TangQiaoYu
commited on
Commit
•
be35992
1
Parent(s):
45fd923
upload
Browse files- README.md +7 -0
- config.json +23 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +34 -0
- trainer_state.json +583 -0
README.md
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
## Introduction
|
2 |
+
`ToolAlpaca` is a large language model demonstrating generalized tool-use alibities, trained only on 3.9k simulated tool-use instances. See [our paper](https://arxiv.org/abs/2306.05301) for more details.
|
3 |
+
|
4 |
+
## Links
|
5 |
+
- Paper: https://arxiv.org/abs/2306.05301
|
6 |
+
- Code & Data: https://github.com/tangqiaoyu/ToolAlpaca
|
7 |
+
- ToolAlpaca-13B: https://huggingface.co/TangQiaoYu/ToolAlpaca-13B
|
config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "models/vicuna-7b/",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 4096,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 11008,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
+
"model_type": "llama",
|
14 |
+
"num_attention_heads": 32,
|
15 |
+
"num_hidden_layers": 32,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"rms_norm_eps": 1e-06,
|
18 |
+
"tie_word_embeddings": false,
|
19 |
+
"torch_dtype": "bfloat16",
|
20 |
+
"transformers_version": "4.29.2",
|
21 |
+
"use_cache": true,
|
22 |
+
"vocab_size": 32000
|
23 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.29.2"
|
7 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:741d8f37ec327ac7074528ff1d11d522940d04b81d5ecf73d5b0bdf1bc0a4102
|
3 |
+
size 13476942241
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"model_max_length": 2048,
|
22 |
+
"pad_token": null,
|
23 |
+
"padding_side": "right",
|
24 |
+
"sp_model_kwargs": {},
|
25 |
+
"tokenizer_class": "LlamaTokenizer",
|
26 |
+
"unk_token": {
|
27 |
+
"__type": "AddedToken",
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,583 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 93,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.03,
|
12 |
+
"learning_rate": 0.0,
|
13 |
+
"loss": 0.6543,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.06,
|
18 |
+
"learning_rate": 1.2618595071429148e-05,
|
19 |
+
"loss": 0.3535,
|
20 |
+
"step": 2
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.1,
|
24 |
+
"learning_rate": 2e-05,
|
25 |
+
"loss": 0.3599,
|
26 |
+
"step": 3
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.13,
|
30 |
+
"learning_rate": 2e-05,
|
31 |
+
"loss": 0.2832,
|
32 |
+
"step": 4
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.16,
|
36 |
+
"learning_rate": 2e-05,
|
37 |
+
"loss": 0.2739,
|
38 |
+
"step": 5
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.19,
|
42 |
+
"learning_rate": 2e-05,
|
43 |
+
"loss": 0.2388,
|
44 |
+
"step": 6
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.23,
|
48 |
+
"learning_rate": 2e-05,
|
49 |
+
"loss": 0.2554,
|
50 |
+
"step": 7
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.26,
|
54 |
+
"learning_rate": 2e-05,
|
55 |
+
"loss": 0.2375,
|
56 |
+
"step": 8
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.29,
|
60 |
+
"learning_rate": 2e-05,
|
61 |
+
"loss": 0.2207,
|
62 |
+
"step": 9
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.32,
|
66 |
+
"learning_rate": 2e-05,
|
67 |
+
"loss": 0.2139,
|
68 |
+
"step": 10
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.35,
|
72 |
+
"learning_rate": 2e-05,
|
73 |
+
"loss": 0.2019,
|
74 |
+
"step": 11
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.39,
|
78 |
+
"learning_rate": 2e-05,
|
79 |
+
"loss": 0.1963,
|
80 |
+
"step": 12
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.42,
|
84 |
+
"learning_rate": 2e-05,
|
85 |
+
"loss": 0.1826,
|
86 |
+
"step": 13
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.45,
|
90 |
+
"learning_rate": 2e-05,
|
91 |
+
"loss": 0.2029,
|
92 |
+
"step": 14
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.48,
