Training in progress, step 14, 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 335922386
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9aee943c88866576b3660584993976cad91a8ccfbe94620f937bc0740728f3a8
|
3 |
size 335922386
|
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 sha256:1d0b607ea403567cbca8c8fef3b4eb224d8a3303f58fdb16fa63b99df273bc5f
|
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:c21e50d3a1bfdf9ca01a5258fbc54dba397e86dfc8fedbdf3aa91d3709f67147
|
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": 2,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -147,6 +147,28 @@
|
|
147 |
"eval_samples_per_second": 3.926,
|
148 |
"eval_steps_per_second": 3.926,
|
149 |
"step": 12
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
150 |
}
|
151 |
],
|
152 |
"logging_steps": 1,
|
@@ -166,7 +188,7 @@
|
|
166 |
"attributes": {}
|
167 |
}
|
168 |
},
|
169 |
-
"total_flos":
|
170 |
"train_batch_size": 1,
|
171 |
"trial_name": null,
|
172 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.00043831842267984754,
|
5 |
"eval_steps": 2,
|
6 |
+
"global_step": 14,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
147 |
"eval_samples_per_second": 3.926,
|
148 |
"eval_steps_per_second": 3.926,
|
149 |
"step": 12
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.0004070099639170013,
|
153 |
+
"grad_norm": NaN,
|
154 |
+
"learning_rate": 0.00018090169943749476,
|
155 |
+
"loss": 0.0,
|
156 |
+
"step": 13
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.00043831842267984754,
|
160 |
+
"grad_norm": NaN,
|
161 |
+
"learning_rate": 0.00016691306063588583,
|
162 |
+
"loss": 0.0,
|
163 |
+
"step": 14
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.00043831842267984754,
|
167 |
+
"eval_loss": NaN,
|
168 |
+
"eval_runtime": 3212.3981,
|
169 |
+
"eval_samples_per_second": 4.187,
|
170 |
+
"eval_steps_per_second": 4.187,
|
171 |
+
"step": 14
|
172 |
}
|
173 |
],
|
174 |
"logging_steps": 1,
|
|
|
188 |
"attributes": {}
|
189 |
}
|
190 |
},
|
191 |
+
"total_flos": 9843812981538816.0,
|
192 |
"train_batch_size": 1,
|
193 |
"trial_name": null,
|
194 |
"trial_params": null
|