Shresthadev403
commited on
Commit
•
cd5eac3
1
Parent(s):
4a4bce1
End of training
Browse files- README.md +6 -6
- logs/events.out.tfevents.1706631907.6842b220c3c1.26.0 +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: 111.
|
19 |
-
- eval_steps_per_second: 1.
|
20 |
-
- epoch:
|
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: 0.8791
|
17 |
+
- eval_runtime: 2008.615
|
18 |
+
- eval_samples_per_second: 111.079
|
19 |
+
- eval_steps_per_second: 1.736
|
20 |
+
- epoch: 26.29
|
21 |
+
- step: 1650000
|
22 |
|
23 |
## Model description
|
24 |
|
logs/events.out.tfevents.1706631907.6842b220c3c1.26.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d887d5ca7717f2391911bdbcbadc952823688d4e53cca22b250049e7e65779c
|
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 sha256:928dde0b96414ccb0efff3d1e781716fc8dec2ee14936cc75b51774b157a21b9
|
3 |
size 497918592
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
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,
|
@@ -455,6 +455,20 @@
|
|
455 |
"eval_samples_per_second": 111.668,
|
456 |
"eval_steps_per_second": 1.745,
|
457 |
"step": 1600000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
458 |
}
|
459 |
],
|
460 |
"logging_steps": 50000,
|
@@ -462,7 +476,7 @@
|
|
462 |
"num_input_tokens_seen": 0,
|
463 |
"num_train_epochs": 500,
|
464 |
"save_steps": 50000,
|
465 |
-
"total_flos": 3.
|
466 |
"train_batch_size": 32,
|
467 |
"trial_name": null,
|
468 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 26.29440168284171,
|
5 |
"eval_steps": 50000,
|
6 |
+
"global_step": 1650000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
455 |
"eval_samples_per_second": 111.668,
|
456 |
"eval_steps_per_second": 1.745,
|
457 |
"step": 1600000
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 26.29,
|
461 |
+
"learning_rate": 4.9920348679702315e-05,
|
462 |
+
"loss": 0.8201,
|
463 |
+
"step": 1650000
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 26.29,
|
467 |
+
"eval_loss": 0.8791316151618958,
|
468 |
+
"eval_runtime": 2008.615,
|
469 |
+
"eval_samples_per_second": 111.079,
|
470 |
+
"eval_steps_per_second": 1.736,
|
471 |
+
"step": 1650000
|
472 |
}
|
473 |
],
|
474 |
"logging_steps": 50000,
|
|
|
476 |
"num_input_tokens_seen": 0,
|
477 |
"num_train_epochs": 500,
|
478 |
"save_steps": 50000,
|
479 |
+
"total_flos": 3.44904633040896e+18,
|
480 |
"train_batch_size": 32,
|
481 |
"trial_name": null,
|
482 |
"trial_params": null
|