Update model
Browse files- config.json +29 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +427 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "stefan-it/it5-efficient-small-el32",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2048,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 512,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "relu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"model_type": "t5",
|
17 |
+
"n_positions": 512,
|
18 |
+
"num_decoder_layers": 6,
|
19 |
+
"num_heads": 8,
|
20 |
+
"num_layers": 32,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_max_distance": 128,
|
24 |
+
"relative_attention_num_buckets": 32,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.19.0.dev0",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 32100
|
29 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9eeff59bc2f669206dea69079dbbddbb9a20cb42bbaef5c8aa7b114c365db90
|
3 |
+
size 569345883
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dffd01fc009b7e92d98eddff8853983e271b41302ed0d363000e8581df12000
|
3 |
+
size 817200
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "special_tokens_map_file": null, "name_or_path": "stefan-it/it5-efficient-small-el32", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,427 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 33746,
|
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": 4.925917145735791e-05,
|
13 |
+
"loss": 3.8221,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.06,
|
18 |
+
"learning_rate": 4.851834291471582e-05,
|
19 |
+
"loss": 3.4549,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.09,
|
24 |
+
"learning_rate": 4.777751437207373e-05,
|
25 |
+
"loss": 3.3319,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.12,
|
30 |
+
"learning_rate": 4.703668582943164e-05,
|
31 |
+
"loss": 3.2774,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.15,
|
36 |
+
"learning_rate": 4.629585728678955e-05,
|
37 |
+
"loss": 3.2101,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.18,
|
42 |
+
"learning_rate": 4.555502874414746e-05,
|
43 |
+
"loss": 3.1803,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.21,
|
48 |
+
"learning_rate": 4.4814200201505366e-05,
|
49 |
+
"loss": 3.1927,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.24,
|
54 |
+
"learning_rate": 4.4073371658863275e-05,
|
55 |
+
"loss": 3.1548,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.27,
|
60 |
+
"learning_rate": 4.3332543116221184e-05,
|
61 |
+
"loss": 3.1122,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.3,
|
66 |
+
"learning_rate": 4.259171457357909e-05,
|
67 |
+
"loss": 3.0989,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.33,
|
72 |
+
"learning_rate": 4.1850886030937e-05,
|
73 |
+
"loss": 3.075,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.36,
|
78 |
+
"learning_rate": 4.111005748829491e-05,
|
79 |
+
"loss": 3.065,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.39,
|
84 |
+
"learning_rate": 4.036922894565282e-05,
|
85 |
+
"loss": 3.0739,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.41,
|
90 |
+
"learning_rate": 3.962840040301073e-05,
|
91 |
+
"loss": 3.0578,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.44,
|
96 |
+
"learning_rate": 3.888757186036864e-05,
|
97 |
+
"loss": 3.0648,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.47,
|
102 |
+
"learning_rate": 3.814674331772655e-05,
|
103 |
+
"loss": 3.0336,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.5,
|
108 |
+
"learning_rate": 3.7405914775084456e-05,
|
109 |
+
"loss": 3.0216,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.53,
|
114 |
+
"learning_rate": 3.6665086232442365e-05,
|
115 |
+
"loss": 2.9867,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.56,
|
120 |
+
"learning_rate": 3.5924257689800274e-05,
|
121 |
+
"loss": 2.9942,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.59,
|
126 |
+