|
96 |
+
"learning_rate": 2e-05,
|
97 |
+
"loss": 0.186,
|
98 |
+
"step": 15
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.52,
|
102 |
+
"learning_rate": 2e-05,
|
103 |
+
"loss": 0.197,
|
104 |
+
"step": 16
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.55,
|
108 |
+
"learning_rate": 2e-05,
|
109 |
+
"loss": 0.1863,
|
110 |
+
"step": 17
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.58,
|
114 |
+
"learning_rate": 2e-05,
|
115 |
+
"loss": 0.1787,
|
116 |
+
"step": 18
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.61,
|
120 |
+
"learning_rate": 2e-05,
|
121 |
+
"loss": 0.1902,
|
122 |
+
"step": 19
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.65,
|
126 |
+
"learning_rate": 2e-05,
|
127 |
+
"loss": 0.1775,
|
128 |
+
"step": 20
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.68,
|
132 |
+
"learning_rate": 2e-05,
|
133 |
+
"loss": 0.1707,
|
134 |
+
"step": 21
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.71,
|
138 |
+
"learning_rate": 2e-05,
|
139 |
+
"loss": 0.1785,
|
140 |
+
"step": 22
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.74,
|
144 |
+
"learning_rate": 2e-05,
|
145 |
+
"loss": 0.1836,
|
146 |
+
"step": 23
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.77,
|
150 |
+
"learning_rate": 2e-05,
|
151 |
+
"loss": 0.1655,
|
152 |
+
"step": 24
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.81,
|
156 |
+
"learning_rate": 2e-05,
|
157 |
+
"loss": 0.1707,
|
158 |
+
"step": 25
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.84,
|
162 |
+
"learning_rate": 2e-05,
|
163 |
+
"loss": 0.1687,
|
164 |
+
"step": 26
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.87,
|
168 |
+
"learning_rate": 2e-05,
|
169 |
+
"loss": 0.1765,
|
170 |
+
"step": 27
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.9,
|
174 |
+
"learning_rate": 2e-05,
|
175 |
+
"loss": 0.1567,
|
176 |
+
"step": 28
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.94,
|
180 |
+
"learning_rate": 2e-05,
|
181 |
+
"loss": 0.1694,
|
182 |
+
"step": 29
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.97,
|
186 |
+
"learning_rate": 2e-05,
|
187 |
+
"loss": 0.1572,
|
188 |
+
"step": 30
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.0,
|
192 |
+
"learning_rate": 2e-05,
|
193 |
+
"loss": 0.1743,
|
194 |
+
"step": 31
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 1.03,
|
198 |
+
"learning_rate": 2e-05,
|
199 |
+
"loss": 0.1055,
|
200 |
+
"step": 32
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 1.06,
|
204 |
+
"learning_rate": 2e-05,
|
205 |
+
"loss": 0.1014,
|
206 |
+
"step": 33
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 1.1,
|
210 |
+
"learning_rate": 2e-05,
|
211 |
+
"loss": 0.0975,
|
212 |
+
"step": 34
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.13,
|
216 |
+
"learning_rate": 2e-05,
|
217 |
+
"loss": 0.0986,
|
218 |
+
"step": 35
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.16,
|
222 |
+
"learning_rate": 2e-05,
|
223 |
+
"loss": 0.0856,
|
224 |
+
"step": 36
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 1.19,
|
228 |
+
"learning_rate": 2e-05,
|
229 |
+
"loss": 0.0837,
|
230 |
+
"step": 37
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.23,
|
234 |
+
"learning_rate": 2e-05,
|
235 |
+
"loss": 0.0979,
|
236 |
+
"step": 38
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 1.26,
|
240 |
+
"learning_rate": 2e-05,
|
241 |
+
"loss": 0.0898,
|
242 |
+
"step": 39
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.29,
|
246 |
+
"learning_rate": 2e-05,
|
247 |
+
"loss": 0.0828,
|
248 |
+
"step": 40
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 1.32,
|
252 |
+
"learning_rate": 2e-05,
|
253 |
+
"loss": 0.0923,
|
254 |
+
"step": 41
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.35,
|
258 |
+
"learning_rate": 2e-05,
|
259 |
+
"loss": 0.1002,
