Shresthadev403
commited on
Commit
•
6ef52b5
1
Parent(s):
148442b
End of training
Browse files- README.md +5 -5
- logs/events.out.tfevents.1703387695.f4341cf79e18.26.0 +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: 1998.
|
18 |
-
- eval_samples_per_second: 111.
|
19 |
- eval_steps_per_second: 1.745
|
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: 0.9041
|
17 |
+
- eval_runtime: 1998.7351
|
18 |
+
- eval_samples_per_second: 111.628
|
19 |
- eval_steps_per_second: 1.745
|
20 |
+
- epoch: 6.37
|
21 |
+
- step: 400000
|
22 |
|
23 |
## Model description
|
24 |
|
logs/events.out.tfevents.1703387695.f4341cf79e18.26.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ce8edc36513ad5a4b843ef8e36c9c34965cf00b88920aedf5ae9be6be2f9efe
|
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 sha256:138a75cd206a202484cd2a6c4b8e80b2fa7b01d519d7871da738b9518489871c
|
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,
|
@@ -105,6 +105,20 @@
|
|
105 |
"eval_samples_per_second": 111.644,
|
106 |
"eval_steps_per_second": 1.745,
|
107 |
"step": 350000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
108 |
}
|
109 |
],
|
110 |
"logging_steps": 50000,
|
@@ -112,7 +126,7 @@
|
|
112 |
"num_input_tokens_seen": 0,
|
113 |
"num_train_epochs": 500,
|
114 |
"save_steps": 50000,
|
115 |
-
"total_flos":
|
116 |
"train_batch_size": 32,
|
117 |
"trial_name": null,
|
118 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.374400407961626,
|
5 |
"eval_steps": 50000,
|
6 |
+
"global_step": 400000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
105 |
"eval_samples_per_second": 111.644,
|
106 |
"eval_steps_per_second": 1.745,
|
107 |
"step": 350000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 6.37,
|
111 |
+
"learning_rate": 4.9920355054102726e-05,
|
112 |
+
"loss": 0.906,
|
113 |
+
"step": 400000
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 6.37,
|
117 |
+
"eval_loss": 0.9041373133659363,
|
118 |
+
"eval_runtime": 1998.7351,
|
119 |
+
"eval_samples_per_second": 111.628,
|
120 |
+
"eval_steps_per_second": 1.745,
|
121 |
+
"step": 400000
|
122 |
}
|
123 |
],
|
124 |
"logging_steps": 50000,
|
|
|
126 |
"num_input_tokens_seen": 0,
|
127 |
"num_train_epochs": 500,
|
128 |
"save_steps": 50000,
|
129 |
+
"total_flos": 8.3613254270976e+17,
|
130 |
"train_batch_size": 32,
|
131 |
"trial_name": null,
|
132 |
"trial_params": null
|