Training in progress, step 120, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 847599616
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4bc4a91559ec824f1fbc56295d9f782d2ff4ed5ae6ada32ec08c77634493a68
|
| 3 |
size 847599616
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1386414411
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2dcc73f76d8bb1f9b2ac33f17d640952304e1a1e7ad719aa95368a59859d9fc0
|
| 3 |
size 1386414411
|
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 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9008b459b5e2e7510f9b1147b0bc700431b3625231c93d35c550ef35f3d4b139
|
| 3 |
size 14917
|
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 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68b4ee4460edbc9eb4534fd16fe1b370a3b5348fe21dec9512c9ac09a43f7dd1
|
| 3 |
size 14917
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23aac2921f9ec292e8c9abc5d0945d71b183f542cd598117a742dbca2be40eb7
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 5,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -213,6 +213,24 @@
|
|
| 213 |
"eval_samples_per_second": 13.958,
|
| 214 |
"eval_steps_per_second": 6.979,
|
| 215 |
"step": 110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 216 |
}
|
| 217 |
],
|
| 218 |
"logging_steps": 100,
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.12,
|
| 6 |
"eval_steps": 5,
|
| 7 |
+
"global_step": 120,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 213 |
"eval_samples_per_second": 13.958,
|
| 214 |
"eval_steps_per_second": 6.979,
|
| 215 |
"step": 110
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.115,
|
| 219 |
+
"eval_accuracy": 0.07686666666666667,
|
| 220 |
+
"eval_loss": 16.71495246887207,
|
| 221 |
+
"eval_runtime": 40.5454,
|
| 222 |
+
"eval_samples_per_second": 12.332,
|
| 223 |
+
"eval_steps_per_second": 6.166,
|
| 224 |
+
"step": 115
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.12,
|
| 228 |
+
"eval_accuracy": 0.07413333333333333,
|
| 229 |
+
"eval_loss": 16.717641830444336,
|
| 230 |
+
"eval_runtime": 34.8477,
|
| 231 |
+
"eval_samples_per_second": 14.348,
|
| 232 |
+
"eval_steps_per_second": 7.174,
|
| 233 |
+
"step": 120
|
| 234 |
}
|
| 235 |
],
|
| 236 |
"logging_steps": 100,
|