Training in progress, step 10, 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 sha256:01482a4ed4f07784bd2be7882ef15be30a36dcc384daa89e6dfd5890ace0ccfb
|
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:aa9740f7ef34783948b62437f5e00eef71668e1b0ed1fc9d910880e8183a3067
|
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 sha256:05c7723b18b4b2e8e43e5950b4101e666de486f4a0f7c20c879a02bb893db131
|
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 sha256:5580a1414d7196055e6fa3fba14479603a1b2051b626d398b0a3cf818e209b87
|
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": 1.6666666666666665,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 10,
|
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": 21590635248.0,
|
17 |
"train_batch_size": 1,
|
18 |
"trial_name": null,
|
19 |
"trial_params": null
|