first commit
Browse files- config.json +27 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +38 -0
- trainer_state.json +544 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "JackFram/llama-160m",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 768,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 3072,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
+
"model_type": "llama",
|
14 |
+
"num_attention_heads": 12,
|
15 |
+
"num_hidden_layers": 12,
|
16 |
+
"num_key_value_heads": 12,
|
17 |
+
"pad_token_id": 1,
|
18 |
+
"pretraining_tp": 1,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 10000.0,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.33.2",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 32000
|
27 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 1,
|
6 |
+
"transformers_version": "4.33.2"
|
7 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6e2132b5c98409434e8b704e1a5d9407a17a6b3144f91cd61aed9825e3a594e
|
3 |
+
size 649705097
|
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 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"legacy": null,
|
22 |
+
"model_max_length": 2048,
|
23 |
+
"pad_token": null,
|
24 |
+
"padding_side": "right",
|
25 |
+
"sp_model_kwargs": {},
|
26 |
+
"spaces_between_special_tokens": false,
|
27 |
+
"tokenizer_class": "LlamaTokenizer",
|
28 |
+
"unk_token": {
|
29 |
+
"__type": "AddedToken",
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
},
|
36 |
+
"use_default_system_prompt": true,
|
37 |
+
"use_fast": true
|
38 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,544 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.9657142857142857,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 86,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"learning_rate": 6.666666666666667e-06,
|
14 |
+
"loss": 3.0025,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.05,
|
19 |
+
"learning_rate": 1.3333333333333333e-05,
|
20 |
+
"loss": 3.3344,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.07,
|
25 |
+
"learning_rate": 2e-05,
|
26 |
+
"loss": 2.8488,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.09,
|
31 |
+
"learning_rate": 1.9992837548163315e-05,
|
32 |
+
"loss": 2.6912,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.11,
|
37 |
+
"learning_rate": 1.9971360452796523e-05,
|
38 |
+
"loss": 2.6867,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.14,
|
43 |
+
"learning_rate": 1.993559947963185e-05,
|
44 |
+
"loss": 2.5857,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.16,
|
49 |
+
"learning_rate": 1.9885605855918887e-05,
|
50 |
+
"loss": 2.6284,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.18,
|
55 |
+
"learning_rate": 1.9821451197042028e-05,
|
56 |
+
"loss": 2.5126,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.21,
|
61 |
+
"learning_rate": 1.9743227403932135e-05,
|
62 |
+
"loss": 2.2892,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.23,
|
67 |
+
"learning_rate": 1.9651046531419335e-05,
|
68 |
+
"loss": 2.3933,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.25,
|
73 |
+
"learning_rate": 1.9545040627715554e-05,
|
74 |
+
"loss": 2.2902,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.27,
|
79 |
+
"learning_rate": 1.942536154525673e-05,
|
80 |
+
"loss": 2.256,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.3,
|
85 |
+
"learning_rate": 1.9292180723175656e-05,
|
86 |
+
"loss": 2.2393,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.32,
|
91 |
+
"learning_rate": 1.9145688941717074e-05,
|
92 |
+
"loss": 2.1966,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.34,
|
97 |
+
"learning_rate": 1.8986096048946826e-05,
|
98 |
+
"loss": 2.1219,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.37,
|
103 |
+
"learning_rate": 1.881363066014649e-05,
|
104 |
+
"loss": 1.9816,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.39,
|
109 |
+
"learning_rate": 1.862853983032423e-05,
|
110 |
+
"loss": 2.1136,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.41,
|
115 |
+
"learning_rate": 1.8431088700310846e-05,
|
116 |
+
"loss": 2.0719,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.43,
|
121 |
+
"learning_rate": 1.8221560116948103e-05,
|
122 |
+
"loss": 2.009,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.46,
|
127 |
+
"learning_rate": 1.8000254227913346e-05,
|
128 |
+
"loss": 1.9665,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.48,
|
133 |
+
"learning_rate": 1.7767488051760858e-05,
|
134 |
+
"loss": 1.9006,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.5,
|
139 |
+
"learning_rate": 1.7523595023795814e-05,
|
140 |
+
"loss": 1.9061,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.53,
|
145 |
+
"learning_rate": 1.7268924518431437e-05,
|
146 |
+
"loss": 1.8054,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.55,
|
151 |
+
"learning_rate": 1.700384134871351e-05,
|
152 |
+
"loss": 1.9808,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.57,
