yongzx commited on
Commit
43d9b35
1 Parent(s): 71613e2

Push to HF hub

Browse files
.gitattributes CHANGED
@@ -31,3 +31,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
31
  *.zip filter=lfs diff=lfs merge=lfs -text
32
  *.zst filter=lfs diff=lfs merge=lfs -text
33
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
31
  *.zip filter=lfs diff=lfs merge=lfs -text
32
  *.zst filter=lfs diff=lfs merge=lfs -text
33
  *tfevents* filter=lfs diff=lfs merge=lfs -text
34
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ checkpoint-20000/
2
+ checkpoint-25000/
3
+ checkpoint-15000/
4
+ checkpoint-10000/
5
+ checkpoint-5000/
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigscience/bloom-7b1",
3
+ "adapters": {
4
+ "adapters": {},
5
+ "config_map": {},
6
+ "fusion_config_map": {},
7
+ "fusions": {}
8
+ },
9
+ "apply_residual_connection_post_layernorm": false,
10
+ "architectures": [
11
+ "BloomForCausalLM"
12
+ ],
13
+ "attention_dropout": 0.0,
14
+ "attention_softmax_in_fp32": true,
15
+ "bias_dropout_fusion": true,
16
+ "bos_token_id": 1,
17
+ "eos_token_id": 2,
18
+ "hidden_dropout": 0.0,
19
+ "hidden_size": 4096,
20
+ "initializer_range": 0.02,
21
+ "layer_norm_epsilon": 1e-05,
22
+ "masked_softmax_fusion": true,
23
+ "model_type": "bloom",
24
+ "n_head": 32,
25
+ "n_inner": null,
26
+ "n_layer": 30,
27
+ "offset_alibi": 100,
28
+ "pad_token_id": 3,
29
+ "pretraining_tp": 1,
30
+ "skip_bias_add": true,
31
+ "skip_bias_add_qkv": false,
32
+ "slow_but_exact": false,
33
+ "torch_dtype": "float16",
34
+ "transformers_version": "4.20.0.dev0",
35
+ "unk_token_id": 0,
36
+ "use_cache": true,
37
+ "vocab_size": 250880
38
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5217314093d835dc2806f3c0a0ba0359e8d8cd59fe00ae7ec8eb0393d118f981
3
+ size 14138066130
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68f2c69f6dfed9f007397c528cae0a296031a6b707b99d11682a32e22f064faf
3
+ size 14138049874
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,373 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16193241088
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
7
+ "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
8
+ "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
9
+ "transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
10
+ "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
11
+ "transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
12
+ "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
13
+ "transformer.h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
14
+ "transformer.h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
15
+ "transformer.h.0.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
16
+ "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
17
+ "transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
18
+ "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
19
+ "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
20
+ "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
21
+ "transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
22
+ "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
23
+ "transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
24
+ "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
25
+ "transformer.h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
26
+ "transformer.h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
27
+ "transformer.h.1.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
28
+ "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
29
+ "transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
30
+ "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
31
+ "transformer.h.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
32
+ "transformer.h.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
33
+ "transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
34
+ "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
35
+ "transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
36
+ "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
37
+ "transformer.h.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
38
+ "transformer.h.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
39
+ "transformer.h.10.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
40
+ "transformer.h.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
41
+ "transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
42
+ "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
43
+ "transformer.h.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
44
+ "transformer.h.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
45
+ "transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
46
+ "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
47
+ "transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
48
+ "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
49
+ "transformer.h.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
50
+ "transformer.h.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
51
+ "transformer.h.11.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
52
+ "transformer.h.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
53
+ "transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
54
+ "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
55
+ "transformer.h.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
56
+ "transformer.h.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
57
+ "transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
58
+ "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
59
+ "transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
60
+ "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
61
+ "transformer.h.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
62
+ "transformer.h.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
63
+ "transformer.h.12.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
64
+ "transformer.h.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
65
+ "transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
66
+ "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
67
+ "transformer.h.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
68
+ "transformer.h.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
69
+ "transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
70
+ "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
71
+ "transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
72
+ "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
73
+ "transformer.h.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
74
+ "transformer.h.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
75
+ "transformer.h.13.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
76
+ "transformer.h.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
77
+ "transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
78
+ "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
79
+ "transformer.h.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
80
+ "transformer.h.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
81
+ "transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
82
+ "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
83
+ "transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
84
+ "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
85
+ "transformer.h.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
86
+ "transformer.h.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
87
+ "transformer.h.14.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
