Upload 7 files
Browse files- scheduler.pt +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +33 -0
- trainer_state.json +556 -0
- training_args.bin +3 -0
- vocab.json +0 -0
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ac7e7acf92fc5a1ee58fb029355df9e9b627ae91c30477ca7530b2e5edc4b66
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": true,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "<|endoftext|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"errors": "replace",
|
22 |
+
"model_max_length": 1000000000000000019884624838656,
|
23 |
+
"pad_token": null,
|
24 |
+
"tokenizer_class": "GPT2Tokenizer",
|
25 |
+
"unk_token": {
|
26 |
+
"__type": "AddedToken",
|
27 |
+
"content": "<|endoftext|>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,556 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.774057048004438,
|
5 |
+
"global_step": 180000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.02,
|
12 |
+
"learning_rate": 4.892535079835384e-05,
|
13 |
+
"loss": 3.2017,
|
14 |
+
"step": 5000
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.02,
|
18 |
+
"eval_accuracy": 0.4179681193308354,
|
19 |
+
"eval_loss": 2.969822883605957,
|
20 |
+
"eval_runtime": 1929.4803,
|
21 |
+
"eval_samples_per_second": 19.496,
|
22 |
+
"eval_steps_per_second": 2.437,
|
23 |
+
"step": 5000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.04,
|
27 |
+
"learning_rate": 4.785070159670768e-05,
|
28 |
+
"loss": 2.9116,
|
29 |
+
"step": 10000
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.04,
|
33 |
+
"eval_accuracy": 0.4297956163670618,
|
34 |
+
"eval_loss": 2.8731179237365723,
|
35 |
+
"eval_runtime": 1919.4124,
|
36 |
+
"eval_samples_per_second": 19.598,
|
37 |
+
"eval_steps_per_second": 2.45,
|
38 |
+
"step": 10000
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.06,
|
42 |
+
"learning_rate": 4.677605239506152e-05,
|
43 |
+
"loss": 2.8412,
|
44 |
+
"step": 15000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.06,
|
48 |
+
"eval_accuracy": 0.4368075611910975,
|
49 |
+
"eval_loss": 2.81874942779541,
|
50 |
+
"eval_runtime": 2015.9454,
|
51 |
+
"eval_samples_per_second": 18.66,
|
52 |
+
"eval_steps_per_second": 2.333,
|
53 |
+
"step": 15000
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.09,
|
57 |
+
"learning_rate": 4.5701403193415356e-05,
|
58 |
+
"loss": 2.7937,
|
59 |
+
"step": 20000
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.09,
|
63 |
+
"eval_accuracy": 0.44204520475458375,
|
64 |
+
"eval_loss": 2.778646230697632,
|
65 |
+
"eval_runtime": 1919.08,
|
66 |
+
"eval_samples_per_second": 19.602,
|
67 |
+
"eval_steps_per_second": 2.451,
|
68 |
+
"step": 20000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.11,
|
72 |
+
"learning_rate": 4.4626753991769196e-05,
|
73 |
+
"loss": 2.7614,
|
74 |
+
"step": 25000
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.11,
|
78 |
+
"eval_accuracy": 0.44610035327770187,
|
79 |
+
"eval_loss": 2.7471842765808105,
|
80 |
+
"eval_runtime": 1919.775,
|
81 |
+
"eval_samples_per_second": 19.594,
|
82 |
+
"eval_steps_per_second": 2.45,
|
83 |
+
"step": 25000
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.13,
|
87 |
+
"learning_rate": 4.355188977427636e-05,
|
88 |
+
"loss": 2.7295,
|
89 |
+
"step": 30000
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.13,
|
93 |
+
"eval_accuracy": 0.4501440419543679,
|
94 |
+
"eval_loss": 2.7196261882781982,
|
95 |
+
"eval_runtime": 1928.9026,
|
96 |
+
"eval_samples_per_second": 19.502,
|
97 |
+
"eval_steps_per_second": 2.438,
|
