Hugging Face's logo

lyan62
/
ar_norm_input_cosine

Transformers
PyTorch
pixel
Inference Endpoints
Model card Files Community
lyan62 commited on
Commit
3113f19
•
1 Parent(s): 4aa4ddd

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:ada50ea7588e0d01a195ed3c52258797ea611d7bf68fddf42eab4bff6dde8dd7
3
  size 402587859
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:666f31b71f688592a2ebec72cbadc00c8aaee821b8eb7771699d6c823471e0cc
3
  size 402587859
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88127dc986747682b7902d2b8811f1746aaae2debe8a28c0147f11edfe5a0861
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca890677bdefc691a4ae67775aa72a92ad5cd2df8c160e6ad53e945377e03e27
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:fbb2dec8b5a6633645b3be7bb619c04ba30c4c898facaedaafd4d002a6ccf4eb
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:850ae05229fe1ff6e41b675b726702223f1525583dd9434a160b5ed0d7191665
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 sha256:7e8ce564a0351c5ea7d80d903ca9508bc0bf1cd93390123133040b08fd58b6d2
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f74419249bf29830712440b12c1e85996438d926aea7250a4e6ac14a39e8683f
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 sha256:95d814a6f2b28cff57c4c2f7cf9d47e2db59f29a7550c7c3a3b68ce3488a8174
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64c1a11cc81ac8192bd75a90c14d20536e7e07041595e558f54ede2d84f1a21
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 sha256:265d1db338e3e3725cf5d6170423bce5139233c6b0325a9de6c92e750b49d96c
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:665c414e8bb61ec28c1998307283516f963f621b54cf6255d89b6f4ba9dd8be9
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 sha256:8617ac21bddb0215639029e71b10a4eb309c92f6b26783c1657277dbc000388a
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 sha256:189312512188440cf844c33231cd5f9af5c7d8dc4e11cd7c24cda5639fe93158
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": 0.1702127659574468,
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": 0.4082,
128
  "step": 10000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
129
  }
130
  ],
131
  "max_steps": 500000,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.2553191489361702,
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": 0.4082,
128
  "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.18,
132
+ "learning_rate": 0.0001498477179020209,
133
+ "loss": 0.406,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.19,
138
+ "learning_rate": 0.00014983287544528573,
139
+ "loss": 0.4042,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.2,
144
+ "learning_rate": 0.0001498173755173638,
145
+ "loss": 0.4026,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.2,
150
+ "learning_rate": 0.0001498011561473246,
151
+ "loss": 0.4014,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.21,
156
+ "learning_rate": 0.00014978424786805407,
157
+ "loss": 0.3999,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.22,
162
+ "learning_rate": 0.00014976665084643018,
163
+ "loss": 0.3985,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.23,
168
+ "learning_rate": 0.00014974836525612832,
169
+ "loss": 0.3971,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.24,
174
+ "learning_rate": 0.00014972939127761998,
175
+ "loss": 0.3961,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.25,
180
+ "learning_rate": 0.0001497097290981706,
181
+ "loss": 0.3949,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.26,
186
+ "learning_rate": 0.00014968937891183796,
187
+ "loss": 0.3938,
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 sha256:88127dc986747682b7902d2b8811f1746aaae2debe8a28c0147f11edfe5a0861
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca890677bdefc691a4ae67775aa72a92ad5cd2df8c160e6ad53e945377e03e27
3
  size 201355195