Training in progress, step 30000
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 sha256:3f3b5dbaaab2ff80c51aab2baf4b9611bddb09fa3492187cd0c4986ca1141032
|
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 sha256:96429bbd5357a90f82f7fd61e1d44d34485eab7d138167bde3c41c27c7bd86a2
|
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 sha256:78b2b81bf435885ea6240f0db616b814b3385f70f79a69209da25c250c62b15a
|
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:ed10c31fea80c2ece39edbebb48082a88208ed521f76de5c0a075b1acc6dcb0d
|
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 sha256:2476364d95c8b4b965537ee7922cb55dcd03a38898d51c99d2f0db9b4afb3995
|
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,
|
@@ -86,11 +86,27 @@
|
|
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":
|
94 |
"trial_name": null,
|
95 |
"trial_params": null
|
96 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9773260359655981,
|
5 |
+
"global_step": 30000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
86 |
"eval_samples_per_second": 7.498,
|
87 |
"eval_steps_per_second": 3.749,
|
88 |
"step": 25000
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.98,
|
92 |
+
"learning_rate": 2.0232277821214492e-05,
|
93 |
+
"loss": 0.8913,
|
94 |
+
"step": 30000
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.98,
|
98 |
+
"eval_exact_match": 81.92488262910798,
|
99 |
+
"eval_f1": 85.96065424027016,
|
100 |
+
"eval_loss": 0.7569286227226257,
|
101 |
+
"eval_runtime": 1529.0019,
|
102 |
+
"eval_samples_per_second": 7.53,
|
103 |
+
"eval_steps_per_second": 3.765,
|
104 |
+
"step": 30000
|
105 |
}
|
106 |
],
|
107 |
"max_steps": 92088,
|
108 |
"num_train_epochs": 3,
|
109 |
+
"total_flos": 6.619410874368e+16,
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|
112 |
}
|
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 sha256:96429bbd5357a90f82f7fd61e1d44d34485eab7d138167bde3c41c27c7bd86a2
|
3 |
size 471708325
|