nebu1a commited on
Commit
206b749
·
verified ·
1 Parent(s): 62b0ae9

Upload folder using huggingface_hub

Browse files
last/pretrained_model/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db6a836ee71d97cd2ab0ad4eba7c61cbd1ef017ad5439c30a51a6e3a997ba854
3
  size 906712552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec3e973cb69111c786f1f88a79209398593daf8be4b736aa864aa204f40b5044
3
  size 906712552
last/training_state/optimizer_param_groups.json CHANGED
@@ -1,6 +1,6 @@
1
  [
2
  {
3
- "lr": 5.125e-05,
4
  "betas": [
5
  0.9,
6
  0.95
 
1
  [
2
  {
3
+ "lr": 3.2594182672201875e-05,
4
  "betas": [
5
  0.9,
6
  0.95
last/training_state/optimizer_state.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0621595e081c2c0f42522b532f73ec6faf1dd5e6b8b3879f540ff44cfa086794
3
  size 412659164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72a1756a58a7c0fb9d467640508d9b20909253cb9a823f98032825f8e0303e71
3
  size 412659164
last/training_state/rng_state.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb19ac8913866c8204472b9ba5fa361678366f03e7a745902071af66938d164f
3
  size 15712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5efc15d9de73c32345e67f6e1b1ac0bb69af9c66f446898604f5dc1cd45bff34
3
  size 15712
last/training_state/scheduler_state.json CHANGED
@@ -2,12 +2,12 @@
2
  "base_lrs": [
3
  0.0001
4
  ],
5
- "last_epoch": 4000,
6
- "_step_count": 4001,
7
  "_is_initial": false,
8
  "_get_lr_called_within_step": false,
9
  "_last_lr": [
10
- 5.125e-05
11
  ],
12
  "lr_lambdas": [
13
  null
 
2
  "base_lrs": [
3
  0.0001
4
  ],
5
+ "last_epoch": 5000,
6
+ "_step_count": 5001,
7
  "_is_initial": false,
8
  "_get_lr_called_within_step": false,
9
  "_last_lr": [
10
+ 3.2594182672201875e-05
11
  ],
12
  "lr_lambdas": [
13
  null
last/training_state/training_step.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "step": 4000,
3
  "dp_world_size": 1,
4
  "batch_size": 8,
5
  "grad_accum_steps": 1,
 
1
  {
2
+ "step": 5000,
3
  "dp_world_size": 1,
4
  "batch_size": 8,
5
  "grad_accum_steps": 1,