Upload 12 files
Browse files- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +3 -12
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aee3fd748594dcf230b2822b9884b379889c6988b2ed992b3a500009f222ecff
|
3 |
+
size 540029536
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bfaac227376285bff86ad9729861d4b3c43f9871edf9ee188edde7bfb115408
|
3 |
+
size 1080178938
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba27a5e51ec0477de1e2f5db295d5983ece41d5e085f8eb9c585e9de57ef6a49
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c015a7929fba91dd37c2abe94ce0ce215b289951d5327e76cdcd20f461119e3d
|
3 |
+
size 1064
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
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,
|
@@ -1795,22 +1795,13 @@
|
|
1795 |
"learning_rate": 1.4754208302595401e-08,
|
1796 |
"loss": 0.0659,
|
1797 |
"step": 149000
|
1798 |
-
},
|
1799 |
-
{
|
1800 |
-
"epoch": 10.0,
|
1801 |
-
"step": 149110,
|
1802 |
-
"total_flos": 9808298492528640.0,
|
1803 |
-
"train_loss": 0.1504479006291696,
|
1804 |
-
"train_runtime": 9647.5503,
|
1805 |
-
"train_samples_per_second": 15.456,
|
1806 |
-
"train_steps_per_second": 15.456
|
1807 |
}
|
1808 |
],
|
1809 |
"logging_steps": 500,
|
1810 |
"max_steps": 149110,
|
1811 |
"num_train_epochs": 10,
|
1812 |
"save_steps": 500,
|
1813 |
-
"total_flos":
|
1814 |
"trial_name": null,
|
1815 |
"trial_params": null
|
1816 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.992622895848703,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 149000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1795 |
"learning_rate": 1.4754208302595401e-08,
|
1796 |
"loss": 0.0659,
|
1797 |
"step": 149000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1798 |
}
|
1799 |
],
|
1800 |
"logging_steps": 500,
|
1801 |
"max_steps": 149110,
|
1802 |
"num_train_epochs": 10,
|
1803 |
"save_steps": 500,
|
1804 |
+
"total_flos": 9801062808576000.0,
|
1805 |
"trial_name": null,
|
1806 |
"trial_params": null
|
1807 |
}
|