|
260 |
+
"step": 42
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.39,
|
264 |
+
"learning_rate": 2e-05,
|
265 |
+
"loss": 0.0935,
|
266 |
+
"step": 43
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 1.42,
|
270 |
+
"learning_rate": 2e-05,
|
271 |
+
"loss": 0.0826,
|
272 |
+
"step": 44
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.45,
|
276 |
+
"learning_rate": 2e-05,
|
277 |
+
"loss": 0.082,
|
278 |
+
"step": 45
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.48,
|
282 |
+
"learning_rate": 2e-05,
|
283 |
+
"loss": 0.0864,
|
284 |
+
"step": 46
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.52,
|
288 |
+
"learning_rate": 2e-05,
|
289 |
+
"loss": 0.0906,
|
290 |
+
"step": 47
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.55,
|
294 |
+
"learning_rate": 2e-05,
|
295 |
+
"loss": 0.0852,
|
296 |
+
"step": 48
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.58,
|
300 |
+
"learning_rate": 2e-05,
|
301 |
+
"loss": 0.0894,
|
302 |
+
"step": 49
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.61,
|
306 |
+
"learning_rate": 2e-05,
|
307 |
+
"loss": 0.0775,
|
308 |
+
"step": 50
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 1.65,
|
312 |
+
"learning_rate": 2e-05,
|
313 |
+
"loss": 0.0885,
|
314 |
+
"step": 51
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.68,
|
318 |
+
"learning_rate": 2e-05,
|
319 |
+
"loss": 0.0818,
|
320 |
+
"step": 52
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 1.71,
|
324 |
+
"learning_rate": 2e-05,
|
325 |
+
"loss": 0.0753,
|
326 |
+
"step": 53
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 1.74,
|
330 |
+
"learning_rate": 2e-05,
|
331 |
+
"loss": 0.0786,
|
332 |
+
"step": 54
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.77,
|
336 |
+
"learning_rate": 2e-05,
|
337 |
+
"loss": 0.0797,
|
338 |
+
"step": 55
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.81,
|
342 |
+
"learning_rate": 2e-05,
|
343 |
+
"loss": 0.0863,
|
344 |
+
"step": 56
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.84,
|
348 |
+
"learning_rate": 2e-05,
|
349 |
+
"loss": 0.0851,
|
350 |
+
"step": 57
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 1.87,
|
354 |
+
"learning_rate": 2e-05,
|
355 |
+
"loss": 0.089,
|
356 |
+
"step": 58
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.9,
|
360 |
+
"learning_rate": 2e-05,
|
361 |
+
"loss": 0.0887,
|
362 |
+
"step": 59
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 1.94,
|
366 |
+
"learning_rate": 2e-05,
|
367 |
+
"loss": 0.0801,
|
368 |
+
"step": 60
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 1.97,
|
372 |
+
"learning_rate": 2e-05,
|
373 |
+
"loss": 0.0938,
|
374 |
+
"step": 61
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 2.0,
|
378 |
+
"learning_rate": 2e-05,
|
379 |
+
"loss": 0.0868,
|
380 |
+
"step": 62
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 2.03,
|
384 |
+
"learning_rate": 2e-05,
|
385 |
+
"loss": 0.0435,
|
386 |
+
"step": 63
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 2.06,
|
390 |
+
"learning_rate": 2e-05,
|
391 |
+
"loss": 0.0484,
|
392 |
+
"step": 64
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 2.1,
|
396 |
+
"learning_rate": 2e-05,
|
397 |
+
"loss": 0.0419,
|
398 |
+
"step": 65
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 2.13,
|
402 |
+
"learning_rate": 2e-05,
|
403 |
+
"loss": 0.0395,
|
404 |
+
"step": 66
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 2.16,
|
408 |
+
"learning_rate": 2e-05,
|
409 |
+
"loss": 0.0421,
|
410 |
+
"step": 67
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 2.19,
|
414 |
+
"learning_rate": 2e-05,
|
415 |
+
"loss": 0.0357,
|
416 |
+
"step": 68
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 2.23,
|
420 |
+
"learning_rate": 2e-05,
|
421 |
+
"loss": 0.0459,
|
422 |
+
"step": 69
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 2.26,
