End of training
Browse files- all_results.json +10 -10
- eval_results.json +6 -6
- pytorch_model.bin +1 -1
- runs/Oct18_18-47-35_955a9c86ed3b/1634582878.0278647/events.out.tfevents.1634582878.955a9c86ed3b.803.1 +3 -0
- runs/Oct18_18-47-35_955a9c86ed3b/events.out.tfevents.1634582877.955a9c86ed3b.803.0 +3 -0
- runs/Oct18_18-47-35_955a9c86ed3b/events.out.tfevents.1634583007.955a9c86ed3b.803.2 +3 -0
- train_results.json +5 -5
- trainer_state.json +12 -12
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_loss": 3.
|
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": 3.
|
10 |
-
"train_runtime":
|
11 |
"train_samples": 14,
|
12 |
-
"train_samples_per_second": 1.
|
13 |
-
"train_steps_per_second": 0.
|
14 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_loss": 3.4109785556793213,
|
4 |
+
"eval_runtime": 2.7473,
|
5 |
"eval_samples": 7,
|
6 |
+
"eval_samples_per_second": 2.548,
|
7 |
+
"eval_steps_per_second": 0.364,
|
8 |
+
"perplexity": 30.294874981347323,
|
9 |
+
"train_loss": 3.1061488560267856,
|
10 |
+
"train_runtime": 125.6009,
|
11 |
"train_samples": 14,
|
12 |
+
"train_samples_per_second": 1.115,
|
13 |
+
"train_steps_per_second": 0.557
|
14 |
}
|
eval_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_loss": 3.
|
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": 10.0,
|
3 |
+
"eval_loss": 3.4109785556793213,
|
4 |
+
"eval_runtime": 2.7473,
|
5 |
"eval_samples": 7,
|
6 |
+
"eval_samples_per_second": 2.548,
|
7 |
+
"eval_steps_per_second": 0.364,
|
8 |
+
"perplexity": 30.294874981347323
|
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 sha256:08ba518aa34a063c4036479df0bf3766dc65b12ffb9104fd0e8364e12b0b5160
|
3 |
size 510403817
|
runs/Oct18_18-47-35_955a9c86ed3b/1634582878.0278647/events.out.tfevents.1634582878.955a9c86ed3b.803.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb9ba401e9a3c67ce1393570671d12af635844442a9b730ad356600bce6d95ae
|
3 |
+
size 4516
|
runs/Oct18_18-47-35_955a9c86ed3b/events.out.tfevents.1634582877.955a9c86ed3b.803.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f342d09ba01b68cbb2cb3b058c5bfa51f8bd41fe78b3a0bf0aabdc5409beb92
|
3 |
+
size 3746
|
runs/Oct18_18-47-35_955a9c86ed3b/events.out.tfevents.1634583007.955a9c86ed3b.803.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95e265264f715e9b7318fba94347bd65b09917f5481886c38bde7c993b58d920
|
3 |
+
size 306
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss": 3.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 14,
|
6 |
-
"train_samples_per_second": 1.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 3.1061488560267856,
|
4 |
+
"train_runtime": 125.6009,
|
5 |
"train_samples": 14,
|
6 |
+
"train_samples_per_second": 1.115,
|
7 |
+
"train_steps_per_second": 0.557
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,25 +1,25 @@
|
|
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 |
-
"step":
|
13 |
-
"total_flos":
|
14 |
-
"train_loss": 3.
|
15 |
-
"train_runtime":
|
16 |
-
"train_samples_per_second": 1.
|
17 |
-
"train_steps_per_second": 0.
|
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": 10.0,
|
5 |
+
"global_step": 70,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 10.0,
|
12 |
+
"step": 70,
|
13 |
+
"total_flos": 73161768960000.0,
|
14 |
+
"train_loss": 3.1061488560267856,
|
15 |
+
"train_runtime": 125.6009,
|
16 |
+
"train_samples_per_second": 1.115,
|
17 |
+
"train_steps_per_second": 0.557
|
18 |
}
|
19 |
],
|
20 |
+
"max_steps": 70,
|
21 |
+
"num_train_epochs": 10,
|
22 |
+
"total_flos": 73161768960000.0,
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2863
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:630412f6e57b7b2288c80bf39e6c56803dab938d5e3d887d132e6f5cc69abb7f
|
3 |
size 2863
|