Commit ·
e126b28
1
Parent(s): 8663160
Training in progress, step 500
Browse files- all_results.json +12 -0
- eval_results.json +12 -0
- pytorch_model.bin +1 -1
- runs/May24_13-32-48_f2ddba3b469d/events.out.tfevents.1684936852.f2ddba3b469d.298.2 +3 -0
- runs/May24_14-01-43_f2ddba3b469d/1684936921.7041402/events.out.tfevents.1684936921.f2ddba3b469d.298.4 +3 -0
- runs/May24_14-01-43_f2ddba3b469d/events.out.tfevents.1684936921.f2ddba3b469d.298.3 +3 -0
- trainer_state.json +1013 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 144.44,
|
| 3 |
+
"eval_avg_rouge_f": 0.3778,
|
| 4 |
+
"eval_gen_len": 16.125,
|
| 5 |
+
"eval_loss": 2.663809299468994,
|
| 6 |
+
"eval_rouge-1": 0.4169,
|
| 7 |
+
"eval_rouge-2": 0.3153,
|
| 8 |
+
"eval_rouge-l": 0.4013,
|
| 9 |
+
"eval_runtime": 3.1537,
|
| 10 |
+
"eval_samples_per_second": 2.537,
|
| 11 |
+
"eval_steps_per_second": 2.537
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 144.44,
|
| 3 |
+
"eval_avg_rouge_f": 0.3778,
|
| 4 |
+
"eval_gen_len": 16.125,
|
| 5 |
+
"eval_loss": 2.663809299468994,
|
| 6 |
+
"eval_rouge-1": 0.4169,
|
| 7 |
+
"eval_rouge-2": 0.3153,
|
| 8 |
+
"eval_rouge-l": 0.4013,
|
| 9 |
+
"eval_runtime": 3.1537,
|
| 10 |
+
"eval_samples_per_second": 2.537,
|
| 11 |
+
"eval_steps_per_second": 2.537
|
| 12 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 977334453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c05fd1a49472594926101c92d9bcc73ae7e57a4200e2e029e7eaf73d6b95cee1
|
| 3 |
size 977334453
|
runs/May24_13-32-48_f2ddba3b469d/events.out.tfevents.1684936852.f2ddba3b469d.298.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42ef5a9b37fa8b6416db78013d774033f65edc450b7993c22d316ac43cec2072
|
| 3 |
+
size 618
|
runs/May24_14-01-43_f2ddba3b469d/1684936921.7041402/events.out.tfevents.1684936921.f2ddba3b469d.298.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffa078a46b1a5a64393fbf4a47c6d8d948c30ab210eda9a7f22f3aea6b897635
|
| 3 |
+
size 6266
|
runs/May24_14-01-43_f2ddba3b469d/events.out.tfevents.1684936921.f2ddba3b469d.298.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:074bfe1159188fdefa2728cbb138e66f52068771bffb6d36b9cf15c0bc1554ff
|
| 3 |
+
size 11274
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1013 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3778,
|
| 3 |
+
"best_model_checkpoint": "rut5-base-absum-tech-support-calls/checkpoint-2000",
|
| 4 |
+
"epoch": 144.44444444444446,
|
| 5 |
+
"global_step": 2600,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 2.78,
|
| 12 |
+
"learning_rate": 5e-06,
|
| 13 |
+
"loss": 2.7022,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 2.78,
|
| 18 |
+
"eval_avg_rouge_f": 0.0,
|
| 19 |
+
"eval_gen_len": 6.875,
|
| 20 |
+
"eval_loss": 2.296959400177002,
|
| 21 |
+
"eval_rouge-1": 0.0,
|
| 22 |
+
"eval_rouge-2": 0.0,
|
| 23 |
+
"eval_rouge-l": 0.0,
|
| 24 |
+
"eval_runtime": 3.1977,
|
| 25 |
+
"eval_samples_per_second": 2.502,
|
| 26 |
+
"eval_steps_per_second": 2.502,
|
| 27 |
+
"step": 50
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 5.56,
|
| 31 |
+
"learning_rate": 1e-05,
|
| 32 |
+
"loss": 2.2932,
|
| 33 |
+
"step": 100
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 5.56,
|
| 37 |
+
"eval_avg_rouge_f": 0.0,
|
| 38 |
+
"eval_gen_len": 10.375,
|
| 39 |
+
"eval_loss": 1.8183443546295166,
|
| 40 |
+
"eval_rouge-1": 0.0,
|
| 41 |
+
"eval_rouge-2": 0.0,
|
| 42 |
+
"eval_rouge-l": 0.0,
|
| 43 |
+
"eval_runtime": 1.7212,
|
| 44 |
+
"eval_samples_per_second": 4.648,
|
| 45 |
+
"eval_steps_per_second": 4.648,
|
| 46 |
+
"step": 100
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 8.33,
|
| 50 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 51 |
+
"loss": 1.8234,
|
| 52 |
+
"step": 150
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 8.33,
|
| 56 |
+
"eval_avg_rouge_f": 0.3018,
|
| 57 |
+
"eval_gen_len": 14.0,
|
| 58 |
+
"eval_loss": 1.4890449047088623,
|
| 59 |
+
"eval_rouge-1": 0.3588,
|
| 60 |
+
"eval_rouge-2": 0.2205,
|
| 61 |
+
"eval_rouge-l": 0.3262,
|
| 62 |
+
"eval_runtime": 2.5527,
|
| 63 |
+
"eval_samples_per_second": 3.134,
|
| 64 |
+
"eval_steps_per_second": 3.134,
|
| 65 |
+
"step": 150
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 11.11,
|
| 69 |
+
"learning_rate": 2e-05,
|
| 70 |
+
"loss": 1.3727,
|
| 71 |
+
"step": 200
