CatkinChen commited on
Commit
be2fafd
·
verified ·
1 Parent(s): 773b522

Add training data

Browse files
Files changed (1) hide show
  1. training_data.json +215 -215
training_data.json CHANGED
@@ -1,227 +1,227 @@
1
  {
2
  "train_losses": [
3
- -0.0019335938850417733,
4
- -0.00031250016763806343,
5
- -0.0003515627468004823,
6
- -0.0016894532600417733,
7
- -0.0029003904201090336,
8
- -0.0007128907018341124,
9
- -0.0029589843470603228,
10
- 0.0007324218167923391,
11
- -0.0016503907972946763,
12
- 0.00024414053768850863,
13
- -0.0012304687406867743,
14
- -0.002773437649011612,
15
- 0.0016113281017169356,
16
- 0.0012695312034338713,
17
- 0.0011425779666751623,
18
- -0.0006542970659211278,
19
- 0.0009960937313735485,
20
- 0.0004394530551508069,
21
- -0.00015625008381903172,
22
- -0.0018945313058793545,
23
- -0.0021289063151925802,
24
- 0.00030273429001681507,
25
- -0.0010546875419095159,
26
- -0.0011523438151925802,
27
- -9.765630238689482e-05,
28
- -0.00028320314595475793,
29
- 0.0007324217003770173,
30
- 0.0014453124022111297,
31
- 0.0013183592818677425,
32
- -0.00028320311685092747,
33
- 0.0015527342911809683,
34
- -0.00017578131519258022,
35
- 0.0015625000232830644,
36
- 0.0008789062267169356,
37
- -0.0008691407274454832,
38
- 0.0018066405318677425,
39
- -0.0019628906156867743,
40
- -0.0013476562453433871,
41
- 0.0015136718284338713,
42
- -0.0009765624417923391,
43
- -3.906257916241884e-05,
44
- 0.0013476562453433871,
45
- -0.001308593899011612,
46
- -0.0007617188384756446,
47
- -0.002119140699505806,
48
- -0.0016210938338190317,
49
- -0.0006054689874872565,
50
- 0.0011425780830904841,
51
- -7.812504190951586e-05,
52
- -0.0012500000884756446,
53
- -0.0010546875419095159,
54
- 0.00038085930282250047,
55
- -0.0019042970379814506,
56
- -0.00016601575771346688,
57
- -0.0006250001606531441,
58
- -0.0003515625139698386,
59
- 0.001425781287252903,
60
- -0.0010449220426380634,
61
- -0.0020703128539025784,
62
- -0.00012695323675870895,
63
- 0.0005175780970603228,
64
- 0.0010644530411809683,
65
- -0.002158203162252903,
66
- -0.0029589845798909664,
67
- -0.0018554688431322575,
68
- -0.0006738282390870154,
69
- -0.0005761720240116119,
70
  -0.0010351564269512892,
71
- -0.0016113284509629011,
72
- -3.906257916241884e-05,
73
- -0.0008984376909211278,
74
- -0.002167969010770321,
75
- 0.0006835937965661287,
76
- -2.929684706032276e-05,
77
- -0.0029199221171438694,
78
- -0.00011718759196810424,
79
- -0.0009765625,
80
- -0.00010742194717749953,
81
- 0.0011132812360301614,
82
- -0.0030761719681322575,
83
- 0.0004003905050922185,
84
- 0.00029296864522621036,
85
- -0.0009960938477888703,
86
- 0.001171874930150807,
87
- -0.005048828199505806,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  -0.0005664062919095159,
89
- -0.0039257812313735485,
90
- -0.0008984376909211278,
91
- 0.0005273436545394361,
92
- 0.0004980468074791133,
93
- -0.0038183594588190317,
94
- -0.0019238280365243554,
95
- -0.005605469457805157,
96
- -0.0008886719588190317,
97
- -0.0028417969588190317,
98
- -0.0008593749953433871,
99
- 0.0010058593470603228,
100
- -0.0018359377281740308,
101
- -0.0026953124906867743,
102
- 0.0005078124231658876,
103
- -0.0005957033135928214,
104
- -0.002089844085276127,
105
- -0.001220703125,
106
- -0.0010351564269512892,
107
- 0.0011621093144640326,
108
- -2.9296934371814132e-05,
109
- 0.000810546800494194,
110
- -0.0006738280644640326,
111
- -0.0010449220426380634,
112
- 0.00035156242665834725,
113
- -0.0024707033298909664,
114
- 0.001259765587747097,
115
- -0.0017773439176380634,
116
- -0.00019531248835846782,
117
- 0.0014355469029396772,
118
- -6.835951353423297e-05,
119
- 4.882804933004081e-05,
120
- -0.00025390624068677425,
121
- -0.002246093936264515,
122
- 5.8593665016815066e-05,
123
- -0.0005957032553851604,
124
