slplab commited on
Commit
eefe938
1 Parent(s): 5008d3b

End of training

Browse files
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: EleutherAI/polyglot-ko-1.3b
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: polyglot-ko-1.3b_pretrained-asd
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # polyglot-ko-1.3b_pretrained-asd
15
+
16
+ This model is a fine-tuned version of [EleutherAI/polyglot-ko-1.3b](https://huggingface.co/EleutherAI/polyglot-ko-1.3b) on the None dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 2e-05
36
+ - train_batch_size: 1
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - gradient_accumulation_steps: 8
40
+ - total_train_batch_size: 8
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 1
44
+ - mixed_precision_training: Native AMP
45
+
46
+ ### Training results
47
+
48
+
49
+
50
+ ### Framework versions
51
+
52
+ - Transformers 4.41.1
53
+ - Pytorch 2.3.0+cu121
54
+ - Datasets 2.19.1
55
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/polyglot-ko-1.3b",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 8192,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "rope_scaling": null,
22
+ "rotary_emb_base": 10000,
23
+ "rotary_pct": 0.5,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.41.1",
27
+ "use_cache": true,
28
+ "use_parallel_residual": true,
29
+ "vocab_size": 30004
30
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.41.1"
6
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7611ff0043214362930f9fd5b66959567f5765a8bd30fb23cc202be9f4fab7b0
3
+ size 4945961776
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24a543363fee47837353b897eddf0a9089d0b6dc7d80a9d541ca2373958d8073
3
+ size 380068632
model.safetensors.index.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5325996032
4
+ },
5
+ "weight_map": {
6
+ "embed_out.weight": "model-00002-of-00002.safetensors",
7
+ "gpt_neox.embed_in.weight": "model-00001-of-00002.safetensors",
8
+ "gpt_neox.final_layer_norm.bias": "model-00002-of-00002.safetensors",
9
+ "gpt_neox.final_layer_norm.weight": "model-00002-of-00002.safetensors",
10
+ "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00002.safetensors",
11
+ "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00002.safetensors",
12
+ "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
13
+ "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
14
+ "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
15
+ "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
16
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
17
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
18
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
19
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
20
+ "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
21
+ "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00002.safetensors",
23
+ "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00002.safetensors",
24
+ "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
25
+ "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
26
+ "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
27
+ "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
28
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
29
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
30
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
31
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
32
+ "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
33
+ "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
34
+ "gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00002.safetensors",
35
+ "gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00002.safetensors",
36
+ "gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
37
+ "gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
38
+ "gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
39
+ "gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
41
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
42
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
43
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
44
+ "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
45
+ "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00002.safetensors",
47
+ "gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00002.safetensors",
48
+ "gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
49
+ "gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
50
+ "gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
51
+ "gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
52
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
53
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
54
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
55
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
56
+ "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
57
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "gpt_neox.layers.12.attention.dense.bias": "model-00001-of-00002.safetensors",
59
+ "gpt_neox.layers.12.attention.dense.weight": "model-00001-of-00002.safetensors",
60
+ "gpt_neox.layers.12.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
61
+ "gpt_neox.layers.12.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
62
+ "gpt_neox.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
63
+ "gpt_neox.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
65
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
66
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
67
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
68
+ "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
69
+ "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
70
+ "gpt_neox.layers.13.attention.dense.bias": "model-00001-of-00002.safetensors",
71
+ "gpt_neox.layers.13.attention.dense.weight": "model-00001-of-00002.safetensors",
72
+ "gpt_neox.layers.13.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
73
+ "gpt_neox.layers.13.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
74
+ "gpt_neox.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
75
+ "gpt_neox.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
77
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
78
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
79
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
80
+ "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
81
+ "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
82
+ "gpt_neox.layers.14.attention.dense.bias": "model-00001-of-00002.safetensors",
83
+ "gpt_neox.layers.14.attention.dense.weight": "model-00001-of-00002.safetensors",
84
+ "gpt_neox.layers.14.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
85
+ "gpt_neox.layers.14.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
86
+ "gpt_neox.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
87
+ "gpt_neox.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
88
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
89
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
90
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
91
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
92
+ "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
93
+ "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "gpt_neox.layers.15.attention.dense.bias": "model-00001-of-00002.safetensors",
95