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 11.11,
|
| 75 |
+
"eval_avg_rouge_f": 0.2771,
|
| 76 |
+
"eval_gen_len": 12.375,
|
| 77 |
+
"eval_loss": 1.373950719833374,
|
| 78 |
+
"eval_rouge-1": 0.3493,
|
| 79 |
+
"eval_rouge-2": 0.1653,
|
| 80 |
+
"eval_rouge-l": 0.3167,
|
| 81 |
+
"eval_runtime": 2.0484,
|
| 82 |
+
"eval_samples_per_second": 3.906,
|
| 83 |
+
"eval_steps_per_second": 3.906,
|
| 84 |
+
"step": 200
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 13.89,
|
| 88 |
+
"learning_rate": 1.9767441860465116e-05,
|
| 89 |
+
"loss": 1.0367,
|
| 90 |
+
"step": 250
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 13.89,
|
| 94 |
+
"eval_avg_rouge_f": 0.1974,
|
| 95 |
+
"eval_gen_len": 15.375,
|
| 96 |
+
"eval_loss": 1.3832566738128662,
|
| 97 |
+
"eval_rouge-1": 0.2607,
|
| 98 |
+
"eval_rouge-2": 0.0984,
|
| 99 |
+
"eval_rouge-l": 0.2331,
|
| 100 |
+
"eval_runtime": 3.0521,
|
| 101 |
+
"eval_samples_per_second": 2.621,
|
| 102 |
+
"eval_steps_per_second": 2.621,
|
| 103 |
+
"step": 250
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 16.67,
|
| 107 |
+
"learning_rate": 1.9534883720930235e-05,
|
| 108 |
+
"loss": 0.841,
|
| 109 |
+
"step": 300
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 16.67,
|
| 113 |
+
"eval_avg_rouge_f": 0.3055,
|
| 114 |
+
"eval_gen_len": 16.0,
|
| 115 |
+
"eval_loss": 1.3515713214874268,
|
| 116 |
+
"eval_rouge-1": 0.3713,
|
| 117 |
+
"eval_rouge-2": 0.1857,
|
| 118 |
+
"eval_rouge-l": 0.3594,
|
| 119 |
+
"eval_runtime": 2.4808,
|
| 120 |
+
"eval_samples_per_second": 3.225,
|
| 121 |
+
"eval_steps_per_second": 3.225,
|
| 122 |
+
"step": 300
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 19.44,
|
| 126 |
+
"learning_rate": 1.9302325581395353e-05,
|
| 127 |
+
"loss": 0.7182,
|
| 128 |
+
"step": 350
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 19.44,
|
| 132 |
+
"eval_avg_rouge_f": 0.2672,
|
| 133 |
+
"eval_gen_len": 16.125,
|
| 134 |
+
"eval_loss": 1.3606797456741333,
|
| 135 |
+
"eval_rouge-1": 0.3352,
|
| 136 |
+
"eval_rouge-2": 0.143,
|
| 137 |
+
"eval_rouge-l": 0.3233,
|
| 138 |
+
"eval_runtime": 2.5469,
|
| 139 |
+
"eval_samples_per_second": 3.141,
|
| 140 |
+
"eval_steps_per_second": 3.141,
|
| 141 |
+
"step": 350
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 22.22,
|
| 145 |
+
"learning_rate": 1.9069767441860468e-05,
|
| 146 |
+
"loss": 0.5102,
|
| 147 |
+
"step": 400
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 22.22,
|
| 151 |
+
"eval_avg_rouge_f": 0.2849,
|
| 152 |
+
"eval_gen_len": 16.625,
|
| 153 |
+
"eval_loss": 1.3673444986343384,
|
| 154 |
+
"eval_rouge-1": 0.36,
|
| 155 |
+
"eval_rouge-2": 0.1597,
|
| 156 |
+
"eval_rouge-l": 0.3349,
|
| 157 |
+
"eval_runtime": 2.6789,
|
| 158 |
+
"eval_samples_per_second": 2.986,
|
| 159 |
+
"eval_steps_per_second": 2.986,
|
| 160 |
+
"step": 400
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 25.0,
|
| 164 |
+
"learning_rate": 1.8837209302325582e-05,
|
| 165 |
+
"loss": 0.4595,
|
| 166 |
+
"step": 450
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 25.0,
|
| 170 |
+
"eval_avg_rouge_f": 0.3228,
|
| 171 |
+
"eval_gen_len": 17.125,
|
| 172 |
+
"eval_loss": 1.371541976928711,
|
| 173 |
+
"eval_rouge-1": 0.3892,
|
| 174 |
+
"eval_rouge-2": 0.2153,
|
| 175 |
+
"eval_rouge-l": 0.3641,
|
| 176 |
+
"eval_runtime": 2.6184,
|
| 177 |
+
"eval_samples_per_second": 3.055,
|
| 178 |
+
"eval_steps_per_second": 3.055,
|
| 179 |
+
"step": 450
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 27.78,
|
| 183 |
+
"learning_rate": 1.86046511627907e-05,
|
| 184 |
+
"loss": 0.3886,
|
| 185 |
+
"step": 500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 27.78,
|
| 189 |
+
"eval_avg_rouge_f": 0.3252,
|
| 190 |
+
"eval_gen_len": 16.375,
|
| 191 |
+
"eval_loss": 1.4634039402008057,
|
| 192 |
+
"eval_rouge-1": 0.3801,
|
| 193 |
+
"eval_rouge-2": 0.2274,
|
| 194 |
+
"eval_rouge-l": 0.3682,
|
| 195 |
+
"eval_runtime": 2.8205,
|
| 196 |
+
"eval_samples_per_second": 2.836,
|
| 197 |
+
"eval_steps_per_second": 2.836,
|
| 198 |
+
"step": 500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 30.56,
|
| 202 |
+
"learning_rate": 1.8372093023255815e-05,
|
| 203 |
+
"loss": 0.3158,
|
| 204 |
+
"step": 550
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 30.56,
|
| 208 |
+
"eval_avg_rouge_f": 0.331,
|
| 209 |
+
"eval_gen_len": 16.75,