98 |
+
"step": 30000
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.15,
|
102 |
+
"learning_rate": 4.24772405726302e-05,
|
103 |
+
"loss": 2.7008,
|
104 |
+
"step": 35000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.15,
|
108 |
+
"eval_accuracy": 0.45296033170252703,
|
109 |
+
"eval_loss": 2.6961302757263184,
|
110 |
+
"eval_runtime": 1926.8386,
|
111 |
+
"eval_samples_per_second": 19.523,
|
112 |
+
"eval_steps_per_second": 2.441,
|
113 |
+
"step": 35000
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.17,
|
117 |
+
"learning_rate": 4.140237635513737e-05,
|
118 |
+
"loss": 2.6827,
|
119 |
+
"step": 40000
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.17,
|
123 |
+
"eval_accuracy": 0.4561378015092748,
|
124 |
+
"eval_loss": 2.6738195419311523,
|
125 |
+
"eval_runtime": 1920.5318,
|
126 |
+
"eval_samples_per_second": 19.587,
|
127 |
+
"eval_steps_per_second": 2.449,
|
128 |
+
"step": 40000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.19,
|
132 |
+
"learning_rate": 4.032772715349121e-05,
|
133 |
+
"loss": 2.6545,
|
134 |
+
"step": 45000
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.19,
|
138 |
+
"eval_accuracy": 0.4590067649734393,
|
139 |
+
"eval_loss": 2.6545751094818115,
|
140 |
+
"eval_runtime": 1933.7083,
|
141 |
+
"eval_samples_per_second": 19.453,
|
142 |
+
"eval_steps_per_second": 2.432,
|
143 |
+
"step": 45000
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.22,
|
147 |
+
"learning_rate": 3.9252862935998384e-05,
|
148 |
+
"loss": 2.6419,
|
149 |
+
"step": 50000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.22,
|
153 |
+
"eval_accuracy": 0.4616434651550895,
|
154 |
+
"eval_loss": 2.635937452316284,
|
155 |
+
"eval_runtime": 1931.385,
|
156 |
+
"eval_samples_per_second": 19.477,
|
157 |
+
"eval_steps_per_second": 2.435,
|
158 |
+
"step": 50000
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.24,
|
162 |
+
"learning_rate": 3.8178213734352224e-05,
|
163 |
+
"loss": 2.6208,
|
164 |
+
"step": 55000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.24,
|
168 |
+
"eval_accuracy": 0.4644954077588773,
|
169 |
+
"eval_loss": 2.617478847503662,
|
170 |
+
"eval_runtime": 1935.6188,
|
171 |
+
"eval_samples_per_second": 19.434,
|
172 |
+
"eval_steps_per_second": 2.43,
|
173 |
+
"step": 55000
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 0.26,
|
177 |
+
"learning_rate": 3.7103564532706064e-05,
|
178 |
+
"loss": 2.604,
|
179 |
+
"step": 60000
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.26,
|
183 |
+
"eval_accuracy": 0.4666273030036154,
|
184 |
+
"eval_loss": 2.6017534732818604,
|
185 |
+
"eval_runtime": 1934.3532,
|
186 |
+
"eval_samples_per_second": 19.447,
|
187 |
+
"eval_steps_per_second": 2.431,
|
188 |
+
"step": 60000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.28,
|
192 |
+
"learning_rate": 3.60289153310599e-05,
|
193 |
+
"loss": 2.5883,
|
194 |
+
"step": 65000
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.28,
|
198 |
+
"eval_accuracy": 0.4690363654190064,
|
199 |
+
"eval_loss": 2.5858962535858154,
|
200 |
+
"eval_runtime": 1937.9051,
|
201 |
+
"eval_samples_per_second": 19.411,
|
202 |
+
"eval_steps_per_second": 2.427,
|
203 |
+
"step": 65000
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 0.3,
|
207 |
+
"learning_rate": 3.495426612941374e-05,
|
208 |
+
"loss": 2.5733,
|
209 |
+
"step": 70000
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.3,
|
213 |
+
"eval_accuracy": 0.47110511457104925,
|
214 |
+
"eval_loss": 2.5711781978607178,
|
215 |
+