+ "gpt_neox.layers.15.attention.dense.weight": "model-00001-of-00002.safetensors",
96
+ "gpt_neox.layers.15.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
97
+ "gpt_neox.layers.15.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
98
+ "gpt_neox.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
99
+ "gpt_neox.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
100
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
101
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
102
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
103
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
104
+ "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
105
+ "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
106
+ "gpt_neox.layers.16.attention.dense.bias": "model-00001-of-00002.safetensors",
107
+ "gpt_neox.layers.16.attention.dense.weight": "model-00001-of-00002.safetensors",
108
+ "gpt_neox.layers.16.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
109
+ "gpt_neox.layers.16.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
110
+ "gpt_neox.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
111
+ "gpt_neox.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
113
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
114
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
115
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
116
+ "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
117
+ "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "gpt_neox.layers.17.attention.dense.bias": "model-00001-of-00002.safetensors",
119
+ "gpt_neox.layers.17.attention.dense.weight": "model-00001-of-00002.safetensors",
120
+ "gpt_neox.layers.17.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
121
+ "gpt_neox.layers.17.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
122
+ "gpt_neox.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
123
+ "gpt_neox.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
124
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
125
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
126
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
127
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
128
+ "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
129
+ "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "gpt_neox.layers.18.attention.dense.bias": "model-00001-of-00002.safetensors",
131
+ "gpt_neox.layers.18.attention.dense.weight": "model-00001-of-00002.safetensors",
132
+ "gpt_neox.layers.18.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
133
+ "gpt_neox.layers.18.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
134
+ "gpt_neox.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
135
+ "gpt_neox.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
136
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
137
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
138
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
139
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
140
+ "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
141
+ "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
142
+ "gpt_neox.layers.19.attention.dense.bias": "model-00001-of-00002.safetensors",
143
+ "gpt_neox.layers.19.attention.dense.weight": "model-00001-of-00002.safetensors",
144
+ "gpt_neox.layers.19.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
145
+ "gpt_neox.layers.19.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
146
+ "gpt_neox.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
147
+ "gpt_neox.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
148
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
149
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
150
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
151
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
152
+ "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
153
+ "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
154
+ "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00002.safetensors",
155
+ "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00002.safetensors",
156
+ "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
157
+ "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
158
+ "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
159
+ "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
160
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
161
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
162
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
163
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
164
+ "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
165
+ "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "gpt_neox.layers.20.attention.dense.bias": "model-00001-of-00002.safetensors",
167
+ "gpt_neox.layers.20.attention.dense.weight": "model-00001-of-00002.safetensors",
168
+ "gpt_neox.layers.20.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
169
+ "gpt_neox.layers.20.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
170
+ "gpt_neox.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
171
+ "gpt_neox.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
172
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
173
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
174
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
175
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
176
+ "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
177
+ "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
178
+ "gpt_neox.layers.21.attention.dense.bias": "model-00001-of-00002.safetensors",
179
+ "gpt_neox.layers.21.attention.dense.weight": "model-00001-of-00002.safetensors",
180
+ "gpt_neox.layers.21.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
181
+ "gpt_neox.layers.21.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
182
+ "gpt_neox.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
183
+ "gpt_neox.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
184
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
185
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
186
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
187
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
188
+ "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
189
+ "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "gpt_neox.layers.22.attention.dense.bias": "model-00001-of-00002.safetensors",
191
+ "gpt_neox.layers.22.attention.dense.weight": "model-00001-of-00002.safetensors",
192
+ "gpt_neox.layers.22.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
193
+ "gpt_neox.layers.22.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
194
+ "gpt_neox.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
195
+ "gpt_neox.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
196
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
197
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
198
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
199
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
200
+ "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
201
+ "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
202
+ "gpt_neox.layers.23.attention.dense.bias": "model-00001-of-00002.safetensors",
203
+ "gpt_neox.layers.23.attention.dense.weight": "model-00001-of-00002.safetensors",
