Training in progress, step 1500, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242041896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b61bc71b3cc573001cb21c7d16728ac98fb53f4c1ba390fdb950d95eb6fd4388
|
3 |
size 242041896
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484163514
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:371fe9e9450ca64eb5adece60b154627164cc865548031009791b704bc0bee75
|
3 |
size 484163514
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bae0760f31519675dc47739c9f2cfff4a7ea43002adf212fc7168ae760ccdf31
|
3 |
size 14244
|
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 sha256:2b713dfcb26e4a0f9f3e12f6748b79f1a98be869457c41d0f2179e2a66581f85
|
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,
|
@@ -19,13 +19,19 @@
|
|
19 |
"learning_rate": 0.0009693063228974831,
|
20 |
"loss": 0.6042,
|
21 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
}
|
23 |
],
|
24 |
"logging_steps": 500,
|
25 |
"max_steps": 32580,
|
26 |
"num_train_epochs": 5,
|
27 |
"save_steps": 500,
|
28 |
-
"total_flos":
|
29 |
"trial_name": null,
|
30 |
"trial_params": null
|
31 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2302025782688766,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
19 |
"learning_rate": 0.0009693063228974831,
|
20 |
"loss": 0.6042,
|
21 |
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.23,
|
25 |
+
"learning_rate": 0.0009539594843462247,
|
26 |
+
"loss": 0.6024,
|
27 |
+
"step": 1500
|
28 |
}
|
29 |
],
|
30 |
"logging_steps": 500,
|
31 |
"max_steps": 32580,
|
32 |
"num_train_epochs": 5,
|
33 |
"save_steps": 500,
|
34 |
+
"total_flos": 793648553263104.0,
|
35 |
"trial_name": null,
|
36 |
"trial_params": null
|
37 |
}
|