"eval_runtime": 1929.1817,
|
216 |
+
"eval_samples_per_second": 19.499,
|
217 |
+
"eval_steps_per_second": 2.438,
|
218 |
+
"step": 70000
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.32,
|
222 |
+
"learning_rate": 3.387940191192091e-05,
|
223 |
+
"loss": 2.5603,
|
224 |
+
"step": 75000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.32,
|
228 |
+
"eval_accuracy": 0.4735584312234197,
|
229 |
+
"eval_loss": 2.5554990768432617,
|
230 |
+
"eval_runtime": 1924.3705,
|
231 |
+
"eval_samples_per_second": 19.548,
|
232 |
+
"eval_steps_per_second": 2.444,
|
233 |
+
"step": 75000
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.34,
|
237 |
+
"learning_rate": 3.280475271027475e-05,
|
238 |
+
"loss": 2.5462,
|
239 |
+
"step": 80000
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 0.34,
|
243 |
+
"eval_accuracy": 0.4755388538038284,
|
244 |
+
"eval_loss": 2.541663646697998,
|
245 |
+
"eval_runtime": 1932.1982,
|
246 |
+
"eval_samples_per_second": 19.469,
|
247 |
+
"eval_steps_per_second": 2.434,
|
248 |
+
"step": 80000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.37,
|
252 |
+
"learning_rate": 3.173010350862859e-05,
|
253 |
+
"loss": 2.5267,
|
254 |
+
"step": 85000
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.37,
|
258 |
+
"eval_accuracy": 0.47766700705788817,
|
259 |
+
"eval_loss": 2.528374433517456,
|
260 |
+
"eval_runtime": 1933.9592,
|
261 |
+
"eval_samples_per_second": 19.451,
|
262 |
+
"eval_steps_per_second": 2.432,
|
263 |
+
"step": 85000
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.39,
|
267 |
+
"learning_rate": 3.0655454306982425e-05,
|
268 |
+
"loss": 2.5153,
|
269 |
+
"step": 90000
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.39,
|
273 |
+
"eval_accuracy": 0.47989050311610376,
|
274 |
+
"eval_loss": 2.514660596847534,
|
275 |
+
"eval_runtime": 1929.164,
|
276 |
+
"eval_samples_per_second": 19.499,
|
277 |
+
"eval_steps_per_second": 2.438,
|
278 |
+
"step": 90000
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.41,
|
282 |
+
"learning_rate": 2.9580805105336262e-05,
|
283 |
+
"loss": 2.5028,
|
284 |
+
"step": 95000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.41,
|
288 |
+
"eval_accuracy": 0.481903668114947,
|
289 |
+
"eval_loss": 2.501615285873413,
|
290 |
+
"eval_runtime": 1929.1634,
|
291 |
+
"eval_samples_per_second": 19.499,
|
292 |
+
"eval_steps_per_second": 2.438,
|
293 |
+
"step": 95000
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 0.43,
|
297 |
+
"learning_rate": 2.8505940887843435e-05,
|
298 |
+
"loss": 2.4881,
|
299 |
+
"step": 100000
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.43,
|
303 |
+
"eval_accuracy": 0.4839338799602133,
|
304 |
+
"eval_loss": 2.488723039627075,
|
305 |
+
"eval_runtime": 1930.4001,
|
306 |
+
"eval_samples_per_second": 19.487,
|
307 |
+
"eval_steps_per_second": 2.436,
|
308 |
+
"step": 100000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.45,
|
312 |
+
"learning_rate": 2.7431291686197276e-05,
|
313 |
+
"loss": 2.4758,
|
314 |
+
"step": 105000
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.45,
|
318 |
+
"eval_accuracy": 0.48596689829848827,
|
319 |
+
"eval_loss": 2.475806951522827,
|
320 |
+
"eval_runtime": 1923.9804,
|
321 |
+
"eval_samples_per_second": 19.552,
|
322 |
+
"eval_steps_per_second": 2.444,
|
323 |
+
"step": 105000
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 0.47,
|
327 |
+
"learning_rate": 2.6356642484551112e-05,
|
328 |
+
"loss": 2.4632,
|
329 |
+
"step": 110000
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 0.47,
