Training in progress, step 8, 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 sha256:146d162f21d6885a599ae47823186efd669faffd51555aea28ea2980c3ba276d
|
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 sha256:28337b7c2b425365ede002b7367ded19801e6211d9e7a1fe9480d2ff0a4306db
|
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 sha256:8ea1738558a9366d944e7310c6a878fb018ff37640bc9d856eea647247684a83
|
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,
|
@@ -56,6 +56,13 @@
|
|
56 |
"learning_rate": 1.4000000000000001e-05,
|
57 |
"loss": 2.036,
|
58 |
"step": 7
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
59 |
}
|
60 |
],
|
61 |
"logging_steps": 1,
|
@@ -75,7 +82,7 @@
|
|
75 |
"attributes": {}
|
76 |
}
|
77 |
},
|
78 |
-
"total_flos":
|
79 |
"train_batch_size": 4,
|
80 |
"trial_name": null,
|
81 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.02194787379972565,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 8,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
56 |
"learning_rate": 1.4000000000000001e-05,
|
57 |
"loss": 2.036,
|
58 |
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.02194787379972565,
|
62 |
+
"grad_norm": 1.5287824869155884,
|
63 |
+
"learning_rate": 1.6000000000000003e-05,
|
64 |
+
"loss": 1.984,
|
65 |
+
"step": 8
|
66 |
}
|
67 |
],
|
68 |
"logging_steps": 1,
|
|
|
82 |
"attributes": {}
|
83 |
}
|
84 |
},
|
85 |
+
"total_flos": 9823019497033728.0,
|
86 |
"train_batch_size": 4,
|
87 |
"trial_name": null,
|
88 |
"trial_params": null
|