Training in progress, step 900, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +11 -3
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 109069176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cbcd9310e10d5fe993b5cf333d88aae96e554801b55f9a8223e27e60cbd5ee7
|
3 |
size 109069176
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 218182650
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27dd51826701f4f4caf7650fd69a5e61f897e08b55abc61a1a1af22c824d7a70
|
3 |
size 218182650
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdf88252bee8ee3fad27d73acc6775e5c54e36b432cba2ce38bd28d90a91cedc
|
3 |
size 15920
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41e967c2ecc8fedac9e0009a302b7be7b77330e19189247194492952af17ea64
|
3 |
size 15920
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66a8969a338902975b0c4c705afc719c7c7b10b35ea13c9c67faffb439307f43
|
3 |
size 15920
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8196d74df85addf8f6045699aed4bb233236ff60e0fc4a401041aedc4272b347
|
3 |
size 15920
|
last-checkpoint/rng_state_4.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03a4c643870f71e5714f51cca20015821a04ab9ad622a0412916ee78037f3515
|
3 |
size 15920
|
last-checkpoint/rng_state_5.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:794ce6be94cae7a6fbdda053c500122338e8c247918fbe8eb826684e5bd3ca24
|
3 |
size 15920
|
last-checkpoint/rng_state_6.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5ca5a1485292bda09ae1ddd0869d5b7f3aa39d96a8386b1e8f008804f4026e8
|
3 |
size 15920
|
last-checkpoint/rng_state_7.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df39b202ceea5786d852b9d29b95d90e78cf3ccd25f2d593dfc4b4c2a64d2ca2
|
3 |
size 15920
|
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 sha256:647afc85c56b5d55d82459efd014f4044d90b731c734f1c96dfdd388b51e583f
|
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": 2.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -78,6 +78,14 @@
|
|
78 |
"eval_samples_per_second": 9.354,
|
79 |
"eval_steps_per_second": 0.292,
|
80 |
"step": 800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
81 |
}
|
82 |
],
|
83 |
"logging_steps": 500,
|
@@ -97,7 +105,7 @@
|
|
97 |
"attributes": {}
|
98 |
}
|
99 |
},
|
100 |
-
"total_flos": 1.
|
101 |
"train_batch_size": 4,
|
102 |
"trial_name": null,
|
103 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.25,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 900,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
78 |
"eval_samples_per_second": 9.354,
|
79 |
"eval_steps_per_second": 0.292,
|
80 |
"step": 800
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 2.25,
|
84 |
+
"eval_loss": 0.012095152400434017,
|
85 |
+
"eval_runtime": 3.4203,
|
86 |
+
"eval_samples_per_second": 9.356,
|
87 |
+
"eval_steps_per_second": 0.292,
|
88 |
+
"step": 900
|
89 |
}
|
90 |
],
|
91 |
"logging_steps": 500,
|
|
|
105 |
"attributes": {}
|
106 |
}
|
107 |
},
|
108 |
+
"total_flos": 1.3327995625065677e+18,
|
109 |
"train_batch_size": 4,
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|