Training in progress, step 26, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 124606
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32358da8093028199b86e13dc23a7e3b069f5ec4df7cd15d6ec1c3b52320307c
|
3 |
size 124606
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:424d06375131df3df5d4883391c61f995c66d877e893fd245f2c624058954297
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 13,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -114,6 +114,105 @@
|
|
114 |
"eval_samples_per_second": 370.246,
|
115 |
"eval_steps_per_second": 185.123,
|
116 |
"step": 13
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
117 |
}
|
118 |
],
|
119 |
"logging_steps": 1,
|
@@ -133,7 +232,7 @@
|
|
133 |
"attributes": {}
|
134 |
}
|
135 |
},
|
136 |
-
"total_flos":
|
137 |
"train_batch_size": 2,
|
138 |
"trial_name": null,
|
139 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.007819695858944717,
|
5 |
"eval_steps": 13,
|
6 |
+
"global_step": 26,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
114 |
"eval_samples_per_second": 370.246,
|
115 |
"eval_steps_per_second": 185.123,
|
116 |
"step": 13
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.004210605462508694,
|
120 |
+
"grad_norm": NaN,
|
121 |
+
"learning_rate": 9.755282581475769e-05,
|
122 |
+
"loss": 0.0,
|
123 |
+
"step": 14
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.004511362995545029,
|
127 |
+
"grad_norm": NaN,
|
128 |
+
"learning_rate": 9.619397662556435e-05,
|
129 |
+
"loss": 0.0,
|
130 |
+
"step": 15
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 0.004812120528581364,
|
134 |
+
"grad_norm": NaN,
|
135 |
+
"learning_rate": 9.45503262094184e-05,
|
136 |
+
"loss": 0.0,
|
137 |
+
"step": 16
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.005112878061617699,
|
141 |
+
"grad_norm": NaN,
|
142 |
+
"learning_rate": 9.263200821770461e-05,
|
143 |
+
"loss": 0.0,
|
144 |
+
"step": 17
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.005413635594654035,
|
148 |
+
"grad_norm": NaN,
|
149 |
+
"learning_rate": 9.045084971874738e-05,
|
150 |
+
"loss": 0.0,
|
151 |
+
"step": 18
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 0.00571439312769037,
|
155 |
+
"grad_norm": NaN,
|
156 |
+
"learning_rate": 8.802029828000156e-05,
|
157 |
+
"loss": 0.0,
|
158 |
+
"step": 19
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.0060151506607267055,
|
162 |
+
"grad_norm": NaN,
|
163 |
+
"learning_rate": 8.535533905932738e-05,
|
164 |
+
"loss": 0.0,
|
165 |
+
"step": 20
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.006315908193763041,
|
169 |
+
"grad_norm": NaN,
|
170 |
+
"learning_rate": 8.247240241650918e-05,
|
171 |
+
"loss": 0.0,
|
172 |
+
"step": 21
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.006616665726799376,
|
176 |
+
"grad_norm": NaN,
|
177 |
+
"learning_rate": 7.938926261462366e-05,
|
178 |
+
"loss": 0.0,
|
179 |
+
"step": 22
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.006917423259835711,
|
183 |
+
"grad_norm": NaN,
|
184 |
+
"learning_rate": 7.612492823579745e-05,
|
185 |
+
"loss": 0.0,
|
186 |
+
"step": 23
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.007218180792872046,
|
190 |
+
"grad_norm": NaN,
|
191 |
+
"learning_rate": 7.269952498697734e-05,
|
192 |
+
"loss": 0.0,
|
193 |
+
"step": 24
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.007518938325908382,
|
197 |
+
"grad_norm": NaN,
|
198 |
+
"learning_rate": 6.91341716182545e-05,
|
199 |
+
"loss": 0.0,
|
200 |
+
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.007819695858944717,
|
204 |
+
"grad_norm": NaN,
|
205 |
+
"learning_rate": 6.545084971874738e-05,
|
206 |
+
"loss": 0.0,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.007819695858944717,
|
211 |
+
"eval_loss": NaN,
|
212 |
+
"eval_runtime": 15.1537,
|
213 |
+
"eval_samples_per_second": 369.547,
|
214 |
+
"eval_steps_per_second": 184.773,
|
215 |
+
"step": 26
|
216 |
}
|
217 |
],
|
218 |
"logging_steps": 1,
|
|
|
232 |
"attributes": {}
|
233 |
}
|
234 |
},
|
235 |
+
"total_flos": 21695003885568.0,
|
236 |
"train_batch_size": 2,
|
237 |
"trial_name": null,
|
238 |
"trial_params": null
|