|
426 |
+
"learning_rate": 2e-05,
|
427 |
+
"loss": 0.041,
|
428 |
+
"step": 70
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 2.29,
|
432 |
+
"learning_rate": 2e-05,
|
433 |
+
"loss": 0.0411,
|
434 |
+
"step": 71
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 2.32,
|
438 |
+
"learning_rate": 2e-05,
|
439 |
+
"loss": 0.0444,
|
440 |
+
"step": 72
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 2.35,
|
444 |
+
"learning_rate": 2e-05,
|
445 |
+
"loss": 0.0406,
|
446 |
+
"step": 73
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 2.39,
|
450 |
+
"learning_rate": 2e-05,
|
451 |
+
"loss": 0.0412,
|
452 |
+
"step": 74
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 2.42,
|
456 |
+
"learning_rate": 2e-05,
|
457 |
+
"loss": 0.0448,
|
458 |
+
"step": 75
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 2.45,
|
462 |
+
"learning_rate": 2e-05,
|
463 |
+
"loss": 0.0374,
|
464 |
+
"step": 76
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 2.48,
|
468 |
+
"learning_rate": 2e-05,
|
469 |
+
"loss": 0.0446,
|
470 |
+
"step": 77
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 2.52,
|
474 |
+
"learning_rate": 2e-05,
|
475 |
+
"loss": 0.0411,
|
476 |
+
"step": 78
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 2.55,
|
480 |
+
"learning_rate": 2e-05,
|
481 |
+
"loss": 0.041,
|
482 |
+
"step": 79
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 2.58,
|
486 |
+
"learning_rate": 2e-05,
|
487 |
+
"loss": 0.0406,
|
488 |
+
"step": 80
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 2.61,
|
492 |
+
"learning_rate": 2e-05,
|
493 |
+
"loss": 0.0444,
|
494 |
+
"step": 81
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 2.65,
|
498 |
+
"learning_rate": 2e-05,
|
499 |
+
"loss": 0.0439,
|
500 |
+
"step": 82
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 2.68,
|
504 |
+
"learning_rate": 2e-05,
|
505 |
+
"loss": 0.0433,
|
506 |
+
"step": 83
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 2.71,
|
510 |
+
"learning_rate": 2e-05,
|
511 |
+
"loss": 0.0443,
|
512 |
+
"step": 84
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 2.74,
|
516 |
+
"learning_rate": 2e-05,
|
517 |
+
"loss": 0.0422,
|
518 |
+
"step": 85
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 2.77,
|
522 |
+
"learning_rate": 2e-05,
|
523 |
+
"loss": 0.0411,
|
524 |
+
"step": 86
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 2.81,
|
528 |
+
"learning_rate": 2e-05,
|
529 |
+
"loss": 0.0463,
|
530 |
+
"step": 87
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 2.84,
|
534 |
+
"learning_rate": 2e-05,
|
535 |
+
"loss": 0.0408,
|
536 |
+
"step": 88
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 2.87,
|
540 |
+
"learning_rate": 2e-05,
|
541 |
+
"loss": 0.0425,
|
542 |
+
"step": 89
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 2.9,
|
546 |
+
"learning_rate": 2e-05,
|
547 |
+
"loss": 0.0441,
|
548 |
+
"step": 90
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 2.94,
|
552 |
+
"learning_rate": 2e-05,
|
553 |
+
"loss": 0.0441,
|
554 |
+
"step": 91
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 2.97,
|
558 |
+
"learning_rate": 2e-05,
|
559 |
+
"loss": 0.0475,
|
560 |
+
"step": 92
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 3.0,
|
564 |
+
"learning_rate": 2e-05,
|
565 |
+
"loss": 0.0456,
|
566 |
+
"step": 93
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 3.0,
|
570 |
+
"step": 93,
|
571 |
+
"total_flos": 38440796160000.0,
|
572 |
+
"train_loss": 0.1174569078671035,
|
573 |
+
"train_runtime": 5368.2591,
|
574 |
+
"train_samples_per_second": 2.2,
|
575 |
+
"train_steps_per_second": 0.017
|
576 |
+
}
|
577 |
+
],
|
578 |
+
"max_steps": 93,
|
579 |
+
"num_train_epochs": 3,
|
580 |
+
"total_flos": 38440796160000.0,
|
581 |
+
"trial_name": null,
|
582 |
+
"trial_params": null
|
583 |
+
}
|