|
| 210 |
+
"eval_loss": 1.5123608112335205,
|
| 211 |
+
"eval_rouge-1": 0.3938,
|
| 212 |
+
"eval_rouge-2": 0.2319,
|
| 213 |
+
"eval_rouge-l": 0.3672,
|
| 214 |
+
"eval_runtime": 3.0478,
|
| 215 |
+
"eval_samples_per_second": 2.625,
|
| 216 |
+
"eval_steps_per_second": 2.625,
|
| 217 |
+
"step": 550
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 33.33,
|
| 221 |
+
"learning_rate": 1.813953488372093e-05,
|
| 222 |
+
"loss": 0.2687,
|
| 223 |
+
"step": 600
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 33.33,
|
| 227 |
+
"eval_avg_rouge_f": 0.3468,
|
| 228 |
+
"eval_gen_len": 16.5,
|
| 229 |
+
"eval_loss": 1.5868151187896729,
|
| 230 |
+
"eval_rouge-1": 0.3987,
|
| 231 |
+
"eval_rouge-2": 0.2568,
|
| 232 |
+
"eval_rouge-l": 0.3848,
|
| 233 |
+
"eval_runtime": 2.5696,
|
| 234 |
+
"eval_samples_per_second": 3.113,
|
| 235 |
+
"eval_steps_per_second": 3.113,
|
| 236 |
+
"step": 600
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 36.11,
|
| 240 |
+
"learning_rate": 1.790697674418605e-05,
|
| 241 |
+
"loss": 0.2361,
|
| 242 |
+
"step": 650
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 36.11,
|
| 246 |
+
"eval_avg_rouge_f": 0.3163,
|
| 247 |
+
"eval_gen_len": 17.75,
|
| 248 |
+
"eval_loss": 1.6459990739822388,
|
| 249 |
+
"eval_rouge-1": 0.375,
|
| 250 |
+
"eval_rouge-2": 0.2107,
|
| 251 |
+
"eval_rouge-l": 0.3631,
|
| 252 |
+
"eval_runtime": 2.8706,
|
| 253 |
+
"eval_samples_per_second": 2.787,
|
| 254 |
+
"eval_steps_per_second": 2.787,
|
| 255 |
+
"step": 650
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 38.89,
|
| 259 |
+
"learning_rate": 1.7674418604651163e-05,
|
| 260 |
+
"loss": 0.1991,
|
| 261 |
+
"step": 700
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 38.89,
|
| 265 |
+
"eval_avg_rouge_f": 0.3085,
|
| 266 |
+
"eval_gen_len": 16.25,
|
| 267 |
+
"eval_loss": 1.6946561336517334,
|
| 268 |
+
"eval_rouge-1": 0.3605,
|
| 269 |
+
"eval_rouge-2": 0.2177,
|
| 270 |
+
"eval_rouge-l": 0.3474,
|
| 271 |
+
"eval_runtime": 2.519,
|
| 272 |
+
"eval_samples_per_second": 3.176,
|
| 273 |
+
"eval_steps_per_second": 3.176,
|
| 274 |
+
"step": 700
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 41.67,
|
| 278 |
+
"learning_rate": 1.744186046511628e-05,
|
| 279 |
+
"loss": 0.151,
|
| 280 |
+
"step": 750
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 41.67,
|
| 284 |
+
"eval_avg_rouge_f": 0.3222,
|
| 285 |
+
"eval_gen_len": 16.5,
|
| 286 |
+
"eval_loss": 1.8248298168182373,
|
| 287 |
+
"eval_rouge-1": 0.3832,
|
| 288 |
+
"eval_rouge-2": 0.2274,
|
| 289 |
+
"eval_rouge-l": 0.3559,
|
| 290 |
+
"eval_runtime": 2.6923,
|
| 291 |
+
"eval_samples_per_second": 2.971,
|
| 292 |
+
"eval_steps_per_second": 2.971,
|
| 293 |
+
"step": 750
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 44.44,
|
| 297 |
+
"learning_rate": 1.7209302325581396e-05,
|
| 298 |
+
"loss": 0.1517,
|
| 299 |
+
"step": 800
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 44.44,
|
| 303 |
+
"eval_avg_rouge_f": 0.3811,
|
| 304 |
+
"eval_gen_len": 16.875,
|
| 305 |
+
"eval_loss": 1.7883902788162231,
|
| 306 |
+
"eval_rouge-1": 0.4309,
|
| 307 |
+
"eval_rouge-2": 0.294,
|
| 308 |
+
"eval_rouge-l": 0.4184,
|
| 309 |
+
"eval_runtime": 2.5559,
|
| 310 |
+
"eval_samples_per_second": 3.13,
|
| 311 |
+
"eval_steps_per_second": 3.13,
|
| 312 |
+
"step": 800
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 47.22,
|
| 316 |
+
"learning_rate": 1.697674418604651e-05,
|
| 317 |
+
"loss": 0.1444,
|
| 318 |
+
"step": 850
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 47.22,
|
| 322 |
+
"eval_avg_rouge_f": 0.322,
|
| 323 |
+
"eval_gen_len": 17.125,
|
| 324 |
+
"eval_loss": 1.8518762588500977,
|
| 325 |
+
"eval_rouge-1": 0.3843,
|
| 326 |
+
"eval_rouge-2": 0.2107,
|
| 327 |
+
"eval_rouge-l": 0.3711,
|
| 328 |
+
"eval_runtime": 2.7195,
|
| 329 |
+
"eval_samples_per_second": 2.942,
|
| 330 |
+
"eval_steps_per_second": 2.942,
|
| 331 |
+
"step": 850
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 50.0,
|
| 335 |
+
"learning_rate": 1.674418604651163e-05,
|
| 336 |
+
"loss": 0.1106,
|
| 337 |
+
"step": 900
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 50.0,
|
| 341 |
+
"eval_avg_rouge_f": 0.3209,
|
| 342 |
+
"eval_gen_len": 17.5,
|
| 343 |
+
"eval_loss": 1.9637408256530762,
|
| 344 |
+
"eval_rouge-1": 0.383,
