Training in progress, step 25, 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 433386912
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8bef12420796eed721698f1c26bf29a79a9e08c74b5577f69642b1236165ccb9
|
3 |
size 433386912
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 866895354
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:055e00764f19a6fe669d0aad8d8fa44c3f585ad151f01fbe9921505ab24faca2
|
3 |
size 866895354
|
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:f77a46ff7cb971c99f52494bad58e0b5a3864a2e621faf3826a710d7b6f9bd18
|
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 sha256:74d3a5573a0e25294b323cfeb6378d9d3ab396748c686bd649593c3bf4adef3c
|
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":
|
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,
|
@@ -13,7 +13,7 @@
|
|
13 |
"num_input_tokens_seen": 0,
|
14 |
"num_train_epochs": 5,
|
15 |
"save_steps": 5,
|
16 |
-
"total_flos":
|
17 |
"train_batch_size": 1,
|
18 |
"trial_name": null,
|
19 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.166666666666667,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 25,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
13 |
"num_input_tokens_seen": 0,
|
14 |
"num_train_epochs": 5,
|
15 |
"save_steps": 5,
|
16 |
+
"total_flos": 48321897936.0,
|
17 |
"train_batch_size": 1,
|
18 |
"trial_name": null,
|
19 |
"trial_params": null
|