s3nh
/

PyTorch
Polish
s3nh commited on
Commit
972476d
1 Parent(s): c81c100

Initial commit

Browse files
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6cccd3ff637b07bdaaa72b47ea09f5574c40809bca7f58d37e3e07ff2032ee8
3
+ size 29426821
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bde7af4c0d017a28ac4aa738e0d0a39bd572bb87cbe3ec56d6ece2daca83217
3
+ size 24335854041
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dada372ed12eab564b032ffe8ceccd4b544e7c4df66e3bfa43e43d8ebf7dd104
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94068978dc32d2a0cefd0a54bc4405327482e97c139e8cd94358d54535b5ff54
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.3133208255159474,
5
+ "global_step": 3500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.38,
12
+ "learning_rate": 9.628378378378378e-07,
13
+ "loss": 4.3599,
14
+ "step": 1000
15
+ },
16
+ {
17
+ "epoch": 0.75,
18
+ "learning_rate": 9.253003003003003e-07,
19
+ "loss": 2.1723,
20
+ "step": 2000
21
+ },
22
+ {
23
+ "epoch": 1.13,
24
+ "learning_rate": 8.877627627627627e-07,
25
+ "loss": 0.7581,
26
+ "step": 3000
27
+ }
28
+ ],
29
+ "max_steps": 26650,
30
+ "num_train_epochs": 10,
31
+ "total_flos": 5.029954774155264e+17,
32
+ "trial_name": null,
33
+ "trial_params": null
34
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82173fdbe39948c9ad908bcc62ccb5bec1c651363934df311ee3f06cad0025af
3
+ size 3259