- 0.000566406175494194,
125
- -0.0007128907600417733,
126
- 0.000605468638241291,
127
- -0.0010546876583248377,
128
- -0.0005664064083248377,
129
- -0.0010937501210719347,
130
- -0.0009667970007285476,
131
- -0.00031250008032657206,
132
- 9.765586582943797e-06,
133
- -0.0012207033578306437,
134
- 0.0002148436615243554,
135
- -0.00351562537252903,
136
- -0.0019824220798909664,
137
- -0.0015332034090533853,
138
- -0.001923828269354999,
139
- -0.0023828125558793545,
140
- -0.0008105468587018549,
141
- -0.0008007814176380634,
142
- 0.00020507804583758116,
143
- -0.0011230467353016138,
144
- -0.0007324219914153218,
145
  -1.1641532182693481e-10,
146
- 0.00014648435171693563,
147
- -0.0008984376909211278,
148
- 0.0009082030737772584,
149
- -0.002011718926951289,
150
- 0.0007617187220603228,
151
- -0.001064453274011612,
152
- 0.0002734375011641532,
153
- 0.0009960937313735485,
154
- -0.0015625000232830644,
155
- -0.0008007814758457243,
156
- -0.000898437574505806,
157
- -0.0006640625651925802,
158
- -0.0006640626234002411,
159
- 0.001054687425494194,
160
- -0.0010839845053851604,
161
- -0.0006835939129814506,
162
  -0.0017773439176380634,
163
- -0.00375976599752903,
164
- -0.001904296805150807,
165
- 0.001054687425494194,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
166
  -0.0028320313431322575,
167
- 0.00039062497671693563,
168
- -0.0058789062313735485,
169
- -0.003261718899011612,
170
- 8.78905993886292e-05,
171
- -0.002011718926951289,
172
- -0.0008300782646983862,
173
- -0.0009765627328306437,
174
- -0.002011718926951289,
175
- 0.00014648429350927472,
176
- -0.001025390694849193,
177
- 0.0005859374650754035,
178
- -0.0008984376327134669,
179
- -0.0017089844914153218,
180
- -0.000859375053551048,
181
- -0.004130859859287739,
182
- -0.003916015848517418,
183
- -0.001757812686264515,
184
- -0.0013085937825962901,
185
- -0.002041015774011612,
186
- -0.0016894532600417733,
187
- -5.820766091346741e-11,
188
- -0.003916015848517418,
189
- -0.002890625037252903,
190
- -0.006044922396540642,
191
- -0.001718750107102096,
192
- -0.0010937500046566129,
193
- -0.0019140626536682248,
194
- -0.002001953311264515,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
195
  -0.0008105470333248377,
196
- -0.0007617189548909664,
197
- -0.001845703343860805
198
  ],
199
  "test_losses": [
200
- -0.3225999999999999,
201
- -0.12879999999999991,
202
- -0.0935999999999998,
203
- -0.21219999999999994,
204
- -0.21459999999999993,
205
- -0.1779999999999999,
206
- -0.2945999999999999,
207
- -0.17379999999999987,
208
- -0.0769999999999999,
209
- -0.1381999999999999,
210
- -0.1471999999999999,
211
- -0.2313999999999999,
212
- -0.29379999999999995,
213
- -0.07139999999999988,
214
- -0.3013999999999999,
215
- -0.3459999999999999,
216
- -0.07079999999999989,
217
- -0.2089999999999999,
218
- -0.08879999999999988
219
  ],
220
  "config": {
221
  "training_type": "online_ppo",
222
  "environment": "MiniHack-Room-Random-15x15-v0",
223
  "total_timesteps": 195,
224
- "training_time": 4089.349448442459,
225
  "device": "cuda",
226
  "ppo_config": {
227
  "learning_rate": 0.0003,
@@ -236,21 +236,21 @@
236
  "curiosity_dyn": false,
237
  "curiosity_skill_entropy": false,
238
  "curiosity_skill_transition_novelty": false,
239
- "curiosity_dyn_coef": 0.003,
240
  "curiosity_hdp_coef": 0.002,
241
  "curiosity_stn_coef": 0.0005,
242
  "use_rnd": true,
243
  "rnd_lr": 0.001,
244
- "rnd_coef": 0.01
245
  },
246
  "model_sources": {
247
  "vae_repo_id": "CatkinChen/nethack-vae-hmm",
248
  "hmm_repo_id": "CatkinChen/nethack-hmm"
249
  }
250
  },
251
- "final_train_loss": -0.001845703343860805,
252
- "final_test_loss": -0.08879999999999988,
253
  "total_epochs": 195,
254
- "best_train_loss": -0.006044922396540642,
255
- "best_test_loss": -0.3459999999999999
256
  }
 
