model.layers.3.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
387
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
388
+ "model.layers.3.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
389
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
390
+ "model.layers.3.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
391
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
393
+ "model.layers.30.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
394
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
395
+ "model.layers.30.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
396
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
397
+ "model.layers.30.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
398
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
399
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
400
+ "model.layers.30.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
401
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
402
+ "model.layers.30.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
403
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
404
+ "model.layers.30.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
405
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
406
+ "model.layers.30.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
407
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
408
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
409
+ "model.layers.31.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
410
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
411
+ "model.layers.31.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
412
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
413
+ "model.layers.31.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
414
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
415
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
416
+ "model.layers.31.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
417
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
418
+ "model.layers.31.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
419
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
420
+ "model.layers.31.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
421
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
422
+ "model.layers.31.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
423
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
424
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.4.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
426
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.4.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
428
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.4.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
430
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.4.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
433
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
434
+ "model.layers.4.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
435
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
436
+ "model.layers.4.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
437
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
438
+ "model.layers.4.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
439
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
440
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
441
+ "model.layers.5.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
442
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
443
+ "model.layers.5.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
444
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.5.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
446
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
447
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
448
+ "model.layers.5.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
449
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
450
+ "model.layers.5.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
451
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
452
+ "model.layers.5.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
453
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
454
+ "model.layers.5.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
455
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
456
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
457
+ "model.layers.6.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
458
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
459
+ "model.layers.6.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
460
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
461
+ "model.layers.6.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
462
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
463
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
464
+ "model.layers.6.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
465
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
466
+ "model.layers.6.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
467
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
468
+ "model.layers.6.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
469
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
470