|
| 345 |
+
"eval_rouge-2": 0.2107,
|
| 346 |
+
"eval_rouge-l": 0.3691,
|
| 347 |
+
"eval_runtime": 2.6625,
|
| 348 |
+
"eval_samples_per_second": 3.005,
|
| 349 |
+
"eval_steps_per_second": 3.005,
|
| 350 |
+
"step": 900
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 52.78,
|
| 354 |
+
"learning_rate": 1.6511627906976747e-05,
|
| 355 |
+
"loss": 0.0961,
|
| 356 |
+
"step": 950
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 52.78,
|
| 360 |
+
"eval_avg_rouge_f": 0.3103,
|
| 361 |
+
"eval_gen_len": 16.75,
|
| 362 |
+
"eval_loss": 2.07181715965271,
|
| 363 |
+
"eval_rouge-1": 0.3645,
|
| 364 |
+
"eval_rouge-2": 0.2177,
|
| 365 |
+
"eval_rouge-l": 0.3488,
|
| 366 |
+
"eval_runtime": 2.7383,
|
| 367 |
+
"eval_samples_per_second": 2.921,
|
| 368 |
+
"eval_steps_per_second": 2.921,
|
| 369 |
+
"step": 950
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 55.56,
|
| 373 |
+
"learning_rate": 1.6279069767441862e-05,
|
| 374 |
+
"loss": 0.1131,
|
| 375 |
+
"step": 1000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 55.56,
|
| 379 |
+
"eval_avg_rouge_f": 0.3067,
|
| 380 |
+
"eval_gen_len": 16.75,
|
| 381 |
+
"eval_loss": 1.9934816360473633,
|
| 382 |
+
"eval_rouge-1": 0.3602,
|
| 383 |
+
"eval_rouge-2": 0.2153,
|
| 384 |
+
"eval_rouge-l": 0.3446,
|
| 385 |
+
"eval_runtime": 2.6295,
|
| 386 |
+
"eval_samples_per_second": 3.042,
|
| 387 |
+
"eval_steps_per_second": 3.042,
|
| 388 |
+
"step": 1000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 58.33,
|
| 392 |
+
"learning_rate": 1.6046511627906977e-05,
|
| 393 |
+
"loss": 0.0996,
|
| 394 |
+
"step": 1050
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 58.33,
|
| 398 |
+
"eval_avg_rouge_f": 0.3712,
|
| 399 |
+
"eval_gen_len": 16.0,
|
| 400 |
+
"eval_loss": 2.06162166595459,
|
| 401 |
+
"eval_rouge-1": 0.4153,
|
| 402 |
+
"eval_rouge-2": 0.2986,
|
| 403 |
+
"eval_rouge-l": 0.3996,
|
| 404 |
+
"eval_runtime": 3.0388,
|
| 405 |
+
"eval_samples_per_second": 2.633,
|
| 406 |
+
"eval_steps_per_second": 2.633,
|
| 407 |
+
"step": 1050
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 61.11,
|
| 411 |
+
"learning_rate": 1.5813953488372095e-05,
|
| 412 |
+
"loss": 0.0663,
|
| 413 |
+
"step": 1100
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 61.11,
|
| 417 |
+
"eval_avg_rouge_f": 0.3786,
|
| 418 |
+
"eval_gen_len": 14.625,
|
| 419 |
+
"eval_loss": 2.1466333866119385,
|
| 420 |
+
"eval_rouge-1": 0.4257,
|
| 421 |
+
"eval_rouge-2": 0.301,
|
| 422 |
+
"eval_rouge-l": 0.409,
|
| 423 |
+
"eval_runtime": 3.1902,
|
| 424 |
+
"eval_samples_per_second": 2.508,
|
| 425 |
+
"eval_steps_per_second": 2.508,
|
| 426 |
+
"step": 1100
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 63.89,
|
| 430 |
+
"learning_rate": 1.558139534883721e-05,
|
| 431 |
+
"loss": 0.0789,
|
| 432 |
+
"step": 1150
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 63.89,
|
| 436 |
+
"eval_avg_rouge_f": 0.3728,
|
| 437 |
+
"eval_gen_len": 16.0,
|
| 438 |
+
"eval_loss": 2.1657214164733887,
|
| 439 |
+
"eval_rouge-1": 0.4166,
|
| 440 |
+
"eval_rouge-2": 0.301,
|
| 441 |
+
"eval_rouge-l": 0.4009,
|
| 442 |
+
"eval_runtime": 2.4781,
|
| 443 |
+
"eval_samples_per_second": 3.228,
|
| 444 |
+
"eval_steps_per_second": 3.228,
|
| 445 |
+
"step": 1150
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 66.67,
|
| 449 |
+
"learning_rate": 1.5348837209302328e-05,
|
| 450 |
+
"loss": 0.073,
|
| 451 |
+
"step": 1200
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 66.67,
|
| 455 |
+
"eval_avg_rouge_f": 0.3713,
|
| 456 |
+
"eval_gen_len": 16.25,
|
| 457 |
+
"eval_loss": 2.251979351043701,
|
| 458 |
+
"eval_rouge-1": 0.4131,
|
| 459 |
+
"eval_rouge-2": 0.301,
|
| 460 |
+
"eval_rouge-l": 0.3999,
|
| 461 |
+
"eval_runtime": 3.4503,
|
| 462 |
+
"eval_samples_per_second": 2.319,
|
| 463 |
+
"eval_steps_per_second": 2.319,
|
| 464 |
+
"step": 1200
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 69.44,
|
| 468 |
+
"learning_rate": 1.5116279069767443e-05,
|
| 469 |
+
"loss": 0.0739,
|
| 470 |
+
"step": 1250
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 69.44,
|
| 474 |
+
"eval_avg_rouge_f": 0.3051,
|
| 475 |
+
"eval_gen_len": 17.0,
|
| 476 |
+
"eval_loss": 2.260244369506836,
|
| 477 |
+
"eval_rouge-1": 0.3582,
|
| 478 |
+
"eval_rouge-2": 0.2145,
|
| 479 |
+
"eval_rouge-l": 0.3426,
|