1
  {
2
  "train_losses": [
3
+ 3.90624045394361e-05,
4
+ 4.8828020226210356e-05,
5
+ -0.0006445313338190317,
6
+ 0.0006347655435092747,
7
+ -0.001953125,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  -0.0010351564269512892,
9
+ 0.0016406248323619366,
10
+ -0.0017968750325962901,
11
+ -0.00024414079962298274,
12
+ -0.0008007813594304025,
13
+ -0.0011230468517169356,
14
+ -0.0002050782786682248,
15
+ -0.0006835939129814506,
16
+ 9.76555747911334e-06,
17
+ -0.0005273438873700798,
18
+ -0.0008691407856531441,
19
+ -0.0016992187593132257,
20
+ 0.0005371093284338713,
21
+ -0.001347656361758709,
22
+ -0.0006933595868758857,
23
+ -0.0008398438221774995,
24
+ -0.003837890923023224,
25
+ 0.000439452996943146,
26
+ -0.0008789062849245965,
27
+ -0.0016601565293967724,
28
+ -0.0018066407646983862,
29
+ -0.002871094038709998,
30
+ -0.0011230469681322575,
31
+ -0.001591796986758709,
32
+ -0.001992187462747097,
33
+ -0.002285156399011612,
34
+ -0.0005566407344304025,
35
+ -0.0004687502223532647,
36
+ -0.0010449219262227416,
37
+ -0.0027539064176380634,
38
+ 4.8828020226210356e-05,
39
+ 8.789054118096828e-05,
40
+ 0.0005761717911809683,
41
+ 0.00029296870343387127,
42
+ -0.0008496094960719347,
43
+ -0.0036132815293967724,
44
+ -0.002001953311264515,
45
+ 0.0019433593843132257,
46
+ -0.0015332030598074198,
47
+ 0.00045898431562818587,
48
+ -0.0006933595286682248,
49
+ -0.0021972658578306437,
50
+ 0.0019726562313735485,
51
+ -0.003134765662252903,
52
+ 0.0007226562593132257,
53
  -0.0005664062919095159,
54
+ 0.00012695297482423484,
55
+ -0.0011425780830904841,
56
+ 4.8828020226210356e-05,
57
+ -0.002783203264698386,
58
+ -0.0011523438151925802,
59
+ -0.0007031250861473382,
60
+ 0.00041992179467342794,
61
+ 0.0018359373789280653,
62
+ 0.0017382812220603228,
63
+ -0.0016699221450835466,
64
+ 0.0020507811568677425,
65
+ 0.000302734348224476,
66
+ -0.00011718759196810424,
67
+ -0.0012695312034338713,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  -1.1641532182693481e-10,
69
+ -0.001396484556607902,
70
+ 0.001298828050494194,
71
+ -0.0018457032274454832,
 
