Training in progress, step 4000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +19 -3
- nbest_predictions.json +0 -0
- predictions.json +0 -0
- 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 880446181
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dbdc000392478004ae6d96779bf4278d1ef18251780930b9f3c799384f5bbf7
|
| 3 |
size 880446181
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 440235825
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:542d1e98b1496a58397fda14504ca6f3da4a82106acb16e6eafe2d17041fd830
|
| 3 |
size 440235825
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a051295dd5bb8f79e33c3a2c94c1992b07d17d0b91ccf5450842b8cded54f3c
|
| 3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d93f82e70bcd6a3d62cba6e3e991ff9feff4305521c6596bf00d78e8721b10d1
|
| 3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -118,11 +118,27 @@
|
|
| 118 |
"eval_samples_per_second": 91.822,
|
| 119 |
"eval_steps_per_second": 11.48,
|
| 120 |
"step": 3500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 121 |
}
|
| 122 |
],
|
| 123 |
"max_steps": 28806,
|
| 124 |
"num_train_epochs": 3,
|
| 125 |
-
"total_flos":
|
| 126 |
"trial_name": null,
|
| 127 |
"trial_params": null
|
| 128 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.41657987919183503,
|
| 5 |
+
"global_step": 4000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 118 |
"eval_samples_per_second": 91.822,
|
| 119 |
"eval_steps_per_second": 11.48,
|
| 120 |
"step": 3500
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.42,
|
| 124 |
+
"learning_rate": 2.583420120808165e-05,
|
| 125 |
+
"loss": 0.8454,
|
| 126 |
+
"step": 4000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.42,
|
| 130 |
+
"eval_exact_match": 65.8320292123109,
|
| 131 |
+
"eval_f1": 70.26703931597173,
|
| 132 |
+
"eval_loss": 0.6987438201904297,
|
| 133 |
+
"eval_runtime": 154.6403,
|
| 134 |
+
"eval_samples_per_second": 91.858,
|
| 135 |
+
"eval_steps_per_second": 11.485,
|
| 136 |
+
"step": 4000
|
| 137 |
}
|
| 138 |
],
|
| 139 |
"max_steps": 28806,
|
| 140 |
"num_train_epochs": 3,
|
| 141 |
+
"total_flos": 8361496215552000.0,
|
| 142 |
"trial_name": null,
|
| 143 |
"trial_params": null
|
| 144 |
}
|
nbest_predictions.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
predictions.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 440235825
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:542d1e98b1496a58397fda14504ca6f3da4a82106acb16e6eafe2d17041fd830
|
| 3 |
size 440235825
|