Hugging Face's logo

lyan62
/
ar_norm_input_cosine

Transformers
PyTorch
pixel
Inference Endpoints
Model card Files Community
lyan62 commited on
Commit
575c2e4
•
1 Parent(s): 7348dc4

Training in progress, step 100000

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 sha256:9383d4666eeeafc05e937e02f292247bb6ed63c694ad2e844acb2473908c89e6
3
  size 402588883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cb52316991dc035129c63e78ad28479c65ee2fd5882bb48caeb7170e09004e3
3
  size 402588883
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4a2faea047cb9b2b0cf113eecb945f723361f63a827436ce80ec70c60bea870
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74fc115b3b2457c56e1c65146879a21f7118b36e042e788e01e89bdbd8bdc422
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 sha256:7efa5cd772ce4ea497b2566a23af159eef5aa21434cb9759b60999a948ec2815
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23ac6e8e677c953af00eb879ba2ba8e420d1743b51fb50c6e943ad2f8f8b192a
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 sha256:651c7e07f7962b9d797a42f3b4c51dec78ffb402b9848fa9f5be146e560eb46a
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c580dd74ee22a1f18620643696334d3394874432fda0a7e5e8feac4eb4634405
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:f1c87d301112719d00df543775e8c189216d1253ac68a2478841b87b7e4ce29a
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392aa9426ea016a7b73f0ed668b0d3a018362e286aa3d505d45b8fb35b8e061a
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 sha256:4130fc24a029257f4fa579f17c078f97fdb453d661ae6ffc0c5e1f7239bf5fe9
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb479d056a6c7dc4823beaa34ce77c3b7804640bf03d276c5b762774e11bb991
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:262727666821e8fc41a0d4ecd6658b6c25f75f8b011184bdd8b59ffeedf4e1b6
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d808041b09fbf1e8ad6c527451ca4c9093942a2934f244b9a687a0c2587bcf99
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c40f39f5b58ba1097e410d23f90905de95dbcf8124e6137d7837a066b34d657
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19ab96e564181be7427a49c4a94ec789b01e8491fee180b1d10d5e92a759c47f
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": 1.6170212765957448,
5
- "global_step": 95000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -1146,6 +1146,66 @@
1146
  "learning_rate": 0.00013790453853658956,
1147
  "loss": 0.3509,
1148
  "step": 95000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1149
  }
1150
  ],
1151
  "max_steps": 500000,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.702127659574468,
5
+ "global_step": 100000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
1146
  "learning_rate": 0.00013790453853658956,
1147
  "loss": 0.3509,
1148
  "step": 95000
1149
+ },
1150
+ {
1151
+ "epoch": 1.63,
1152
+ "learning_rate": 0.00013778068554637154,
1153
+ "loss": 0.3509,
1154
+ "step": 95500
1155
+ },
1156
+ {
1157
+ "epoch": 1.63,
1158
+ "learning_rate": 0.00013765626228411418,
1159
+ "loss": 0.3504,
1160
+ "step": 96000
1161
+ },
1162
+ {
1163
+ "epoch": 1.64,
1164
+ "learning_rate": 0.00013753126997782485,
1165
+ "loss": 0.3507,
1166
+ "step": 96500
1167
+ },
1168
+ {
1169
+ "epoch": 1.65,
1170
+ "learning_rate": 0.00013740570986112716,
1171
+ "loss": 0.351,
1172
+ "step": 97000
1173
+ },
1174
+ {
1175
+ "epoch": 1.66,
1176
+ "learning_rate": 0.00013727983599123606,
1177
+ "loss": 0.35,
1178
+ "step": 97500
1179
+ },
1180
+ {
1181
+ "epoch": 1.67,
1182
+ "learning_rate": 0.00013715314510640312,
1183
+ "loss": 0.35,
1184
+ "step": 98000
1185
+ },
1186
+ {
1187
+ "epoch": 1.68,
1188
+ "learning_rate": 0.00013702614521514468,
1189
+ "loss": 0.3502,
1190
+ "step": 98500
1191
+ },
1192
+ {
1193
+ "epoch": 1.69,
1194
+ "learning_rate": 0.00013689832855371767,
1195
+ "loss": 0.3502,
1196
+ "step": 99000
1197
+ },
1198
+ {
1199
+ "epoch": 1.69,
1200
+ "learning_rate": 0.0001367699503287586,
1201
+ "loss": 0.3499,
1202
+ "step": 99500
1203
+ },
1204
+ {
1205
+ "epoch": 1.7,
1206
+ "learning_rate": 0.00013664101180730875,
1207
+ "loss": 0.3498,
1208
+ "step": 100000
1209
  }
1210
  ],
1211
  "max_steps": 500000,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4a2faea047cb9b2b0cf113eecb945f723361f63a827436ce80ec70c60bea870
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74fc115b3b2457c56e1c65146879a21f7118b36e042e788e01e89bdbd8bdc422
3
  size 201355195