 
 
 
 
 
 
 
 
 
 
 
 
72
  -0.0017773439176380634,
73
+ 0.0005468748859129846,
74
+ -5.859381053596735e-05,
75
+ -0.003154297126457095,
76
+ -0.002812500111758709,
77
+ 0.0011523438151925802,
78
+ -0.00595703162252903,
79
+ 0.00031249987659975886,
80
+ 0.00035156242665834725,
81
+ 0.0015234374441206455,
82
+ -0.002822265727445483,
83
+ -0.0006347657763399184,
84
+ 0.0011621093144640326,
85
+ 0.0001562499674037099,
86
+ -0.0028027347289025784,
87
+ -0.0019335938850417733,
88
+ -0.0007714844541624188,
89
+ 0.0002441405667923391,
90
+ 0.0008007811848074198,
91
+ -0.0010839845053851604,
92
+ 0.0001953124301508069,
93
+ -0.0017480470705777407,
94
+ -0.0019921876955777407,
95
+ -0.002490234561264515,
96
+ -0.0017480470705777407,
97
+ -0.0015917971031740308,
98
+ 2.9296788852661848e-05,
99
+ -0.0012109376257285476,
100
+ -0.0006738281808793545,
101
+ -0.0020996094681322575,
102
+ 0.0011718750465661287,
103
+ -0.0015429687919095159,
104
+ -0.0036230471450835466,
105
+ 0.0010253905784338713,
106
+ 0.0010058593470603228,
107
+ -0.0013476562453433871,
108
+ -0.0013964844401925802,
109
+ -0.0019335938850417733,
110
+ -0.0021386719308793545,
111
+ 5.859363591298461e-05,
112
+ 0.0011523436987772584,
113
+ -0.0017675783019512892,
114
+ 0.00029296864522621036,
115
+ -0.00014648435171693563,
116
+ -0.0018164063803851604,
117
+ 1.9531173165887594e-05,
118
+ -0.0021875000093132257,
119
+ -0.002246093936264515,
120
+ -0.002177734626457095,
121
+ -0.0008007812430150807,
122
+ 2.929684706032276e-05,
123
+ -0.0007910158019512892,
124
+ -0.0010253905784338713,
125
+ -0.0007031251443549991,
126
+ 0.00016601558309048414,
127
+ -0.002597656100988388,
128
+ 0.00015624993829987943,
129
  -0.0028320313431322575,
130
+ 0.0008496093796566129,
131
+ -2.9296992579475045e-05,
132
+ 0.00016601552488282323,
133
+ 0.0012792968191206455,
134
+ -0.004755859263241291,
135
+ 0.00042968749767169356,
136
+ -0.0005078126559965312,
137
+ -0.0018457032274454832,
138
+ -0.001064453274011612,
139
+ -0.0009570313268341124,
140
+ -0.005585937760770321,
141
+ -0.00020507824956439435,
142
+ -0.0019433597335591912,
143
+ 0.0005468749441206455,
144
+ -0.0008300780900754035,
145
+ -0.0008007813594304025,
146
+ -0.000693359412252903,
147
+ -0.0006835937965661287,
148
+ -9.76564479060471e-06,
149
+ 0.0001171874173451215,
150
+ -0.0010058593470603228,
151
+ -0.0020117186941206455,
152
+ -0.003017578274011612,
153
+ 0.0011425779666751623,
154
+ -0.0017480470705777407,
155
+ -0.0005468750605359674,
156
+ 0.0010644530411809683,
157
+ 0.00013671861961483955,
158
+ -0.004570312798023224,
159
+ 0.001210937392897904,
160
+ -0.007050781510770321,
161
+ -0.0013183595146983862,
162
+ 0.0003027342609129846,
163
+ -1.9531347788870335e-05,
164
+ -0.0004492188454605639,
165
+ -0.0012500002048909664,
166
+ -0.00011718750465661287,
167
+ -0.0010058594634756446,
168
+ -0.0015722656389698386,
169
+ -0.000986328232102096,
170
+ 0.0003320312243886292,
171
+ -0.0004980469821020961,
172
+ 0.00042968743946403265,
173
+ -0.00019531266298145056,
174
+ -0.004062499850988388,
175
+ 3.90624045394361e-05,
176
+ -0.001875000074505806,
177
+ 5.859363591298461e-05,
178
+ -0.004638672340661287,
179
+ -0.0011523438151925802,
180
+ -0.0009277344797737896,
181
+ 0.0011718750465661287,
182
+ -0.0016308597987517715,
183
+ -0.002695312723517418,
184
+ 0.0012011718936264515,
185
+ -0.0012695312034338713,
186
+ -0.0001562500256113708,
187
+ -0.0027148439548909664,
188
+ 0.0008203124743886292,
189
+ -0.002080078236758709,
190
+ -0.0010839843889698386,
191
+ 0.0011132811196148396,
192
+ -0.002744140801951289,
193
+ -0.0003417969564907253,
194
+ -0.001474609598517418,
195
+ 0.00024414050858467817,
196
  -0.0008105470333248377,
197
+ 0.001181640662252903
 