88
+ "transformer.h.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
89
+ "transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
90
+ "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
91
+ "transformer.h.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
92
+ "transformer.h.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
93
+ "transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
94
+ "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
95
+ "transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
96
+ "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
97
+ "transformer.h.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
98
+ "transformer.h.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
99
+ "transformer.h.15.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
100
+ "transformer.h.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
101
+ "transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
102
+ "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
103
+ "transformer.h.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
104
+ "transformer.h.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
105
+ "transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
106
+ "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
107
+ "transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
108
+ "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
109
+ "transformer.h.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
110
+ "transformer.h.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
111
+ "transformer.h.16.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
112
+ "transformer.h.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
113
+ "transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
114
+ "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
115
+ "transformer.h.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
116
+ "transformer.h.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
117
+ "transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
118
+ "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
119
+ "transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
120
+ "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
121
+ "transformer.h.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
122
+ "transformer.h.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
123
+ "transformer.h.17.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
124
+ "transformer.h.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
125
+ "transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
126
+ "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
127
+ "transformer.h.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
128
+ "transformer.h.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
129
+ "transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
130
+ "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
131
+ "transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
132
+ "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
133
+ "transformer.h.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
134
+ "transformer.h.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
135
+ "transformer.h.18.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
136
+ "transformer.h.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
137
+ "transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
138
+ "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
139
+ "transformer.h.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
140
+ "transformer.h.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
141
+ "transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
142
+ "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
143
+ "transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
144
+ "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
145
+ "transformer.h.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
146
+ "transformer.h.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
147
+ "transformer.h.19.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
148
+ "transformer.h.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
149
+ "transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
150
+ "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
151
+ "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
152
+ "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
153
+ "transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
154
+ "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
155
+ "transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
156
+ "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
157
+ "transformer.h.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
158
+ "transformer.h.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
159
+ "transformer.h.2.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
160
+ "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
161
+ "transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
162
+ "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
163
+ "transformer.h.20.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
164
+ "transformer.h.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
165
+ "transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
166
+ "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
167
+ "transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
168
+ "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
169
+ "transformer.h.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
170
+ "transformer.h.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
171
+ "transformer.h.20.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
172
+ "transformer.h.20.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
173
+ "transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
174
+ "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
175
+ "transformer.h.21.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
176
+ "transformer.h.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
177
+ "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
178
+ "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
179
+ "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
180
+ "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
181
+ "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
182
+ "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
183
+ "transformer.h.21.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
184
+ "transformer.h.21.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
185
+ "transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
186
+ "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
187
+ "transformer.h.22.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
188
+ "transformer.h.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
189
+ "transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
190
+ "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
191
+ "transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
192
+ "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
193
+ "transformer.h.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
194
+ "transformer.h.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
195
+ "transformer.h.22.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
196
+ "transformer.h.22.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
197
+ "transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
