Shresthadev403
commited on
Commit
•
c6e7c38
1
Parent(s):
cebd4ff
End of training
Browse files- README.md +1 -1
- logs/events.out.tfevents.1702723291.a235c334750e.1882.0 +3 -0
- model.safetensors +1 -1
- trainer_state.json +13 -4
- training_args.bin +1 -1
README.md
CHANGED
@@ -36,7 +36,7 @@ The following hyperparameters were used during training:
|
|
36 |
- seed: 42
|
37 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
38 |
- lr_scheduler_type: linear
|
39 |
-
- num_epochs: 0.
|
40 |
- mixed_precision_training: Native AMP
|
41 |
|
42 |
### Training results
|
|
|
36 |
- seed: 42
|
37 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
38 |
- lr_scheduler_type: linear
|
39 |
+
- num_epochs: 0.09
|
40 |
- mixed_precision_training: Native AMP
|
41 |
|
42 |
### Training results
|
logs/events.out.tfevents.1702723291.a235c334750e.1882.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f048ffa597afaafd35632cc331e084a702fcba049eab99916dfd97b2b7a8ac9d
|
3 |
+
size 4867
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497918592
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c4de7f5916f44599f9620dafeb5655aeda10ebec759dcf9c996dcdb8733eb74
|
3 |
size 497918592
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 8000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -16,13 +16,22 @@
|
|
16 |
"train_runtime": 322.5365,
|
17 |
"train_samples_per_second": 62.257,
|
18 |
"train_steps_per_second": 1.947
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 8000,
|
22 |
-
"max_steps":
|
23 |
"num_train_epochs": 1,
|
24 |
"save_steps": 8000,
|
25 |
-
"total_flos":
|
26 |
"trial_name": null,
|
27 |
"trial_params": null
|
28 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.09000653376041816,
|
5 |
"eval_steps": 8000,
|
6 |
+
"global_step": 5648,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
16 |
"train_runtime": 322.5365,
|
17 |
"train_samples_per_second": 62.257,
|
18 |
"train_steps_per_second": 1.947
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 0.09,
|
22 |
+
"step": 5648,
|
23 |
+
"total_flos": 1.1806219173888e+16,
|
24 |
+
"train_loss": 1.0376979406427054,
|
25 |
+
"train_runtime": 2474.3011,
|
26 |
+
"train_samples_per_second": 73.04,
|
27 |
+
"train_steps_per_second": 2.283
|
28 |
}
|
29 |
],
|
30 |
"logging_steps": 8000,
|
31 |
+
"max_steps": 5648,
|
32 |
"num_train_epochs": 1,
|
33 |
"save_steps": 8000,
|
34 |
+
"total_flos": 1.1806219173888e+16,
|
35 |
"trial_name": null,
|
36 |
"trial_params": null
|
37 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38704735567bbcf51c349997edab9d7540450f26004fd210e7261e2de78eb5fc
|
3 |
size 4600
|