Hugging Face's logo

lyan62
/
ar_norm_input_lrsmall

Transformers
PyTorch
pixel
masked-auto-encoding
Generated from Trainer
Inference Endpoints
Model card Files Community
lyan62 commited on
Commit
b063900
•
1 Parent(s): dcf327c

Training in progress, step 15000

Browse files
Files changed (10) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state_0.pth +1 -1
  4. last-checkpoint/rng_state_1.pth +1 -1
  5. last-checkpoint/rng_state_2.pth +1 -1
  6. last-checkpoint/rng_state_3.pth +1 -1
  7. last-checkpoint/scaler.pt +1 -1
  8. last-checkpoint/scheduler.pt +1 -1
  9. last-checkpoint/trainer_state.json +62 -2
  10. 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 sha256:42b7119dae26f95e759af87d2694035b4627e484829fa085b9887307e584027d
3
  size 402587859
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de9c1066ffe7cedd3790cf74f90e6b42b28010adb6f755977ef3da6115d6d433
3
  size 402587859
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d721a5d92de7c3e7b282220f9260ab6283761aa6c0a67633f01b73f4484e88a
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24c90f2b89c141a63dd59fa57c3a3739114415c665224cdb6d8703c01f21b2f5
3
  size 201355195
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ced61c2ca16a8b9af34ec22215625eca8ece206506bd667270651e29c50d152c
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef6fab0aad647d44150184b9e3a085bf5367acaceef4345dfcb5f1b251e74c61
3
  size 14503
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fab9432af2478fa523c3f480312c9b289cccc342f6c08d159285299a420f2d2
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1145a3091a460210ae7da3675a1a49999755433b2c836a2ac8ae1975b4b3b67c
3
  size 14503
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8de7b9d2730e6e1ffa628554e02f762aed35f57534bbe4eca6576f8bf323a2b8
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa7aa39f02a35206d52f24c94bb57385d48d208a5d017ded38bea7374ae7e8a
3
  size 14503
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:351b749df84f2ebffd7b8765a4b4f3c28b010ec954ada54a535dd8e6072b32f3
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45753a61dd9d065df5cc764cca8cc81c848dd8932990c9f4f549f46fe7721b45
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a28e8be2a3887ca8072f99cc9bcae55040769870a8c9d9965493ca683763af7
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2332b5dfef9cf69443c488e4f08214dae793b15c742568c8e56acc2a65ad60b
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3134a72416abec950fef9303930c8b660ea9e82e18cbbb0f68ee969677327d0
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3513f15afaa200bb7041b668e62843503210a13b0c4a572a8b74a3c40d994fe
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": 0.17021131735049064,
5
- "global_step": 10000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -126,6 +126,66 @@
126
  "learning_rate": 0.000149861870989979,
127
  "loss": 0.4075,
128
  "step": 10000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
129
  }
130
  ],
131
  "max_steps": 500000,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.25531697602573594,
5
+ "global_step": 15000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
126
  "learning_rate": 0.000149861870989979,
127
  "loss": 0.4075,
128
  "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.18,
132
+ "learning_rate": 0.0001498477758876907,
133
+ "loss": 0.4057,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.19,
138
+ "learning_rate": 0.00014983293618814342,
139
+ "loss": 0.4038,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.2,
144
+ "learning_rate": 0.00014981740726570863,
145
+ "loss": 0.4021,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.2,
150
+ "learning_rate": 0.00014980118927365057,
151
+ "loss": 0.4005,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.21,
156
+ "learning_rate": 0.00014978428237203426,
157
+ "loss": 0.3991,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.22,
162
+ "learning_rate": 0.00014976668672772396,
163
+ "loss": 0.3977,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.23,
168
+ "learning_rate": 0.00014974843976988143,
169
+ "loss": 0.3968,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.24,
174
+ "learning_rate": 0.00014972946854455738,
175
+ "loss": 0.3953,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.25,
180
+ "learning_rate": 0.00014970980911752974,
181
+ "loss": 0.3945,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.26,
186
+ "learning_rate": 0.0001496894616828291,
187
+ "loss": 0.3931,
188
+ "step": 15000
189
  }
190
  ],
191
  "max_steps": 500000,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d721a5d92de7c3e7b282220f9260ab6283761aa6c0a67633f01b73f4484e88a
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24c90f2b89c141a63dd59fa57c3a3739114415c665224cdb6d8703c01f21b2f5
3
  size 201355195