Training in progress, step 110, 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 sha256:9b3998b176a4525c2cf9b2b734ab8fb419139d239cab3162d41fc05de5f077ab
|
| 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:aae3a42e69d455708464f4a58a775d880475966b809f1a1a54a9769a98accae2
|
| 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 sha256:1b27ae7d6f38450658320bdffedd47d09af17c9e1449062b8f2fa2aea432eaf1
|
| 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:f0a1e0d54a02c6f14a1c7a43fecc9a842563289319d03c6cd79300955358a0d7
|
| 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 sha256:99d16cab34d3063794ffae54504420d044755bf222f0176748d5967e74613981
|
| 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,
|
|
@@ -195,6 +195,24 @@
|
|
| 195 |
"eval_samples_per_second": 13.895,
|
| 196 |
"eval_steps_per_second": 6.948,
|
| 197 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 198 |
}
|
| 199 |
],
|
| 200 |
"logging_steps": 100,
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.11,
|
| 6 |
"eval_steps": 5,
|
| 7 |
+
"global_step": 110,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 195 |
"eval_samples_per_second": 13.895,
|
| 196 |
"eval_steps_per_second": 6.948,
|
| 197 |
"step": 100
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.105,
|
| 201 |
+
"eval_accuracy": 0.075,
|
| 202 |
+
"eval_loss": 16.776647567749023,
|
| 203 |
+
"eval_runtime": 40.0532,
|
| 204 |
+
"eval_samples_per_second": 12.483,
|
| 205 |
+
"eval_steps_per_second": 6.242,
|
| 206 |
+
"step": 105
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.11,
|
| 210 |
+
"eval_accuracy": 0.07446666666666667,
|
| 211 |
+
"eval_loss": 16.77096176147461,
|
| 212 |
+
"eval_runtime": 35.8224,
|
| 213 |
+
"eval_samples_per_second": 13.958,
|
| 214 |
+
"eval_steps_per_second": 6.979,
|
| 215 |
+
"step": 110
|
| 216 |
}
|
| 217 |
],
|
| 218 |
"logging_steps": 100,
|