Training in progress, step 215, 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 sha256:9919332f81d5d5b883cad030582389e20f058a61306a571d8225c59ec351c54d
|
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:b97479a9ebdfc40326763536562f5b83d05283ac0e1bf4e1a50f5de5908f1708
|
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 sha256:86ca27e6ab41112bbcd58358d08377980438330a59138fb91fb36e8afa2a012b
|
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,
|
@@ -1505,6 +1505,13 @@
|
|
1505 |
"learning_rate": 0.00011363636363636365,
|
1506 |
"loss": 1.2256,
|
1507 |
"step": 214
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1508 |
}
|
1509 |
],
|
1510 |
"logging_steps": 1,
|
@@ -1524,7 +1531,7 @@
|
|
1524 |
"attributes": {}
|
1525 |
}
|
1526 |
},
|
1527 |
-
"total_flos": 2.
|
1528 |
"train_batch_size": 4,
|
1529 |
"trial_name": null,
|
1530 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5898491083676269,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 215,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1505 |
"learning_rate": 0.00011363636363636365,
|
1506 |
"loss": 1.2256,
|
1507 |
"step": 214
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 0.5898491083676269,
|
1511 |
+
"grad_norm": 0.18230263888835907,
|
1512 |
+
"learning_rate": 0.0001128787878787879,
|
1513 |
+
"loss": 1.1579,
|
1514 |
+
"step": 215
|
1515 |
}
|
1516 |
],
|
1517 |
"logging_steps": 1,
|
|
|
1531 |
"attributes": {}
|
1532 |
}
|
1533 |
},
|
1534 |
+
"total_flos": 2.6613228931631923e+17,
|
1535 |
"train_batch_size": 4,
|
1536 |
"trial_name": null,
|
1537 |
"trial_params": null
|