Commit
·
d95e6cf
1
Parent(s):
c19ea2a
Training in progress, epoch 5, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 615849402
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72b6ff8f4fbe34ee98597fdbd9ea794f71158f338b211d878558fe285a771764
|
| 3 |
size 615849402
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 307910594
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee25594ec1bdaffc52c6ede7a76b4077a6c4b6020b68e09c21000db301257e16
|
| 3 |
size 307910594
|
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:dd78d1561e066f186bca4ce7d8194cca36baf92bf62b3d97353057ddcb13d425
|
| 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 sha256:2d10b9183447b6cea880d1ce58ae96165a9ab620d0b7bf22402d25de4f2330e5
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "flanT5-description-generation/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -59,13 +59,26 @@
|
|
| 59 |
"eval_samples_per_second": 11.672,
|
| 60 |
"eval_steps_per_second": 1.481,
|
| 61 |
"step": 396
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
}
|
| 63 |
],
|
| 64 |
"logging_steps": 500,
|
| 65 |
"max_steps": 495,
|
| 66 |
"num_train_epochs": 5,
|
| 67 |
"save_steps": 500,
|
| 68 |
-
"total_flos":
|
| 69 |
"trial_name": null,
|
| 70 |
"trial_params": null
|
| 71 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.3688497543334961,
|
| 3 |
+
"best_model_checkpoint": "flanT5-description-generation/checkpoint-495",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 495,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 59 |
"eval_samples_per_second": 11.672,
|
| 60 |
"eval_steps_per_second": 1.481,
|
| 61 |
"step": 396
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 5.0,
|
| 65 |
+
"eval_gen_len": 4.604060913705584,
|
| 66 |
+
"eval_loss": 0.3688497543334961,
|
| 67 |
+
"eval_rouge1": 6.3055,
|
| 68 |
+
"eval_rouge2": 5.5351,
|
| 69 |
+
"eval_rougeL": 5.9301,
|
| 70 |
+
"eval_rougeLsum": 5.9371,
|
| 71 |
+
"eval_runtime": 15.2339,
|
| 72 |
+
"eval_samples_per_second": 12.932,
|
| 73 |
+
"eval_steps_per_second": 1.641,
|
| 74 |
+
"step": 495
|
| 75 |
}
|
| 76 |
],
|
| 77 |
"logging_steps": 500,
|
| 78 |
"max_steps": 495,
|
| 79 |
"num_train_epochs": 5,
|
| 80 |
"save_steps": 500,
|
| 81 |
+
"total_flos": 731479136010240.0,
|
| 82 |
"trial_name": null,
|
| 83 |
"trial_params": null
|
| 84 |
}
|