Hugging Face's logo

ICT3214-Group5
/
MD5_gpt_neo_L_v1.0.0

Text Generation
Transformers
TensorBoard
Safetensors
gpt_neo
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
dariuslimzh commited on
Commit
2a435ef
•
1 Parent(s): 87b12aa

Training in progress, epoch 0

Browse files
Files changed (6) hide show
  1. config.json +75 -0
  2. model-00001-of-00002.safetensors +3 -0
  3. model-00002-of-00002.safetensors +3 -0
  4. model.safetensors.index.json +323 -0
  5. runs/Nov04_06-22-17_c0127cf41be4/events.out.tfevents.1730701339.c0127cf41be4.7577.0 +3 -0
  6. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-1.3B",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local",
21
+ "global",
22
+ "local",
23
+ "global",
24
+ "local",
25
+ "global",
26
+ "local",
27
+ "global",
28
+ "local",
29
+ "global",
30
+ "local",
31
+ "global",
32
+ "local"
33
+ ],
34
+ "attention_types": [
35
+ [
36
+ [
37
+ "global",
38
+ "local"
39
+ ],
40
+ 12
41
+ ]
42
+ ],
43
+ "bos_token_id": 50256,
44
+ "classifier_dropout": 0.1,
45
+ "embed_dropout": 0,
46
+ "eos_token_id": 50256,
47
+ "gradient_checkpointing": false,
48
+ "hidden_size": 2048,
49
+ "initializer_range": 0.02,
50
+ "intermediate_size": null,
51
+ "layer_norm_epsilon": 1e-05,
52
+ "max_position_embeddings": 2048,
53
+ "model_type": "gpt_neo",
54
+ "num_heads": 16,
55
+ "num_layers": 24,
56
+ "resid_dropout": 0,
57
+ "summary_activation": null,
58
+ "summary_first_dropout": 0.1,
59
+ "summary_proj_to_labels": true,
60
+ "summary_type": "cls_index",
61
+ "summary_use_proj": true,
62
+ "task_specific_params": {
63
+ "text-generation": {
64
+ "do_sample": true,
65
+ "max_length": 50,
66
+ "temperature": 0.9
67
+ }
68
+ },
69
+ "tokenizer_class": "GPT2Tokenizer",
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.44.2",
72
+ "use_cache": true,
73
+ "vocab_size": 50257,
74
+ "window_size": 256
75
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec50bc3f29d1ef2f2922b50f326022ae20040eb7d14d4ca2180e6ae41119b7be
3
+ size 4993794184
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c245832987f8ce1325077878b05b55a9cb00ed6077e7c4257791447ed6653d4
3
+ size 268543784
model.safetensors.index.json ADDED
@@ -0,0 +1,323 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5262303232
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
7
+ "transformer.h.0.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
8
+ "transformer.h.0.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
9
+ "transformer.h.0.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
10
+ "transformer.h.0.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
11
+ "transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
12
+ "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
13
+ "transformer.h.0.ln_2.bias": "model-00001-of-00002.safetensors",
14
+ "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
15
+ "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
16
+ "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
17
+ "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
18
+ "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
19
+ "transformer.h.1.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
20
+ "transformer.h.1.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
21
+ "transformer.h.1.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
22
+ "transformer.h.1.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
23
+ "transformer.h.1.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
24
+ "transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
25
+ "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
26
+ "transformer.h.1.ln_2.bias": "model-00001-of-00002.safetensors",
27
+ "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
28
+ "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
29
+ "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
30
+ "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
31
+ "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
32
+ "transformer.h.10.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
33
+ "transformer.h.10.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
34
+ "transformer.h.10.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
35
+ "transformer.h.10.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
36
+ "transformer.h.10.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
37
+ "transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
38
+ "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
39
+ "transformer.h.10.ln_2.bias": "model-00001-of-00002.safetensors",
40
+ "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
41
+ "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
42
+ "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
43
+ "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
44
+ "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
45
+ "transformer.h.11.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
46
+ "transformer.h.11.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
47
+ "transformer.h.11.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
48
+ "transformer.h.11.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
49
+ "transformer.h.11.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
50
+ "transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
51
+ "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
52
+ "transformer.h.11.ln_2.bias": "model-00001-of-00002.safetensors",
53
+ "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
54
+ "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
55
+ "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
56
+ "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
57
+ "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
58
+ "transformer.h.12.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "transformer.h.12.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
60
+ "transformer.h.12.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
61
+ "transformer.h.12.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
62
+ "transformer.h.12.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
63
+ "transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
64
+ "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
65
+ "transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
66
+ "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
67
+ "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
68
+ "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
69
+ "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
70
+ "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
71
+ "transformer.h.13.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
72
+ "transformer.h.13.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
73
+ "transformer.h.13.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
74
+ "transformer.h.13.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
75
+ "transformer.h.13.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
76
+ "transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
77
+ "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
78
+ "transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
79
+ "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
80
+ "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
81
+ "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
82
+ "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
83
+ "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
84
+ "transformer.h.14.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
85
+ "transformer.h.14.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
86
+ "transformer.h.14.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
87
+ "transformer.h.14.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "transformer.h.14.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
90
+ "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
91
+ "transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
92
+ "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
93
