End of training
Browse files- all_results.json +10 -10
- eval_results.json +6 -6
- pytorch_model.bin +1 -1
- runs/Oct18_19-15-28_955a9c86ed3b/events.out.tfevents.1634584539.955a9c86ed3b.1240.0 +2 -2
- runs/Oct18_19-15-28_955a9c86ed3b/events.out.tfevents.1634585850.955a9c86ed3b.1240.2 +3 -0
- train_results.json +5 -5
- trainer_state.json +18 -12
all_results.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime": 2.
|
5 |
"eval_samples": 7,
|
6 |
-
"eval_samples_per_second": 2.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
-
"perplexity":
|
9 |
-
"train_loss":
|
10 |
-
"train_runtime":
|
11 |
"train_samples": 14,
|
12 |
-
"train_samples_per_second": 1.
|
13 |
-
"train_steps_per_second": 0.
|
14 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 100.0,
|
3 |
+
"eval_loss": 5.787299633026123,
|
4 |
+
"eval_runtime": 2.7515,
|
5 |
"eval_samples": 7,
|
6 |
+
"eval_samples_per_second": 2.544,
|
7 |
+
"eval_steps_per_second": 0.363,
|
8 |
+
"perplexity": 326.131160418949,
|
9 |
+
"train_loss": 0.858495488848005,
|
10 |
+
"train_runtime": 1306.0127,
|
11 |
"train_samples": 14,
|
12 |
+
"train_samples_per_second": 1.072,
|
13 |
+
"train_steps_per_second": 0.536
|
14 |
}
|
eval_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime": 2.
|
5 |
"eval_samples": 7,
|
6 |
-
"eval_samples_per_second": 2.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
-
"perplexity":
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 100.0,
|
3 |
+
"eval_loss": 5.787299633026123,
|
4 |
+
"eval_runtime": 2.7515,
|
5 |
"eval_samples": 7,
|
6 |
+
"eval_samples_per_second": 2.544,
|
7 |
+
"eval_steps_per_second": 0.363,
|
8 |
+
"perplexity": 326.131160418949
|
9 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510403817
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:765d8b17199f60da6867acfc46c3277707402f8d4aa2ed5f3dc789e84ac5ac0e
|
3 |
size 510403817
|
runs/Oct18_19-15-28_955a9c86ed3b/events.out.tfevents.1634584539.955a9c86ed3b.1240.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c313c09245ee9d0b6f71dcafb5a8df5cb21df5e8cb33c575796b7cf407259b49
|
3 |
+
size 3910
|
runs/Oct18_19-15-28_955a9c86ed3b/events.out.tfevents.1634585850.955a9c86ed3b.1240.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da6f162c85d096fa063f34368e9a265f0f06318999056b6ce4c3f3c9d9568dd8
|
3 |
+
size 311
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss":
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 14,
|
6 |
-
"train_samples_per_second": 1.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 100.0,
|
3 |
+
"train_loss": 0.858495488848005,
|
4 |
+
"train_runtime": 1306.0127,
|
5 |
"train_samples": 14,
|
6 |
+
"train_samples_per_second": 1.072,
|
7 |
+
"train_steps_per_second": 0.536
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,25 +1,31 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
-
"epoch":
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
|
16 |
-
|
17 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
}
|
19 |
],
|
20 |
-
"max_steps":
|
21 |
-
"num_train_epochs":
|
22 |
-
"total_flos":
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 100.0,
|
5 |
+
"global_step": 700,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 71.43,
|
12 |
+
"learning_rate": 1.4285714285714285e-05,
|
13 |
+
"loss": 1.119,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 100.0,
|
18 |
+
"step": 700,
|
19 |
+
"total_flos": 731617689600000.0,
|
20 |
+
"train_loss": 0.858495488848005,
|
21 |
+
"train_runtime": 1306.0127,
|
22 |
+
"train_samples_per_second": 1.072,
|
23 |
+
"train_steps_per_second": 0.536
|
24 |
}
|
25 |
],
|
26 |
+
"max_steps": 700,
|
27 |
+
"num_train_epochs": 100,
|
28 |
+
"total_flos": 731617689600000.0,
|
29 |
"trial_name": null,
|
30 |
"trial_params": null
|
31 |
}
|