lovellmnot
commited on
Commit
•
f54b331
1
Parent(s):
5a181b0
Training in progress, step 1120, 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 218138576
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1953745bb1e4d1a52adab1da9a3ffac023ee80f911184724df85c70b02bb3ff3
|
3 |
size 218138576
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 436423418
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56fadcca18d07e6b0dcf0ad8b18bf4a204fdf4ad948163efcee300bb5e8db634
|
3 |
size 436423418
|
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 sha256:5612005e57bd15a47b619f3ec26c56a8dcaa1d6eadef7d23851ee0274186a06f
|
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:e05a1947ee0fa86dffa6b4fcaeb0fc556a1c156b269fd0266bdb33aa5b4d903b
|
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":
|
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,
|
@@ -1568,6 +1568,13 @@
|
|
1568 |
"learning_rate": 2.4587060106245895e-09,
|
1569 |
"loss": 0.5558,
|
1570 |
"step": 1115
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1571 |
}
|
1572 |
],
|
1573 |
"logging_steps": 5,
|
@@ -1582,12 +1589,12 @@
|
|
1582 |
"should_evaluate": false,
|
1583 |
"should_log": false,
|
1584 |
"should_save": true,
|
1585 |
-
"should_training_stop":
|
1586 |
},
|
1587 |
"attributes": {}
|
1588 |
}
|
1589 |
},
|
1590 |
-
"total_flos": 1.
|
1591 |
"train_batch_size": 1,
|
1592 |
"trial_name": null,
|
1593 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 20.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1120,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1568 |
"learning_rate": 2.4587060106245895e-09,
|
1569 |
"loss": 0.5558,
|
1570 |
"step": 1115
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 20.0,
|
1574 |
+
"grad_norm": 1.2500131130218506,
|
1575 |
+
"learning_rate": 0.0,
|
1576 |
+
"loss": 0.6466,
|
1577 |
+
"step": 1120
|
1578 |
}
|
1579 |
],
|
1580 |
"logging_steps": 5,
|
|
|
1589 |
"should_evaluate": false,
|
1590 |
"should_log": false,
|
1591 |
"should_save": true,
|
1592 |
+
"should_training_stop": true
|
1593 |
},
|
1594 |
"attributes": {}
|
1595 |
}
|
1596 |
},
|
1597 |
+
"total_flos": 1.0403739277983744e+17,
|
1598 |
"train_batch_size": 1,
|
1599 |
"trial_name": null,
|
1600 |
"trial_params": null
|