mprzibilla
commited on
Commit
•
ac76095
1
Parent(s):
e1b2c55
Training in progress, step 68600
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
- 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 168299
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f7342a43c6e2e5c35a08dc8aa853d670bf98d47e17ff4b7eb4abb344937b419
|
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:b09b84ab5587a3bfa1923cf0003efabd1e1c9a782e41dac55140d92ac8bf4696
|
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:da0193a55eaae86ebfabda1a7bf9d50eada1154afe462bb3a69aff41d53633e6
|
3 |
size 14639
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f1e9096c733b8b579b17c07d4598f80c4b7275508a27b0f3190f80183995e0f
|
3 |
size 557
|
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 sha256:9a19c959f34971abca48245c64db574c46e853361dc44970962475f4372eed67
|
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,
|
@@ -118,11 +118,27 @@
|
|
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.
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|
128 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 200.0,
|
5 |
+
"global_step": 68600,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
118 |
"eval_steps_per_second": 3.498,
|
119 |
"eval_wer": 1.0,
|
120 |
"step": 60025
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 200.0,
|
124 |
+
"learning_rate": 2.10930115512564e-05,
|
125 |
+
"loss": 2.2292,
|
126 |
+
"step": 68600
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 200.0,
|
130 |
+
"eval_cer": 0.8995670995670996,
|
131 |
+
"eval_loss": 2.8907620906829834,
|
132 |
+
"eval_runtime": 7.7141,
|
133 |
+
"eval_samples_per_second": 27.223,
|
134 |
+
"eval_steps_per_second": 3.5,
|
135 |
+
"eval_wer": 1.0,
|
136 |
+
"step": 68600
|
137 |
}
|
138 |
],
|
139 |
"max_steps": 85750,
|
140 |
"num_train_epochs": 250,
|
141 |
+
"total_flos": 4.773812733077e+19,
|
142 |
"trial_name": null,
|
143 |
"trial_params": null
|
144 |
}
|
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:b09b84ab5587a3bfa1923cf0003efabd1e1c9a782e41dac55140d92ac8bf4696
|
3 |
size 377643361
|