Training in progress, step 224, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2c535d186834cdb2cd6ff4f2a1cc8a4f2a884817bc5c8a49b37406162c63e47
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b58ceab34bf515ec3560dfe423b9b0e06215b576c63685fb188ff1612fb90e7
|
3 |
size 37430836
|
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 sha256:81cbf1339ad1f512235514675c5ddcaa6f9e184ab94e9ea1442f012058d175f3
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1561,6 +1561,20 @@
|
|
1561 |
"learning_rate": 0.00010757575757575758,
|
1562 |
"loss": 1.1755,
|
1563 |
"step": 222
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1564 |
}
|
1565 |
],
|
1566 |
"logging_steps": 1,
|
@@ -1580,7 +1594,7 @@
|
|
1580 |
"attributes": {}
|
1581 |
}
|
1582 |
},
|
1583 |
-
"total_flos": 2.
|
1584 |
"train_batch_size": 4,
|
1585 |
"trial_name": null,
|
1586 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6145404663923183,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 224,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1561 |
"learning_rate": 0.00010757575757575758,
|
1562 |
"loss": 1.1755,
|
1563 |
"step": 222
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.6117969821673526,
|
1567 |
+
"grad_norm": 0.2119123786687851,
|
1568 |
+
"learning_rate": 0.00010681818181818181,
|
1569 |
+
"loss": 1.1784,
|
1570 |
+
"step": 223
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 0.6145404663923183,
|
1574 |
+
"grad_norm": 0.20988301932811737,
|
1575 |
+
"learning_rate": 0.00010606060606060606,
|
1576 |
+
"loss": 1.1841,
|
1577 |
+
"step": 224
|
1578 |
}
|
1579 |
],
|
1580 |
"logging_steps": 1,
|
|
|
1594 |
"attributes": {}
|
1595 |
}
|
1596 |
},
|
1597 |
+
"total_flos": 2.7759428460853248e+17,
|
1598 |
"train_batch_size": 4,
|
1599 |
"trial_name": null,
|
1600 |
"trial_params": null
|