Upload 9 files
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +2 -2
- scaler.pt +1 -1
- scheduler.pt +1 -1
- trainer_state.json +54 -3
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2490594117
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bed063b4186f03787edb99c074dbb586b99f5162085d5c16e0db4cbcb0a4f632
|
3 |
size 2490594117
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262168365
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a5e177135e49a5cecca9645170889d50c62923d9a76429da7138d06c224d1da
|
3 |
size 1262168365
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b5477abcf468982052803c535d0ca7e85d3b5529a3db76f938926b09683583b
|
3 |
+
size 14575
|
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 sha256:25b49edd22c6273e0961ea9beb65cba08c556a16b608c3406a5432bac4cb2a57
|
3 |
size 557
|
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:d955e432a5975234ea4c4b68a9fcfc654a3b35487b3555ca89a82642063ca66b
|
3 |
size 627
|
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 +102,62 @@
|
|
102 |
"eval_steps_per_second": 2.207,
|
103 |
"eval_wer": 0.16558235092696766,
|
104 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
105 |
}
|
106 |
],
|
107 |
"max_steps": 1140000,
|
108 |
"num_train_epochs": 10000,
|
109 |
-
"total_flos":
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|
112 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 26.314754098360655,
|
5 |
+
"global_step": 3000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
102 |
"eval_steps_per_second": 2.207,
|
103 |
"eval_wer": 0.16558235092696766,
|
104 |
"step": 2000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 18.42,
|
108 |
+
"learning_rate": 9.982463373980174e-06,
|
109 |
+
"loss": 0.0184,
|
110 |
+
"step": 2100
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 19.73,
|
114 |
+
"learning_rate": 9.981147469076235e-06,
|
115 |
+
"loss": 0.0186,
|
116 |
+
"step": 2250
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 21.05,
|
120 |
+
"learning_rate": 9.979831564172297e-06,
|
121 |
+
"loss": 0.0174,
|
122 |
+
"step": 2400
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 22.37,
|
126 |
+
"learning_rate": 9.978515659268357e-06,
|
127 |
+
"loss": 0.0175,
|
128 |
+
"step": 2550
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 23.68,
|
132 |
+
"learning_rate": 9.977199754364418e-06,
|
133 |
+
"loss": 0.0169,
|
134 |
+
"step": 2700
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 25.0,
|
138 |
+
"learning_rate": 9.97588384946048e-06,
|
139 |
+
"loss": 0.0174,
|
140 |
+
"step": 2850
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 26.31,
|
144 |
+
"learning_rate": 9.974567944556542e-06,
|
145 |
+
"loss": 0.0175,
|
146 |
+
"step": 3000
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 26.31,
|
150 |
+
"eval_loss": 0.23709918558597565,
|
151 |
+
"eval_runtime": 224.4917,
|
152 |
+
"eval_samples_per_second": 18.174,
|
153 |
+
"eval_steps_per_second": 2.272,
|
154 |
+
"eval_wer": 0.16504426943207945,
|
155 |
+
"step": 3000
|
156 |
}
|
157 |
],
|
158 |
"max_steps": 1140000,
|
159 |
"num_train_epochs": 10000,
|
160 |
+
"total_flos": 8.535940964167849e+19,
|
161 |
"trial_name": null,
|
162 |
"trial_params": null
|
163 |
}
|