| 480 |
+
"eval_runtime": 2.5948,
|
| 481 |
+
"eval_samples_per_second": 3.083,
|
| 482 |
+
"eval_steps_per_second": 3.083,
|
| 483 |
+
"step": 1250
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 72.22,
|
| 487 |
+
"learning_rate": 1.488372093023256e-05,
|
| 488 |
+
"loss": 0.0799,
|
| 489 |
+
"step": 1300
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 72.22,
|
| 493 |
+
"eval_avg_rouge_f": 0.3156,
|
| 494 |
+
"eval_gen_len": 16.75,
|
| 495 |
+
"eval_loss": 2.3278074264526367,
|
| 496 |
+
"eval_rouge-1": 0.369,
|
| 497 |
+
"eval_rouge-2": 0.2242,
|
| 498 |
+
"eval_rouge-l": 0.3534,
|
| 499 |
+
"eval_runtime": 3.3341,
|
| 500 |
+
"eval_samples_per_second": 2.399,
|
| 501 |
+
"eval_steps_per_second": 2.399,
|
| 502 |
+
"step": 1300
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 75.0,
|
| 506 |
+
"learning_rate": 1.4651162790697674e-05,
|
| 507 |
+
"loss": 0.0546,
|
| 508 |
+
"step": 1350
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 75.0,
|
| 512 |
+
"eval_avg_rouge_f": 0.3164,
|
| 513 |
+
"eval_gen_len": 16.5,
|
| 514 |
+
"eval_loss": 2.402118444442749,
|
| 515 |
+
"eval_rouge-1": 0.369,
|
| 516 |
+
"eval_rouge-2": 0.2242,
|
| 517 |
+
"eval_rouge-l": 0.3559,
|
| 518 |
+
"eval_runtime": 2.5497,
|
| 519 |
+
"eval_samples_per_second": 3.138,
|
| 520 |
+
"eval_steps_per_second": 3.138,
|
| 521 |
+
"step": 1350
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 77.78,
|
| 525 |
+
"learning_rate": 1.441860465116279e-05,
|
| 526 |
+
"loss": 0.0674,
|
| 527 |
+
"step": 1400
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 77.78,
|
| 531 |
+
"eval_avg_rouge_f": 0.3697,
|
| 532 |
+
"eval_gen_len": 17.25,
|
| 533 |
+
"eval_loss": 2.3492679595947266,
|
| 534 |
+
"eval_rouge-1": 0.4149,
|
| 535 |
+
"eval_rouge-2": 0.2924,
|
| 536 |
+
"eval_rouge-l": 0.4017,
|
| 537 |
+
"eval_runtime": 3.1613,
|
| 538 |
+
"eval_samples_per_second": 2.531,
|
| 539 |
+
"eval_steps_per_second": 2.531,
|
| 540 |
+
"step": 1400
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 80.56,
|
| 544 |
+
"learning_rate": 1.4186046511627909e-05,
|
| 545 |
+
"loss": 0.0459,
|
| 546 |
+
"step": 1450
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 80.56,
|
| 550 |
+
"eval_avg_rouge_f": 0.3839,
|
| 551 |
+
"eval_gen_len": 16.125,
|
| 552 |
+
"eval_loss": 2.3503048419952393,
|
| 553 |
+
"eval_rouge-1": 0.426,
|
| 554 |
+
"eval_rouge-2": 0.3153,
|
| 555 |
+
"eval_rouge-l": 0.4104,
|
| 556 |
+
"eval_runtime": 2.4756,
|
| 557 |
+
"eval_samples_per_second": 3.232,
|
| 558 |
+
"eval_steps_per_second": 3.232,
|
| 559 |
+
"step": 1450
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 83.33,
|
| 563 |
+
"learning_rate": 1.3953488372093025e-05,
|
| 564 |
+
"loss": 0.0501,
|
| 565 |
+
"step": 1500
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 83.33,
|
| 569 |
+
"eval_avg_rouge_f": 0.3732,
|
| 570 |
+
"eval_gen_len": 15.375,
|
| 571 |
+
"eval_loss": 2.371870517730713,
|
| 572 |
+
"eval_rouge-1": 0.4172,
|
| 573 |
+
"eval_rouge-2": 0.301,
|
| 574 |
+
"eval_rouge-l": 0.4016,
|
| 575 |
+
"eval_runtime": 2.8658,
|
| 576 |
+
"eval_samples_per_second": 2.792,
|
| 577 |
+
"eval_steps_per_second": 2.792,
|
| 578 |
+
"step": 1500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 86.11,
|
| 582 |
+
"learning_rate": 1.372093023255814e-05,
|
| 583 |
+
"loss": 0.0509,
|
| 584 |
+
"step": 1550
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 86.11,
|
| 588 |
+
"eval_avg_rouge_f": 0.3926,
|
| 589 |
+
"eval_gen_len": 16.375,
|
| 590 |
+
"eval_loss": 2.4419479370117188,
|
| 591 |
+
"eval_rouge-1": 0.4361,
|
| 592 |
+
"eval_rouge-2": 0.3188,
|
| 593 |
+
"eval_rouge-l": 0.4229,
|
| 594 |
+
"eval_runtime": 3.0315,
|
| 595 |
+
"eval_samples_per_second": 2.639,
|
| 596 |
+
"eval_steps_per_second": 2.639,
|
| 597 |
+
"step": 1550
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 88.89,
|
| 601 |
+
"learning_rate": 1.3488372093023257e-05,
|
| 602 |
+
"loss": 0.0449,
|
| 603 |
+
"step": 1600
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 88.89,
|
| 607 |
+
"eval_avg_rouge_f": 0.4026,
|
| 608 |
+
"eval_gen_len": 16.375,
|
| 609 |
+
"eval_loss": 2.3171658515930176,
|
| 610 |
+
"eval_rouge-1": 0.4514,
|
| 611 |
+
"eval_rouge-2": 0.3188,
|
| 612 |
+
"eval_rouge-l": 0.4375,
|
| 613 |
+
"eval_runtime": 3.636,
|
| 614 |
+
"eval_samples_per_second": 2.2,
