Training in progress, step 2000, 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 sha256:4ab92723c53b61690dd4e6adc89be4bad87f23308b597935371f7baa5fd7092e
|
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:b043a5e02a43092868d088ed3b37cff8e6699603c9bcf82b104e8089a4ad566c
|
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 sha256:751be9ef02bac0823c942ed1bd370540e3227b7fe38581b0d6ab7b85fc6f4018
|
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 sha256:7af67e15c7ea7b999b8506cb053f1ebebef8ff413acf74ef75da83a900869e05
|
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,
|
@@ -25,13 +25,19 @@
|
|
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":
|
35 |
"trial_name": null,
|
36 |
"trial_params": null
|
37 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3069367710251688,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
25 |
"learning_rate": 0.0009539594843462247,
|
26 |
"loss": 0.6024,
|
27 |
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.31,
|
31 |
+
"learning_rate": 0.0009386126457949663,
|
32 |
+
"loss": 0.6057,
|
33 |
+
"step": 2000
|
34 |
}
|
35 |
],
|
36 |
"logging_steps": 500,
|
37 |
"max_steps": 32580,
|
38 |
"num_train_epochs": 5,
|
39 |
"save_steps": 500,
|
40 |
+
"total_flos": 1057438183194624.0,
|
41 |
"trial_name": null,
|
42 |
"trial_params": null
|
43 |
}
|