Shresthadev403
commited on
Commit
•
ecc733f
1
Parent(s):
ed1c350
End of training
Browse files- README.md +6 -6
- logs/events.out.tfevents.1706959201.da32439aada9.27.0 +3 -0
- model.safetensors +1 -1
- trainer_state.json +17 -3
README.md
CHANGED
@@ -13,12 +13,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
This model was trained from scratch on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
- eval_loss: 0.
|
17 |
-
- eval_runtime:
|
18 |
-
- eval_samples_per_second:
|
19 |
-
- eval_steps_per_second: 1.
|
20 |
-
- epoch: 27.
|
21 |
-
- step:
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
13 |
|
14 |
This model was trained from scratch on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- eval_loss: 0.8755
|
17 |
+
- eval_runtime: 2011.2204
|
18 |
+
- eval_samples_per_second: 110.935
|
19 |
+
- eval_steps_per_second: 1.734
|
20 |
+
- epoch: 27.89
|
21 |
+
- step: 1750000
|
22 |
|
23 |
## Model description
|
24 |
|
logs/events.out.tfevents.1706959201.da32439aada9.27.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78170dcdced1e0eb4f4cc7998c6687cb55b9d9832697924e5109cdff08996864
|
3 |
+
size 5099
|
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:d01d405f1fd949e31599c2d9dcedc77bbf8a8dd66e8e7243f43e7b70e2c97dd7
|
3 |
size 497918592
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 27.
|
5 |
"eval_steps": 50000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -483,6 +483,20 @@
|
|
483 |
"eval_samples_per_second": 111.493,
|
484 |
"eval_steps_per_second": 1.742,
|
485 |
"step": 1700000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
486 |
}
|
487 |
],
|
488 |
"logging_steps": 50000,
|
@@ -490,7 +504,7 @@
|
|
490 |
"num_input_tokens_seen": 0,
|
491 |
"num_train_epochs": 500,
|
492 |
"save_steps": 50000,
|
493 |
-
"total_flos": 3.
|
494 |
"train_batch_size": 32,
|
495 |
"trial_name": null,
|
496 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 27.888001784832113,
|
5 |
"eval_steps": 50000,
|
6 |
+
"global_step": 1750000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
483 |
"eval_samples_per_second": 111.493,
|
484 |
"eval_steps_per_second": 1.742,
|
485 |
"step": 1700000
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 27.89,
|
489 |
+
"learning_rate": 4.992035186690252e-05,
|
490 |
+
"loss": 0.8188,
|
491 |
+
"step": 1750000
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 27.89,
|
495 |
+
"eval_loss": 0.875482976436615,
|
496 |
+
"eval_runtime": 2011.2204,
|
497 |
+
"eval_samples_per_second": 110.935,
|
498 |
+
"eval_steps_per_second": 1.734,
|
499 |
+
"step": 1750000
|
500 |
}
|
501 |
],
|
502 |
"logging_steps": 50000,
|
|
|
504 |
"num_input_tokens_seen": 0,
|
505 |
"num_train_epochs": 500,
|
506 |
"save_steps": 50000,
|
507 |
+
"total_flos": 3.65807962939392e+18,
|
508 |
"train_batch_size": 32,
|
509 |
"trial_name": null,
|
510 |
"trial_params": null
|