|
333 |
+
"eval_accuracy": 0.4880078683669545,
|
334 |
+
"eval_loss": 2.463679552078247,
|
335 |
+
"eval_runtime": 1943.6457,
|
336 |
+
"eval_samples_per_second": 19.354,
|
337 |
+
"eval_steps_per_second": 2.42,
|
338 |
+
"step": 110000
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.49,
|
342 |
+
"learning_rate": 2.5281993282904953e-05,
|
343 |
+
"loss": 2.4543,
|
344 |
+
"step": 115000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.49,
|
348 |
+
"eval_accuracy": 0.4898118976645586,
|
349 |
+
"eval_loss": 2.4515490531921387,
|
350 |
+
"eval_runtime": 1940.3072,
|
351 |
+
"eval_samples_per_second": 19.387,
|
352 |
+
"eval_steps_per_second": 2.424,
|
353 |
+
"step": 115000
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.52,
|
357 |
+
"learning_rate": 2.4206914049565453e-05,
|
358 |
+
"loss": 2.4416,
|
359 |
+
"step": 120000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.52,
|
363 |
+
"eval_accuracy": 0.49199028194626443,
|
364 |
+
"eval_loss": 2.4388370513916016,
|
365 |
+
"eval_runtime": 1928.5903,
|
366 |
+
"eval_samples_per_second": 19.505,
|
367 |
+
"eval_steps_per_second": 2.439,
|
368 |
+
"step": 120000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.54,
|
372 |
+
"learning_rate": 2.313247986376596e-05,
|
373 |
+
"loss": 2.4256,
|
374 |
+
"step": 125000
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.54,
|
378 |
+
"eval_accuracy": 0.49386564294117247,
|
379 |
+
"eval_loss": 2.4272964000701904,
|
380 |
+
"eval_runtime": 1927.1096,
|
381 |
+
"eval_samples_per_second": 19.52,
|
382 |
+
"eval_steps_per_second": 2.44,
|
383 |
+
"step": 125000
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.56,
|
387 |
+
"learning_rate": 2.20578306621198e-05,
|
388 |
+
"loss": 2.4166,
|
389 |
+
"step": 130000
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.56,
|
393 |
+
"eval_accuracy": 0.4959010260096677,
|
394 |
+
"eval_loss": 2.4158496856689453,
|
395 |
+
"eval_runtime": 1932.6805,
|
396 |
+
"eval_samples_per_second": 19.464,
|
397 |
+
"eval_steps_per_second": 2.433,
|
398 |
+
"step": 130000
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.58,
|
402 |
+
"learning_rate": 2.0982751428780303e-05,
|
403 |
+
"loss": 2.4052,
|
404 |
+
"step": 135000
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.58,
|
408 |
+
"eval_accuracy": 0.4977953568184306,
|
409 |
+
"eval_loss": 2.4038643836975098,
|
410 |
+
"eval_runtime": 1925.4197,
|
411 |
+
"eval_samples_per_second": 19.537,
|
412 |
+
"eval_steps_per_second": 2.443,
|
413 |
+
"step": 135000
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 0.6,
|
417 |
+
"learning_rate": 1.990831724298081e-05,
|
418 |
+
"loss": 2.3936,
|
419 |
+
"step": 140000
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 0.6,
|
423 |
+
"eval_accuracy": 0.49973316228278164,
|
424 |
+
"eval_loss": 2.392191171646118,
|
425 |
+
"eval_runtime": 1928.0691,
|
426 |
+
"eval_samples_per_second": 19.51,
|
427 |
+
"eval_steps_per_second": 2.439,
|
428 |
+
"step": 140000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.62,
|
432 |
+
"learning_rate": 1.8833668041334647e-05,
|
433 |
+
"loss": 2.379,
|
434 |
+
"step": 145000
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.62,
|
438 |
+
"eval_accuracy": 0.5019234221876816,
|
439 |
+
"eval_loss": 2.38037371635437,
|
440 |
+
"eval_runtime": 1923.4067,
|
441 |
+
"eval_samples_per_second": 19.557,
|
442 |
+
"eval_steps_per_second": 2.445,
|
443 |
+
"step": 145000
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.65,
|
447 |
+