|
157 |
+
"learning_rate": 1.672872524372919e-05,
|
158 |
+
"loss": 1.9158,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.59,
|
163 |
+
"learning_rate": 1.644397030464877e-05,
|
164 |
+
"loss": 1.8382,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.62,
|
169 |
+
"learning_rate": 1.614998444017954e-05,
|
170 |
+
"loss": 1.8274,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.64,
|
175 |
+
"learning_rate": 1.5847188782240473e-05,
|
176 |
+
"loss": 1.745,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.66,
|
181 |
+
"learning_rate": 1.5536017082694846e-05,
|
182 |
+
"loss": 1.7769,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.69,
|
187 |
+
"learning_rate": 1.5216915092004847e-05,
|
188 |
+
"loss": 1.9155,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.71,
|
193 |
+
"learning_rate": 1.4890339920698334e-05,
|
194 |
+
"loss": 1.7167,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.73,
|
199 |
+
"learning_rate": 1.4556759384562418e-05,
|
200 |
+
"loss": 1.8109,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.75,
|
205 |
+
"learning_rate": 1.421665133450184e-05,
|
206 |
+
"loss": 1.6917,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.78,
|
211 |
+
"learning_rate": 1.3870502972022175e-05,
|
212 |
+
"loss": 1.6803,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.8,
|
217 |
+
"learning_rate": 1.351881015131833e-05,
|
218 |
+
"loss": 1.6432,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.82,
|
223 |
+
"learning_rate": 1.316207666896824e-05,
|
224 |
+
"loss": 1.71,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.85,
|
229 |
+
"learning_rate": 1.2800813542249073e-05,
|
230 |
+
"loss": 1.732,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.87,
|
235 |
+
"learning_rate": 1.2435538277109919e-05,
|
236 |
+
"loss": 1.7514,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.89,
|
241 |
+
"learning_rate": 1.206677412684953e-05,
|
242 |
+
"loss": 1.7247,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.91,
|
247 |
+
"learning_rate": 1.1695049342560969e-05,
|
248 |
+
"loss": 1.6718,
|
249 |
+
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.94,
|
253 |
+
"learning_rate": 1.1320896416417026e-05,
|
254 |
+
"loss": 1.7548,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.96,
|
259 |
+
"learning_rate": 1.0944851318880314e-05,
|
260 |
+
"loss": 1.7024,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.98,
|
265 |
+
"learning_rate": 1.0567452730930743e-05,
|
266 |
+
"loss": 1.56,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 1.01,
|
271 |
+
"learning_rate": 1.0189241272410191e-05,
|
272 |
+
"loss": 1.6043,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 1.03,
|
277 |
+
"learning_rate": 9.810758727589814e-06,
|
278 |
+
"loss": 1.69,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 1.05,
|
283 |
+
"learning_rate": 9.43254726906926e-06,
|
284 |
+
"loss": 1.5612,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 1.07,
|
289 |
+
"learning_rate": 9.055148681119688e-06,
|
290 |
+
"loss": 1.6349,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 1.1,
|
295 |
+
"learning_rate": 8.67910358358298e-06,
|
296 |
+
"loss": 1.6196,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 1.12,
|
301 |
+
"learning_rate": 8.304950657439034e-06,
|
302 |
+
"loss": 1.6262,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.14,
|
307 |
+
"learning_rate": 7.93322587315047e-06,
|
308 |
+
"loss": 1.5572,
|
309 |
+
"step": 50
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 1.17,
|
313 |
+
"learning_rate": 7.564461722890082e-06,
|
314 |
+
"loss": 1.6005,
|
315 |
+
"step": 51
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 1.19,
|
319 |
+
"learning_rate": 7.199186457750931e-06,
|
320 |
+
"loss": 1.3992,
|
321 |
+
"step": 52
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 1.21,
|
325 |
+
"learning_rate": 6.837923331031761e-06,
|
326 |
+
"loss": 1.6098,
|
327 |
+
"step": 53
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 1.23,
|
331 |
+
"learning_rate": 6.48118984868167e-06,
|
332 |
+
"loss": 1.5493,
|
333 |
+
"step": 54
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 1.26,
|
337 |
+
"learning_rate": 6.129497027977829e-06,
|
338 |
+
"loss": 1.5581,
|
339 |
+
"step": 55
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 1.28,
|
343 |
+
"learning_rate": 5.78334866549816e-06,
|
344 |
+
"loss": 1.5138,
|
345 |
+
"step": 56
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 1.3,
|
349 |
+
"learning_rate": 5.443240615437586e-06,
|
350 |
+
"loss": 1.6091,
|
351 |
+
"step": 57
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 1.33,
|
355 |
+
"learning_rate": 5.109660079301668e-06,
|
356 |
+
"loss": 1.5832,
|
357 |
+
"step": 58
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 1.35,
|
361 |
+
"learning_rate": 4.783084907995156e-06,
|
362 |
+
"loss": 1.531,
|
363 |
+
"step": 59