|
| 615 |
+
"eval_steps_per_second": 2.2,
|
| 616 |
+
"step": 1600
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 91.67,
|
| 620 |
+
"learning_rate": 1.3255813953488372e-05,
|
| 621 |
+
"loss": 0.0408,
|
| 622 |
+
"step": 1650
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 91.67,
|
| 626 |
+
"eval_avg_rouge_f": 0.3906,
|
| 627 |
+
"eval_gen_len": 16.25,
|
| 628 |
+
"eval_loss": 2.4437549114227295,
|
| 629 |
+
"eval_rouge-1": 0.4349,
|
| 630 |
+
"eval_rouge-2": 0.3153,
|
| 631 |
+
"eval_rouge-l": 0.4217,
|
| 632 |
+
"eval_runtime": 2.4939,
|
| 633 |
+
"eval_samples_per_second": 3.208,
|
| 634 |
+
"eval_steps_per_second": 3.208,
|
| 635 |
+
"step": 1650
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 94.44,
|
| 639 |
+
"learning_rate": 1.302325581395349e-05,
|
| 640 |
+
"loss": 0.0357,
|
| 641 |
+
"step": 1700
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 94.44,
|
| 645 |
+
"eval_avg_rouge_f": 0.3831,
|
| 646 |
+
"eval_gen_len": 16.25,
|
| 647 |
+
"eval_loss": 2.540635108947754,
|
| 648 |
+
"eval_rouge-1": 0.4236,
|
| 649 |
+
"eval_rouge-2": 0.3153,
|
| 650 |
+
"eval_rouge-l": 0.4104,
|
| 651 |
+
"eval_runtime": 3.5767,
|
| 652 |
+
"eval_samples_per_second": 2.237,
|
| 653 |
+
"eval_steps_per_second": 2.237,
|
| 654 |
+
"step": 1700
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 97.22,
|
| 658 |
+
"learning_rate": 1.2790697674418606e-05,
|
| 659 |
+
"loss": 0.0403,
|
| 660 |
+
"step": 1750
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 97.22,
|
| 664 |
+
"eval_avg_rouge_f": 0.3748,
|
| 665 |
+
"eval_gen_len": 16.375,
|
| 666 |
+
"eval_loss": 2.4441065788269043,
|
| 667 |
+
"eval_rouge-1": 0.4111,
|
| 668 |
+
"eval_rouge-2": 0.3153,
|
| 669 |
+
"eval_rouge-l": 0.398,
|
| 670 |
+
"eval_runtime": 2.5203,
|
| 671 |
+
"eval_samples_per_second": 3.174,
|
| 672 |
+
"eval_steps_per_second": 3.174,
|
| 673 |
+
"step": 1750
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 100.0,
|
| 677 |
+
"learning_rate": 1.2558139534883723e-05,
|
| 678 |
+
"loss": 0.0489,
|
| 679 |
+
"step": 1800
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 100.0,
|
| 683 |
+
"eval_avg_rouge_f": 0.3768,
|
| 684 |
+
"eval_gen_len": 16.125,
|
| 685 |
+
"eval_loss": 2.459872245788574,
|
| 686 |
+
"eval_rouge-1": 0.4154,
|
| 687 |
+
"eval_rouge-2": 0.3153,
|
| 688 |
+
"eval_rouge-l": 0.3997,
|
| 689 |
+
"eval_runtime": 3.4884,
|
| 690 |
+
"eval_samples_per_second": 2.293,
|
| 691 |
+
"eval_steps_per_second": 2.293,
|
| 692 |
+
"step": 1800
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 102.78,
|
| 696 |
+
"learning_rate": 1.2325581395348838e-05,
|
| 697 |
+
"loss": 0.032,
|
| 698 |
+
"step": 1850
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 102.78,
|
| 702 |
+
"eval_avg_rouge_f": 0.407,
|
| 703 |
+
"eval_gen_len": 15.0,
|
| 704 |
+
"eval_loss": 2.623534679412842,
|
| 705 |
+
"eval_rouge-1": 0.4515,
|
| 706 |
+
"eval_rouge-2": 0.3335,
|
| 707 |
+
"eval_rouge-l": 0.4359,
|
| 708 |
+
"eval_runtime": 2.3389,
|
| 709 |
+
"eval_samples_per_second": 3.42,
|
| 710 |
+
"eval_steps_per_second": 3.42,
|
| 711 |
+
"step": 1850
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 105.56,
|
| 715 |
+
"learning_rate": 1.2093023255813954e-05,
|
| 716 |
+
"loss": 0.0379,
|
| 717 |
+
"step": 1900
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 105.56,
|
| 721 |
+
"eval_avg_rouge_f": 0.407,
|
| 722 |
+
"eval_gen_len": 15.125,
|
| 723 |
+
"eval_loss": 2.6058127880096436,
|
| 724 |
+
"eval_rouge-1": 0.4515,
|
| 725 |
+
"eval_rouge-2": 0.3335,
|
| 726 |
+
"eval_rouge-l": 0.4359,
|
| 727 |
+
"eval_runtime": 3.2938,
|
| 728 |
+
"eval_samples_per_second": 2.429,
|
| 729 |
+
"eval_steps_per_second": 2.429,
|
| 730 |
+
"step": 1900
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 108.33,
|
| 734 |
+
"learning_rate": 1.1860465116279072e-05,
|
| 735 |
+
"loss": 0.0466,
|
| 736 |
+
"step": 1950
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 108.33,
|
| 740 |
+
"eval_avg_rouge_f": 0.3768,
|
| 741 |
+
"eval_gen_len": 16.125,
|
| 742 |
+
"eval_loss": 2.5748019218444824,
|
| 743 |
+
"eval_rouge-1": 0.4154,
|
| 744 |
+
"eval_rouge-2": 0.3153,
|
| 745 |
+
"eval_rouge-l": 0.3997,
|
| 746 |
+
"eval_runtime": 2.4802,
|
| 747 |
+
"eval_samples_per_second": 3.226,
|
| 748 |
+
"eval_steps_per_second": 3.226,
|
| 749 |
+
