Training in progress, step 1000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +23 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484015877
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c318274b9e69ca15d787840901e5bad0f748e669ca6a376cbb8ff2ba58b87440
|
3 |
size 484015877
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242014297
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e2dfdee4d7e75e8661622e097ff1e10ee5c8afc9aae20e5f930126f250e2c6e
|
3 |
size 242014297
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eaef02ab8b67579aa70c9ab6ff61fabf7587a5da367ec704bf81333ce8386341
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6be6f394af4e26beaac13be32587b2f57676614cd6ad9f656259a62b2b7708fa
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87b9097c2fa6fe7e76f005295cc0f44ad72751203fbe52b0e2a8b21cbe743411
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 0.5382577445488361,
|
3 |
"best_model_checkpoint": "results/checkpoint-500",
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -26,11 +26,31 @@
|
|
26 |
"eval_samples_per_second": 33.892,
|
27 |
"eval_steps_per_second": 1.695,
|
28 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
}
|
30 |
],
|
31 |
"max_steps": 15000,
|
32 |
"num_train_epochs": 3,
|
33 |
-
"total_flos":
|
34 |
"trial_name": null,
|
35 |
"trial_params": null
|
36 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 0.5382577445488361,
|
3 |
"best_model_checkpoint": "results/checkpoint-500",
|
4 |
+
"epoch": 0.2,
|
5 |
+
"global_step": 1000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
26 |
"eval_samples_per_second": 33.892,
|
27 |
"eval_steps_per_second": 1.695,
|
28 |
"step": 500
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 0.2,
|
32 |
+
"learning_rate": 9.828070175438598e-05,
|
33 |
+
"loss": 0.8761,
|
34 |
+
"step": 1000
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 0.2,
|
38 |
+
"eval_bleu": 0.11272954562081616,
|
39 |
+
"eval_exact_match": 0.1475,
|
40 |
+
"eval_loss": 0.901577353477478,
|
41 |
+
"eval_rouge1": 0.5359795989196405,
|
42 |
+
"eval_rouge2": 0.3649742450836393,
|
43 |
+
"eval_rougeL": 0.5187273882783475,
|
44 |
+
"eval_rougeLsum": 0.5253745777261007,
|
45 |
+
"eval_runtime": 55.4587,
|
46 |
+
"eval_samples_per_second": 36.063,
|
47 |
+
"eval_steps_per_second": 1.803,
|
48 |
+
"step": 1000
|
49 |
}
|
50 |
],
|
51 |
"max_steps": 15000,
|
52 |
"num_train_epochs": 3,
|
53 |
+
"total_flos": 2563405440614400.0,
|
54 |
"trial_name": null,
|
55 |
"trial_params": null
|
56 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242014297
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e2dfdee4d7e75e8661622e097ff1e10ee5c8afc9aae20e5f930126f250e2c6e
|
3 |
size 242014297
|