Training in progress, step 287, 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:fde0d3ad37d0483d18c5d7361407a20d989b3d2c0689e306d1fe1de128f04797
|
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 37431220
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8d6db45fcee13b463abad4a2b5756d70d818f0b8c4b3ee64bf2e8db4d111a40
|
3 |
size 37431220
|
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:e6ccb5457083f4bd786c0f7a87422b9be39cb5b5c43390c1e58364cca7cf5143
|
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,
|
@@ -1995,6 +1995,27 @@
|
|
1995 |
"learning_rate": 6.060606060606061e-05,
|
1996 |
"loss": 1.1664,
|
1997 |
"step": 284
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1998 |
}
|
1999 |
],
|
2000 |
"logging_steps": 1,
|
@@ -2014,7 +2035,7 @@
|
|
2014 |
"attributes": {}
|
2015 |
}
|
2016 |
},
|
2017 |
-
"total_flos": 3.
|
2018 |
"train_batch_size": 4,
|
2019 |
"trial_name": null,
|
2020 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7873799725651578,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 287,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1995 |
"learning_rate": 6.060606060606061e-05,
|
1996 |
"loss": 1.1664,
|
1997 |
"step": 284
|
1998 |
+
},
|
1999 |
+
{
|
2000 |
+
"epoch": 0.7818930041152263,
|
2001 |
+
"grad_norm": 0.16307595372200012,
|
2002 |
+
"learning_rate": 5.9848484848484854e-05,
|
2003 |
+
"loss": 1.2355,
|
2004 |
+
"step": 285
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 0.7846364883401921,
|
2008 |
+
"grad_norm": 0.16836188733577728,
|
2009 |
+
"learning_rate": 5.90909090909091e-05,
|
2010 |
+
"loss": 1.2188,
|
2011 |
+
"step": 286
|
2012 |
+
},
|
2013 |
+
{
|
2014 |
+
"epoch": 0.7873799725651578,
|
2015 |
+
"grad_norm": 0.17626118659973145,
|
2016 |
+
"learning_rate": 5.833333333333334e-05,
|
2017 |
+
"loss": 1.1807,
|
2018 |
+
"step": 287
|
2019 |
}
|
2020 |
],
|
2021 |
"logging_steps": 1,
|
|
|
2035 |
"attributes": {}
|
2036 |
}
|
2037 |
},
|
2038 |
+
"total_flos": 3.552107643804426e+17,
|
2039 |
"train_batch_size": 4,
|
2040 |
"trial_name": null,
|
2041 |
"trial_params": null
|