"learning_rate": 1.7759018839688484e-05,
|
448 |
+
"loss": 2.3659,
|
449 |
+
"step": 150000
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 0.65,
|
453 |
+
"eval_accuracy": 0.5037539832386363,
|
454 |
+
"eval_loss": 2.3692569732666016,
|
455 |
+
"eval_runtime": 1925.9734,
|
456 |
+
"eval_samples_per_second": 19.531,
|
457 |
+
"eval_steps_per_second": 2.442,
|
458 |
+
"step": 150000
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.67,
|
462 |
+
"learning_rate": 1.6684154622195657e-05,
|
463 |
+
"loss": 2.3588,
|
464 |
+
"step": 155000
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.67,
|
468 |
+
"eval_accuracy": 0.5057738006653519,
|
469 |
+
"eval_loss": 2.357806444168091,
|
470 |
+
"eval_runtime": 1927.4777,
|
471 |
+
"eval_samples_per_second": 19.516,
|
472 |
+
"eval_steps_per_second": 2.44,
|
473 |
+
"step": 155000
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.69,
|
477 |
+
"learning_rate": 1.5609505420549494e-05,
|
478 |
+
"loss": 2.3529,
|
479 |
+
"step": 160000
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.69,
|
483 |
+
"eval_accuracy": 0.5079495603563737,
|
484 |
+
"eval_loss": 2.3464465141296387,
|
485 |
+
"eval_runtime": 1926.6683,
|
486 |
+
"eval_samples_per_second": 19.524,
|
487 |
+
"eval_steps_per_second": 2.441,
|
488 |
+
"step": 160000
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.71,
|
492 |
+
"learning_rate": 1.4535071234750002e-05,
|
493 |
+
"loss": 2.3338,
|
494 |
+
"step": 165000
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.71,
|
498 |
+
"eval_accuracy": 0.5098386939558613,
|
499 |
+
"eval_loss": 2.335519313812256,
|
500 |
+
"eval_runtime": 1925.6719,
|
501 |
+
"eval_samples_per_second": 19.534,
|
502 |
+
"eval_steps_per_second": 2.442,
|
503 |
+
"step": 165000
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 0.73,
|
507 |
+
"learning_rate": 1.3460422033103839e-05,
|
508 |
+
"loss": 2.3238,
|
509 |
+
"step": 170000
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 0.73,
|
513 |
+
"eval_accuracy": 0.5118405290384843,
|
514 |
+
"eval_loss": 2.3250160217285156,
|
515 |
+
"eval_runtime": 1925.0126,
|
516 |
+
"eval_samples_per_second": 19.541,
|
517 |
+
"eval_steps_per_second": 2.443,
|
518 |
+
"step": 170000
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.75,
|
522 |
+
"learning_rate": 1.2385557815611011e-05,
|
523 |
+
"loss": 2.3139,
|
524 |
+
"step": 175000
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.75,
|
528 |
+
"eval_accuracy": 0.5137200997729053,
|
529 |
+
"eval_loss": 2.314518451690674,
|
530 |
+
"eval_runtime": 1927.2965,
|
531 |
+
"eval_samples_per_second": 19.518,
|
532 |
+
"eval_steps_per_second": 2.44,
|
533 |
+
"step": 175000
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 0.77,
|
537 |
+
"learning_rate": 1.1311123629811518e-05,
|
538 |
+
"loss": 2.3035,
|
539 |
+
"step": 180000
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 0.77,
|
543 |
+
"eval_accuracy": 0.5153991621734844,
|
544 |
+
"eval_loss": 2.3050577640533447,
|
545 |
+
"eval_runtime": 1927.482,
|
546 |
+
"eval_samples_per_second": 19.516,
|
547 |
+
"eval_steps_per_second": 2.44,
|
548 |
+
"step": 180000
|
549 |
+
}
|
550 |
+
],
|
551 |
+
"max_steps": 232541,
|
552 |
+
"num_train_epochs": 1,
|
553 |
+
"total_flos": 2.138588502294528e+19,
|
554 |
+
"trial_name": null,
|
555 |
+
"trial_params": null
|
556 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b33031977e3e2319a3bd5e94fe11042151c004762041fcd9d3e2684f231264c
|
3 |
+
size 3643
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|