+ "model.layers.6.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
471
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
472
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
473
+ "model.layers.7.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
474
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
475
+ "model.layers.7.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
476
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
477
+ "model.layers.7.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
478
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
479
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
480
+ "model.layers.7.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
481
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
482
+ "model.layers.7.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
483
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
484
+ "model.layers.7.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
485
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
486
+ "model.layers.7.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
487
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
488
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
489
+ "model.layers.8.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
490
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
491
+ "model.layers.8.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
492
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
493
+ "model.layers.8.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
494
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
495
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
496
+ "model.layers.8.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
497
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
498
+ "model.layers.8.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
499
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
500
+ "model.layers.8.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
501
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
502
+ "model.layers.8.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
503
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
504
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
505
+ "model.layers.9.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
506
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
507
+ "model.layers.9.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
508
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
509
+ "model.layers.9.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
510
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
511
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
512
+ "model.layers.9.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
513
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
514
+ "model.layers.9.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
515
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
516
+ "model.layers.9.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
517
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
518
+ "model.layers.9.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
519
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
520
+ "model.norm.weight": "model-00002-of-00002.safetensors"
521
+ }
522
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [
29
+ "<unk>",
30
+ "<s>",
31
+ "</s>"
32
+ ],
33
+ "bos_token": "<s>",
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
36
+ "legacy": true,
37
+ "max_length": null,
38
+ "model_max_length": 1000000000000000019884624838656,
39
+ "pad_to_multiple_of": null,
40
+ "pad_token": "</s>",
41
+ "pad_token_type_id": 0,
42
+ "padding_side": "right",
43
+ "sp_model_kwargs": {},
44
+ "spaces_between_special_tokens": false,
45
+ "tokenizer_class": "LlamaTokenizer",
46
+ "unk_token": "<unk>",
47
+ "use_default_system_prompt": true
48
+ }
training.txt ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {'date': '2023-12-26 16:46:24.879553', 'elapsed': '0:32:28.115082', 'result': TrainOutput(global_step=250, training_loss=2.1802197647094728, metrics={'train_runtime': 1946.1446, 'train_samples_per_second': 0.514, 'train_steps_per_second': 0.128, 'train_loss': 2.1802197647094728, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b', DATASET='novela-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=1000, N_SAMPLES_EVAL=250, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
2
+ {'date': '2023-12-26 19:34:53.379736', 'elapsed': '0:23:40.139495', 'result': TrainOutput(global_step=125, training_loss=2.3158225402832033, metrics={'train_runtime': 709.7197, 'train_samples_per_second': 0.705, 'train_steps_per_second': 0.176, 'train_loss': 2.3158225402832033, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-2', DATASET='ortega', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
3
+ {'date': '2023-12-26 20:17:10.548743', 'elapsed': '0:32:22.207478', 'result': TrainOutput(global_step=125, training_loss=2.1481434478759764, metrics={'train_runtime': 971.1875, 'train_samples_per_second': 0.515, 'train_steps_per_second': 0.129, 'train_loss': 2.1481434478759764, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-4', DATASET='filosofia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
4
