Upload checkpoint-220000 to giorom-3d-t-plasticine3d
Browse files- config.json +1 -2
- model.safetensors +1 -1
- optimizer.pt +2 -2
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +10 -10
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,10 +1,9 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/scratch/gilbreth/hviswan/GIOROM/saved_models/checkpoint-220000",
|
3 |
"architectures": [
|
4 |
"PhysicsEngine"
|
5 |
],
|
6 |
"dim": 3,
|
7 |
-
"gno_radius": 0.
|
8 |
"heads": 3,
|
9 |
"hidden_size": 128,
|
10 |
"in_gno_mlp_hidden_layers": [
|
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"PhysicsEngine"
|
4 |
],
|
5 |
"dim": 3,
|
6 |
+
"gno_radius": 0.165,
|
7 |
"heads": 3,
|
8 |
"hidden_size": 128,
|
9 |
"in_gno_mlp_hidden_layers": [
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9568276
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbae34bf29e1d2db971aa80ea138ae658c5725a051106ee6157754d8917b3851
|
3 |
size 9568276
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59ec1eb13b63796ad34b3fef55cef5056298b124dd60cca8d2e20ae55308cf75
|
3 |
+
size 19246970
|
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 sha256:4083aa1322a231a785325c26497b14a004df92984d3c40f4ec4ece66ac2e9b09
|
3 |
size 14244
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1000
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60e429bed308f3741637c88d0bd73b051342308591193d374d219af1d4ac4d5d
|
3 |
size 1000
|
trainer_state.json
CHANGED
@@ -1,33 +1,33 @@
|
|
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,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"avg_loss": 0.
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 0.
|
16 |
-
"lr":
|
17 |
-
"step":
|
18 |
}
|
19 |
],
|
20 |
"logging_steps": 1500,
|
21 |
"max_steps": 37680000,
|
22 |
"num_input_tokens_seen": 0,
|
23 |
"num_train_epochs": 2000,
|
24 |
-
"save_steps":
|
25 |
"stateful_callbacks": {
|
26 |
"TrainerControl": {
|
27 |
"args": {
|
28 |
"should_epoch_stop": false,
|
29 |
"should_evaluate": false,
|
30 |
-
"should_log":
|
31 |
"should_save": true,
|
32 |
"should_training_stop": false
|
33 |
},
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 15.923566878980893,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 300000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"avg_loss": 0.17167335909317713,
|
13 |
+
"grad_norm": 0.0,
|
14 |
+
"learning_rate": 7.585775750096955e-05,
|
15 |
+
"loss": 0.1428,
|
16 |
+
"lr": 7.585779243476592e-05,
|
17 |
+
"step": 299999
|
18 |
}
|
19 |
],
|
20 |
"logging_steps": 1500,
|
21 |
"max_steps": 37680000,
|
22 |
"num_input_tokens_seen": 0,
|
23 |
"num_train_epochs": 2000,
|
24 |
+
"save_steps": 100000,
|
25 |
"stateful_callbacks": {
|
26 |
"TrainerControl": {
|
27 |
"args": {
|
28 |
"should_epoch_stop": false,
|
29 |
"should_evaluate": false,
|
30 |
+
"should_log": true,
|
31 |
"should_save": true,
|
32 |
"should_training_stop": false
|
33 |
},
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d6b918707d435205378f09b443e0d4952a640bd1a9256371c045e60abfaaf21
|
3 |
size 5240
|