"step": 1950
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 111.11,
|
| 753 |
+
"learning_rate": 1.1627906976744187e-05,
|
| 754 |
+
"loss": 0.0317,
|
| 755 |
+
"step": 2000
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 111.11,
|
| 759 |
+
"eval_avg_rouge_f": 0.3778,
|
| 760 |
+
"eval_gen_len": 16.125,
|
| 761 |
+
"eval_loss": 2.663809299468994,
|
| 762 |
+
"eval_rouge-1": 0.4169,
|
| 763 |
+
"eval_rouge-2": 0.3153,
|
| 764 |
+
"eval_rouge-l": 0.4013,
|
| 765 |
+
"eval_runtime": 3.2301,
|
| 766 |
+
"eval_samples_per_second": 2.477,
|
| 767 |
+
"eval_steps_per_second": 2.477,
|
| 768 |
+
"step": 2000
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 113.89,
|
| 772 |
+
"learning_rate": 1.1395348837209304e-05,
|
| 773 |
+
"loss": 0.0234,
|
| 774 |
+
"step": 2050
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 113.89,
|
| 778 |
+
"eval_avg_rouge_f": 0.3888,
|
| 779 |
+
"eval_gen_len": 15.5,
|
| 780 |
+
"eval_loss": 2.740657091140747,
|
| 781 |
+
"eval_rouge-1": 0.4334,
|
| 782 |
+
"eval_rouge-2": 0.3153,
|
| 783 |
+
"eval_rouge-l": 0.4178,
|
| 784 |
+
"eval_runtime": 4.1851,
|
| 785 |
+
"eval_samples_per_second": 1.912,
|
| 786 |
+
"eval_steps_per_second": 1.912,
|
| 787 |
+
"step": 2050
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 116.67,
|
| 791 |
+
"learning_rate": 1.116279069767442e-05,
|
| 792 |
+
"loss": 0.0308,
|
| 793 |
+
"step": 2100
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 116.67,
|
| 797 |
+
"eval_avg_rouge_f": 0.3799,
|
| 798 |
+
"eval_gen_len": 16.125,
|
| 799 |
+
"eval_loss": 2.70857572555542,
|
| 800 |
+
"eval_rouge-1": 0.4201,
|
| 801 |
+
"eval_rouge-2": 0.3153,
|
| 802 |
+
"eval_rouge-l": 0.4044,
|
| 803 |
+
"eval_runtime": 2.5313,
|
| 804 |
+
"eval_samples_per_second": 3.16,
|
| 805 |
+
"eval_steps_per_second": 3.16,
|
| 806 |
+
"step": 2100
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 119.44,
|
| 810 |
+
"learning_rate": 1.0930232558139535e-05,
|
| 811 |
+
"loss": 0.0305,
|
| 812 |
+
"step": 2150
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 119.44,
|
| 816 |
+
"eval_avg_rouge_f": 0.3598,
|
| 817 |
+
"eval_gen_len": 15.5,
|
| 818 |
+
"eval_loss": 2.7068228721618652,
|
| 819 |
+
"eval_rouge-1": 0.4059,
|
| 820 |
+
"eval_rouge-2": 0.2831,
|
| 821 |
+
"eval_rouge-l": 0.3902,
|
| 822 |
+
"eval_runtime": 2.7634,
|
| 823 |
+
"eval_samples_per_second": 2.895,
|
| 824 |
+
"eval_steps_per_second": 2.895,
|
| 825 |
+
"step": 2150
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 122.22,
|
| 829 |
+
"learning_rate": 1.0697674418604651e-05,
|
| 830 |
+
"loss": 0.0289,
|
| 831 |
+
"step": 2200
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 122.22,
|
| 835 |
+
"eval_avg_rouge_f": 0.3598,
|
| 836 |
+
"eval_gen_len": 15.5,
|
| 837 |
+
"eval_loss": 2.8503403663635254,
|
| 838 |
+
"eval_rouge-1": 0.4059,
|
| 839 |
+
"eval_rouge-2": 0.2831,
|
| 840 |
+
"eval_rouge-l": 0.3902,
|
| 841 |
+
"eval_runtime": 2.4338,
|
| 842 |
+
"eval_samples_per_second": 3.287,
|
| 843 |
+
"eval_steps_per_second": 3.287,
|
| 844 |
+
"step": 2200
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 125.0,
|
| 848 |
+
"learning_rate": 1.046511627906977e-05,
|
| 849 |
+
"loss": 0.0555,
|
| 850 |
+
"step": 2250
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 125.0,
|
| 854 |
+
"eval_avg_rouge_f": 0.3598,
|
| 855 |
+
"eval_gen_len": 15.5,
|
| 856 |
+
"eval_loss": 2.8522231578826904,
|
| 857 |
+
"eval_rouge-1": 0.4059,
|
| 858 |
+
"eval_rouge-2": 0.2831,
|
| 859 |
+
"eval_rouge-l": 0.3902,
|
| 860 |
+
"eval_runtime": 2.8814,
|
| 861 |
+
"eval_samples_per_second": 2.776,
|
| 862 |
+
"eval_steps_per_second": 2.776,
|
| 863 |
+
"step": 2250
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 127.78,
|
| 867 |
+
"learning_rate": 1.0232558139534884e-05,
|
| 868 |
+
"loss": 0.022,
|
| 869 |
+
"step": 2300
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 127.78,
|
| 873 |
+
"eval_avg_rouge_f": 0.3598,
|
| 874 |
+
"eval_gen_len": 15.5,
|
| 875 |
+
"eval_loss": 2.9057185649871826,
|
| 876 |
+
"eval_rouge-1": 0.4059,
|
| 877 |
+
"eval_rouge-2": 0.2831,
|
| 878 |
+
"eval_rouge-l": 0.3902,
|
| 879 |
+
"eval_runtime": 2.43,
|
| 880 |
+
"eval_samples_per_second": 3.292,
|
| 881 |
+
"eval_steps_per_second": 3.292,
|
| 882 |
+
"step": 2300
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 130.56,
