Training in progress, step 45, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201892112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6315465c164780deb519915edc9e104307b05c8f298e831fe2515191fa2988d
|
3 |
size 201892112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102864548
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67ae825530459d1e63fff4f06fdde3c8236d8b8c193f48d39132116f51992d9a
|
3 |
size 102864548
|
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 sha256:9a531f0b89c2b0fb6f1db4cde1840947beee42f99467840233f7378d12bc13d5
|
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 sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
|
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,
|
@@ -170,6 +170,28 @@
|
|
170 |
"eval_samples_per_second": 49.279,
|
171 |
"eval_steps_per_second": 6.163,
|
172 |
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
173 |
}
|
174 |
],
|
175 |
"logging_steps": 3,
|
@@ -189,7 +211,7 @@
|
|
189 |
"attributes": {}
|
190 |
}
|
191 |
},
|
192 |
-
"total_flos":
|
193 |
"train_batch_size": 8,
|
194 |
"trial_name": null,
|
195 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.02116153303550435,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 45,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
170 |
"eval_samples_per_second": 49.279,
|
171 |
"eval_steps_per_second": 6.163,
|
172 |
"step": 40
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.019750764166470727,
|
176 |
+
"grad_norm": 0.3560473918914795,
|
177 |
+
"learning_rate": 9.549150281252633e-06,
|
178 |
+
"loss": 1.1565,
|
179 |
+
"step": 42
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.02116153303550435,
|
183 |
+
"grad_norm": 0.4546699523925781,
|
184 |
+
"learning_rate": 3.8060233744356633e-06,
|
185 |
+
"loss": 1.175,
|
186 |
+
"step": 45
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.02116153303550435,
|
190 |
+
"eval_loss": 1.13008713722229,
|
191 |
+
"eval_runtime": 72.7277,
|
192 |
+
"eval_samples_per_second": 49.252,
|
193 |
+
"eval_steps_per_second": 6.16,
|
194 |
+
"step": 45
|
195 |
}
|
196 |
],
|
197 |
"logging_steps": 3,
|
|
|
211 |
"attributes": {}
|
212 |
}
|
213 |
},
|
214 |
+
"total_flos": 9599165336125440.0,
|
215 |
"train_batch_size": 8,
|
216 |
"trial_name": null,
|
217 |
"trial_params": null
|