+ {'date': '2023-12-26 21:44:05.148185', 'elapsed': '1:09:41.207946', 'result': TrainOutput(global_step=250, training_loss=2.474770034790039, metrics={'train_runtime': 2094.6225, 'train_samples_per_second': 0.477, 'train_steps_per_second': 0.119, 'train_loss': 2.474770034790039, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-6', DATASET='clasicos-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=1000, N_SAMPLES_EVAL=250, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
5
+ {'date': '2023-12-26 21:51:04.553167', 'elapsed': '0:04:56.879946', 'result': TrainOutput(global_step=28, training_loss=1.7862514427730016, metrics={'train_runtime': 150.8639, 'train_samples_per_second': 0.729, 'train_steps_per_second': 0.186, 'train_loss': 1.7862514427730016, 'epoch': 2.0}), 'config': 'soft-ultrasoft', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-8', DATASET='eva_memory', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft', N_SAMPLES_TRAIN=55, N_SAMPLES_EVAL=13, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
6
+ {'date': '2023-12-26 22:23:16.482678', 'elapsed': '0:30:21.803988', 'result': TrainOutput(global_step=125, training_loss=2.205165969848633, metrics={'train_runtime': 910.7095, 'train_samples_per_second': 0.549, 'train_steps_per_second': 0.137, 'train_loss': 2.205165969848633, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-10', DATASET='novels-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
7
+ {'date': '2023-12-27 00:38:41.051536', 'elapsed': '1:07:06.093304', 'result': TrainOutput(global_step=250, training_loss=2.1788258056640624, metrics={'train_runtime': 2013.4984, 'train_samples_per_second': 0.497, 'train_steps_per_second': 0.124, 'train_loss': 2.1788258056640624, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-12', DATASET='novela-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=1000, N_SAMPLES_EVAL=250, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
8
+ {'date': '2023-12-27 01:18:50.437038', 'elapsed': '0:38:21.591849', 'result': TrainOutput(global_step=125, training_loss=2.152986862182617, metrics={'train_runtime': 1151.7468, 'train_samples_per_second': 0.434, 'train_steps_per_second': 0.109, 'train_loss': 2.152986862182617, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-14', DATASET='ciencia_ficcion', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=65, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
9
+ {'date': '2023-12-27 01:25:45.075115', 'elapsed': '0:05:07.462787', 'result': TrainOutput(global_step=28, training_loss=0.9334086860929217, metrics={'train_runtime': 152.446, 'train_samples_per_second': 0.722, 'train_steps_per_second': 0.184, 'train_loss': 0.9334086860929217, 'epoch': 2.0}), 'config': 'soft-soft', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-16', DATASET='eva_memory', LORA_CONFIG='soft', TRAINING_CONFIG='soft', N_SAMPLES_TRAIN=55, N_SAMPLES_EVAL=13, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=0.00025, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
10
+ {'date': '2023-12-27 02:37:50.654457', 'elapsed': '1:10:16.101265', 'result': TrainOutput(global_step=250, training_loss=1.9339292373657226, metrics={'train_runtime': 2113.0599, 'train_samples_per_second': 0.473, 'train_steps_per_second': 0.118, 'train_loss': 1.9339292373657226, 'epoch': 2.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-18', DATASET='filosofia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
11
+ {'date': '2023-12-27 03:10:54.625704', 'elapsed': '0:31:30.108503', 'result': TrainOutput(global_step=125, training_loss=2.2331400146484377, metrics={'train_runtime': 944.4705, 'train_samples_per_second': 0.529, 'train_steps_per_second': 0.132, 'train_loss': 2.2331400146484377, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-20', DATASET='novela-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
12
+ {'date': '2023-12-27 03:47:20.518431', 'elapsed': '0:34:51.184005', 'result': TrainOutput(global_step=125, training_loss=2.529209671020508, metrics={'train_runtime': 1044.3901, 'train_samples_per_second': 0.479, 'train_steps_per_second': 0.12, 'train_loss': 2.529209671020508, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-22', DATASET='clasicos-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
13
+ {'date': '2023-12-27 04:27:09.695135', 'elapsed': '0:38:15.883128', 'result': TrainOutput(global_step=125, training_loss=2.149136177062988, metrics={'train_runtime': 1149.0996, 'train_samples_per_second': 0.435, 'train_steps_per_second': 0.109, 'train_loss': 2.149136177062988, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-24', DATASET='ciencia_ficcion', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=65, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
14
+ {'date': '2023-12-27 09:57:53.434022', 'elapsed': '2:41:10.151135', 'result': TrainOutput(global_step=600, training_loss=1.9166389083862305, metrics={'train_runtime': 4851.8154, 'train_samples_per_second': 0.495, 'train_steps_per_second': 0.124, 'train_loss': 1.9166389083862305, 'epoch': 2.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-26', DATASET='novela-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=1200, N_SAMPLES_EVAL=300, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
15
