Training in progress, step 40, 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 341314196
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d4bca8dc6894e75279e93a96b36f4359e88ace00e60885863270ad773f3055e
|
3 |
size 341314196
|
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 sha256:803204066549837dd8a2bdf36310112a59051c0940b62e4b204b9807aa0430df
|
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:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
|
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": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -148,6 +148,28 @@
|
|
148 |
"eval_samples_per_second": 13.632,
|
149 |
"eval_steps_per_second": 1.704,
|
150 |
"step": 35
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
151 |
}
|
152 |
],
|
153 |
"logging_steps": 3,
|
@@ -167,7 +189,7 @@
|
|
167 |
"attributes": {}
|
168 |
}
|
169 |
},
|
170 |
-
"total_flos":
|
171 |
"train_batch_size": 8,
|
172 |
"trial_name": null,
|
173 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.002693466659933,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 40,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
148 |
"eval_samples_per_second": 13.632,
|
149 |
"eval_steps_per_second": 1.704,
|
150 |
"step": 35
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.0024241199939397,
|
154 |
+
"grad_norm": NaN,
|
155 |
+
"learning_rate": 2.7300475013022663e-05,
|
156 |
+
"loss": 0.0,
|
157 |
+
"step": 36
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.002626129993434675,
|
161 |
+
"grad_norm": NaN,
|
162 |
+
"learning_rate": 1.7527597583490822e-05,
|
163 |
+
"loss": 0.0,
|
164 |
+
"step": 39
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.002693466659933,
|
168 |
+
"eval_loss": NaN,
|
169 |
+
"eval_runtime": 1835.1009,
|
170 |
+
"eval_samples_per_second": 13.63,
|
171 |
+
"eval_steps_per_second": 1.704,
|
172 |
+
"step": 40
|
173 |
}
|
174 |
],
|
175 |
"logging_steps": 3,
|
|
|
189 |
"attributes": {}
|
190 |
}
|
191 |
},
|
192 |
+
"total_flos": 6.147192833389363e+16,
|
193 |
"train_batch_size": 8,
|
194 |
"trial_name": null,
|
195 |
"trial_params": null
|