Training in progress, step 24, 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 70667778
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a86ba9385bb768d29deab79937c811ef79a601d619335c9e94af62c9f11709ce
|
3 |
size 70667778
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff1de991a5e8b028670d79166d941671fcf1f558f0044b08eaf5154d066f0048
|
3 |
size 14512
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a5995616407d184ecedacf74ac31cd0731474c7e2323f03405d89945bad93ff
|
3 |
size 14512
|
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:b375860c66674ec9637bb873a1ff676ec525ee5502840d2f1d554d4237b8f0c4
|
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": 12,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -107,6 +107,98 @@
|
|
107 |
"eval_samples_per_second": 21.668,
|
108 |
"eval_steps_per_second": 5.486,
|
109 |
"step": 12
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
110 |
}
|
111 |
],
|
112 |
"logging_steps": 1,
|
@@ -126,7 +218,7 @@
|
|
126 |
"attributes": {}
|
127 |
}
|
128 |
},
|
129 |
-
"total_flos":
|
130 |
"train_batch_size": 2,
|
131 |
"trial_name": null,
|
132 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.512,
|
5 |
"eval_steps": 12,
|
6 |
+
"global_step": 24,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
107 |
"eval_samples_per_second": 21.668,
|
108 |
"eval_steps_per_second": 5.486,
|
109 |
"step": 12
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 0.2773333333333333,
|
113 |
+
"grad_norm": NaN,
|
114 |
+
"learning_rate": 2.6000000000000002e-05,
|
115 |
+
"loss": 0.0,
|
116 |
+
"step": 13
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.2986666666666667,
|
120 |
+
"grad_norm": NaN,
|
121 |
+
"learning_rate": 2.8000000000000003e-05,
|
122 |
+
"loss": 0.0,
|
123 |
+
"step": 14
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.32,
|
127 |
+
"grad_norm": NaN,
|
128 |
+
"learning_rate": 3e-05,
|
129 |
+
"loss": 0.0,
|
130 |
+
"step": 15
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 0.3413333333333333,
|
134 |
+
"grad_norm": NaN,
|
135 |
+
"learning_rate": 3.2000000000000005e-05,
|
136 |
+
"loss": 0.0,
|
137 |
+
"step": 16
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.3626666666666667,
|
141 |
+
"grad_norm": NaN,
|
142 |
+
"learning_rate": 3.4000000000000007e-05,
|
143 |
+
"loss": 0.0,
|
144 |
+
"step": 17
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.384,
|
148 |
+
"grad_norm": NaN,
|
149 |
+
"learning_rate": 3.6e-05,
|
150 |
+
"loss": 0.0,
|
151 |
+
"step": 18
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 0.4053333333333333,
|
155 |
+
"grad_norm": NaN,
|
156 |
+
"learning_rate": 3.8e-05,
|
157 |
+
"loss": 0.0,
|
158 |
+
"step": 19
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.4266666666666667,
|
162 |
+
"grad_norm": NaN,
|
163 |
+
"learning_rate": 4e-05,
|
164 |
+
"loss": 0.0,
|
165 |
+
"step": 20
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.448,
|
169 |
+
"grad_norm": NaN,
|
170 |
+
"learning_rate": 4.2e-05,
|
171 |
+
"loss": 0.0,
|
172 |
+
"step": 21
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.4693333333333333,
|
176 |
+
"grad_norm": NaN,
|
177 |
+
"learning_rate": 4.4000000000000006e-05,
|
178 |
+
"loss": 0.0,
|
179 |
+
"step": 22
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.49066666666666664,
|
183 |
+
"grad_norm": NaN,
|
184 |
+
"learning_rate": 4.600000000000001e-05,
|
185 |
+
"loss": 0.0,
|
186 |
+
"step": 23
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.512,
|
190 |
+
"grad_norm": NaN,
|
191 |
+
"learning_rate": 4.8e-05,
|
192 |
+
"loss": 0.0,
|
193 |
+
"step": 24
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.512,
|
197 |
+
"eval_loss": NaN,
|
198 |
+
"eval_runtime": 3.751,
|
199 |
+
"eval_samples_per_second": 21.061,
|
200 |
+
"eval_steps_per_second": 5.332,
|
201 |
+
"step": 24
|
202 |
}
|
203 |
],
|
204 |
"logging_steps": 1,
|
|
|
218 |
"attributes": {}
|
219 |
}
|
220 |
},
|
221 |
+
"total_flos": 3460580643962880.0,
|
222 |
"train_batch_size": 2,
|
223 |
"trial_name": null,
|
224 |
"trial_params": null
|