"learning_rate": 3.5183429147158183e-05,
|
127 |
+
"loss": 2.9679,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.62,
|
132 |
+
"learning_rate": 3.444260060451609e-05,
|
133 |
+
"loss": 2.9864,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.65,
|
138 |
+
"learning_rate": 3.3701772061874e-05,
|
139 |
+
"loss": 2.9922,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.68,
|
144 |
+
"learning_rate": 3.296094351923191e-05,
|
145 |
+
"loss": 2.9836,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.71,
|
150 |
+
"learning_rate": 3.222011497658982e-05,
|
151 |
+
"loss": 2.9676,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.74,
|
156 |
+
"learning_rate": 3.147928643394773e-05,
|
157 |
+
"loss": 2.9757,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.77,
|
162 |
+
"learning_rate": 3.073845789130564e-05,
|
163 |
+
"loss": 2.9746,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.8,
|
168 |
+
"learning_rate": 2.9997629348663547e-05,
|
169 |
+
"loss": 2.9523,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.83,
|
174 |
+
"learning_rate": 2.9256800806021456e-05,
|
175 |
+
"loss": 2.9345,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.86,
|
180 |
+
"learning_rate": 2.8515972263379365e-05,
|
181 |
+
"loss": 2.9482,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.89,
|
186 |
+
"learning_rate": 2.7775143720737274e-05,
|
187 |
+
"loss": 2.9369,
|
188 |
+
"step": 15000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.92,
|
192 |
+
"learning_rate": 2.7034315178095183e-05,
|
193 |
+
"loss": 2.9248,
|
194 |
+
"step": 15500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.95,
|
198 |
+
"learning_rate": 2.6293486635453092e-05,
|
199 |
+
"loss": 2.893,
|
200 |
+
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.98,
|
204 |
+
"learning_rate": 2.5552658092810998e-05,
|
205 |
+
"loss": 2.9236,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 1.01,
|
210 |
+
"learning_rate": 2.481182955016891e-05,
|
211 |
+
"loss": 2.8986,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.04,
|
216 |
+
"learning_rate": 2.407100100752682e-05,
|
217 |
+
"loss": 2.8414,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.07,
|
222 |
+
"learning_rate": 2.333017246488473e-05,
|
223 |
+
"loss": 2.8639,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 1.1,
|
228 |
+
"learning_rate": 2.2589343922242637e-05,
|
229 |
+
"loss": 2.8561,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.13,
|
234 |
+
"learning_rate": 2.1848515379600546e-05,
|
235 |
+
"loss": 2.8553,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 1.16,
|
240 |
+
"learning_rate": 2.1107686836958456e-05,
|
241 |
+
"loss": 2.8641,
|
242 |
+
"step": 19500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.19,
|
246 |
+
"learning_rate": 2.0366858294316365e-05,
|
247 |
+
"loss": 2.896,
|
248 |
+
"step": 20000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 1.21,
|
252 |
+
"learning_rate": 1.9626029751674274e-05,
|
253 |
+
"loss": 2.8837,
|
254 |
+
"step": 20500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.24,
|
258 |
+
"learning_rate": 1.8885201209032183e-05,
|
259 |
+
"loss": 2.8799,
|
260 |
+
"step": 21000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.27,
|
264 |
+
"learning_rate": 1.8144372666390092e-05,
|
265 |
+
"loss": 2.8677,
|
266 |
+
"step": 21500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 1.3,
|
270 |
+
"learning_rate": 1.7403544123748e-05,
|
271 |
+
"loss": 2.8618,
|
272 |
+
"step": 22000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.33,
|
276 |
+
"learning_rate": 1.666271558110591e-05,
|
277 |
+
"loss": 2.8484,
|
278 |
+
"step": 22500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.36,
|
282 |
+
"learning_rate": 1.592188703846382e-05,
|
283 |
+
"loss": 2.8276,
|
284 |
+
"step": 23000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.39,
|
288 |
+
"learning_rate": 1.518105849582173e-05,
