Shresthadev403
commited on
Commit
•
f0a40e0
1
Parent(s):
59b7afa
End of training
Browse files- README.md +6 -6
- logs/events.out.tfevents.1704595968.052fb87a7a0a.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:
|
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: 0.8838
|
17 |
+
- eval_runtime: 2005.9725
|
18 |
+
- eval_samples_per_second: 111.225
|
19 |
+
- eval_steps_per_second: 1.738
|
20 |
+
- epoch: 13.55
|
21 |
+
- step: 850000
|
22 |
|
23 |
## Model description
|
24 |
|
logs/events.out.tfevents.1704595968.052fb87a7a0a.26.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:debf9c06661bf9df642e3b1ade2311e20b967f39c08b8268beaa5b7e4b0b4408
|
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:a152f01e2eed2929de814ef9415645fd4bbd68cd7b31bf6c5438a5dc762577da
|
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,
|
@@ -231,6 +231,20 @@
|
|
231 |
"eval_samples_per_second": 110.993,
|
232 |
"eval_steps_per_second": 1.735,
|
233 |
"step": 800000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
234 |
}
|
235 |
],
|
236 |
"logging_steps": 50000,
|
@@ -238,7 +252,7 @@
|
|
238 |
"num_input_tokens_seen": 0,
|
239 |
"num_train_epochs": 500,
|
240 |
"save_steps": 50000,
|
241 |
-
"total_flos": 1.
|
242 |
"train_batch_size": 32,
|
243 |
"trial_name": null,
|
244 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 13.545600866918456,
|
5 |
"eval_steps": 50000,
|
6 |
+
"global_step": 850000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
231 |
"eval_samples_per_second": 110.993,
|
232 |
"eval_steps_per_second": 1.735,
|
233 |
"step": 800000
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 13.55,
|
237 |
+
"learning_rate": 4.9920348679702315e-05,
|
238 |
+
"loss": 0.8599,
|
239 |
+
"step": 850000
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 13.55,
|
243 |
+
"eval_loss": 0.883805513381958,
|
244 |
+
"eval_runtime": 2005.9725,
|
245 |
+
"eval_samples_per_second": 111.225,
|
246 |
+
"eval_steps_per_second": 1.738,
|
247 |
+
"step": 850000
|
248 |
}
|
249 |
],
|
250 |
"logging_steps": 50000,
|
|
|
252 |
"num_input_tokens_seen": 0,
|
253 |
"num_train_epochs": 500,
|
254 |
"save_steps": 50000,
|
255 |
+
"total_flos": 1.77678157160448e+18,
|
256 |
"train_batch_size": 32,
|
257 |
"trial_name": null,
|
258 |
"trial_params": null
|