Nekofox commited on
Commit
4188f4a
1 Parent(s): 816d33c

Training in progress, step 8000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b084cd633540520d4323a2fd7fc4f21c70ac06d1668ad0a091f5c3ad4da4d4e7
3
  size 3871543575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86a344de794efe76499e05226f84f9b9eb183ce1856b9f543366c91090aa50d5
3
  size 3871543575
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24ff144f7065891dac07b66cb010b6680157abde1f0f55d54f6a0f4af170df9f
3
  size 1944201353
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd9644cb39fc77ce0ecf8404c68767bf11e83b492f019e8898a2c4793d943f36
3
  size 1944201353
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a0bf5eac1bdc0ccacc5a1114bf24232a4e303e52d3dce9ddaaa7b8bf9f46698
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48ad0a43aae89b9c2d626e990511e66a4021355e52a4c9454762a9fb104c6dc4
3
  size 14575
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9878f2a57c72a87cdd42970b74283283ecca71e876c37aa500b36a760854b67e
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466cc5f8b444b6e6a08a358b89d91b894e9359170249f4e3593cf66128c9e459
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a0373611573f56c821d5425b20794db9519d4201fd07fb1e247b00166c614a2
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988143f54fcd42be170761e4e90014713b8da045b4b00b0b1cea0538e6c4a720
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.06359907145355678,
5
- "global_step": 6000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -78,11 +78,35 @@
78
  "learning_rate": 4.542013052892988e-07,
79
  "loss": 1.9152,
80
  "step": 6000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
81
  }
82
  ],
83
  "max_steps": 943410,
84
  "num_train_epochs": 10,
85
- "total_flos": 3421278296948736.0,
86
  "trial_name": null,
87
  "trial_params": null
88
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0847987619380757,
5
+ "global_step": 8000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
78
  "learning_rate": 4.542013052892988e-07,
79
  "loss": 1.9152,
80
  "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.07,
84
+ "learning_rate": 4.920577234664366e-07,
85
+ "loss": 1.8736,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.07,
90
+ "learning_rate": 5.299141416435743e-07,
91
+ "loss": 1.8995,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.08,
96
+ "learning_rate": 5.677705598207121e-07,
97
+ "loss": 1.8825,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.08,
102
+ "learning_rate": 6.055512651614955e-07,
103
+ "loss": 1.8569,
104
+ "step": 8000
105
  }
106
  ],
107
  "max_steps": 943410,
108
  "num_train_epochs": 10,
109
+ "total_flos": 4555211547377664.0,
110
  "trial_name": null,
111
  "trial_params": null
112
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24ff144f7065891dac07b66cb010b6680157abde1f0f55d54f6a0f4af170df9f
3
  size 1944201353
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd9644cb39fc77ce0ecf8404c68767bf11e83b492f019e8898a2c4793d943f36
3
  size 1944201353
runs/May10_10-08-53_fe5daffb52a2/events.out.tfevents.1683713360.fe5daffb52a2.366.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edfa2e9aebafc2ad1ff7e3d97686c3288712929acd88087bb7b02fc8217e93dd
3
- size 6348
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bced457006191011c0ab229a510202b432d288722032cf70f0ba39b77efe85cd
3
+ size 6976