Commit
·
a279158
1
Parent(s):
831aec7
Training in progress, epoch 3, 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 sha256:6b14ca092add6f83afa8592d7cc107f9a67c8e22970174dcecb8c088b5de4169
|
| 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 sha256:53b82483abfbf4ffd8c243b766dabbb4812428d1894516eada10c5a9bfc6fd48
|
| 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 sha256:8ede5b6194a7298561178c49b95e0507051d3deed7c4f79c181647c4a85f692c
|
| 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:f47fdf6b0fbbab3a9ea4d27bd0147fa6ed4e838983e0cf3922c7879c115ad6f0
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 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,
|
|
@@ -33,13 +33,26 @@
|
|
| 33 |
"eval_samples_per_second": 12.237,
|
| 34 |
"eval_steps_per_second": 1.553,
|
| 35 |
"step": 198
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
}
|
| 37 |
],
|
| 38 |
"logging_steps": 500,
|
| 39 |
"max_steps": 495,
|
| 40 |
"num_train_epochs": 5,
|
| 41 |
"save_steps": 500,
|
| 42 |
-
"total_flos":
|
| 43 |
"trial_name": null,
|
| 44 |
"trial_params": null
|
| 45 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7071468234062195,
|
| 3 |
+
"best_model_checkpoint": "flanT5-description-generation/checkpoint-297",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 297,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 33 |
"eval_samples_per_second": 12.237,
|
| 34 |
"eval_steps_per_second": 1.553,
|
| 35 |
"step": 198
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 3.0,
|
| 39 |
+
"eval_gen_len": 3.0406091370558377,
|
| 40 |
+
"eval_loss": 0.7071468234062195,
|
| 41 |
+
"eval_rouge1": 6.887,
|
| 42 |
+
"eval_rouge2": 6.1128,
|
| 43 |
+
"eval_rougeL": 6.512,
|
| 44 |
+
"eval_rougeLsum": 6.515,
|
| 45 |
+
"eval_runtime": 12.3043,
|
| 46 |
+
"eval_samples_per_second": 16.011,
|
| 47 |
+
"eval_steps_per_second": 2.032,
|
| 48 |
+
"step": 297
|
| 49 |
}
|
| 50 |
],
|
| 51 |
"logging_steps": 500,
|
| 52 |
"max_steps": 495,
|
| 53 |
"num_train_epochs": 5,
|
| 54 |
"save_steps": 500,
|
| 55 |
+
"total_flos": 438887481606144.0,
|
| 56 |
"trial_name": null,
|
| 57 |
"trial_params": null
|
| 58 |
}
|