nebu1a commited on
Commit
616b594
·
verified ·
1 Parent(s): 8e28422

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 sha256:0f4aa5e54e5b371692d4c5027e42cc6e99f48f8e5f93566b3171d93ab7d3b9dd
3
  size 906712552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3229b0d2b8ecd1e5c148ea0f8fbed2a08263bbcff737a3abce621ddf00b97041
3
  size 906712552
last/training_state/optimizer_param_groups.json CHANGED
@@ -1,6 +1,6 @@
1
  [
2
  {
3
- "lr": 9.628912720992524e-05,
4
  "betas": [
5
  0.9,
6
  0.95
 
1
  [
2
  {
3
+ "lr": 8.572145558284418e-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 sha256:5dd2def99236317cc3ce4f4cd0bf62da1f1a78cbd4da7e307186dfaf9ed64c1d
3
  size 412659164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d16699bd5c01f32ba786ae922dbb33fb5da4111eff658a07bfa5532665157b08
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 sha256:6efd038fae7dae62d0d8e4eff132e13658aba10b0dcedae2a12466ecb837f883
3
  size 15712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00baf7c77684ecd3f8768ede415117ba378d4f47014877d238f44000f1769ef1
3
  size 15712
last/training_state/scheduler_state.json CHANGED
@@ -2,12 +2,12 @@
2
  "base_lrs": [
3
  0.0001
4
  ],
5
- "last_epoch": 1000,
6
- "_step_count": 1001,
7
  "_is_initial": false,
8
  "_get_lr_called_within_step": false,
9
  "_last_lr": [
10
- 9.628912720992524e-05
11
  ],
12
  "lr_lambdas": [
13
  null
 
2
  "base_lrs": [
3
  0.0001
4
  ],
5
+ "last_epoch": 2000,
6
+ "_step_count": 2001,
7
  "_is_initial": false,
8
  "_get_lr_called_within_step": false,
9
  "_last_lr": [
10
+ 8.572145558284418e-05
11
  ],
12
  "lr_lambdas": [
13
  null
last/training_state/training_step.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "step": 1000,
3
  "dp_world_size": 1,
4
  "batch_size": 8,
5
  "grad_accum_steps": 1,
 
1
  {
2
+ "step": 2000,
3
  "dp_world_size": 1,
4
  "batch_size": 8,
5
  "grad_accum_steps": 1,