Training in progress, step 25000
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 +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 943333453
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96afa5b935c4ba0d2f5a64c6c549d5cce4e378b683d7e5c0c4ec6ee8a7caa7b1
|
3 |
size 943333453
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 471708325
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bab3cb9aef35a7f62022e8366c00ec1553f006427b61616b2d9605a2064469f1
|
3 |
size 471708325
|
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 sha256:8ce17dd362010b9febb4c382825dfdcaf98b66d0f2a90b38a39446ca8e56c66a
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c7d6ae114f124f82b43c783fc16b8f427729c24044a8a223ba79e1f91d66047
|
3 |
size 559
|
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:c019e460b0a3b004dbe486f597f54f4d81a353de840b5f0d23f56053d32e0dd3
|
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,
|
@@ -70,11 +70,27 @@
|
|
70 |
"eval_samples_per_second": 7.469,
|
71 |
"eval_steps_per_second": 3.735,
|
72 |
"step": 20000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
73 |
}
|
74 |
],
|
75 |
"max_steps": 92088,
|
76 |
"num_train_epochs": 3,
|
77 |
-
"total_flos":
|
78 |
"trial_name": null,
|
79 |
"trial_params": null
|
80 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.8144383633046651,
|
5 |
+
"global_step": 25000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
70 |
"eval_samples_per_second": 7.469,
|
71 |
"eval_steps_per_second": 3.735,
|
72 |
"step": 20000
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.81,
|
76 |
+
"learning_rate": 2.1860502997133176e-05,
|
77 |
+
"loss": 0.9329,
|
78 |
+
"step": 25000
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 0.81,
|
82 |
+
"eval_exact_match": 81.264127977743,
|
83 |
+
"eval_f1": 85.43481659242194,
|
84 |
+
"eval_loss": 0.7231199741363525,
|
85 |
+
"eval_runtime": 1535.496,
|
86 |
+
"eval_samples_per_second": 7.498,
|
87 |
+
"eval_steps_per_second": 3.749,
|
88 |
+
"step": 25000
|
89 |
}
|
90 |
],
|
91 |
"max_steps": 92088,
|
92 |
"num_train_epochs": 3,
|
93 |
+
"total_flos": 5.51617572864e+16,
|
94 |
"trial_name": null,
|
95 |
"trial_params": null
|
96 |
}
|
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 471708325
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bab3cb9aef35a7f62022e8366c00ec1553f006427b61616b2d9605a2064469f1
|
3 |
size 471708325
|