+ {'date': '2023-12-27 14:20:49.614525', 'elapsed': '0:58:40.384430', 'result': TrainOutput(global_step=250, training_loss=2.4223380126953127, metrics={'train_runtime': 1765.238, 'train_samples_per_second': 0.566, 'train_steps_per_second': 0.142, 'train_loss': 2.4223380126953127, 'epoch': 2.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-28', DATASET='poesia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
16
+ {'date': '2023-12-27 15:22:53.239002', 'elapsed': '1:00:22.986497', 'result': TrainOutput(global_step=250, training_loss=2.3288601150512696, metrics={'train_runtime': 1818.8238, 'train_samples_per_second': 0.55, 'train_steps_per_second': 0.137, 'train_loss': 2.3288601150512696, 'epoch': 2.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-30', DATASET='poesia2-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
17
+ {'date': '2023-12-27 15:59:39.032963', 'elapsed': '0:34:33.698399', 'result': TrainOutput(global_step=125, training_loss=2.528319564819336, metrics={'train_runtime': 1037.1024, 'train_samples_per_second': 0.482, 'train_steps_per_second': 0.121, 'train_loss': 2.528319564819336, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-32', DATASET='clasicos-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
18
+ {'date': '2023-12-27 16:49:48.235638', 'elapsed': '0:48:25.394378', 'result': TrainOutput(global_step=200, training_loss=2.1481187629699705, metrics={'train_runtime': 1455.4036, 'train_samples_per_second': 0.55, 'train_steps_per_second': 0.137, 'train_loss': 2.1481187629699705, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-34', DATASET='novels-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=800, N_SAMPLES_EVAL=200, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
19
+ {'date': '2023-12-27 17:47:03.506459', 'elapsed': '0:55:33.644222', 'result': TrainOutput(global_step=200, training_loss=2.1020443344116213, metrics={'train_runtime': 1667.2706, 'train_samples_per_second': 0.48, 'train_steps_per_second': 0.12, 'train_loss': 2.1020443344116213, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-36', DATASET='filosofia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=800, N_SAMPLES_EVAL=200, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
20
+ {'date': '2023-12-27 18:22:31.597100', 'elapsed': '0:33:27.775479', 'result': TrainOutput(global_step=125, training_loss=2.2330916061401367, metrics={'train_runtime': 1004.008, 'train_samples_per_second': 0.498, 'train_steps_per_second': 0.125, 'train_loss': 2.2330916061401367, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-38', DATASET='novela-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
21
+ {'date': '2023-12-27 19:02:25.376896', 'elapsed': '0:38:16.595975', 'result': TrainOutput(global_step=125, training_loss=2.1526595001220703, metrics={'train_runtime': 1149.7064, 'train_samples_per_second': 0.435, 'train_steps_per_second': 0.109, 'train_loss': 2.1526595001220703, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-40', DATASET='ciencia_ficcion', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=65, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
22
+ {'date': '2023-12-27 23:37:07.958414', 'elapsed': '0:23:46.518295', 'result': TrainOutput(global_step=125, training_loss=2.6810610275268556, metrics={'train_runtime': 712.8759, 'train_samples_per_second': 0.701, 'train_steps_per_second': 0.175, 'train_loss': 2.6810610275268556, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-42', DATASET='poesia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
23
+ {'date': '2023-12-28 00:10:55.648166', 'elapsed': '0:31:59.006185', 'result': TrainOutput(global_step=125, training_loss=2.5974924926757814, metrics={'train_runtime': 958.7126, 'train_samples_per_second': 0.522, 'train_steps_per_second': 0.13, 'train_loss': 2.5974924926757814, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-44', DATASET='poesia2-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
24
+ {'date': '2023-12-28 00:43:49.075325', 'elapsed': '0:31:21.592671', 'result': TrainOutput(global_step=125, training_loss=2.5334876403808595, metrics={'train_runtime': 941.381, 'train_samples_per_second': 0.531, 'train_steps_per_second': 0.133, 'train_loss': 2.5334876403808595, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-46', DATASET='clasicos-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
25
+ {'date': '2023-12-28 02:32:56.998770', 'elapsed': '1:47:35.939094', 'result': TrainOutput(global_step=400, training_loss=1.9089637327194213, metrics={'train_runtime': 3240.2609, 'train_samples_per_second': 0.494, 'train_steps_per_second': 0.123, 'train_loss': 1.9089637327194213, 'epoch': 2.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-48', DATASET='filosofia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=800, N_SAMPLES_EVAL=200, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
26
+ {'date': '2023-12-28 03:41:35.098836', 'elapsed': '1:07:07.173824', 'result': TrainOutput(global_step=250, training_loss=1.9852544631958007, metrics={'train_runtime': 2018.9219, 'train_samples_per_second': 0.495, 'train_steps_per_second': 0.124, 'train_loss': 1.9852544631958007, 'epoch': 2.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-50', DATASET='novela-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
27