|
| 886 |
+
"learning_rate": 1e-05,
|
| 887 |
+
"loss": 0.0369,
|
| 888 |
+
"step": 2350
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 130.56,
|
| 892 |
+
"eval_avg_rouge_f": 0.3598,
|
| 893 |
+
"eval_gen_len": 15.5,
|
| 894 |
+
"eval_loss": 2.8735642433166504,
|
| 895 |
+
"eval_rouge-1": 0.4059,
|
| 896 |
+
"eval_rouge-2": 0.2831,
|
| 897 |
+
"eval_rouge-l": 0.3902,
|
| 898 |
+
"eval_runtime": 3.0784,
|
| 899 |
+
"eval_samples_per_second": 2.599,
|
| 900 |
+
"eval_steps_per_second": 2.599,
|
| 901 |
+
"step": 2350
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 133.33,
|
| 905 |
+
"learning_rate": 9.767441860465117e-06,
|
| 906 |
+
"loss": 0.0195,
|
| 907 |
+
"step": 2400
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 133.33,
|
| 911 |
+
"eval_avg_rouge_f": 0.3598,
|
| 912 |
+
"eval_gen_len": 15.5,
|
| 913 |
+
"eval_loss": 2.7636728286743164,
|
| 914 |
+
"eval_rouge-1": 0.4059,
|
| 915 |
+
"eval_rouge-2": 0.2831,
|
| 916 |
+
"eval_rouge-l": 0.3902,
|
| 917 |
+
"eval_runtime": 2.4413,
|
| 918 |
+
"eval_samples_per_second": 3.277,
|
| 919 |
+
"eval_steps_per_second": 3.277,
|
| 920 |
+
"step": 2400
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 136.11,
|
| 924 |
+
"learning_rate": 9.534883720930234e-06,
|
| 925 |
+
"loss": 0.0387,
|
| 926 |
+
"step": 2450
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 136.11,
|
| 930 |
+
"eval_avg_rouge_f": 0.3598,
|
| 931 |
+
"eval_gen_len": 15.5,
|
| 932 |
+
"eval_loss": 2.743685007095337,
|
| 933 |
+
"eval_rouge-1": 0.4059,
|
| 934 |
+
"eval_rouge-2": 0.2831,
|
| 935 |
+
"eval_rouge-l": 0.3902,
|
| 936 |
+
"eval_runtime": 2.9809,
|
| 937 |
+
"eval_samples_per_second": 2.684,
|
| 938 |
+
"eval_steps_per_second": 2.684,
|
| 939 |
+
"step": 2450
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 138.89,
|
| 943 |
+
"learning_rate": 9.30232558139535e-06,
|
| 944 |
+
"loss": 0.0298,
|
| 945 |
+
"step": 2500
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 138.89,
|
| 949 |
+
"eval_avg_rouge_f": 0.3443,
|
| 950 |
+
"eval_gen_len": 16.25,
|
| 951 |
+
"eval_loss": 2.8817646503448486,
|
| 952 |
+
"eval_rouge-1": 0.391,
|
| 953 |
+
"eval_rouge-2": 0.2665,
|
| 954 |
+
"eval_rouge-l": 0.3754,
|
| 955 |
+
"eval_runtime": 2.5341,
|
| 956 |
+
"eval_samples_per_second": 3.157,
|
| 957 |
+
"eval_steps_per_second": 3.157,
|
| 958 |
+
"step": 2500
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 141.67,
|
| 962 |
+
"learning_rate": 9.069767441860465e-06,
|
| 963 |
+
"loss": 0.0265,
|
| 964 |
+
"step": 2550
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 141.67,
|
| 968 |
+
"eval_avg_rouge_f": 0.3353,
|
| 969 |
+
"eval_gen_len": 16.5,
|
| 970 |
+
"eval_loss": 2.834005355834961,
|
| 971 |
+
"eval_rouge-1": 0.3776,
|
| 972 |
+
"eval_rouge-2": 0.2665,
|
| 973 |
+
"eval_rouge-l": 0.362,
|
| 974 |
+
"eval_runtime": 3.3656,
|
| 975 |
+
"eval_samples_per_second": 2.377,
|
| 976 |
+
"eval_steps_per_second": 2.377,
|
| 977 |
+
"step": 2550
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 144.44,
|
| 981 |
+
"learning_rate": 8.837209302325582e-06,
|
| 982 |
+
"loss": 0.0182,
|
| 983 |
+
"step": 2600
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 144.44,
|
| 987 |
+
"eval_avg_rouge_f": 0.3598,
|
| 988 |
+
"eval_gen_len": 15.5,
|
| 989 |
+
"eval_loss": 2.873906135559082,
|
| 990 |
+
"eval_rouge-1": 0.4059,
|
| 991 |
+
"eval_rouge-2": 0.2831,
|
| 992 |
+
"eval_rouge-l": 0.3902,
|
| 993 |
+
"eval_runtime": 2.4328,
|
| 994 |
+
"eval_samples_per_second": 3.288,
|
| 995 |
+
"eval_steps_per_second": 3.288,
|
| 996 |
+
"step": 2600
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 144.44,
|
| 1000 |
+
"step": 2600,
|
| 1001 |
+
"total_flos": 3409770731258880.0,
|
| 1002 |
+
"train_loss": 0.29600492647060983,
|
| 1003 |
+
"train_runtime": 1522.0987,
|
| 1004 |
+
"train_samples_per_second": 8.869,
|
| 1005 |
+
"train_steps_per_second": 2.956
|
| 1006 |
+
}
|
| 1007 |
+
],
|
| 1008 |
+
"max_steps": 4500,
|
| 1009 |
+
"num_train_epochs": 250,
|
| 1010 |
+
"total_flos": 3409770731258880.0,
|
| 1011 |
+
"trial_name": null,
|
| 1012 |
+
"trial_params": null
|
| 1013 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4091
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80379659fa2a444b0146368cbedeb2127a444464453e23c94bfa2ef88b1d7337
|
| 3 |
size 4091
|