204
+ "gpt_neox.layers.23.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
205
+ "gpt_neox.layers.23.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
206
+ "gpt_neox.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
207
+ "gpt_neox.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
208
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
209
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
210
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
211
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
212
+ "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
213
+ "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
214
+ "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00002.safetensors",
215
+ "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00002.safetensors",
216
+ "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
217
+ "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
218
+ "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
219
+ "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
220
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
221
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
222
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
223
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
224
+ "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
225
+ "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
226
+ "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00002.safetensors",
227
+ "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00002.safetensors",
228
+ "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
229
+ "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
230
+ "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
231
+ "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
232
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
233
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
234
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
235
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
236
+ "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
237
+ "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
238
+ "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00002.safetensors",
239
+ "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00002.safetensors",
240
+ "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
241
+ "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
242
+ "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
243
+ "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
244
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
245
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
246
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
247
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
248
+ "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
249
+ "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
250
+ "gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00002.safetensors",
251
+ "gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00002.safetensors",
252
+ "gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
253
+ "gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
254
+ "gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
255
+ "gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
256
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
257
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
258
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
259
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
260
+ "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
261
+ "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
262
+ "gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00002.safetensors",
263
+ "gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00002.safetensors",
264
+ "gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
265
+ "gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
266
+ "gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
267
+ "gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
268
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
269
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
270
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
271
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
272
+ "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
273
+ "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
274
+ "gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00002.safetensors",
275
+ "gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00002.safetensors",
276
+ "gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
277
+ "gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
278
+ "gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
279
+ "gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
280
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
281
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
282
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
283
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
284
+ "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
285
+ "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
286
+ "gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00002.safetensors",
287
+ "gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00002.safetensors",
288
+ "gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
289
+ "gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
290
+ "gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
291
+ "gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
292
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
293
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
294
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
295
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
296
+ "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
297
+ "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors"
298
+ }
299
+ }
runs/Jul30_19-45-12_oem-WS-C621E-SAGE-Series/events.out.tfevents.1722336319.oem-WS-C621E-SAGE-Series.2698331.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3957ee53e3c2ca3ff3532841401138e9ddde2112d32eaa8bc3de1c93e5c191a1
3
+ size 5101
runs/Jul30_20-22-55_oem-WS-C621E-SAGE-Series/events.out.tfevents.1722338578.oem-WS-C621E-SAGE-Series.2699069.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f08818660989995fa637d96d241fb0061ac71d13a87cd533974a61e09d599721
3
+ size 5101
runs/Jul30_20-28-06_oem-WS-C621E-SAGE-Series/events.out.tfevents.1722338886.oem-WS-C621E-SAGE-Series.2699368.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b97e05cd2eca1a0bced050cec826a6b5e36ec771926718a07de53fa67b3c5ce
3
+ size 5101
runs/Jul30_20-33-59_oem-WS-C621E-SAGE-Series/events.out.tfevents.1722339240.oem-WS-C621E-SAGE-Series.2699717.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfacbad6744985a00512d4b7a4c11117acbfe4a2077fc4a9a9f7f65fedbc4e70
3
+ size 5101
runs/Jul30_20-37-39_oem-WS-C621E-SAGE-Series/events.out.tfevents.1722339460.oem-WS-C621E-SAGE-Series.2699976.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a07c20df45a39db401e31615e3fe7dd528e40185ffdedc133d2ef5e062f955
3
+ size 5873
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4229a36a3b671af113e7da7127b13e4b50b77787aef375bf5aff4ffbb067800
3
+ size 5240