Training in progress, step 3000, 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 sha256:8aac1669065ba26d9c8064c351eb402f1f03c58e93db68b02f8fbd713bd4f78a
|
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 sha256:3e177a4ea050f3054998776f28b10aaf5df197c33ccde13af7bb851da38edd5b
|
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 sha256:3e121bedda6b1a7054990c1698c0f1b3c4e3edb7eafc5b595ed1b5b631d3865e
|
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 sha256:9e9331bd819c2583e413c7abb35fc97e31c67e958ad170c5f91e35dc74e5028d
|
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,
|
@@ -37,13 +37,19 @@
|
|
37 |
"learning_rate": 0.0009232658072437078,
|
38 |
"loss": 0.6143,
|
39 |
"step": 2500
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
}
|
41 |
],
|
42 |
"logging_steps": 500,
|
43 |
"max_steps": 32580,
|
44 |
"num_train_epochs": 5,
|
45 |
"save_steps": 500,
|
46 |
-
"total_flos":
|
47 |
"trial_name": null,
|
48 |
"trial_params": null
|
49 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4604051565377532,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 3000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
37 |
"learning_rate": 0.0009232658072437078,
|
38 |
"loss": 0.6143,
|
39 |
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.46,
|
43 |
+
"learning_rate": 0.0009079189686924494,
|
44 |
+
"loss": 0.6081,
|
45 |
+
"step": 3000
|
46 |
}
|
47 |
],
|
48 |
"logging_steps": 500,
|
49 |
"max_steps": 32580,
|
50 |
"num_train_epochs": 5,
|
51 |
"save_steps": 500,
|
52 |
+
"total_flos": 1587229435625472.0,
|
53 |
"trial_name": null,
|
54 |
"trial_params": null
|
55 |
}
|