+ "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
94
+ "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
95
+ "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
96
+ "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
97
+ "transformer.h.15.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
98
+ "transformer.h.15.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
99
+ "transformer.h.15.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
100
+ "transformer.h.15.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
101
+ "transformer.h.15.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
102
+ "transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
103
+ "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
104
+ "transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
105
+ "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
106
+ "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
107
+ "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
108
+ "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
109
+ "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
110
+ "transformer.h.16.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
111
+ "transformer.h.16.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
112
+ "transformer.h.16.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
113
+ "transformer.h.16.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "transformer.h.16.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
116
+ "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
117
+ "transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
118
+ "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
119
+ "transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
120
+ "transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
121
+ "transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
122
+ "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
123
+ "transformer.h.17.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
124
+ "transformer.h.17.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
125
+ "transformer.h.17.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
126
+ "transformer.h.17.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
127
+ "transformer.h.17.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
128
+ "transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
129
+ "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
130
+ "transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
131
+ "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
132
+ "transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
133
+ "transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
134
+ "transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
135
+ "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
136
+ "transformer.h.18.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
137
+ "transformer.h.18.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
138
+ "transformer.h.18.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
139
+ "transformer.h.18.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
140
+ "transformer.h.18.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
141
+ "transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
142
+ "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
143
+ "transformer.h.18.ln_2.bias": "model-00001-of-00002.safetensors",
144
+ "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
145
+ "transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
146
+ "transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
147
+ "transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
148
+ "transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
149
+ "transformer.h.19.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
150
+ "transformer.h.19.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
151
+ "transformer.h.19.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
152
+ "transformer.h.19.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
153
+ "transformer.h.19.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
154
+ "transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
155
+ "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
156
+ "transformer.h.19.ln_2.bias": "model-00001-of-00002.safetensors",
157
+ "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
158
+ "transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
159
+ "transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
160
+ "transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
161
+ "transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
162
+ "transformer.h.2.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
163
+ "transformer.h.2.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
164
+ "transformer.h.2.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
165
+ "transformer.h.2.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
166
+ "transformer.h.2.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
167
+ "transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
168
+ "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
169
+ "transformer.h.2.ln_2.bias": "model-00001-of-00002.safetensors",
170
+ "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
171
+ "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
172
+ "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
173
+ "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
174
+ "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
175
+ "transformer.h.20.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
176
+ "transformer.h.20.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
177
+ "transformer.h.20.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
178
+ "transformer.h.20.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
179
+ "transformer.h.20.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
180
+ "transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
181
+ "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
182
+ "transformer.h.20.ln_2.bias": "model-00001-of-00002.safetensors",
183
+ "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
184
+ "transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
185
+ "transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
186
+ "transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
187
+ "transformer.h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
188
+ "transformer.h.21.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
189
+ "transformer.h.21.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
190
+ "transformer.h.21.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
191
+ "transformer.h.21.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
192
+ "transformer.h.21.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
193
+ "transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
194
+ "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
195
+ "transformer.h.21.ln_2.bias": "model-00001-of-00002.safetensors",
196
+ "transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
197
+ "transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
198
+ "transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
199
+ "transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
200
+ "transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
201
+ "transformer.h.22.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
202
+ "transformer.h.22.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
203
+ "transformer.h.22.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
204
+ "transformer.h.22.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
205
+ "transformer.h.22.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
206
+ "transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
207
+ "transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
208
+ "transformer.h.22.ln_2.bias": "model-00001-of-00002.safetensors",
209
+ "transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
210