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 1.37,
|
367 |
+
"learning_rate": 4.463982917305155e-06,
|
368 |
+
"loss": 1.4781,
|
369 |
+
"step": 60
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 1.39,
|
373 |
+
"learning_rate": 4.152811217759529e-06,
|
374 |
+
"loss": 1.5776,
|
375 |
+
"step": 61
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 1.42,
|
379 |
+
"learning_rate": 3.850015559820465e-06,
|
380 |
+
"loss": 1.617,
|
381 |
+
"step": 62
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 1.44,
|
385 |
+
"learning_rate": 3.5560296953512296e-06,
|
386 |
+
"loss": 1.4925,
|
387 |
+
"step": 63
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.46,
|
391 |
+
"learning_rate": 3.2712747562708115e-06,
|
392 |
+
"loss": 1.538,
|
393 |
+
"step": 64
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 1.49,
|
397 |
+
"learning_rate": 2.9961586512864947e-06,
|
398 |
+
"loss": 1.5641,
|
399 |
+
"step": 65
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 1.51,
|
403 |
+
"learning_rate": 2.7310754815685627e-06,
|
404 |
+
"loss": 1.4769,
|
405 |
+
"step": 66
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 1.53,
|
409 |
+
"learning_rate": 2.4764049762041874e-06,
|
410 |
+
"loss": 1.5378,
|
411 |
+
"step": 67
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 1.55,
|
415 |
+
"learning_rate": 2.2325119482391466e-06,
|
416 |
+
"loss": 1.4627,
|
417 |
+
"step": 68
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 1.58,
|
421 |
+
"learning_rate": 1.9997457720866554e-06,
|
422 |
+
"loss": 1.5337,
|
423 |
+
"step": 69
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 1.6,
|
427 |
+
"learning_rate": 1.7784398830519002e-06,
|
428 |
+
"loss": 1.5069,
|
429 |
+
"step": 70
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 1.62,
|
433 |
+
"learning_rate": 1.5689112996891576e-06,
|
434 |
+
"loss": 1.467,
|
435 |
+
"step": 71
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 1.65,
|
439 |
+
"learning_rate": 1.3714601696757713e-06,
|
440 |
+
"loss": 1.5326,
|
441 |
+
"step": 72
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 1.67,
|
445 |
+
"learning_rate": 1.1863693398535115e-06,
|
446 |
+
"loss": 1.5425,
|
447 |
+
"step": 73
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 1.69,
|
451 |
+
"learning_rate": 1.01390395105318e-06,
|
452 |
+
"loss": 1.5971,
|
453 |
+
"step": 74
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 1.71,
|
457 |
+
"learning_rate": 8.543110582829272e-07,
|
458 |
+
"loss": 1.5567,
|
459 |
+
"step": 75
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 1.74,
|
463 |
+
"learning_rate": 7.078192768243486e-07,
|
464 |
+
"loss": 1.4339,
|
465 |
+
"step": 76
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.76,
|
469 |
+
"learning_rate": 5.746384547432738e-07,
|
470 |
+
"loss": 1.4543,
|
471 |
+
"step": 77
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 1.78,
|
475 |
+
"learning_rate": 4.549593722844492e-07,
|
476 |
+
"loss": 1.4892,
|
477 |
+
"step": 78
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 1.81,
|
481 |
+
"learning_rate": 3.4895346858066723e-07,
|
482 |
+
"loss": 1.4933,
|
483 |
+
"step": 79
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 1.83,
|
487 |
+
"learning_rate": 2.5677259606786686e-07,
|
488 |
+
"loss": 1.5602,
|
489 |
+
"step": 80
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 1.85,
|
493 |
+
"learning_rate": 1.7854880295797406e-07,
|
494 |
+
"loss": 1.5017,
|
495 |
+
"step": 81
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 1.87,
|
499 |
+
"learning_rate": 1.1439414408111471e-07,
|
500 |
+
"loss": 1.5328,
|
501 |
+
"step": 82
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 1.9,
|
505 |
+
"learning_rate": 6.440052036815081e-08,
|
506 |
+
"loss": 1.5076,
|
507 |
+
"step": 83
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 1.92,
|
511 |
+
"learning_rate": 2.86395472034795e-08,
|
512 |
+
"loss": 1.4469,
|
513 |
+
"step": 84
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 1.94,
|
517 |
+
"learning_rate": 7.162451836685291e-09,
|
518 |
+
"loss": 1.4975,
|
519 |
+
"step": 85
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 1.97,
|
523 |
+
"learning_rate": 0.0,
|
524 |
+
"loss": 1.4956,
|
525 |
+
"step": 86
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 1.97,
|
529 |
+
"step": 86,
|
530 |
+
"total_flos": 1.864529779831603e+16,
|
531 |
+
"train_loss": 1.8037537461103395,
|
532 |
+
"train_runtime": 866.9782,
|
533 |
+
"train_samples_per_second": 12.918,
|
534 |
+
"train_steps_per_second": 0.099
|
535 |
+
}
|
536 |
+
],
|
537 |
+
"logging_steps": 1.0,
|
538 |
+
"max_steps": 86,
|
539 |
+
"num_train_epochs": 2,
|
540 |
+
"save_steps": 1000,
|
541 |
+
"total_flos": 1.864529779831603e+16,
|
542 |
+
"trial_name": null,
|
543 |
+
"trial_params": null
|
544 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f014ad654061146f92c42ace1c0efc43c92d55f5df2e0a640bf42a49146f7692
|
3 |
+
size 4027
|