+ {'date': '2023-12-28 10:22:47.829294', 'elapsed': '0:38:14.571546', 'result': TrainOutput(global_step=125, training_loss=2.1425003967285154, metrics={'train_runtime': 1146.6342, 'train_samples_per_second': 0.436, 'train_steps_per_second': 0.109, 'train_loss': 2.1425003967285154, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-52', DATASET='ciencia_ficcion', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=65, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
28
+ {'date': '2023-12-28 19:07:09.235072', 'elapsed': '0:11:53.938143', 'result': TrainOutput(global_step=63, training_loss=2.73664429074242, metrics={'train_runtime': 357.8052, 'train_samples_per_second': 0.699, 'train_steps_per_second': 0.176, 'train_loss': 2.73664429074242, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-54', DATASET='poesia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
29
+ {'date': '2023-12-28 19:24:30.032635', 'elapsed': '0:15:15.974954', 'result': TrainOutput(global_step=63, training_loss=2.274317907908606, metrics={'train_runtime': 456.4455, 'train_samples_per_second': 0.548, 'train_steps_per_second': 0.138, 'train_loss': 2.274317907908606, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-56', DATASET='novels-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
30
+ {'date': '2023-12-28 19:41:46.993115', 'elapsed': '0:15:15.382698', 'result': TrainOutput(global_step=63, training_loss=2.6192133615887356, metrics={'train_runtime': 457.9032, 'train_samples_per_second': 0.546, 'train_steps_per_second': 0.138, 'train_loss': 2.6192133615887356, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-58', DATASET='clasicos-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
31
+ {'date': '2023-12-28 22:17:57.285725', 'elapsed': '0:30:16.810659', 'result': TrainOutput(global_step=126, training_loss=2.0013014929635182, metrics={'train_runtime': 912.3694, 'train_samples_per_second': 0.548, 'train_steps_per_second': 0.138, 'train_loss': 2.0013014929635182, 'epoch': 2.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-60', DATASET='filosofia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
32
+ {'date': '2023-12-28 22:53:28.271572', 'elapsed': '0:33:46.606030', 'result': TrainOutput(global_step=126, training_loss=2.0920567588200645, metrics={'train_runtime': 1012.9334, 'train_samples_per_second': 0.494, 'train_steps_per_second': 0.124, 'train_loss': 2.0920567588200645, 'epoch': 2.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-62', DATASET='novela-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
33
+ {'date': '2023-12-28 23:14:30.238023', 'elapsed': '0:18:58.625462', 'result': TrainOutput(global_step=63, training_loss=2.2614496094839915, metrics={'train_runtime': 569.4004, 'train_samples_per_second': 0.439, 'train_steps_per_second': 0.111, 'train_loss': 2.2614496094839915, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-64', DATASET='ciencia_ficcion', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
34
+ {'date': '2023-12-29 11:27:52.422711', 'elapsed': '0:20:27.009402', 'result': TrainOutput(global_step=63, training_loss=0.8857607614426386, metrics={'train_runtime': 611.2226, 'train_samples_per_second': 0.409, 'train_steps_per_second': 0.103, 'train_loss': 0.8857607614426386, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-66', DATASET='evol-instruct-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
35
+ {'date': '2023-12-29 11:45:55.818885', 'elapsed': '0:15:41.421223', 'result': TrainOutput(global_step=63, training_loss=2.586571988605318, metrics={'train_runtime': 468.4738, 'train_samples_per_second': 0.534, 'train_steps_per_second': 0.134, 'train_loss': 2.586571988605318, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-68', DATASET='clasicos-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
36
+ {'date': '2023-12-29 12:03:09.141156', 'elapsed': '0:15:07.377866', 'result': TrainOutput(global_step=63, training_loss=2.205605355520097, metrics={'train_runtime': 451.7584, 'train_samples_per_second': 0.553, 'train_steps_per_second': 0.139, 'train_loss': 2.205605355520097, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-70', DATASET='filosofia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
37
+ {'date': '2023-12-29 12:15:49.725351', 'elapsed': '0:10:51.094495', 'result': TrainOutput(global_step=63, training_loss=2.405070910378108, metrics={'train_runtime': 325.2157, 'train_samples_per_second': 0.769, 'train_steps_per_second': 0.194, 'train_loss': 2.405070910378108, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-72', DATASET='ortega', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
38
+ {'date': '2023-12-29 12:33:54.589552', 'elapsed': '0:16:22.761513', 'result': TrainOutput(global_step=63, training_loss=2.308999606541225, metrics={'train_runtime': 490.5357, 'train_samples_per_second': 0.51, 'train_steps_per_second': 0.128, 'train_loss': 2.308999606541225, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-74', DATASET='novela-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}
39
+ {'date': '2023-12-29 12:54:46.289934', 'elapsed': '0:19:05.067157', 'result': TrainOutput(global_step=63, training_loss=2.2411288155449762, metrics={'train_runtime': 572.3977, 'train_samples_per_second': 0.437, 'train_steps_per_second': 0.11, 'train_loss': 2.2411288155449762, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-76', DATASET='ciencia_ficcion', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}