+ "transformer.h.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
211
+ "transformer.h.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
212
+ "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
213
+ "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
214
+ "transformer.h.23.attn.attention.k_proj.weight": "model-00002-of-00002.safetensors",
215
+ "transformer.h.23.attn.attention.out_proj.bias": "model-00002-of-00002.safetensors",
216
+ "transformer.h.23.attn.attention.out_proj.weight": "model-00002-of-00002.safetensors",
217
+ "transformer.h.23.attn.attention.q_proj.weight": "model-00002-of-00002.safetensors",
218
+ "transformer.h.23.attn.attention.v_proj.weight": "model-00002-of-00002.safetensors",
219
+ "transformer.h.23.ln_1.bias": "model-00002-of-00002.safetensors",
220
+ "transformer.h.23.ln_1.weight": "model-00002-of-00002.safetensors",
221
+ "transformer.h.23.ln_2.bias": "model-00002-of-00002.safetensors",
222
+ "transformer.h.23.ln_2.weight": "model-00002-of-00002.safetensors",
223
+ "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
224
+ "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
225
+ "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
226
+ "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
227
+ "transformer.h.3.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
228
+ "transformer.h.3.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
229
+ "transformer.h.3.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
230
+ "transformer.h.3.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
231
+ "transformer.h.3.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
232
+ "transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
233
+ "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
234
+ "transformer.h.3.ln_2.bias": "model-00001-of-00002.safetensors",
235
+ "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
236
+ "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
237
+ "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
238
+ "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
239
+ "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
240
+ "transformer.h.4.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
241
+ "transformer.h.4.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
242
+ "transformer.h.4.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
243
+ "transformer.h.4.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
244
+ "transformer.h.4.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
245
+ "transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
246
+ "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
247
+ "transformer.h.4.ln_2.bias": "model-00001-of-00002.safetensors",
248
+ "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
249
+ "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
250
+ "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
251
+ "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
252
+ "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
253
+ "transformer.h.5.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
254
+ "transformer.h.5.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
255
+ "transformer.h.5.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
256
+ "transformer.h.5.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
257
+ "transformer.h.5.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
258
+ "transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
259
+ "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
260
+ "transformer.h.5.ln_2.bias": "model-00001-of-00002.safetensors",
261
+ "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
262
+ "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
263
+ "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
264
+ "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
265
+ "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
266
+ "transformer.h.6.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
267
+ "transformer.h.6.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
268
+ "transformer.h.6.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
269
+ "transformer.h.6.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
270
+ "transformer.h.6.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
271
+ "transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
272
+ "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
273
+ "transformer.h.6.ln_2.bias": "model-00001-of-00002.safetensors",
274
+ "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
275
+ "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
276
+ "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
277
+ "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
278
+ "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
279
+ "transformer.h.7.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
280
+ "transformer.h.7.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
281
+ "transformer.h.7.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
282
+ "transformer.h.7.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
283
+ "transformer.h.7.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
284
+ "transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
285
+ "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
286
+ "transformer.h.7.ln_2.bias": "model-00001-of-00002.safetensors",
287
+ "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
288
+ "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
289
+ "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
290
+ "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
291
+ "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
292
+ "transformer.h.8.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
293
+ "transformer.h.8.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
294
+ "transformer.h.8.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
295
+ "transformer.h.8.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
296
+ "transformer.h.8.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
297
+ "transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
298
+ "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
299
+ "transformer.h.8.ln_2.bias": "model-00001-of-00002.safetensors",
300
+ "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
301
+ "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
302
+ "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
303
+ "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
304
+ "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
305
+ "transformer.h.9.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
306
+ "transformer.h.9.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
307
+ "transformer.h.9.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
308
+ "transformer.h.9.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
309
+ "transformer.h.9.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
310
+ "transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
311
+ "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
312
+ "transformer.h.9.ln_2.bias": "model-00001-of-00002.safetensors",
313
+ "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
314
+ "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
315
+ "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
316
+ "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
317
+ "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
318
+ "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
319
+ "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
320
+ "transformer.wpe.weight": "model-00001-of-00002.safetensors",
321
+ "transformer.wte.weight": "model-00001-of-00002.safetensors"
322
+ }
323
+ }
runs/Nov04_06-22-17_c0127cf41be4/events.out.tfevents.1730701339.c0127cf41be4.7577.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1a5c1a6e9ec9485f4b20a62fbe64efe88d71814c357806d312e241aaaf02ff2
3
+ size 6147
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b0736698bb7105a3dcd9060af3796f1586d2b8257e12113bfe96a76d576734
3
+ size 5240