198
+ "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
199
+ "transformer.h.23.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
200
+ "transformer.h.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
201
+ "transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
202
+ "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
203
+ "transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
204
+ "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
205
+ "transformer.h.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
206
+ "transformer.h.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
207
+ "transformer.h.23.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
208
+ "transformer.h.23.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
209
+ "transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
210
+ "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
211
+ "transformer.h.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
212
+ "transformer.h.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
213
+ "transformer.h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
214
+ "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
215
+ "transformer.h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
216
+ "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
217
+ "transformer.h.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
218
+ "transformer.h.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
219
+ "transformer.h.24.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
220
+ "transformer.h.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
221
+ "transformer.h.24.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
222
+ "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
223
+ "transformer.h.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
224
+ "transformer.h.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
225
+ "transformer.h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
226
+ "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
227
+ "transformer.h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
228
+ "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
229
+ "transformer.h.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
230
+ "transformer.h.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
231
+ "transformer.h.25.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
232
+ "transformer.h.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
233
+ "transformer.h.25.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
234
+ "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
235
+ "transformer.h.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
236
+ "transformer.h.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
237
+ "transformer.h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
238
+ "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
239
+ "transformer.h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
240
+ "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
241
+ "transformer.h.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
242
+ "transformer.h.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
243
+ "transformer.h.26.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
244
+ "transformer.h.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
245
+ "transformer.h.26.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
246
+ "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
247
+ "transformer.h.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
248
+ "transformer.h.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
249
+ "transformer.h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
250
+ "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
251
+ "transformer.h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
252
+ "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
253
+ "transformer.h.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
254
+ "transformer.h.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
255
+ "transformer.h.27.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
256
+ "transformer.h.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
257
+ "transformer.h.27.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
258
+ "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
259
+ "transformer.h.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
260
+ "transformer.h.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
261
+ "transformer.h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
262
+ "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
263
+ "transformer.h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
264
+ "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
265
+ "transformer.h.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
266
+ "transformer.h.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
267
+ "transformer.h.28.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
268
+ "transformer.h.28.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
269
+ "transformer.h.28.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
270
+ "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
271
+ "transformer.h.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
272
+ "transformer.h.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
273
+ "transformer.h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
274
+ "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
275
+ "transformer.h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
276
+ "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
277
+ "transformer.h.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
278
+ "transformer.h.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
279
+ "transformer.h.29.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
280
+ "transformer.h.29.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
281
+ "transformer.h.29.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
282
+ "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
283
+ "transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
284
+ "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
285
+ "transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
286
+ "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
287
+ "transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
288
+ "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
289
+ "transformer.h.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
290
+ "transformer.h.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
291
+ "transformer.h.3.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
292
+ "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
293
+ "transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
294
+ "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
295
+ "transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
296
+ "transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
297
+ "transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
298
+ "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
299
+ "transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
300
+ "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
301
+ "transformer.h.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
302
+ "transformer.h.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
303
+ "transformer.h.4.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
304
+ "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
