Training in progress, step 100
Browse files
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 335638221
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18d9ad4f8dc933ad6e407f8768604fa8df673a51ff20e3fc2b2b72b58b96296c
|
3 |
size 335638221
|
last-checkpoint/adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 335638221
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18d9ad4f8dc933ad6e407f8768604fa8df673a51ff20e3fc2b2b72b58b96296c
|
3 |
size 335638221
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 671246597
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5645adc0e815427bee2525b551ef19301c3bd58feffe8f523abeea2acf1157d
|
3 |
size 671246597
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2a4a57d3543837f3d3fec93400bac8989273bbf35e51c30c34f8bfa85b258ee
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -60,11 +60,17 @@
|
|
60 |
"learning_rate": 0.0002,
|
61 |
"loss": 1.4887,
|
62 |
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
}
|
64 |
],
|
65 |
"max_steps": 100,
|
66 |
"num_train_epochs": 1,
|
67 |
-
"total_flos": 5.
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|
70 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6498781478472786,
|
5 |
+
"global_step": 100,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
60 |
"learning_rate": 0.0002,
|
61 |
"loss": 1.4887,
|
62 |
"step": 90
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.65,
|
66 |
+
"learning_rate": 0.0002,
|
67 |
+
"loss": 1.5132,
|
68 |
+
"step": 100
|
69 |
}
|
70 |
],
|
71 |
"max_steps": 100,
|
72 |
"num_train_epochs": 1,
|
73 |
+
"total_flos": 5.7895286734848e+16,
|
74 |
"trial_name": null,
|
75 |
"trial_params": null
|
76 |
}
|
runs/Jul04_00-42-28_06a0078a8833/events.out.tfevents.1688431447.06a0078a8833.315.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:234d3567338b4b818eea4a3bd8f27e320b5f47d2eccf3c8fa4319bb780be8fbc
|
3 |
+
size 5965
|