Hugging Face's logo

lyan62
/
ar_norm_input_cosine

Transformers
PyTorch
pixel
Inference Endpoints
Model card Files Community
lyan62 commited on
Commit
16688b6
•
1 Parent(s): ca49d1e

Training in progress, step 180000

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:fd48b74ac1e83833752e1a90bba5608cc1040bf624f4eac82239aba5a9238261
3
  size 402588883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8d7c5ac12edf9dc3676f9bdb7cd4b3a7c3b9f2fdac1dd8cec20e69f551b609
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:cd14386b0a649570c4d20a23842f7cf3b08d541c3d4b898951a36f146b09ab68
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b81075edadb4944d69f2034c6e79f67d97e879cd6f5e5a1d17c26d4077124878
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 sha256:2348a48dcae284e3bf0c4419f1eea9e78d3eef8b466335308875b9d862c8d4b1
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e93df9e7edf4d7dbddc99825e81c638aa95f1630a9722ed9513333e0b41f73
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 sha256:48d4abc3f2899f95311dbce965fd7563d9bdfb75cedf302c2d6fbc196e24dd8e
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ef1f41bc3b3fcb427f183fa39c9bbaddeee7f2707cf15bd37633d3a15aa1d04
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:aff782f4812b791b760dc647ac3fa41d358c36cf6c112c7cfd80ff3953fbd063
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e0777f27c5f89b88c226f0682b60cae85c6ce6903fc585c8a9eaf10ca908705
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 sha256:38531ecfec32b4f297fe204a04355aff6cc1b483e1e12ef7f2e8e8035519573b
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69bf24e75031f190271b91b52c39ba180614c59a395874d34e7fdfff6924458
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a183546506b409eaad8c229377dbaa51518042a7de70abf5671d9a48e04957b
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c2e988cdfbb899e1efcf3975072ae124857055cb175197acb92345cd0f6e455
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5d0f109ace001d7b1f30324beb3a2855f010a09846e498b98d99bc13aaefb31
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92c9ca47e0acb93ad569761b5617c67c7c09a8afde7672db3f6aa7d74fb69d09
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": 2.978723404255319,
5
- "global_step": 175000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -2106,6 +2106,66 @@
2106
  "learning_rate": 0.00011180519666756124,
2107
  "loss": 0.3343,
2108
  "step": 175000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2109
  }
2110
  ],
2111
  "max_steps": 500000,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.0638297872340425,
5
+ "global_step": 180000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
2106
  "learning_rate": 0.00011180519666756124,
2107
  "loss": 0.3343,
2108
  "step": 175000
2109
+ },
2110
+ {
2111
+ "epoch": 2.99,
2112
+ "learning_rate": 0.00011160913888760783,
2113
+ "loss": 0.3347,
2114
+ "step": 175500
2115
+ },
2116
+ {
2117
+ "epoch": 3.0,
2118
+ "learning_rate": 0.00011141316218777135,
2119
+ "loss": 0.3349,
2120
+ "step": 176000
2121
+ },
2122
+ {
2123
+ "epoch": 3.0,
2124
+ "learning_rate": 0.00011121648302515513,
2125
+ "loss": 0.3347,
2126
+ "step": 176500
2127
+ },
2128
+ {
2129
+ "epoch": 3.01,
2130
+ "learning_rate": 0.00011101949576845408,
2131
+ "loss": 0.3344,
2132
+ "step": 177000
2133
+ },
2134
+ {
2135
+ "epoch": 3.02,
2136
+ "learning_rate": 0.00011082220236185285,
2137
+ "loss": 0.3343,
2138
+ "step": 177500
2139
+ },
2140
+ {
2141
+ "epoch": 3.03,
2142
+ "learning_rate": 0.00011062460475255774,
2143
+ "loss": 0.3342,
2144
+ "step": 178000
2145
+ },
2146
+ {
2147
+ "epoch": 3.04,
2148
+ "learning_rate": 0.00011042710099085118,
2149
+ "loss": 0.3367,
2150
+ "step": 178500
2151
+ },
2152
+ {
2153
+ "epoch": 3.05,
2154
+ "learning_rate": 0.00011022890142842465,
2155
+ "loss": 0.3387,
2156
+ "step": 179000
2157
+ },
2158
+ {
2159
+ "epoch": 3.06,
2160
+ "learning_rate": 0.00011003119810229468,
2161
+ "loss": 0.3392,
2162
+ "step": 179500
2163
+ },
2164
+ {
2165
+ "epoch": 3.06,
2166
+ "learning_rate": 0.0001098324049865014,
2167
+ "loss": 0.3392,
2168
+ "step": 180000
2169
  }
2170
  ],
2171
  "max_steps": 500000,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd14386b0a649570c4d20a23842f7cf3b08d541c3d4b898951a36f146b09ab68
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b81075edadb4944d69f2034c6e79f67d97e879cd6f5e5a1d17c26d4077124878
3
  size 201355195