rf300 commited on
Commit
2382e2e
·
verified ·
1 Parent(s): e959ef7

Model save

Browse files
README.md CHANGED
@@ -33,7 +33,7 @@ More information needed
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 2e-05
36
- - train_batch_size: 16
37
  - eval_batch_size: 8
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 2e-05
36
+ - train_batch_size: 100
37
  - eval_batch_size: 8
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 4.891794921875,
4
+ "train_runtime": 1355.1502,
5
+ "train_samples_per_second": 4.423,
6
+ "train_steps_per_second": 0.277
7
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d13f58695578f83005a2af95b749ec34e9db21ffb9ad5f9dbced4621b10532e
3
  size 343875434
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e0f3be3d3196c2864f86f7dcc2f54fa5b548b1bd2ab6f07dd98ee54687d1b2
3
  size 343875434
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 4.891794921875,
4
+ "train_runtime": 1355.1502,
5
+ "train_samples_per_second": 4.423,
6
+ "train_steps_per_second": 0.277
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 3000,
6
+ "global_step": 375,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "step": 375,
14
+ "total_flos": 4.6531126963696435e+17,
15
+ "train_loss": 4.891794921875,
16
+ "train_runtime": 1355.1502,
17
+ "train_samples_per_second": 4.423,
18
+ "train_steps_per_second": 0.277
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 375,
23
+ "num_train_epochs": 1,
24
+ "save_steps": 3000,
25
+ "total_flos": 4.6531126963696435e+17,
26
+ "trial_name": null,
27
+ "trial_params": null
28
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4054a98f7a29bff3d64b95d1fd586ecb89bff913f8d355a30e7fadd7d61bd3fb
3
  size 4472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22590141c34c1c71972c41a35f0066b128b2b676917bdb1d1d2cc47f5fcd0edb
3
  size 4472