|
289 |
+
"loss": 2.8684,
|
290 |
+
"step": 23500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.42,
|
294 |
+
"learning_rate": 1.4440229953179637e-05,
|
295 |
+
"loss": 2.8236,
|
296 |
+
"step": 24000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.45,
|
300 |
+
"learning_rate": 1.3699401410537546e-05,
|
301 |
+
"loss": 2.8551,
|
302 |
+
"step": 24500
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.48,
|
306 |
+
"learning_rate": 1.2958572867895455e-05,
|
307 |
+
"loss": 2.8524,
|
308 |
+
"step": 25000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 1.51,
|
312 |
+
"learning_rate": 1.2217744325253364e-05,
|
313 |
+
"loss": 2.8609,
|
314 |
+
"step": 25500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.54,
|
318 |
+
"learning_rate": 1.1476915782611273e-05,
|
319 |
+
"loss": 2.839,
|
320 |
+
"step": 26000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 1.57,
|
324 |
+
"learning_rate": 1.0736087239969182e-05,
|
325 |
+
"loss": 2.8376,
|
326 |
+
"step": 26500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 1.6,
|
330 |
+
"learning_rate": 9.995258697327091e-06,
|
331 |
+
"loss": 2.8293,
|
332 |
+
"step": 27000
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.63,
|
336 |
+
"learning_rate": 9.254430154685e-06,
|
337 |
+
"loss": 2.8262,
|
338 |
+
"step": 27500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.66,
|
342 |
+
"learning_rate": 8.51360161204291e-06,
|
343 |
+
"loss": 2.8106,
|
344 |
+
"step": 28000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.69,
|
348 |
+
"learning_rate": 7.772773069400818e-06,
|
349 |
+
"loss": 2.8243,
|
350 |
+
"step": 28500
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 1.72,
|
354 |
+
"learning_rate": 7.031944526758727e-06,
|
355 |
+
"loss": 2.8452,
|
356 |
+
"step": 29000
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.75,
|
360 |
+
"learning_rate": 6.291115984116637e-06,
|
361 |
+
"loss": 2.7935,
|
362 |
+
"step": 29500
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 1.78,
|
366 |
+
"learning_rate": 5.550287441474546e-06,
|
367 |
+
"loss": 2.8216,
|
368 |
+
"step": 30000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 1.81,
|
372 |
+
"learning_rate": 4.809458898832455e-06,
|
373 |
+
"loss": 2.8083,
|
374 |
+
"step": 30500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.84,
|
378 |
+
"learning_rate": 4.068630356190364e-06,
|
379 |
+
"loss": 2.8216,
|
380 |
+
"step": 31000
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.87,
|
384 |
+
"learning_rate": 3.3278018135482724e-06,
|
385 |
+
"loss": 2.8277,
|
386 |
+
"step": 31500
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 1.9,
|
390 |
+
"learning_rate": 2.586973270906182e-06,
|
391 |
+
"loss": 2.82,
|
392 |
+
"step": 32000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 1.93,
|
396 |
+
"learning_rate": 1.8461447282640907e-06,
|
397 |
+
"loss": 2.839,
|
398 |
+
"step": 32500
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 1.96,
|
402 |
+
"learning_rate": 1.1053161856219998e-06,
|
403 |
+
"loss": 2.8287,
|
404 |
+
"step": 33000
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 1.99,
|
408 |
+
"learning_rate": 3.644876429799088e-07,
|
409 |
+
"loss": 2.8189,
|
410 |
+
"step": 33500
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 2.0,
|
414 |
+
"step": 33746,
|
415 |
+
"total_flos": 4.844299814948045e+16,
|
416 |
+
"train_loss": 2.9583861975510755,
|
417 |
+
"train_runtime": 11802.9622,
|
418 |
+
"train_samples_per_second": 11.436,
|
419 |
+
"train_steps_per_second": 2.859
|
420 |
+
}
|
421 |
+
],
|
422 |
+
"max_steps": 33746,
|
423 |
+
"num_train_epochs": 2,
|
424 |
+
"total_flos": 4.844299814948045e+16,
|
425 |
+
"trial_name": null,
|
426 |
+
"trial_params": null
|
427 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f27302cdb6d3e60337f75676302bdf6c3b77fc493f4a288865ba13c539561c9
|
3 |
+
size 3247
|