mprzibilla
commited on
Commit
•
e1b2c55
1
Parent(s):
3e4503f
Training in progress, step 60025
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 168299
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abf0eeb2a31f783c8d259fad495e0cd75b9a6f65a36545660db7809bf9f4da1e
|
3 |
size 168299
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377643361
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15c12d49fa9c3645b82ff5c731ce043fb2e0fd4cc77e4d45420239ad32d04316
|
3 |
size 377643361
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14639
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48078035f33770b5536275849abc622689e726a3f730ca49b645d1b7e3018ab2
|
3 |
size 14639
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:421cd3c4d20318c91960c572a915b2b09d4a732fa6675a77ec4da7b8fecc42b8
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -102,11 +102,27 @@
|
|
102 |
"eval_steps_per_second": 3.496,
|
103 |
"eval_wer": 1.0,
|
104 |
"step": 51450
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
105 |
}
|
106 |
],
|
107 |
"max_steps": 85750,
|
108 |
"num_train_epochs": 250,
|
109 |
-
"total_flos":
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|
112 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 175.0,
|
5 |
+
"global_step": 60025,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
102 |
"eval_steps_per_second": 3.496,
|
103 |
"eval_wer": 1.0,
|
104 |
"step": 51450
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 175.0,
|
108 |
+
"learning_rate": 3.161435252814161e-05,
|
109 |
+
"loss": 2.2432,
|
110 |
+
"step": 60025
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 175.0,
|
114 |
+
"eval_cer": 0.8995670995670996,
|
115 |
+
"eval_loss": 2.889348030090332,
|
116 |
+
"eval_runtime": 7.7196,
|
117 |
+
"eval_samples_per_second": 27.203,
|
118 |
+
"eval_steps_per_second": 3.498,
|
119 |
+
"eval_wer": 1.0,
|
120 |
+
"step": 60025
|
121 |
}
|
122 |
],
|
123 |
"max_steps": 85750,
|
124 |
"num_train_epochs": 250,
|
125 |
+
"total_flos": 4.176972541986562e+19,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|
128 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377643361
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15c12d49fa9c3645b82ff5c731ce043fb2e0fd4cc77e4d45420239ad32d04316
|
3 |
size 377643361
|