Training in progress, step 10, 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 8749702
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c80c941b99ab1a2d847d5b184ed53b249ecf04ec8c20bcbd98c67ba878195fa
|
3 |
size 8749702
|
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 sha256:64572aa9b99302feee23ce7c20814b34973b30930af2c6e6079dd58374608e8d
|
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 2080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e1e1bd201cfd1ba8791b6d7a185d4c58672855baa1f1a7b06dddf2bf699723c
|
3 |
size 2080
|
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": 1,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -142,6 +142,21 @@
|
|
142 |
"eval_samples_per_second": 16.957,
|
143 |
"eval_steps_per_second": 16.957,
|
144 |
"step": 9
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
145 |
}
|
146 |
],
|
147 |
"logging_steps": 1,
|
@@ -156,12 +171,12 @@
|
|
156 |
"should_evaluate": false,
|
157 |
"should_log": false,
|
158 |
"should_save": true,
|
159 |
-
"should_training_stop":
|
160 |
},
|
161 |
"attributes": {}
|
162 |
}
|
163 |
},
|
164 |
-
"total_flos":
|
165 |
"train_batch_size": 1,
|
166 |
"trial_name": null,
|
167 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.033948652662847446,
|
5 |
"eval_steps": 1,
|
6 |
+
"global_step": 10,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
142 |
"eval_samples_per_second": 16.957,
|
143 |
"eval_steps_per_second": 16.957,
|
144 |
"step": 9
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.033948652662847446,
|
148 |
+
"grad_norm": NaN,
|
149 |
+
"learning_rate": 0.0,
|
150 |
+
"loss": 0.0,
|
151 |
+
"step": 10
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 0.033948652662847446,
|
155 |
+
"eval_loss": NaN,
|
156 |
+
"eval_runtime": 14.816,
|
157 |
+
"eval_samples_per_second": 16.806,
|
158 |
+
"eval_steps_per_second": 16.806,
|
159 |
+
"step": 10
|
160 |
}
|
161 |
],
|
162 |
"logging_steps": 1,
|
|
|
171 |
"should_evaluate": false,
|
172 |
"should_log": false,
|
173 |
"should_save": true,
|
174 |
+
"should_training_stop": true
|
175 |
},
|
176 |
"attributes": {}
|
177 |
}
|
178 |
},
|
179 |
+
"total_flos": 632774511820800.0,
|
180 |
"train_batch_size": 1,
|
181 |
"trial_name": null,
|
182 |
"trial_params": null
|