Training in progress, epoch 0, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1625422896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1255a94d2c1035af8dbc9eb029ca8d19edd8580cd1fefddbb0533da356c06da4
|
3 |
size 1625422896
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3250751759
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22f4c77a84f947dfb17a762837ce68600173a81613853abdb277eab37875a658
|
3 |
size 3250751759
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a457733086cbe7abd20572f0e67e51fe98999fd6109df376bc8fdc3d383f128
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fbfec159ab7e0d68181fb11bece118120bcca365523f884bfbee292654046da
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint":
|
4 |
"epoch": 0.9991967871485944,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 622,
|
@@ -10,23 +10,10 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.8032128514056225,
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate": 3.
|
15 |
-
"loss": 2.
|
16 |
"step": 500
|
17 |
-
},
|
18 |
-
{
|
19 |
-
"epoch": 0.9991967871485944,
|
20 |
-
"eval_gen_len": 129.0868,
|
21 |
-
"eval_loss": 2.343903064727783,
|
22 |
-
"eval_rouge1": 0.3301,
|
23 |
-
"eval_rouge2": 0.067,
|
24 |
-
"eval_rougeL": 0.204,
|
25 |
-
"eval_rougeLsum": 0.2851,
|
26 |
-
"eval_runtime": 796.5612,
|
27 |
-
"eval_samples_per_second": 0.694,
|
28 |
-
"eval_steps_per_second": 0.175,
|
29 |
-
"step": 622
|
30 |
}
|
31 |
],
|
32 |
"logging_steps": 500,
|
|
|
1 |
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
"epoch": 0.9991967871485944,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 622,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.8032128514056225,
|
13 |
+
"grad_norm": 8.627903938293457,
|
14 |
+
"learning_rate": 3.987138263665595e-06,
|
15 |
+
"loss": 2.1852,
|
16 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
}
|
18 |
],
|
19 |
"logging_steps": 500,
|