Hugging Face's logo

lyan62
/
ar_norm_input_cosine

Transformers
PyTorch
pixel
Inference Endpoints
Model card Files Community
lyan62 commited on
Commit
4aa4ddd
•
1 Parent(s): 649f7d0

Training in progress, step 10000

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 sha256:490bf4f8dd5a0d76a73d5838153d2b9b438ad6e382a72b0c89aac8b518d52ca9
3
  size 402587859
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ada50ea7588e0d01a195ed3c52258797ea611d7bf68fddf42eab4bff6dde8dd7
3
  size 402587859
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14939662bed420a1b81f1fff2713b52cccbb592116282f8fcf6d94cdd2006ddf
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88127dc986747682b7902d2b8811f1746aaae2debe8a28c0147f11edfe5a0861
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 sha256:04b16f2fbaf1194b69e4b667ecf509f1b3e3ed17acd1bee3f17caedcaf65a663
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb2dec8b5a6633645b3be7bb619c04ba30c4c898facaedaafd4d002a6ccf4eb
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 sha256:646c48c6454b11ba3b84f27ede60f57c74517de526b9207fe07290c8809793b7
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e8ce564a0351c5ea7d80d903ca9508bc0bf1cd93390123133040b08fd58b6d2
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 sha256:865e307b4e009262fe9bdb8b6d9d9a7bd67af3792ee343bbdf8af60b8359ca7c
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95d814a6f2b28cff57c4c2f7cf9d47e2db59f29a7550c7c3a3b68ce3488a8174
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 sha256:503103ede15c3cebf206c440d287ac4e603a37822858231915e9f8e0cf8bb41e
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:265d1db338e3e3725cf5d6170423bce5139233c6b0325a9de6c92e750b49d96c
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:018632b7efb97680221078f777b72fc854385a42730f0e76446b2116c7b5ff33
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a28e8be2a3887ca8072f99cc9bcae55040769870a8c9d9965493ca683763af7
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0e8ba5e8a79631162151d1ac9f60167dfa7fb6dea5ba86993956bb6b1d9e50b
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3134a72416abec950fef9303930c8b660ea9e82e18cbbb0f68ee969677327d0
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": 0.0851063829787234,
5
- "global_step": 5000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -66,6 +66,66 @@
66
  "learning_rate": 0.0001499654592256012,
67
  "loss": 0.4466,
68
  "step": 5000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "max_steps": 500000,
 
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,
 
66
  "learning_rate": 0.0001499654592256012,
67
  "loss": 0.4466,
68
  "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.09,
72
+ "learning_rate": 0.0001499582063848481,
73
+ "loss": 0.4398,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.1,
78
+ "learning_rate": 0.00014995026308484122,
79
+ "loss": 0.4341,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.11,
84
+ "learning_rate": 0.00014994162940397778,
85
+ "loss": 0.4288,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.12,
90
+ "learning_rate": 0.00014993230542746872,
91
+ "loss": 0.4247,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.13,
96
+ "learning_rate": 0.00014992229124733788,
97
+ "loss": 0.4207,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.14,
102
+ "learning_rate": 0.0001499115869624212,
103
+ "loss": 0.4175,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.14,
108
+ "learning_rate": 0.00014990019267836565,
109
+ "loss": 0.4146,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.15,
114
+ "learning_rate": 0.00014988810850762824,
115
+ "loss": 0.4122,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.16,
120
+ "learning_rate": 0.00014987533456947482,
121
+ "loss": 0.4097,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.17,
126
+ "learning_rate": 0.000149861870989979,
127
+ "loss": 0.4082,
128
+ "step": 10000
129
  }
130
  ],
131
  "max_steps": 500000,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14939662bed420a1b81f1fff2713b52cccbb592116282f8fcf6d94cdd2006ddf
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88127dc986747682b7902d2b8811f1746aaae2debe8a28c0147f11edfe5a0861
3
  size 201355195