198
  ],
199
  "test_losses": [
200
+ -0.2047999999999999,
201
+ -0.08539999999999986,
202
+ -0.09079999999999981,
203
+ -0.18799999999999986,
204
+ -0.18919999999999992,
205
+ -0.10079999999999988,
206
+ -0.08519999999999989,
207
+ -0.38599999999999995,
208
+ -0.002199999999999885,
209
+ -0.06919999999999989,
210
+ -0.17019999999999993,
211
+ -0.24119999999999991,
212
+ -0.22859999999999991,
213
+ -0.2961999999999999,
214
+ -0.27079999999999993,
215
+ -0.18319999999999992,
216
+ -0.1423999999999999,
217
+ -0.23659999999999992,
218
+ -0.11899999999999991
219
  ],
220
  "config": {
221
  "training_type": "online_ppo",
222
  "environment": "MiniHack-Room-Random-15x15-v0",
223
  "total_timesteps": 195,
224
+ "training_time": 4585.824229717255,
225
  "device": "cuda",
226
  "ppo_config": {
227
  "learning_rate": 0.0003,
 
236
  "curiosity_dyn": false,
237
  "curiosity_skill_entropy": false,
238
  "curiosity_skill_transition_novelty": false,
239
+ "curiosity_dyn_coef": 0.03,
240
  "curiosity_hdp_coef": 0.002,
241
  "curiosity_stn_coef": 0.0005,
242
  "use_rnd": true,
243
  "rnd_lr": 0.001,
244
+ "rnd_coef": 0.002
245
  },
246
  "model_sources": {
247
  "vae_repo_id": "CatkinChen/nethack-vae-hmm",
248
  "hmm_repo_id": "CatkinChen/nethack-hmm"
249
  }
250
  },
251
+ "final_train_loss": 0.001181640662252903,
252
+ "final_test_loss": -0.11899999999999991,
253
  "total_epochs": 195,
254
+ "best_train_loss": -0.007050781510770321,
255
+ "best_test_loss": -0.38599999999999995
256
  }