Training in progress, step 5120, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4725595416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:869b484e58461f1536cc21d599303cb514c3d752e29ef44231f6d6c363605817
|
3 |
size 4725595416
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9179193343
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14a089b06ff32225e1d8e28e6b6c1cab9f01e70af7cbc2eac64ef56b2989354d
|
3 |
size 9179193343
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc1239486b7f83e4a2231cde24a50b503b22ee79d6ee232760274da141c18674
|
3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ce8999a5d1b14a256d594f72ba3d10015736fefa5fd7057a03491428983da78
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint": "mgh6/TCS_Pairing_VAE/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 512,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -107,6 +107,106 @@
|
|
107 |
"eval_samples_per_second": 69.222,
|
108 |
"eval_steps_per_second": 69.222,
|
109 |
"step": 2560
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
110 |
}
|
111 |
],
|
112 |
"logging_steps": 256,
|
|
|
1 |
{
|
2 |
+
"best_metric": 4288.33056640625,
|
3 |
+
"best_model_checkpoint": "mgh6/TCS_Pairing_VAE/checkpoint-5120",
|
4 |
+
"epoch": 0.37828901798165815,
|
5 |
"eval_steps": 512,
|
6 |
+
"global_step": 5120,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
107 |
"eval_samples_per_second": 69.222,
|
108 |
"eval_steps_per_second": 69.222,
|
109 |
"step": 2560
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 0.21,
|
113 |
+
"learning_rate": 9.58386286389833e-05,
|
114 |
+
"loss": 15475.9717,
|
115 |
+
"step": 2816
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.23,
|
119 |
+
"learning_rate": 9.546032215161815e-05,
|
120 |
+
"loss": 11322.8867,
|
121 |
+
"step": 3072
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.23,
|
125 |
+
"eval_loss": 8387.529296875,
|
126 |
+
"eval_runtime": 56.5145,
|
127 |
+
"eval_samples_per_second": 60.126,
|
128 |
+
"eval_steps_per_second": 60.126,
|
129 |
+
"step": 3072
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.25,
|
133 |
+
"learning_rate": 9.5082015664253e-05,
|
134 |
+
"loss": 8684.2373,
|
135 |
+
"step": 3328
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.26,
|
139 |
+
"learning_rate": 9.470370917688785e-05,
|
140 |
+
"loss": 6917.9409,
|
141 |
+
"step": 3584
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.26,
|
145 |
+
"eval_loss": 5089.6796875,
|
146 |
+
"eval_runtime": 52.3172,
|
147 |
+
"eval_samples_per_second": 64.95,
|
148 |
+
"eval_steps_per_second": 64.95,
|
149 |
+
"step": 3584
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.28,
|
153 |
+
"learning_rate": 9.43254026895227e-05,
|
154 |
+
"loss": 6025.4263,
|
155 |
+
"step": 3840
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.3,
|
159 |
+
"learning_rate": 9.394709620215754e-05,
|
160 |
+
"loss": 5538.1548,
|
161 |
+
"step": 4096
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.3,
|
165 |
+
"eval_loss": 4470.64990234375,
|
166 |
+
"eval_runtime": 49.8023,
|
167 |
+
"eval_samples_per_second": 68.23,
|
168 |
+
"eval_steps_per_second": 68.23,
|
169 |
+
"step": 4096
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 0.32,
|
173 |
+
"learning_rate": 9.356878971479238e-05,
|
174 |
+
"loss": 5257.3623,
|
175 |
+
"step": 4352
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 0.34,
|
179 |
+
"learning_rate": 9.319048322742722e-05,
|
180 |
+
"loss": 5375.1353,
|
181 |
+
"step": 4608
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.34,
|
185 |
+
"eval_loss": 4827.8271484375,
|
186 |
+
"eval_runtime": 49.3721,
|
187 |
+
"eval_samples_per_second": 68.824,
|
188 |
+
"eval_steps_per_second": 68.824,
|
189 |
+
"step": 4608
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.36,
|
193 |
+
"learning_rate": 9.281217674006207e-05,
|
194 |
+
"loss": 5494.5615,
|
195 |
+
"step": 4864
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.38,
|
199 |
+
"learning_rate": 9.243387025269692e-05,
|
200 |
+
"loss": 5258.2065,
|
201 |
+
"step": 5120
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.38,
|
205 |
+
"eval_loss": 4288.33056640625,
|
206 |
+
"eval_runtime": 51.0091,
|
207 |
+
"eval_samples_per_second": 66.616,
|
208 |
+
"eval_steps_per_second": 66.616,
|
209 |
+
"step": 5120
|
210 |
}
|
211 |
],
|
212 |
"logging_steps": 256,
|