305
+ "transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
306
+ "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
307
+ "transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
308
+ "transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
309
+ "transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
310
+ "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
311
+ "transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
312
+ "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
313
+ "transformer.h.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
314
+ "transformer.h.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
315
+ "transformer.h.5.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
316
+ "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
317
+ "transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
318
+ "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
319
+ "transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
320
+ "transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
321
+ "transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
322
+ "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
323
+ "transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
324
+ "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
325
+ "transformer.h.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
326
+ "transformer.h.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
327
+ "transformer.h.6.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
328
+ "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
329
+ "transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
330
+ "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
331
+ "transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
332
+ "transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
333
+ "transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
334
+ "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
335
+ "transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
336
+ "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
337
+ "transformer.h.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
338
+ "transformer.h.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
339
+ "transformer.h.7.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
340
+ "transformer.h.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
341
+ "transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
342
+ "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
343
+ "transformer.h.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
344
+ "transformer.h.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
345
+ "transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
346
+ "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
347
+ "transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
348
+ "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
349
+ "transformer.h.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
350
+ "transformer.h.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
351
+ "transformer.h.8.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
352
+ "transformer.h.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
353
+ "transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
354
+ "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
355
+ "transformer.h.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
356
+ "transformer.h.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
357
+ "transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
358
+ "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
359
+ "transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
360
+ "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
361
+ "transformer.h.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
362
+ "transformer.h.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
363
+ "transformer.h.9.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
364
+ "transformer.h.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
365
+ "transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
366
+ "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
367
+ "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
368
+ "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
369
+ "transformer.word_embeddings.weight": "pytorch_model-00001-of-00002.bin",
370
+ "transformer.word_embeddings_layernorm.bias": "pytorch_model-00001-of-00002.bin",
371
+ "transformer.word_embeddings_layernorm.weight": "pytorch_model-00001-of-00002.bin"
372
+ }
373
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f6efc66e73f1fd69da4f436e48befb519fdff3fe18910850c1d41bd862293a5
3
+ size 14500443
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "add_prefix_space": false, "name_or_path": "bigscience/bloom-7b1", "special_tokens_map_file": null, "padding_side": "left", "tokenizer_class": "BloomTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.08203125,
3
+ "best_model_checkpoint": "/home/zhengxinyong/outputs/bloom-7b1_th_continual-pretrain_100000samples_-1vocab_original/checkpoint-25000",
4
+ "epoch": 1.2926577042399172,
5
+ "global_step": 25000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.13,
12
+ "learning_rate": 0.0001,
13
+ "loss": 1.5461,
14
+ "step": 2500
15
+ },
16
+ {
17
+ "epoch": 0.26,
18
+ "learning_rate": 0.0001,
19
+ "loss": 1.2551,
20
+ "step": 5000
21
+ },
22
+ {
23
+ "epoch": 0.26,
24
+ "eval_loss": 1.248046875,
25
+ "eval_runtime": 23.2835,
26
+ "eval_samples_per_second": 66.442,
27
+ "eval_steps_per_second": 8.332,
28
+ "step": 5000
29
+ },
30
+ {
31
+ "epoch": 0.39,
32
+ "learning_rate": 0.0001,
33
+ "loss": 1.1849,
34
+ "step": 7500
35
+ },
36
+ {
37
+ "epoch": 0.52,
38
+ "learning_rate": 0.0001,
39
+ "loss": 1.1396,
40
+ "step": 10000
41
+ },
42
+ {
43
+ "epoch": 0.52,
44
+ "eval_loss": 1.1669921875,
45
+ "eval_runtime": 23.3161,
46
+ "eval_samples_per_second": 66.349,
47
+ "eval_steps_per_second": 8.32,
48
+ "step": 10000
49
+ },
50
+ {
51
+ "epoch": 0.65,
52
+ "learning_rate": 0.0001,
53
+ "loss": 1.117,
54
+ "step": 12500
55
+ },
56
+ {
57
+ "epoch": 0.78,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.09,
60
+ "step": 15000
61
+ },
62
+ {
63
+ "epoch": 0.78,
64
+ "eval_loss": 1.1279296875,
65
+ "eval_runtime": 23.3005,
66
+ "eval_samples_per_second": 66.393,
67
+ "eval_steps_per_second": 8.326,
68
+ "step": 15000
69
+ },
70
+ {
71
+ "epoch": 0.9,
72
+ "learning_rate": 0.0001,
73
+ "loss": 1.0693,
74
+ "step": 17500
75
+ },
76
+ {
77
+ "epoch": 1.03,
78
+ "learning_rate": 0.0001,
79
+ "loss": 1.0416,
80
+ "step": 20000
81
+ },
82
+ {
83
+ "epoch": 1.03,
84
+ "eval_loss": 1.099609375,
85
+ "eval_runtime": 23.2985,
86
+ "eval_samples_per_second": 66.399,
87
+ "eval_steps_per_second": 8.327,
88
+ "step": 20000
89
+ },
90
+ {
91
+ "epoch": 1.16,
92
+ "learning_rate": 0.0001,
93
+ "loss": 0.9778,
94
+ "step": 22500
95
+ },
96
+ {
97
+ "epoch": 1.29,
98
+ "learning_rate": 0.0001,
99
+ "loss": 0.9761,
100
+ "step": 25000
101
+ },
102
+ {
103
+ "epoch": 1.29,
104
+ "eval_loss": 1.08203125,
105
+ "eval_runtime": 23.3142,
106
+ "eval_samples_per_second": 66.354,
107
+ "eval_steps_per_second": 8.321,
108
+ "step": 25000
109
+ }
110
+ ],
111
+ "max_steps": 25000,
112
+ "num_train_epochs": 2,
113
+ "total_flos": 7.423686731586601e+18,
114
+ "trial_name": null,
115
+ "trial_params": null
116
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e7dac8d45932ad34215827081e93a780d408b5670d445a75fed4423272ce37e
3
+ size 4411